Merge tag 'amd-drm-fixes-6.19-2026-01-22' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-6.19-2026-01-22:

amdgpu:
- GC 12 fix
- Misc error path fixes
- DC analog fix
- SMU 6 fixes
- TLB flush fix
- DC idle optimization fix

amdkfd:
- GC 11 cooperative launch fix

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patch.msgid.link/20260122204308.946339-1-alexander.deucher@amd.com

9 files changed, 36 insertions, 48 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 06c333b2213b..d78d9e7fb9d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -763,7 +763,7 @@ void amdgpu_fence_save_wptr(struct amdgpu_fence *af)
 }
 
 static void amdgpu_ring_backup_unprocessed_command(struct amdgpu_ring *ring,
-						   u64 start_wptr, u32 end_wptr)
+						   u64 start_wptr, u64 end_wptr)
 {
 	unsigned int first_idx = start_wptr & ring->buf_mask;
 	unsigned int last_idx = end_wptr & ring->buf_mask;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 8924380086c8..7e623f91f2d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -733,8 +733,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 
 	if (!adev->gmc.flush_pasid_uses_kiq || !ring->sched.ready) {
 
-		if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid)
-			return 0;
+		if (!adev->gmc.gmc_funcs->flush_gpu_tlb_pasid) {
+			r = 0;
+			goto error_unlock_reset;
+		}
 
 		if (adev->gmc.flush_tlb_needs_extra_type_2)
 			adev->gmc.gmc_funcs->flush_gpu_tlb_pasid(adev, pasid,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 586a58facca1..72ec455fa932 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -302,7 +302,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
 		if (job && job->vmid)
 			amdgpu_vmid_reset(adev, ring->vm_hub, job->vmid);
 		amdgpu_ring_undo(ring);
-		return r;
+		goto free_fence;
 	}
 	*f = &af->base;
 	/* get a ref for the job */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 0a0dcbf0798d..7ccb724b2488 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -217,8 +217,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (!entity)
 		return 0;
 
-	return drm_sched_job_init(&(*job)->base, entity, 1, owner,
-				  drm_client_id);
+	r = drm_sched_job_init(&(*job)->base, entity, 1, owner, drm_client_id);
+	if (!r)
+		return 0;
+
+	kfree((*job)->hw_vm_fence);
 
 err_fence:
 	kfree((*job)->hw_fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index d01d2712cf57..b786967022d2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -278,7 +278,6 @@ static void gfx_v12_0_select_se_sh(struct amdgpu_device *adev, u32 se_num,
 				   u32 sh_num, u32 instance, int xcc_id);
 static u32 gfx_v12_0_get_wgp_active_bitmap_per_sh(struct amdgpu_device *adev);
 
-static void gfx_v12_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure);
 static void gfx_v12_0_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg,
 				     uint32_t val);
 static int gfx_v12_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev);
@@ -4634,16 +4633,6 @@ static int gfx_v12_0_ring_preempt_ib(struct amdgpu_ring *ring)
 	return r;
 }
 
-static void gfx_v12_0_ring_emit_frame_cntl(struct amdgpu_ring *ring,
-					   bool start,
-					   bool secure)
-{
-	uint32_t v = secure ? FRAME_TMZ : 0;
-
-	amdgpu_ring_write(ring, PACKET3(PACKET3_FRAME_CONTROL, 0));
-	amdgpu_ring_write(ring, v | FRAME_CMD(start ? 0 : 1));
-}
-
 static void gfx_v12_0_ring_emit_rreg(struct amdgpu_ring *ring, uint32_t reg,
 				     uint32_t reg_val_offs)
 {
@@ -5520,7 +5509,6 @@ static const struct amdgpu_ring_funcs gfx_v12_0_ring_funcs_gfx = {
 	.emit_cntxcntl = gfx_v12_0_ring_emit_cntxcntl,
 	.init_cond_exec = gfx_v12_0_ring_emit_init_cond_exec,
 	.preempt_ib = gfx_v12_0_ring_preempt_ib,
-	.emit_frame_cntl = gfx_v12_0_ring_emit_frame_cntl,
 	.emit_wreg = gfx_v12_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v12_0_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = gfx_v12_0_ring_emit_reg_write_reg_wait,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
index 27aa1a5b120f..fbb751821c69 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
@@ -120,8 +120,7 @@ static inline bool kfd_dbg_has_gws_support(struct kfd_node *dev)
 			&& dev->kfd->mec2_fw_version < 0x1b6) ||
 		(KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1)
 			&& dev->kfd->mec2_fw_version < 0x30) ||
-		(KFD_GC_VERSION(dev) >= IP_VERSION(11, 0, 0) &&
-			KFD_GC_VERSION(dev) < IP_VERSION(12, 0, 0)))
+		kfd_dbg_has_cwsr_workaround(dev))
 		return false;
 
 	/* Assume debugging and cooperative launch supported otherwise. */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
index 697e232acebf..9fcd72d87d25 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c
@@ -248,8 +248,6 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 	struct vblank_control_work *vblank_work =
 		container_of(work, struct vblank_control_work, work);
 	struct amdgpu_display_manager *dm = vblank_work->dm;
-	struct amdgpu_device *adev = drm_to_adev(dm->ddev);
-	int r;
 
 	mutex_lock(&dm->dc_lock);
 
@@ -279,16 +277,7 @@ static void amdgpu_dm_crtc_vblank_control_worker(struct work_struct *work)
 
 	if (dm->active_vblank_irq_count == 0) {
 		dc_post_update_surfaces_to_stream(dm->dc);
-
-		r = amdgpu_dpm_pause_power_profile(adev, true);
-		if (r)
-			dev_warn(adev->dev, "failed to set default power profile mode\n");
-
 		dc_allow_idle_optimizations(dm->dc, true);
-
-		r = amdgpu_dpm_pause_power_profile(adev, false);
-		if (r)
-			dev_warn(adev->dev, "failed to restore the power profile mode\n");
 	}
 
 	mutex_unlock(&dm->dc_lock);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 0a2a3f233a0e..e7b0928bd3db 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -915,13 +915,19 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 		struct amdgpu_dm_connector *amdgpu_dm_connector;
 		const struct dc_link *dc_link;
 
-		use_polling |= connector->polled != DRM_CONNECTOR_POLL_HPD;
-
 		if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
 			continue;
 
 		amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
 
+		/*
+		 * Analog connectors may be hot-plugged unlike other connector
+		 * types that don't support HPD. Only poll analog connectors.
+		 */
+		use_polling |=
+			amdgpu_dm_connector->dc_link &&
+			dc_connector_supports_analog(amdgpu_dm_connector->dc_link->link_id.id);
+
 		dc_link = amdgpu_dm_connector->dc_link;
 
 		/*
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index 1f539cc65f41..695432d3045f 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -2273,8 +2273,6 @@ static int si_populate_smc_tdp_limits(struct amdgpu_device *adev,
 		if (scaling_factor == 0)
 			return -EINVAL;
 
-		memset(smc_table, 0, sizeof(SISLANDS_SMC_STATETABLE));
-
 		ret = si_calculate_adjusted_tdp_limits(adev,
 						       false, /* ??? */
 						       adev->pm.dpm.tdp_adjustment,
@@ -2283,6 +2281,12 @@ static int si_populate_smc_tdp_limits(struct amdgpu_device *adev,
 		if (ret)
 			return ret;
 
+		if (adev->pdev->device == 0x6611 && adev->pdev->revision == 0x87) {
+			/* Workaround buggy powertune on Radeon 430 and 520. */
+			tdp_limit = 32;
+			near_tdp_limit = 28;
+		}
+
 		smc_table->dpm2Params.TDPLimit =
 			cpu_to_be32(si_scale_power_for_smc(tdp_limit, scaling_factor) * 1000);
 		smc_table->dpm2Params.NearTDPLimit =
@@ -2328,16 +2332,8 @@ static int si_populate_smc_tdp_limits_2(struct amdgpu_device *adev,
 
 	if (ni_pi->enable_power_containment) {
 		SISLANDS_SMC_STATETABLE *smc_table = &si_pi->smc_statetable;
-		u32 scaling_factor = si_get_smc_power_scaling_factor(adev);
 		int ret;
 
-		memset(smc_table, 0, sizeof(SISLANDS_SMC_STATETABLE));
-
-		smc_table->dpm2Params.NearTDPLimit =
-			cpu_to_be32(si_scale_power_for_smc(adev->pm.dpm.near_tdp_limit_adjusted, scaling_factor) * 1000);
-		smc_table->dpm2Params.SafePowerLimit =
-			cpu_to_be32(si_scale_power_for_smc((adev->pm.dpm.near_tdp_limit_adjusted * SISLANDS_DPM2_TDP_SAFE_LIMIT_PERCENT) / 100, scaling_factor) * 1000);
-
 		ret = amdgpu_si_copy_bytes_to_smc(adev,
 						  (si_pi->state_table_start +
 						   offsetof(SISLANDS_SMC_STATETABLE, dpm2Params) +
@@ -3473,10 +3469,15 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		    (adev->pdev->revision == 0x80) ||
 		    (adev->pdev->revision == 0x81) ||
 		    (adev->pdev->revision == 0x83) ||
-		    (adev->pdev->revision == 0x87) ||
+		    (adev->pdev->revision == 0x87 &&
+				adev->pdev->device != 0x6611) ||
 		    (adev->pdev->device == 0x6604) ||
 		    (adev->pdev->device == 0x6605)) {
 			max_sclk = 75000;
+		} else if (adev->pdev->revision == 0x87 &&
+				adev->pdev->device == 0x6611) {
+			/* Radeon 430 and 520 */
+			max_sclk = 78000;
 		}
 	}
 
@@ -7600,12 +7601,12 @@ static int si_dpm_set_interrupt_state(struct amdgpu_device *adev,
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT);
 			cg_thermal_int |= CG_THERMAL_INT__THERM_INT_MASK_HIGH_MASK;
-			WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int);
+			WREG32(mmCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT);
 			cg_thermal_int &= ~CG_THERMAL_INT__THERM_INT_MASK_HIGH_MASK;
-			WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int);
+			WREG32(mmCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
 			break;
@@ -7617,12 +7618,12 @@ static int si_dpm_set_interrupt_state(struct amdgpu_device *adev,
 		case AMDGPU_IRQ_STATE_DISABLE:
 			cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT);
 			cg_thermal_int |= CG_THERMAL_INT__THERM_INT_MASK_LOW_MASK;
-			WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int);
+			WREG32(mmCG_THERMAL_INT, cg_thermal_int);
 			break;
 		case AMDGPU_IRQ_STATE_ENABLE:
 			cg_thermal_int = RREG32_SMC(mmCG_THERMAL_INT);
 			cg_thermal_int &= ~CG_THERMAL_INT__THERM_INT_MASK_LOW_MASK;
-			WREG32_SMC(mmCG_THERMAL_INT, cg_thermal_int);
+			WREG32(mmCG_THERMAL_INT, cg_thermal_int);
 			break;
 		default:
 			break;