Merge tag 'drm-next-2022-12-23' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Holiday fixes!

  Two batches from amd, and one group of i915 changes.

  amdgpu:
   - Spelling fix
   - BO pin fix
   - Properly handle polaris 10/11 overlap asics
   - GMC9 fix
   - SR-IOV suspend fix
   - DCN 3.1.4 fix
   - KFD userptr locking fix
   - SMU13.x fixes
   - GDS/GWS/OA handling fix
   - Reserved VMID handling fixes
   - FRU EEPROM fix
   - BO validation fixes
   - Avoid large variable on the stack
   - S0ix fixes
   - SMU 13.x fixes
   - VCN fix
   - Add missing fence reference

  amdkfd:
   - Fix init vm error handling
   - Fix double release of compute pasid

  i915
   - Documentation fixes
   - OA-perf related fix
   - VLV/CHV HDMI/DP audio fix
   - Display DDI/Transcoder fix
   - Migrate fixes"

* tag 'drm-next-2022-12-23' of git://anongit.freedesktop.org/drm/drm: (39 commits)
  drm/amdgpu: grab extra fence reference for drm_sched_job_add_dependency
  drm/amdgpu: enable VCN DPG for GC IP v11.0.4
  drm/amdgpu: skip mes self test after s0i3 resume for MES IP v11.0
  drm/amd/pm: correct the fan speed retrieving in PWM for some SMU13 asics
  drm/amd/pm: bump SMU13.0.0 driver_if header to version 0x34
  drm/amdgpu: skip MES for S0ix as well since it's part of GFX
  drm/amd/pm: avoid large variable on kernel stack
  drm/amdkfd: Fix double release compute pasid
  drm/amdkfd: Fix kfd_process_device_init_vm error handling
  drm/amd/pm: update SMU13.0.0 reported maximum shader clock
  drm/amd/pm: correct SMU13.0.0 pstate profiling clock settings
  drm/amd/pm: enable GPO dynamic control support for SMU13.0.7
  drm/amd/pm: enable GPO dynamic control support for SMU13.0.0
  drm/amdgpu: revert "generally allow over-commit during BO allocation"
  drm/amdgpu: Remove unnecessary domain argument
  drm/amdgpu: Fix size validation for non-exclusive domains (v4)
  drm/amdgpu: Check if fru_addr is not NULL (v2)
  drm/i915/ttm: consider CCS for backup objects
  drm/i915/migrate: fix corner case in CCS aux copying
  drm/amdgpu: rework reserved VMID handling
  ...

3 files changed, 26 insertions, 5 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 733696057761..1a0886b8aaa1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -785,6 +785,9 @@ bool i915_gem_object_needs_ccs_pages(struct drm_i915_gem_object *obj)
 	if (!HAS_FLAT_CCS(to_i915(obj->base.dev)))
 		return false;
 
+	if (obj->flags & I915_BO_ALLOC_CCS_AUX)
+		return true;
+
 	for (i = 0; i < obj->mm.n_placements; i++) {
 		/* Compression is not allowed for the objects with smem placement */
 		if (obj->mm.placements[i]->type == INTEL_MEMORY_SYSTEM)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index d0d6772e6f36..ab4c2f90a564 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -327,16 +327,18 @@ struct drm_i915_gem_object {
  * dealing with userspace objects the CPU fault handler is free to ignore this.
  */
 #define I915_BO_ALLOC_GPU_ONLY	  BIT(6)
+#define I915_BO_ALLOC_CCS_AUX	  BIT(7)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \
 			     I915_BO_ALLOC_VOLATILE | \
 			     I915_BO_ALLOC_CPU_CLEAR | \
 			     I915_BO_ALLOC_USER | \
 			     I915_BO_ALLOC_PM_VOLATILE | \
 			     I915_BO_ALLOC_PM_EARLY | \
-			     I915_BO_ALLOC_GPU_ONLY)
-#define I915_BO_READONLY          BIT(7)
-#define I915_TILING_QUIRK_BIT     8 /* unknown swizzling; do not release! */
-#define I915_BO_PROTECTED         BIT(9)
+			     I915_BO_ALLOC_GPU_ONLY | \
+			     I915_BO_ALLOC_CCS_AUX)
+#define I915_BO_READONLY          BIT(8)
+#define I915_TILING_QUIRK_BIT     9 /* unknown swizzling; do not release! */
+#define I915_BO_PROTECTED         BIT(10)
 	/**
 	 * @mem_flags - Mutable placement-related flags
 	 *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
index 07e49f22f2de..7e67742bc65e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
@@ -50,6 +50,7 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply,
 		container_of(bo->bdev, typeof(*i915), bdev);
 	struct drm_i915_gem_object *backup;
 	struct ttm_operation_ctx ctx = {};
+	unsigned int flags;
 	int err = 0;
 
 	if (bo->resource->mem_type == I915_PL_SYSTEM || obj->ttm.backup)
@@ -65,7 +66,22 @@ static int i915_ttm_backup(struct i915_gem_apply_to_region *apply,
 	if (obj->flags & I915_BO_ALLOC_PM_VOLATILE)
 		return 0;
 
-	backup = i915_gem_object_create_shmem(i915, obj->base.size);
+	/*
+	 * It seems that we might have some framebuffers still pinned at this
+	 * stage, but for such objects we might also need to deal with the CCS
+	 * aux state. Make sure we force the save/restore of the CCS state,
+	 * otherwise we might observe display corruption, when returning from
+	 * suspend.
+	 */
+	flags = 0;
+	if (i915_gem_object_needs_ccs_pages(obj)) {
+		WARN_ON_ONCE(!i915_gem_object_is_framebuffer(obj));
+		WARN_ON_ONCE(!pm_apply->allow_gpu);
+
+		flags = I915_BO_ALLOC_CCS_AUX;
+	}
+	backup = i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_SMEM],
+					       obj->base.size, 0, flags);
 	if (IS_ERR(backup))
 		return PTR_ERR(backup);