Merge tag 'amd-drm-fixes-5.16-2021-11-03' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-fixes-5.16-2021-11-03:

amdgpu:
- GPU reset fix
- Aldebaran fix
- Yellow Carp fixes
- DCN2.1 DMCUB fix
- IOMMU regression fix for Picasso
- DSC display fixes
- BPC display calculation fixes
- Other misc display fixes

amdkfd:
- SVM fixes
- Fix gfx version for renoir

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211104024447.4535-1-alexander.deucher@amd.com

4 files changed, 25 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 6e40cc1bc6dc..6c38dd9f41be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2398,10 +2398,6 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.pending_reset)
 		amdgpu_amdkfd_device_init(adev);
 
-	r = amdgpu_amdkfd_resume_iommu(adev);
-	if (r)
-		goto init_failed;
-
 	amdgpu_fru_get_product_info(adev);
 
 init_failed:
@@ -4850,6 +4846,9 @@ static void amdgpu_device_recheck_guilty_jobs(
 
 		/* clear job's guilty and depend the folowing step to decide the real one */
 		drm_sched_reset_karma(s_job);
+		/* for the real bad job, it will be resubmitted twice, adding a dma_fence_get
+		 * to make sure fence is balanced */
+		dma_fence_get(s_job->s_fence->parent);
 		drm_sched_resubmit_jobs_ext(&ring->sched, 1);
 
 		ret = dma_fence_wait_timeout(s_job->s_fence->parent, false, ring->sched.timeout);
@@ -4885,6 +4884,7 @@ retry:
 
 		/* got the hw fence, signal finished fence */
 		atomic_dec(ring->sched.score);
+		dma_fence_put(s_job->s_fence->parent);
 		dma_fence_get(&s_job->s_fence->finished);
 		dma_fence_signal(&s_job->s_fence->finished);
 		dma_fence_put(&s_job->s_fence->finished);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index dfe667ea8b05..651c7abfde03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1423,6 +1423,8 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 	struct drm_amdgpu_info_firmware fw_info;
 	struct drm_amdgpu_query_fw query_fw;
 	struct atom_context *ctx = adev->mode_info.atom_context;
+	uint8_t smu_minor, smu_debug;
+	uint16_t smu_major;
 	int ret, i;
 
 	static const char *ta_fw_name[TA_FW_TYPE_MAX_INDEX] = {
@@ -1568,8 +1570,11 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
 	ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
 	if (ret)
 		return ret;
-	seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x\n",
-		   fw_info.feature, fw_info.ver);
+	smu_major = (fw_info.ver >> 16) & 0xffff;
+	smu_minor = (fw_info.ver >> 8) & 0xff;
+	smu_debug = (fw_info.ver >> 0) & 0xff;
+	seq_printf(m, "SMC feature version: %u, firmware version: 0x%08x (%d.%d.%d)\n",
+		   fw_info.feature, fw_info.ver, smu_major, smu_minor, smu_debug);
 
 	/* SDMA */
 	query_fw.fw_type = AMDGPU_INFO_FW_SDMA;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 90a834dc4008..b53b36f5ae92 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -8316,11 +8316,8 @@ static void gfx_v10_cntl_power_gating(struct amdgpu_device *adev, bool enable)
 	if (enable && (adev->pg_flags & AMD_PG_SUPPORT_GFX_PG)) {
 		switch (adev->ip_versions[GC_HWIP][0]) {
 		case IP_VERSION(10, 3, 1):
-			data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
-			WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
-			break;
 		case IP_VERSION(10, 3, 3):
-			data = 0x1388 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
+			data = 0x4E20 & RLC_PG_DELAY_3__CGCG_ACTIVE_BEFORE_CGPG_MASK_Vangogh;
 			WREG32_SOC15(GC, 0, mmRLC_PG_DELAY_3, data);
 			break;
 		default:
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
index 497b86c376c6..90f0aefbdb39 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@@ -54,15 +54,17 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 		seg_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE_ALDE),
 			MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+		max_region =
+			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE, PF_MAX_REGION);
 	} else {
 		xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL);
 		seg_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE),
 			MC_VM_XGMI_LFB_SIZE, PF_LFB_SIZE) << 24;
+		max_region =
+			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
 	}
 
-	max_region =
-		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
 
 
 	switch (adev->asic_type) {
@@ -89,9 +91,15 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 		if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes)
 			return -EINVAL;
 
-		adev->gmc.xgmi.physical_node_id =
-		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
-			      PF_LFB_REGION);
+		if (adev->asic_type == CHIP_ALDEBARAN) {
+			adev->gmc.xgmi.physical_node_id =
+				REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL_ALDE,
+						PF_LFB_REGION);
+		} else {
+			adev->gmc.xgmi.physical_node_id =
+				REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL,
+						PF_LFB_REGION);
+		}
 
 		if (adev->gmc.xgmi.physical_node_id > max_physical_node_id)
 			return -EINVAL;