Merge tag 'drm-next-2024-01-19' of git://anongit.freedesktop.org/drm/drm

Pull more drm fixes from Dave Airlie:
 "This is mostly amdgpu and xe fixes, with an amdkfd and nouveau fix
  thrown in.

  The amdgpu ones are just the usual couple of weeks of fixes. The xe
  ones are bunch of cleanups for the new xe driver, the fix you put in
  on the merge commit and the kconfig fix that was hiding the problem
  from me.

  amdgpu:
   - DSC fixes
   - DC resource pool fixes
   - OTG fix
   - DML2 fixes
   - Aux fix
   - GFX10 RLC firmware handling fix
   - Revert a broken workaround for SMU 13.0.2
   - DC writeback fix
   - Enable gfxoff when ROCm apps are active on gfx11 with the proper FW
     version

  amdkfd:
   - Fix dma-buf exports using GEM handles

  nouveau:
   - fix a unneeded WARN_ON triggering

  xe:
   - Fix for definition of wakeref_t
   - Fix for an error code aliasing
   - Fix for VM_UNBIND_ALL in the case there are no bound VMAs
   - Fixes for a number of __iomem address space mismatches reported by
     sparse
   - Fixes for the assignment of exec_queue priority
   - A Fix for skip_guc_pc not taking effect
   - Workaround for a build problem on GCC 11
   - A couple of fixes for error paths
   - Fix a Flat CCS compression metadata copy issue
   - Fix a misplace array bounds checking
   - Don't have display support depend on EXPERT (as discussed on IRC)"

* tag 'drm-next-2024-01-19' of git://anongit.freedesktop.org/drm/drm: (71 commits)
  nouveau/vmm: don't set addr on the fail path to avoid warning
  drm/amdgpu: Enable GFXOFF for Compute on GFX11
  drm/amd/display: Drop 'acrtc' and add 'new_crtc_state' NULL check for writeback requests.
  drm/amdgpu: revert "Adjust removal control flow for smu v13_0_2"
  drm/amdkfd: init drm_client with funcs hook
  drm/amd/display: Fix a switch statement in populate_dml_output_cfg_from_stream_state()
  drm/amdgpu: Fix the null pointer when load rlc firmware
  drm/amd/display: Align the returned error code with legacy DP
  drm/amd/display: Fix DML2 watermark calculation
  drm/amd/display: Clear OPTC mem select on disable
  drm/amd/display: Port DENTIST hang and TDR fixes to OTG disable W/A
  drm/amd/display: Add logging resource checks
  drm/amd/display: Init link enc resources in dc_state only if res_pool presents
  drm/amd/display: Fix late derefrence 'dsc' check in 'link_set_dsc_pps_packet()'
  drm/amd/display: Avoid enum conversion warning
  drm/amd/pm: Fix smuv13.0.6 current clock reporting
  drm/amd/pm: Add error log for smu v13.0.6 reset
  drm/amdkfd: Fix 'node' NULL check in 'svm_range_get_range_boundaries()'
  drm/amdgpu: drop exp hw support check for GC 9.4.3
  drm/amdgpu: move debug options init prior to amdgpu device init
  ...

1 files changed, 8 insertions, 39 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 852cec98ff26..cc69005f5b46 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -128,6 +128,7 @@ enum AMDGPU_DEBUG_MASK {
 	AMDGPU_DEBUG_VM = BIT(0),
 	AMDGPU_DEBUG_LARGEBAR = BIT(1),
 	AMDGPU_DEBUG_DISABLE_GPU_SOFT_RECOVERY = BIT(2),
+	AMDGPU_DEBUG_USE_VRAM_FW_BUF = BIT(3),
 };
 
 unsigned int amdgpu_vram_limit = UINT_MAX;
@@ -210,7 +211,6 @@ int amdgpu_seamless = -1; /* auto */
 uint amdgpu_debug_mask;
 int amdgpu_agp = -1; /* auto */
 int amdgpu_wbrf = -1;
-int fw_bo_location = -1;
 
 static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work);
 
@@ -990,10 +990,6 @@ MODULE_PARM_DESC(wbrf,
 	"Enable Wifi RFI interference mitigation (0 = disabled, 1 = enabled, -1 = auto(default)");
 module_param_named(wbrf, amdgpu_wbrf, int, 0444);
 
-MODULE_PARM_DESC(fw_bo_location,
-	"location to put firmware bo for frontdoor loading (-1 = auto (default), 0 = on ram, 1 = on vram");
-module_param(fw_bo_location, int, 0644);
-
 /* These devices are not supported by amdgpu.
  * They are supported by the mach64, r128, radeon drivers
  */
@@ -2122,6 +2118,11 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev)
 		pr_info("debug: soft reset for GPU recovery disabled\n");
 		adev->debug_disable_soft_recovery = true;
 	}
+
+	if (amdgpu_debug_mask & AMDGPU_DEBUG_USE_VRAM_FW_BUF) {
+		pr_info("debug: place fw in vram for frontdoor loading\n");
+		adev->debug_use_vram_fw_buf = true;
+	}
 }
 
 static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags)
@@ -2233,6 +2234,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
 
 	pci_set_drvdata(pdev, ddev);
 
+	amdgpu_init_debug_options(adev);
+
 	ret = amdgpu_driver_load_kms(adev, flags);
 	if (ret)
 		goto err_pci;
@@ -2313,8 +2316,6 @@ retry_init:
 			amdgpu_get_secondary_funcs(adev);
 	}
 
-	amdgpu_init_debug_options(adev);
-
 	return 0;
 
 err_pci:
@@ -2336,38 +2337,6 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 		pm_runtime_forbid(dev->dev);
 	}
 
-	if (amdgpu_ip_version(adev, MP1_HWIP, 0) == IP_VERSION(13, 0, 2) &&
-	    !amdgpu_sriov_vf(adev)) {
-		bool need_to_reset_gpu = false;
-
-		if (adev->gmc.xgmi.num_physical_nodes > 1) {
-			struct amdgpu_hive_info *hive;
-
-			hive = amdgpu_get_xgmi_hive(adev);
-			if (hive->device_remove_count == 0)
-				need_to_reset_gpu = true;
-			hive->device_remove_count++;
-			amdgpu_put_xgmi_hive(hive);
-		} else {
-			need_to_reset_gpu = true;
-		}
-
-		/* Workaround for ASICs need to reset SMU.
-		 * Called only when the first device is removed.
-		 */
-		if (need_to_reset_gpu) {
-			struct amdgpu_reset_context reset_context;
-
-			adev->shutdown = true;
-			memset(&reset_context, 0, sizeof(reset_context));
-			reset_context.method = AMD_RESET_METHOD_NONE;
-			reset_context.reset_req_dev = adev;
-			set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
-			set_bit(AMDGPU_RESET_FOR_DEVICE_REMOVE, &reset_context.flags);
-			amdgpu_device_gpu_recover(adev, NULL, &reset_context);
-		}
-	}
-
 	amdgpu_driver_unload_kms(dev);
 
 	/*