Merge tag 'amd-drm-fixes-7.0-2026-03-12' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-7.0-2026-03-12:

amdgpu:
- SMU13 fix
- SMU14 fix
- Fixes for bringup hw testing
- Kerneldoc fix
- GC12 idle power fix for compute workloads
- DCCG fixes

amdkfd:
- Fix missing BO unreserve in an error path

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patch.msgid.link/20260312180351.3874990-1-alexander.deucher@amd.com

13 files changed, 73 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3e19b51a2763..d8296dfc5e8a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2690,8 +2690,10 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 		break;
 	default:
 		r = amdgpu_discovery_set_ip_blocks(adev);
-		if (r)
+		if (r) {
+			adev->num_ip_blocks = 0;
 			return r;
+		}
 		break;
 	}
 
@@ -3247,6 +3249,8 @@ int amdgpu_device_set_cg_state(struct amdgpu_device *adev,
 		i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip CG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
@@ -3286,6 +3290,8 @@ int amdgpu_device_set_pg_state(struct amdgpu_device *adev,
 		i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		/* skip PG for GFX, SDMA on S0ix */
 		if (adev->in_s0ix &&
 		    (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX ||
@@ -3493,6 +3499,8 @@ static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (!adev->ip_blocks[i].version->funcs->early_fini)
 			continue;
 
@@ -3570,6 +3578,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 		if (!adev->ip_blocks[i].status.sw)
 			continue;
 
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GMC) {
 			amdgpu_ucode_free_bo(adev);
 			amdgpu_free_static_csa(&adev->virt.csa_obj);
@@ -3596,6 +3606,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.late_initialized)
 			continue;
+		if (!adev->ip_blocks[i].version)
+			continue;
 		if (adev->ip_blocks[i].version->funcs->late_fini)
 			adev->ip_blocks[i].version->funcs->late_fini(&adev->ip_blocks[i]);
 		adev->ip_blocks[i].status.late_initialized = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 77e2133de5cf..7f19554b9ad1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -83,7 +83,7 @@ void amdgpu_driver_unload_kms(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = drm_to_adev(dev);
 
-	if (adev == NULL)
+	if (adev == NULL || !adev->num_ip_blocks)
 		return;
 
 	amdgpu_unregister_gpu_instance(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
index dc8d2f52c7d6..e244c12ceb23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h
@@ -368,15 +368,15 @@ struct amdgpu_mode_info {
 
 	struct drm_property *plane_ctm_property;
 	/**
-	 * @shaper_lut_property: Plane property to set pre-blending shaper LUT
-	 * that converts color content before 3D LUT. If
-	 * plane_shaper_tf_property != Identity TF, AMD color module will
+	 * @plane_shaper_lut_property: Plane property to set pre-blending
+	 * shaper LUT that converts color content before 3D LUT.
+	 * If plane_shaper_tf_property != Identity TF, AMD color module will
 	 * combine the user LUT values with pre-defined TF into the LUT
 	 * parameters to be programmed.
 	 */
 	struct drm_property *plane_shaper_lut_property;
 	/**
-	 * @shaper_lut_size_property: Plane property for the size of
+	 * @plane_shaper_lut_size_property: Plane property for the size of
 	 * pre-blending shaper LUT as supported by the driver (read-only).
 	 */
 	struct drm_property *plane_shaper_lut_size_property;
@@ -400,10 +400,10 @@ struct amdgpu_mode_info {
 	 */
 	struct drm_property *plane_lut3d_property;
 	/**
-	 * @plane_degamma_lut_size_property: Plane property to define the max
-	 * size of 3D LUT as supported by the driver (read-only). The max size
-	 * is the max size of one dimension and, therefore, the max number of
-	 * entries for 3D LUT array is the 3D LUT size cubed;
+	 * @plane_lut3d_size_property: Plane property to define the max size
+	 * of 3D LUT as supported by the driver (read-only). The max size is
+	 * the max size of one dimension and, therefore, the max number of
+	 * entries for 3D LUT array is the 3D LUT size cubed.
 	 */
 	struct drm_property *plane_lut3d_size_property;
 	/**
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 5bfa5d1d0b36..023c7345ea54 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -731,6 +731,9 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	int i;
 	struct amdgpu_device *adev = mes->adev;
 	union MESAPI_SET_HW_RESOURCES mes_set_hw_res_pkt;
+	uint32_t mes_rev = (pipe == AMDGPU_MES_SCHED_PIPE) ?
+		(mes->sched_version & AMDGPU_MES_VERSION_MASK) :
+		(mes->kiq_version & AMDGPU_MES_VERSION_MASK);
 
 	memset(&mes_set_hw_res_pkt, 0, sizeof(mes_set_hw_res_pkt));
 
@@ -785,7 +788,7 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	 * handling support, other queue will not use the oversubscribe timer.
 	 * handling  mode - 0: disabled; 1: basic version; 2: basic+ version
 	 */
-	mes_set_hw_res_pkt.oversubscription_timer = 50;
+	mes_set_hw_res_pkt.oversubscription_timer = mes_rev < 0x8b ? 0 : 50;
 	mes_set_hw_res_pkt.unmapped_doorbell_handling = 1;
 
 	if (amdgpu_mes_log_enable) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 8ea31699d38b..f5d2847e1cbb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -593,6 +593,7 @@ int pqm_update_queue_properties(struct process_queue_manager *pqm,
 					 p->queue_size)) {
 			pr_debug("ring buf 0x%llx size 0x%llx not mapped on GPU\n",
 				 p->queue_address, p->queue_size);
+			amdgpu_bo_unreserve(vm->root.bo);
 			return -EFAULT;
 		}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
index 3711d400773a..4c4e61bc91b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn20/dcn20_dccg.h
@@ -38,7 +38,11 @@
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 0),\
 	DCCG_SRII(PIXEL_RATE_CNTL, OTG, 1),\
 	SR(DISPCLK_FREQ_CHANGE_CNTL),\
-	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL)
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_REG_LIST_DCN2() \
 	DCCG_COMMON_REG_LIST_DCN_BASE(),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
index 75c69348027e..c4d4eea140f3 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn21/dcn21_dccg.c
@@ -96,6 +96,25 @@ static void dccg21_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppcl
 	dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk;
 }
 
+/*
+ * On DCN21 S0i3 resume, BIOS programs MICROSECOND_TIME_BASE_DIV to
+ * 0x00120464 as a marker that golden init has already been done.
+ * dcn21_s0i3_golden_init_wa() reads this marker later in bios_golden_init()
+ * to decide whether to skip golden init.
+ *
+ * dccg2_init() unconditionally overwrites MICROSECOND_TIME_BASE_DIV to
+ * 0x00120264, destroying the marker before it can be read.
+ *
+ * Guard the call: if the S0i3 marker is present, skip dccg2_init() so the
+ * WA can function correctly. bios_golden_init() will handle init in that case.
+ */
+static void dccg21_init(struct dccg *dccg)
+{
+	if (dccg2_is_s0i3_golden_init_wa_done(dccg))
+		return;
+
+	dccg2_init(dccg);
+}
 
 static const struct dccg_funcs dccg21_funcs = {
 	.update_dpp_dto = dccg21_update_dpp_dto,
@@ -103,7 +122,7 @@ static const struct dccg_funcs dccg21_funcs = {
 	.set_fifo_errdet_ovr_en = dccg2_set_fifo_errdet_ovr_en,
 	.otg_add_pixel = dccg2_otg_add_pixel,
 	.otg_drop_pixel = dccg2_otg_drop_pixel,
-	.dccg_init = dccg2_init,
+	.dccg_init = dccg21_init,
 	.refclk_setup = dccg2_refclk_setup, /* Deprecated - for backward compatibility only */
 	.allow_clock_gating = dccg2_allow_clock_gating,
 	.enable_memory_low_power = dccg2_enable_memory_low_power,
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
index 067e49cb238e..e2381ca0be0b 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn301/dcn301_dccg.h
@@ -34,7 +34,13 @@
 	DCCG_SRII(DTO_PARAM, DPPCLK, 1),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 2),\
 	DCCG_SRII(DTO_PARAM, DPPCLK, 3),\
-	SR(REFCLK_CNTL)
+	SR(REFCLK_CNTL),\
+	SR(DISPCLK_FREQ_CHANGE_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV),\
+	SR(MILLISECOND_TIME_BASE_DIV),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
+	SR(DCCG_GATE_DISABLE_CNTL2)
 
 #define DCCG_MASK_SH_LIST_DCN301(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_ENABLE, DPPCLK, 0, mask_sh),\
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
index bf659920d4cc..b5e3849ef12a 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn31/dcn31_dccg.h
@@ -64,9 +64,12 @@
 	SR(DSCCLK1_DTO_PARAM),\
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
-	SR(HDMISTREAMCLK0_DTO_PARAM)
+	SR(HDMISTREAMCLK0_DTO_PARAM),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 
 #define DCCG_MASK_SH_LIST_DCN31(mask_sh) \
diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
index a609635f35db..ecbdc05f7c45 100644
--- a/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn314/dcn314_dccg.h
@@ -70,11 +70,14 @@
 	SR(DSCCLK2_DTO_PARAM),\
 	SR(DSCCLK3_DTO_PARAM),\
 	SR(DSCCLK_DTO_CTRL),\
+	SR(DCCG_GATE_DISABLE_CNTL),\
 	SR(DCCG_GATE_DISABLE_CNTL2),\
 	SR(DCCG_GATE_DISABLE_CNTL3),\
 	SR(HDMISTREAMCLK0_DTO_PARAM),\
 	SR(OTG_PIXEL_RATE_DIV),\
-	SR(DTBCLK_P_CNTL)
+	SR(DTBCLK_P_CNTL),\
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL),\
+	SR(MICROSECOND_TIME_BASE_DIV)
 
 #define DCCG_MASK_SH_LIST_DCN314_COMMON(mask_sh) \
 	DCCG_SFI(DPPCLK_DTO_CTRL, DTO_DB_EN, DPPCLK, 0, mask_sh),\
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index b32c053950c9..a8d63d4d1f6e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -2222,7 +2222,8 @@ static int smu_v13_0_0_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_0_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
index f08cfa510a8a..5500a0f12f0e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
@@ -2224,7 +2224,8 @@ static int smu_v13_0_7_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v13_0_7_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
index 9994d4369da8..73762d9b5969 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
@@ -2311,7 +2311,8 @@ static int smu_v14_0_2_restore_user_od_settings(struct smu_context *smu)
 	user_od_table->OverDriveTable.FeatureCtrlMask = BIT(PP_OD_FEATURE_GFXCLK_BIT) |
 							BIT(PP_OD_FEATURE_UCLK_BIT) |
 							BIT(PP_OD_FEATURE_GFX_VF_CURVE_BIT) |
-							BIT(PP_OD_FEATURE_FAN_CURVE_BIT);
+							BIT(PP_OD_FEATURE_FAN_CURVE_BIT) |
+							BIT(PP_OD_FEATURE_ZERO_FAN_BIT);
 	res = smu_v14_0_2_upload_overdrive_table(smu, user_od_table);
 	user_od_table->OverDriveTable.FeatureCtrlMask = 0;
 	if (res == 0)