Merge tag 'drm-fixes-2023-12-01' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Weekly fixes, mostly amdgpu fixes with a scattering of nouveau, i915,
  and a couple of reverts. Hopefully it will quieten down in coming
  weeks.

  drm:
   - Revert unexport of prime helpers for fd/handle conversion

  dma_resv:
   - Do not double add fences in dma_resv_add_fence.

  gpuvm:
   - Fix GPUVM license identifier.

  i915:
   - Mark internal GSC engine with reserved uabi class
   - Take VGA converters into account in eDP probe
   - Fix intel_pre_plane_updates() call to ensure workarounds get applied

  panel:
   - Revert panel fixes as they require exporting device_is_dependent.

  nouveau:
   - fix oversized allocations in new vm path
   - fix zero-length array
   - remove a stray lock

  nt36523:
   - Fix error check for nt36523.

  amdgpu:
   - DMUB fix
   - DCN 3.5 fixes
   - XGMI fix
   - DCN 3.2 fixes
   - Vangogh suspend fix
   - NBIO 7.9 fix
   - GFX11 golden register fix
   - Backlight fix
   - NBIO 7.11 fix
   - IB test overflow fix
   - DCN 3.1.4 fixes
   - fix a runtime pm ref count
   - Retimer fix
   - ABM fix
   - DCN 3.1.5 fix
   - Fix AGP addressing
   - Fix possible memory leak in SMU error path
   - Make sure PME is enabled in D3
   - Fix possible NULL pointer dereference in debugfs
   - EEPROM fix
   - GC 9.4.3 fix

  amdkfd:
   - IP version check fix
   - Fix memory leak in pqm_uninit()"

* tag 'drm-fixes-2023-12-01' of git://anongit.freedesktop.org/drm/drm: (53 commits)
  Revert "drm/prime: Unexport helpers for fd/handle conversion"
  drm/amdgpu: Use another offset for GC 9.4.3 remap
  drm/amd/display: Fix some HostVM parameters in DML
  drm/amdkfd: Free gang_ctx_bo and wptr_bo in pqm_uninit
  drm/amdgpu: Update EEPROM I2C address for smu v13_0_0
  drm/amd/display: Allow DTBCLK disable for DCN35
  drm/amdgpu: Fix cat debugfs amdgpu_regs_didt causes kernel null pointer
  drm/amd: Enable PCIe PME from D3
  drm/amd/pm: fix a memleak in aldebaran_tables_init
  drm/amdgpu: fix AGP addressing when GART is not at 0
  drm/amd/display: update dcn315 lpddr pstate latency
  drm/amd/display: fix ABM disablement
  drm/amd/display: Fix black screen on video playback with embedded panel
  drm/amd/display: Fix conversions between bytes and KB
  drm/amdkfd: Use common function for IP version check
  drm/amd/display: Remove config update
  drm/amd/display: Update DCN35 clock table policy
  drm/amd/display: force toggle rate wa for first link training for a retimer
  drm/amdgpu: correct the amdgpu runtime dereference usage count
  drm/amd/display: Update min Z8 residency time to 2100 for DCN314
  ...

7 files changed, 42 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 08cb79401410..8ec11da0319f 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -181,6 +181,24 @@ int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 	return ret;
 }
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en)
+{
+	int ret = 0;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs && pp_funcs->notify_rlc_state) {
+		mutex_lock(&adev->pm.mutex);
+
+		ret = pp_funcs->notify_rlc_state(
+				adev->powerplay.pp_handle,
+				en);
+
+		mutex_unlock(&adev->pm.mutex);
+	}
+
+	return ret;
+}
+
 bool amdgpu_dpm_is_baco_supported(struct amdgpu_device *adev)
 {
 	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
index feccd2a7120d..482ea30147ab 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_dpm.h
@@ -415,6 +415,8 @@ int amdgpu_dpm_mode1_reset(struct amdgpu_device *adev);
 int amdgpu_dpm_set_mp1_state(struct amdgpu_device *adev,
 			     enum pp_mp1_state mp1_state);
 
+int amdgpu_dpm_notify_rlc_state(struct amdgpu_device *adev, bool en);
+
 int amdgpu_dpm_set_gfx_power_up_by_imu(struct amdgpu_device *adev);
 
 int amdgpu_dpm_baco_exit(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
index 1ead323f1c78..e1a5ee911dbb 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
@@ -1710,6 +1710,16 @@ static int smu_disable_dpms(struct smu_context *smu)
 		}
 	}
 
+	/* Notify SMU RLC is going to be off, stop RLC and SMU interaction.
+	 * otherwise SMU will hang while interacting with RLC if RLC is halted
+	 * this is a WA for Vangogh asic which fix the SMU hang issue.
+	 */
+	ret = smu_notify_rlc_state(smu, false);
+	if (ret) {
+		dev_err(adev->dev, "Fail to notify rlc status!\n");
+		return ret;
+	}
+
 	if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 4, 2) &&
 	    !((adev->flags & AMD_IS_APU) && adev->gfx.imu.funcs) &&
 	    !amdgpu_sriov_vf(adev) && adev->gfx.rlc.funcs->stop)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
index 8def291b18bc..23fa71cafb14 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
@@ -1360,6 +1360,11 @@ struct pptable_funcs {
 	 *                       management.
 	 */
 	int (*dpm_set_umsch_mm_enable)(struct smu_context *smu, bool enable);
+
+	/**
+	 * @notify_rlc_state: Notify RLC power state to SMU.
+	 */
+	int (*notify_rlc_state)(struct smu_context *smu, bool en);
 };
 
 typedef enum {
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 762b31455a0b..2ff6deedef95 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -2193,8 +2193,7 @@ static int vangogh_get_dpm_clock_table(struct smu_context *smu, struct dpm_clock
 	return 0;
 }
 
-
-static int vangogh_system_features_control(struct smu_context *smu, bool en)
+static int vangogh_notify_rlc_state(struct smu_context *smu, bool en)
 {
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
@@ -2523,7 +2522,7 @@ static const struct pptable_funcs vangogh_ppt_funcs = {
 	.print_clk_levels = vangogh_common_print_clk_levels,
 	.set_default_dpm_table = vangogh_set_default_dpm_tables,
 	.set_fine_grain_gfx_freq_parameters = vangogh_set_fine_grain_gfx_freq_parameters,
-	.system_features_control = vangogh_system_features_control,
+	.notify_rlc_state = vangogh_notify_rlc_state,
 	.feature_is_enabled = smu_cmn_feature_is_enabled,
 	.set_power_profile_mode = vangogh_set_power_profile_mode,
 	.get_power_profile_mode = vangogh_get_power_profile_mode,
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 1a6675d70a4b..f1440869d1ce 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -257,8 +257,11 @@ static int aldebaran_tables_init(struct smu_context *smu)
 	}
 
 	smu_table->ecc_table = kzalloc(tables[SMU_TABLE_ECCINFO].size, GFP_KERNEL);
-	if (!smu_table->ecc_table)
+	if (!smu_table->ecc_table) {
+		kfree(smu_table->metrics_table);
+		kfree(smu_table->gpu_metrics_table);
 		return -ENOMEM;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
index 80b3c3efc006..64766ac69c53 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h
@@ -97,6 +97,7 @@
 #define smu_get_default_config_table_settings(smu, config_table)	smu_ppt_funcs(get_default_config_table_settings, -EOPNOTSUPP, smu, config_table)
 #define smu_set_config_table(smu, config_table)				smu_ppt_funcs(set_config_table, -EOPNOTSUPP, smu, config_table)
 #define smu_init_pptable_microcode(smu)					smu_ppt_funcs(init_pptable_microcode, 0, smu)
+#define smu_notify_rlc_state(smu, en)					smu_ppt_funcs(notify_rlc_state, 0, smu, en)
 
 #endif
 #endif