Merge tag 'amd-drm-fixes-6.2-2023-02-08' of...

Merge tag 'amd-drm-fixes-6.2-2023-02-08' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.2-2023-02-08:

amdgpu:
- Flickering fixes for DCN 2.1, 3.1.2/3
- Re-enable S/G display on DCN 3.1.4
- Properly fix S/G display with AGP aperture enabled
- Fix cursor offset with 180 rotation
- SMU13 fixes
- Use TGID for GPUVM traces
- Fix oops on in fence error path
- Don't run IB tests on hw rings when sw rings are in use
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230209045321.565132-1-alexander.deucher@amd.com

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

@@ -618,7 +618,13 @@ void amdgpu_fence_driver_sw_fini(struct amdgpu_device *adev)
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
-		if (!ring->no_scheduler)
+		/*
+		 * Notice we check for sched.ops since there's some
+		 * override on the meaning of sched.ready by amdgpu.
+		 * The natural check would be sched.ready, which is
+		 * set as drm_sched_init() finishes...
+		 */
+		if (ring->sched.ops)
 			drm_sched_fini(&ring->sched);
 
 		for (j = 0; j <= ring->fence_drv.num_fences_mask; ++j)

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

@@ -295,7 +295,7 @@ struct amdgpu_ring {
 #define amdgpu_ring_parse_cs(r, p, job, ib) ((r)->funcs->parse_cs((p), (job), (ib)))
 #define amdgpu_ring_patch_cs_in_place(r, p, job, ib) ((r)->funcs->patch_cs_in_place((p), (job), (ib)))
 #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
-#define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t))
+#define amdgpu_ring_test_ib(r, t) ((r)->funcs->test_ib ? (r)->funcs->test_ib((r), (t)) : 0)
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
 #define amdgpu_ring_get_wptr(r) (r)->funcs->get_wptr((r))
 #define amdgpu_ring_set_wptr(r) (r)->funcs->set_wptr((r))

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

@@ -974,7 +974,7 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params,
 			trace_amdgpu_vm_update_ptes(params, frag_start, upd_end,
 						    min(nptes, 32u), dst, incr,
 						    upd_flags,
-						    vm->task_info.pid,
+						    vm->task_info.tgid,
 						    vm->immediate.fence_context);
 			amdgpu_vm_pte_update_flags(params, to_amdgpu_bo_vm(pt),
 						   cursor.level, pe_start, dst,

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c

@@ -6877,7 +6877,6 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_gfx = {
 	.emit_gds_switch = gfx_v9_0_ring_emit_gds_switch,
 	.emit_hdp_flush = gfx_v9_0_ring_emit_hdp_flush,
 	.test_ring = gfx_v9_0_ring_test_ring,
-	.test_ib = gfx_v9_0_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_switch_buffer = gfx_v9_ring_emit_sb,

drivers/gpu/drm/amd/amdgpu/soc21.c

@@ -641,7 +641,9 @@ static int soc21_common_early_init(void *handle)
 			AMD_CG_SUPPORT_GFX_CGLS |
 			AMD_CG_SUPPORT_REPEATER_FGCG |
 			AMD_CG_SUPPORT_GFX_MGCG |
-			AMD_CG_SUPPORT_HDP_SD;
+			AMD_CG_SUPPORT_HDP_SD |
+			AMD_CG_SUPPORT_ATHUB_MGCG |
+			AMD_CG_SUPPORT_ATHUB_LS;
 		adev->pg_flags = AMD_PG_SUPPORT_VCN |
 			AMD_PG_SUPPORT_VCN_DPG |
 			AMD_PG_SUPPORT_JPEG;

drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c

@@ -1184,9 +1184,25 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 
 	memset(pa_config, 0, sizeof(*pa_config));
 
-	logical_addr_low  = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
-	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
+	agp_base = 0;
+	agp_bot = adev->gmc.agp_start >> 24;
+	agp_top = adev->gmc.agp_end >> 24;
 
+	/* AGP aperture is disabled */
+	if (agp_bot == agp_top) {
+		logical_addr_low  = adev->gmc.vram_start >> 18;
+		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
+			/*
+			 * Raven2 has a HW issue that it is unable to use the vram which
+			 * is out of MC_VM_SYSTEM_APERTURE_HIGH_ADDR. So here is the
+			 * workaround that increase system aperture high address (add 1)
+			 * to get rid of the VM fault and hardware hang.
+			 */
+			logical_addr_high = (adev->gmc.fb_end >> 18) + 0x1;
+		else
+			logical_addr_high = adev->gmc.vram_end >> 18;
+	} else {
+		logical_addr_low  = min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18;
 		if (adev->apu_flags & AMD_APU_IS_RAVEN2)
 			/*
 			 * Raven2 has a HW issue that it is unable to use the vram which
@@ -1197,11 +1213,9 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
 			logical_addr_high = max((adev->gmc.fb_end >> 18) + 0x1, adev->gmc.agp_end >> 18);
 		else
 			logical_addr_high = max(adev->gmc.fb_end, adev->gmc.agp_end) >> 18;
+	}
 
-	agp_base = 0;
-	agp_bot = adev->gmc.agp_start >> 24;
-	agp_top = adev->gmc.agp_end >> 24;
-
+	pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
 
 	page_table_start.high_part = (u32)(adev->gmc.gart_start >> 44) & 0xF;
 	page_table_start.low_part = (u32)(adev->gmc.gart_start >> 12);
@@ -1499,10 +1513,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 			    (adev->apu_flags & AMD_APU_IS_PICASSO))
 				init_data.flags.gpu_vm_support = true;
 			break;
-		case IP_VERSION(2, 1, 0):
 		case IP_VERSION(3, 0, 1):
-		case IP_VERSION(3, 1, 2):
-		case IP_VERSION(3, 1, 3):
+		case IP_VERSION(3, 1, 4):
 		case IP_VERSION(3, 1, 6):
 			init_data.flags.gpu_vm_support = true;
 			break;

drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c

@@ -3626,7 +3626,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 						(int)hubp->curs_attr.width || pos_cpy.x
 						<= (int)hubp->curs_attr.width +
 						pipe_ctx->plane_state->src_rect.x) {
-						pos_cpy.x = temp_x + viewport_width;
+						pos_cpy.x = 2 * viewport_width - temp_x;
 					}
 				}
 			} else {

drivers/gpu/drm/amd/pm/amdgpu_pm.c

@@ -1991,6 +1991,8 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_
 		case IP_VERSION(9, 4, 2):
 		case IP_VERSION(10, 3, 0):
 		case IP_VERSION(11, 0, 0):
+		case IP_VERSION(11, 0, 1):
+		case IP_VERSION(11, 0, 2):
 			*states = ATTR_STATE_SUPPORTED;
 			break;
 		default:

drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h

@@ -123,7 +123,8 @@
 									(1 << FEATURE_DS_FCLK_BIT) | \
 									(1 << FEATURE_DS_LCLK_BIT) | \
 									(1 << FEATURE_DS_DCFCLK_BIT) | \
-									(1 << FEATURE_DS_UCLK_BIT))
+									(1 << FEATURE_DS_UCLK_BIT) | \
+									(1ULL << FEATURE_DS_VCN_BIT))
 
 //For use with feature control messages
 typedef enum {
@@ -522,9 +523,9 @@ typedef enum  {
   TEMP_HOTSPOT_M,
   TEMP_MEM,
   TEMP_VR_GFX,
-  TEMP_VR_SOC,
   TEMP_VR_MEM0,
   TEMP_VR_MEM1,
+  TEMP_VR_SOC,
   TEMP_VR_U,
   TEMP_LIQUID0,
   TEMP_LIQUID1,

drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_7.h

@@ -113,7 +113,7 @@
 #define NUM_FEATURES                          64
 
 #define ALLOWED_FEATURE_CTRL_DEFAULT 0xFFFFFFFFFFFFFFFFULL
-#define ALLOWED_FEATURE_CTRL_SCPM        (1 << FEATURE_DPM_GFXCLK_BIT) | \
+#define ALLOWED_FEATURE_CTRL_SCPM	((1 << FEATURE_DPM_GFXCLK_BIT) | \
 					(1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \
 					(1 << FEATURE_DPM_UCLK_BIT) | \
 					(1 << FEATURE_DPM_FCLK_BIT) | \
@@ -126,7 +126,8 @@
 					(1 << FEATURE_DS_FCLK_BIT) | \
 					(1 << FEATURE_DS_LCLK_BIT) | \
 					(1 << FEATURE_DS_DCFCLK_BIT) | \
-                                         (1 << FEATURE_DS_UCLK_BIT)
+					(1 << FEATURE_DS_UCLK_BIT) | \
+					(1ULL << FEATURE_DS_VCN_BIT))
 
 //For use with feature control messages
 typedef enum {

drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h

@@ -28,11 +28,11 @@
 #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
 #define SMU13_DRIVER_IF_VERSION_ALDE 0x08
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x34
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_0 0x37
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x35
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x37
 #define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D
 
 #define SMU13_MODE1_RESET_WAIT_TIME_IN_MS 500  //500ms

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c

@@ -407,6 +407,9 @@ static int smu_v13_0_0_setup_pptable(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 
+	if (amdgpu_sriov_vf(smu->adev))
+		return 0;
+
 	ret = smu_v13_0_0_get_pptable_from_pmfw(smu,
 						&smu_table->power_play_table,
 						&smu_table->power_play_table_size);
@@ -1257,6 +1260,9 @@ static int smu_v13_0_0_get_thermal_temperature_range(struct smu_context *smu,
 		table_context->power_play_table;
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 
+	if (amdgpu_sriov_vf(smu->adev))
+		return 0;
+
 	if (!range)
 		return -EINVAL;
 

drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c

@@ -124,6 +124,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_7_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(DFCstateControl,		PPSMC_MSG_SetExternalClientDfCstateAllow, 0),
 	MSG_MAP(ArmD3,				PPSMC_MSG_ArmD3,                       0),
 	MSG_MAP(AllowGpo,			PPSMC_MSG_SetGpoAllow,           0),
+	MSG_MAP(GetPptLimit,			PPSMC_MSG_GetPptLimit,                 0),
 };
 
 static struct cmn2asic_mapping smu_v13_0_7_clk_map[SMU_CLK_COUNT] = {