Merge tag 'drm-fixes-2024-08-10' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Weekly regular fixes, mostly amdgpu with i915/xe having a few each,
  and then some misc bits across the board, seems about right for rc3
  time.

  client:
   - fix null ptr deref

  bridge:
   - connector: fix double free

  atomic:
   - fix async flip update

  panel:
   - document panel

  omap:
   - add config dependency

  tests:
   - fix gem shmem test

  drm buddy:
   - Add start address to trim function

  amdgpu:
   - DMCUB fix
   - Fix DET programming on some DCNs
   - DCC fixes
   - DCN 4.0.1 fixes
   - SMU 14.0.x update
   - MMHUB fix
   - DCN 3.1.4 fix
   - GC 12.0 fixes
   - Fix soft recovery error propogation
   - SDMA 7.0 fixes
   - DSC fix

  xe:
   - Fix off-by-one when processing RTP rules
   - Use dma_fence_chain_free in chain fence unused as a sync
   - Fix PL1 disable flow in xe_hwmon_power_max_write
   - Take ref to VM in delayed dump snapshot

  i915:
   - correct dual pps handling for MTL_PCH+ [display]
   - Adjust vma offset for framebuffer mmap offset [gem]
   - Fix Virtual Memory mapping boundaries calculation [gem]
   - Allow evicting to use the requested placement
   - Attempt to get pages without eviction first"

* tag 'drm-fixes-2024-08-10' of https://gitlab.freedesktop.org/drm/kernel: (31 commits)
  drm/xe: Take ref to VM in delayed snapshot
  drm/xe/hwmon: Fix PL1 disable flow in xe_hwmon_power_max_write
  drm/xe: Use dma_fence_chain_free in chain fence unused as a sync
  drm/xe/rtp: Fix off-by-one when processing rules
  drm/amdgpu: Add DCC GFX12 flag to enable address alignment
  drm/amdgpu: correct sdma7 max dw
  drm/amdgpu: Add address alignment support to DCC buffers
  drm/amd/display: Skip Recompute DSC Params if no Stream on Link
  drm/amdgpu: change non-dcc buffer copy configuration
  drm/amdgpu: Forward soft recovery errors to userspace
  drm/amdgpu: add golden setting for gc v12
  drm/buddy: Add start address support to trim function
  drm/amd/display: Add missing program DET segment call to pipe init
  drm/amd/display: Add missing DCN314 to the DML Makefile
  drm/amdgpu: force to use legacy inv in mmhub
  drm/amd/pm: update powerplay structure on smu v14.0.2/3
  drm/amd/display: Add missing mcache registers
  drm/amd/display: Add dcc propagation value
  drm/amd/display: Add missing DET segments programming
  drm/amd/display: Replace dm_execute_dmub_cmd with dc_wake_and_execute_dmub_cmd
  ...

2 files changed, 56 insertions, 12 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index a2195e28b625..cac6d4184506 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -290,6 +290,41 @@ out:
 	return i915_error_to_vmf_fault(err);
 }
 
+static void set_address_limits(struct vm_area_struct *area,
+			       struct i915_vma *vma,
+			       unsigned long obj_offset,
+			       unsigned long *start_vaddr,
+			       unsigned long *end_vaddr)
+{
+	unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */
+	long start, end; /* memory boundaries */
+
+	/*
+	 * Let's move into the ">> PAGE_SHIFT"
+	 * domain to be sure not to lose bits
+	 */
+	vm_start = area->vm_start >> PAGE_SHIFT;
+	vm_end = area->vm_end >> PAGE_SHIFT;
+	vma_size = vma->size >> PAGE_SHIFT;
+
+	/*
+	 * Calculate the memory boundaries by considering the offset
+	 * provided by the user during memory mapping and the offset
+	 * provided for the partial mapping.
+	 */
+	start = vm_start;
+	start -= obj_offset;
+	start += vma->gtt_view.partial.offset;
+	end = start + vma_size;
+
+	start = max_t(long, start, vm_start);
+	end = min_t(long, end, vm_end);
+
+	/* Let's move back into the "<< PAGE_SHIFT" domain */
+	*start_vaddr = (unsigned long)start << PAGE_SHIFT;
+	*end_vaddr = (unsigned long)end << PAGE_SHIFT;
+}
+
 static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 {
 #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT)
@@ -302,14 +337,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 	struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
 	bool write = area->vm_flags & VM_WRITE;
 	struct i915_gem_ww_ctx ww;
+	unsigned long obj_offset;
+	unsigned long start, end; /* memory boundaries */
 	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	pgoff_t page_offset;
+	unsigned long pfn;
 	int srcu;
 	int ret;
 
-	/* We don't use vmf->pgoff since that has the fake offset */
+	obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node);
 	page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT;
+	page_offset += obj_offset;
 
 	trace_i915_gem_object_fault(obj, page_offset, true, write);
 
@@ -402,12 +441,14 @@ retry:
 	if (ret)
 		goto err_unpin;
 
+	set_address_limits(area, vma, obj_offset, &start, &end);
+
+	pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT;
+	pfn += (start - area->vm_start) >> PAGE_SHIFT;
+	pfn += obj_offset - vma->gtt_view.partial.offset;
+
 	/* Finally, remap it using the new GTT offset */
-	ret = remap_io_mapping(area,
-			       area->vm_start + (vma->gtt_view.partial.offset << PAGE_SHIFT),
-			       (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT,
-			       min_t(u64, vma->size, area->vm_end - area->vm_start),
-			       &ggtt->iomap);
+	ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap);
 	if (ret)
 		goto err_fence;
 
@@ -1084,6 +1125,8 @@ int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma
 		mmo = mmap_offset_attach(obj, mmap_type, NULL);
 		if (IS_ERR(mmo))
 			return PTR_ERR(mmo);
+
+		vma->vm_pgoff += drm_vma_node_start(&mmo->vma_node);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index e6f177183c0f..5c72462d1f57 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -165,7 +165,6 @@ i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
 	i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
 				   obj->mm.region, &places[0], obj->bo_offset,
 				   obj->base.size, flags);
-	places[0].flags |= TTM_PL_FLAG_DESIRED;
 
 	/* Cache this on object? */
 	for (i = 0; i < num_allowed; ++i) {
@@ -779,13 +778,16 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 		.interruptible = true,
 		.no_wait_gpu = false,
 	};
-	int real_num_busy;
+	struct ttm_placement initial_placement;
+	struct ttm_place initial_place;
 	int ret;
 
 	/* First try only the requested placement. No eviction. */
-	real_num_busy = placement->num_placement;
-	placement->num_placement = 1;
-	ret = ttm_bo_validate(bo, placement, &ctx);
+	initial_placement.num_placement = 1;
+	memcpy(&initial_place, placement->placement, sizeof(struct ttm_place));
+	initial_place.flags |= TTM_PL_FLAG_DESIRED;
+	initial_placement.placement = &initial_place;
+	ret = ttm_bo_validate(bo, &initial_placement, &ctx);
 	if (ret) {
 		ret = i915_ttm_err_to_gem(ret);
 		/*
@@ -800,7 +802,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
 		 * If the initial attempt fails, allow all accepted placements,
 		 * evicting if necessary.
 		 */
-		placement->num_placement = real_num_busy;
 		ret = ttm_bo_validate(bo, placement, &ctx);
 		if (ret)
 			return i915_ttm_err_to_gem(ret);