Merge tag 'drm-fixes-2021-09-17' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Slightly busier than usual rc2, but mostly scattered amdgpu fixes,
  some i915 and etnaviv resolves an MMU/runtime PM blowup.

  amdgpu:
   - UBSAN fix
   - Powerplay table update fix
   - Fix use after free in BO moves
   - Debugfs init fixes
   - vblank workqueue fixes for headless devices
   - FPU fixes
   - sysfs_emit fixes
   - SMU updates for cyan skillfish
   - Backlight fixes when DMCU is not initialized
   - DP MST fixes
   - HDCP compliance fix
   - Link training fix
   - Runtime pm fix
   - Panel orientation fixes
   - Display GPUVM fix for yellow carp
   - Add missing license

  amdkfd:
   - Drop PCI atomics requirement if proper firmware is available
   - Suspend/resume fixes for IOMMUv2 cases

  radeon:
   - AGP fix

  i915:
   - Propagate DP link training error returns
   - Use max link params for eDP 1.3 and earlier
   - Build warning fixes
   - Gem selftest fixes
   - Ensure wakeref is held before hardware access

  etnaviv:
   - MMU context vs runtime PM fix"

* tag 'drm-fixes-2021-09-17' of git://anongit.freedesktop.org/drm/drm: (44 commits)
  drm/amdgpu/display: add a proper license to dc_link_dp.c
  drm/amd/display: Fix white screen page fault for gpuvm
  amd/display: enable panel orientation quirks
  drm/amdgpu: Demote TMZ unsupported log message from warning to info
  drm/amdgpu: Drop inline from amdgpu_ras_eeprom_max_record_count
  drm/amd/pm: fix runpm hang when amdgpu loaded prior to sound driver
  drm/radeon: pass drm dev radeon_agp_head_init directly
  drm/amdgpu: move iommu_resume before ip init/resume
  drm/amdgpu: add amdgpu_amdkfd_resume_iommu
  drm/amdkfd: separate kfd_iommu_resume from kfd_resume
  drm/amd/display: Link training retry fix for abort case
  drm/amd/display: Fix unstable HPCP compliance on Chrome Barcelo
  drm/amd/display: dsc mst 2 4K displays go dark with 2 lane HBR3
  drm/amd/display: Get backlight from PWM if DMCU is not initialized
  drm/amdkfd: make needs_pcie_atomics FW-version dependent
  drm/amdgpu: add manual sclk/vddc setting support for cyan skilfish(v3)
  drm/amdgpu: add some pptable funcs for cyan skilfish(v3)
  drm/amdgpu: update SMU driver interface for cyan skilfish(v3)
  drm/amdgpu: update SMU PPSMC for cyan skilfish
  drm/amdgpu: fix sysfs_emit/sysfs_emit_at warnings(v2)
  ...

Author: torvalds

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

@@ -758,7 +758,7 @@ enum amd_hw_ip_block_type {
 	MAX_HWIP
 };
 
-#define HWIP_MAX_INSTANCE	8
+#define HWIP_MAX_INSTANCE	10
 
 struct amd_powerplay {
 	void *pp_handle;

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

@@ -192,6 +192,16 @@ void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm)
 		kgd2kfd_suspend(adev->kfd.dev, run_pm);
 }
 
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd.dev)
+		r = kgd2kfd_resume_iommu(adev->kfd.dev);
+
+	return r;
+}
+
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm)
 {
 	int r = 0;

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

@@ -137,6 +137,7 @@ int amdgpu_amdkfd_init(void);
 void amdgpu_amdkfd_fini(void);
 
 void amdgpu_amdkfd_suspend(struct amdgpu_device *adev, bool run_pm);
+int amdgpu_amdkfd_resume_iommu(struct amdgpu_device *adev);
 int amdgpu_amdkfd_resume(struct amdgpu_device *adev, bool run_pm);
 void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
 			const void *ih_ring_entry);
@@ -327,6 +328,7 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
 void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm);
+int kgd2kfd_resume_iommu(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm);
 int kgd2kfd_pre_reset(struct kfd_dev *kfd);
 int kgd2kfd_post_reset(struct kfd_dev *kfd);
@@ -365,6 +367,11 @@ static inline void kgd2kfd_suspend(struct kfd_dev *kfd, bool run_pm)
 {
 }
 
+static int __maybe_unused kgd2kfd_resume_iommu(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
 static inline int kgd2kfd_resume(struct kfd_dev *kfd, bool run_pm)
 {
 	return 0;

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

@@ -1544,20 +1544,18 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	struct dentry *ent;
 	int r, i;
 
-
-
 	ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev,
 				  &fops_ib_preempt);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	ent = debugfs_create_file("amdgpu_force_sclk", 0200, root, adev,
 				  &fops_sclk_set);
-	if (!ent) {
+	if (IS_ERR(ent)) {
 		DRM_ERROR("unable to create amdgpu_set_sclk debugsfs file\n");
-		return -EIO;
+		return PTR_ERR(ent);
 	}
 
 	/* Register debugfs entries for amdgpu_ttm */

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

@@ -2394,6 +2394,10 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (r)
 		goto init_failed;
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		goto init_failed;
+
 	r = amdgpu_device_ip_hw_init_phase1(adev);
 	if (r)
 		goto init_failed;
@@ -3148,6 +3152,10 @@ static int amdgpu_device_ip_resume(struct amdgpu_device *adev)
 {
 	int r;
 
+	r = amdgpu_amdkfd_resume_iommu(adev);
+	if (r)
+		return r;
+
 	r = amdgpu_device_ip_resume_phase1(adev);
 	if (r)
 		return r;
@@ -4601,6 +4609,10 @@ int amdgpu_do_asic_reset(struct list_head *device_list_handle,
 				dev_warn(tmp_adev->dev, "asic atom init failed!");
 			} else {
 				dev_info(tmp_adev->dev, "GPU reset succeeded, trying to resume\n");
+				r = amdgpu_amdkfd_resume_iommu(tmp_adev);
+				if (r)
+					goto out;
+
 				r = amdgpu_device_ip_resume_phase1(tmp_adev);
 				if (r)
 					goto out;

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

@@ -598,7 +598,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 		break;
 	default:
 		adev->gmc.tmz_enabled = false;
-		dev_warn(adev->dev,
+		dev_info(adev->dev,
 			 "Trusted Memory Zone (TMZ) feature not supported\n");
 		break;
 	}

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

@@ -757,7 +757,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 	return res;
 }
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void)
+uint32_t amdgpu_ras_eeprom_max_record_count(void)
 {
 	return RAS_MAX_RECORD_COUNT;
 }

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

@@ -120,7 +120,7 @@ int amdgpu_ras_eeprom_read(struct amdgpu_ras_eeprom_control *control,
 int amdgpu_ras_eeprom_append(struct amdgpu_ras_eeprom_control *control,
 			     struct eeprom_table_record *records, const u32 num);
 
-inline uint32_t amdgpu_ras_eeprom_max_record_count(void);
+uint32_t amdgpu_ras_eeprom_max_record_count(void);
 
 void amdgpu_ras_debugfs_set_ret_size(struct amdgpu_ras_eeprom_control *control);
 

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

@@ -428,8 +428,8 @@ int amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
 	ent = debugfs_create_file(name,
 				  S_IFREG | S_IRUGO, root,
 				  ring, &amdgpu_debugfs_ring_fops);
-	if (!ent)
-		return -ENOMEM;
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
 
 	i_size_write(ent->d_inode, ring->ring_size + 12);
 	ring->ent = ent;

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

@@ -515,6 +515,15 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 		goto out;
 	}
 
+	if (bo->type == ttm_bo_type_device &&
+	    new_mem->mem_type == TTM_PL_VRAM &&
+	    old_mem->mem_type != TTM_PL_VRAM) {
+		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
+		 * accesses the BO after it's moved.
+		 */
+		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) ||
@@ -545,15 +554,6 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
 			return r;
 	}
 
-	if (bo->type == ttm_bo_type_device &&
-	    new_mem->mem_type == TTM_PL_VRAM &&
-	    old_mem->mem_type != TTM_PL_VRAM) {
-		/* amdgpu_bo_fault_reserve_notify will re-set this if the CPU
-		 * accesses the BO after it's moved.
-		 */
-		abo->flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	}
-
 out:
 	/* update statistics */
 	atomic64_add(bo->base.size, &adev->num_bytes_moved);