Merge tag 'drm-fixes-2022-11-25' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Weekly fixes, amdgpu has not quite settled down.

  Most of the changes are small, and the non-amdgpu ones are all fine.
  There are a bunch of DP MST DSC fixes that fix some issues introduced
  in a previous larger MST rework.

  The biggest one is mainly propagating some error values properly
  instead of bool returns, and I think it just looks large but doesn't
  really change anything too much, except propagating errors that are
  required to avoid deadlocks. I've gone over it and a few others and
  they've had some decent testing over the last few weeks.

  Summary:

  amdgpu:
   - amdgpu gang submit fix
   - DCN 3.1.4 fixes
   - DP MST DSC deadlock fixes
   - HMM userptr fixes
   - Fix Aldebaran CU occupancy reporting
   - GFX11 fixes
   - PSP suspend/resume fix
   - DCE12 KASAN fix
   - DCN 3.2.x fixes
   - Rotated cursor fix
   - SMU 13.x fix
   - DELL platform suspend/resume fixes
   - VCN4 SR-IOV fix
   - Display regression fix for polled connectors

  i915:
   - Fix GVT KVM reference count handling
   - Never purge busy TTM objects
   - Fix warn in intel_display_power_*_domain() functions

  dma-buf:
   - Use dma_fence_unwrap_for_each when importing sync files
   - Fix race in dma_heap_add()

  fbcon:
   - Fix use of uninitialized memory in logo"

* tag 'drm-fixes-2022-11-25' of git://anongit.freedesktop.org/drm/drm: (30 commits)
  drm/amdgpu/vcn: re-use original vcn0 doorbell value
  drm/amdgpu: Partially revert "drm/amdgpu: update drm_display_info correctly when the edid is read"
  drm/amd/display: No display after resume from WB/CB
  drm/amdgpu: fix use-after-free during gpu recovery
  drm/amd/pm: update driver if header for smu_13_0_7
  drm/amd/display: Fix rotated cursor offset calculation
  drm/amd/display: Use new num clk levels struct for max mclk index
  drm/amd/display: Avoid setting pixel rate divider to N/A
  drm/amd/display: Use viewport height for subvp mall allocation size
  drm/amd/display: Update soc bounding box for dcn32/dcn321
  drm/amd/dc/dce120: Fix audio register mapping, stop triggering KASAN
  drm/amdgpu/psp: don't free PSP buffers on suspend
  fbcon: Use kzalloc() in fbcon_prepare_logo()
  dma-buf: fix racing conflict of dma_heap_add()
  drm/amd/amdgpu: reserve vm invalidation engine for firmware
  drm/amdgpu: Enable Aldebaran devices to report CU Occupancy
  drm/amdgpu: fix userptr HMM range handling v2
  drm/amdgpu: always register an MMU notifier for userptr
  drm/amdgpu/dm/mst: Fix uninitialized var in pre_compute_mst_dsc_configs_for_state()
  drm/amdgpu/dm/dp_mst: Don't grab mst_mgr->lock when computing DSC state
  ...

Author: torvalds

drivers/dma-buf/dma-buf.c

@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/dma-buf.h>
 #include <linux/dma-fence.h>
+#include <linux/dma-fence-unwrap.h>
 #include <linux/anon_inodes.h>
 #include <linux/export.h>
 #include <linux/debugfs.h>
@@ -391,8 +392,10 @@ static long dma_buf_import_sync_file(struct dma_buf *dmabuf,
 				     const void __user *user_data)
 {
 	struct dma_buf_import_sync_file arg;
-	struct dma_fence *fence;
+	struct dma_fence *fence, *f;
 	enum dma_resv_usage usage;
+	struct dma_fence_unwrap iter;
+	unsigned int num_fences;
 	int ret = 0;
 
 	if (copy_from_user(&arg, user_data, sizeof(arg)))
@@ -411,13 +414,21 @@ static long dma_buf_import_sync_file(struct dma_buf *dmabuf,
 	usage = (arg.flags & DMA_BUF_SYNC_WRITE) ? DMA_RESV_USAGE_WRITE :
 						   DMA_RESV_USAGE_READ;
 
-	dma_resv_lock(dmabuf->resv, NULL);
+	num_fences = 0;
+	dma_fence_unwrap_for_each(f, &iter, fence)
+		++num_fences;
 
-	ret = dma_resv_reserve_fences(dmabuf->resv, 1);
-	if (!ret)
-		dma_resv_add_fence(dmabuf->resv, fence, usage);
+	if (num_fences > 0) {
+		dma_resv_lock(dmabuf->resv, NULL);
 
-	dma_resv_unlock(dmabuf->resv);
+		ret = dma_resv_reserve_fences(dmabuf->resv, num_fences);
+		if (!ret) {
+			dma_fence_unwrap_for_each(f, &iter, fence)
+				dma_resv_add_fence(dmabuf->resv, f, usage);
+		}
+
+		dma_resv_unlock(dmabuf->resv);
+	}
 
 	dma_fence_put(fence);
 

drivers/dma-buf/dma-heap.c

@@ -233,18 +233,6 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info)
 		return ERR_PTR(-EINVAL);
 	}
 
-	/* check the name is unique */
-	mutex_lock(&heap_list_lock);
-	list_for_each_entry(h, &heap_list, list) {
-		if (!strcmp(h->name, exp_info->name)) {
-			mutex_unlock(&heap_list_lock);
-			pr_err("dma_heap: Already registered heap named %s\n",
-			       exp_info->name);
-			return ERR_PTR(-EINVAL);
-		}
-	}
-	mutex_unlock(&heap_list_lock);
-
 	heap = kzalloc(sizeof(*heap), GFP_KERNEL);
 	if (!heap)
 		return ERR_PTR(-ENOMEM);
@@ -283,13 +271,27 @@ struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info)
 		err_ret = ERR_CAST(dev_ret);
 		goto err2;
 	}
-	/* Add heap to the list */
+
 	mutex_lock(&heap_list_lock);
+	/* check the name is unique */
+	list_for_each_entry(h, &heap_list, list) {
+		if (!strcmp(h->name, exp_info->name)) {
+			mutex_unlock(&heap_list_lock);
+			pr_err("dma_heap: Already registered heap named %s\n",
+			       exp_info->name);
+			err_ret = ERR_PTR(-EINVAL);
+			goto err3;
+		}
+	}
+
+	/* Add heap to the list */
 	list_add(&heap->list, &heap_list);
 	mutex_unlock(&heap_list_lock);
 
 	return heap;
 
+err3:
+	device_destroy(dma_heap_class, heap->heap_devt);
 err2:
 	cdev_del(&heap->heap_cdev);
 err1:

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c

@@ -41,5 +41,6 @@ const struct kfd2kgd_calls aldebaran_kfd2kgd = {
 	.get_atc_vmid_pasid_mapping_info =
 				kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
+	.get_cu_occupancy = kgd_gfx_v9_get_cu_occupancy,
 	.program_trap_handler_settings = kgd_gfx_v9_program_trap_handler_settings
 };

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -986,6 +986,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 	struct amdkfd_process_info *process_info = mem->process_info;
 	struct amdgpu_bo *bo = mem->bo;
 	struct ttm_operation_ctx ctx = { true, false };
+	struct hmm_range *range;
 	int ret = 0;
 
 	mutex_lock(&process_info->lock);
@@ -1015,7 +1016,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 		return 0;
 	}
 
-	ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);
+	ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages, &range);
 	if (ret) {
 		pr_err("%s: Failed to get user pages: %d\n", __func__, ret);
 		goto unregister_out;
@@ -1033,7 +1034,7 @@ static int init_user_pages(struct kgd_mem *mem, uint64_t user_addr,
 	amdgpu_bo_unreserve(bo);
 
 release_out:
-	amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+	amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range);
 unregister_out:
 	if (ret)
 		amdgpu_mn_unregister(bo);
@@ -2370,6 +2371,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 	/* Go through userptr_inval_list and update any invalid user_pages */
 	list_for_each_entry(mem, &process_info->userptr_inval_list,
 			    validate_list.head) {
+		struct hmm_range *range;
+
 		invalid = atomic_read(&mem->invalid);
 		if (!invalid)
 			/* BO hasn't been invalidated since the last
@@ -2380,7 +2383,8 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 		bo = mem->bo;
 
 		/* Get updated user pages */
-		ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);
+		ret = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages,
+						   &range);
 		if (ret) {
 			pr_debug("Failed %d to get user pages\n", ret);
 
@@ -2399,7 +2403,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 			 * FIXME: Cannot ignore the return code, must hold
 			 * notifier_lock
 			 */
-			amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+			amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range);
 		}
 
 		/* Mark the BO as valid unless it was invalidated

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

@@ -209,6 +209,7 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 			list_add_tail(&e->tv.head, &bucket[priority]);
 
 		e->user_pages = NULL;
+		e->range = NULL;
 	}
 
 	/* Connect the sorted buckets in the output list. */

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h

@@ -26,6 +26,8 @@
 #include <drm/ttm/ttm_execbuf_util.h>
 #include <drm/amdgpu_drm.h>
 
+struct hmm_range;
+
 struct amdgpu_device;
 struct amdgpu_bo;
 struct amdgpu_bo_va;
@@ -36,6 +38,7 @@ struct amdgpu_bo_list_entry {
 	struct amdgpu_bo_va		*bo_va;
 	uint32_t			priority;
 	struct page			**user_pages;
+	struct hmm_range		*range;
 	bool				user_invalidated;
 };
 

drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c

@@ -328,7 +328,6 @@ static void amdgpu_connector_free_edid(struct drm_connector *connector)
 
 	kfree(amdgpu_connector->edid);
 	amdgpu_connector->edid = NULL;
-	drm_connector_update_edid_property(connector, NULL);
 }
 
 static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector)

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c

@@ -913,7 +913,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			goto out_free_user_pages;
 		}
 
-		r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages);
+		r = amdgpu_ttm_tt_get_user_pages(bo, e->user_pages, &e->range);
 		if (r) {
 			kvfree(e->user_pages);
 			e->user_pages = NULL;
@@ -991,9 +991,10 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 		if (!e->user_pages)
 			continue;
-		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range);
 		kvfree(e->user_pages);
 		e->user_pages = NULL;
+		e->range = NULL;
 	}
 	mutex_unlock(&p->bo_list->bo_list_mutex);
 	return r;
@@ -1273,7 +1274,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
 
-		r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+		r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range);
+		e->range = NULL;
 	}
 	if (r) {
 		r = -EAGAIN;

drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c

@@ -378,6 +378,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	struct amdgpu_device *adev = drm_to_adev(dev);
 	struct drm_amdgpu_gem_userptr *args = data;
 	struct drm_gem_object *gobj;
+	struct hmm_range *range;
 	struct amdgpu_bo *bo;
 	uint32_t handle;
 	int r;
@@ -413,14 +414,13 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 	if (r)
 		goto release_object;
 
-	if (args->flags & AMDGPU_GEM_USERPTR_REGISTER) {
-		r = amdgpu_mn_register(bo, args->addr);
-		if (r)
-			goto release_object;
-	}
+	r = amdgpu_mn_register(bo, args->addr);
+	if (r)
+		goto release_object;
 
 	if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE) {
-		r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages);
+		r = amdgpu_ttm_tt_get_user_pages(bo, bo->tbo.ttm->pages,
+						 &range);
 		if (r)
 			goto release_object;
 
@@ -443,7 +443,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 
 user_pages_done:
 	if (args->flags & AMDGPU_GEM_USERPTR_VALIDATE)
-		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, range);
 
 release_object:
 	drm_gem_object_put(gobj);

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c

@@ -479,6 +479,12 @@ int amdgpu_gmc_allocate_vm_inv_eng(struct amdgpu_device *adev)
 	unsigned i;
 	unsigned vmhub, inv_eng;
 
+	if (adev->enable_mes) {
+		/* reserve engine 5 for firmware */
+		for (vmhub = 0; vmhub < AMDGPU_MAX_VMHUBS; vmhub++)
+			vm_inv_engs[vmhub] &= ~(1 << 5);
+	}
+
 	for (i = 0; i < adev->num_rings; ++i) {
 		ring = adev->rings[i];
 		vmhub = ring->funcs->vmhub;