Merge tag 'amd-drm-fixes-7.0-2026-02-26' of https://gitlab.freedesktop.org/agd5f/linux into drm-fixes

amd-drm-fixes-7.0-2026-02-26:

amdgpu:
- UserQ fixes
- DC fix
- RAS fixes
- VCN 5 fix
- Slot reset fix
- Remove MES workaround that's no longer needed

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patch.msgid.link/20260226161330.3549393-1-alexander.deucher@amd.com

8 files changed, 42 insertions, 28 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
index afe5ca81beec..db7858fe0c3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
@@ -641,6 +641,7 @@ static void aca_error_fini(struct aca_error *aerr)
 		aca_bank_error_remove(aerr, bank_error);
 
 out_unlock:
+	mutex_unlock(&aerr->lock);
 	mutex_destroy(&aerr->lock);
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d9789e0b5201..3e19b51a2763 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -7059,6 +7059,15 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	dev_info(adev->dev, "PCI error: slot reset callback!!\n");
 
 	memset(&reset_context, 0, sizeof(reset_context));
+	INIT_LIST_HEAD(&device_list);
+	hive = amdgpu_get_xgmi_hive(adev);
+	if (hive) {
+		mutex_lock(&hive->hive_lock);
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
+			list_add_tail(&tmp_adev->reset_list, &device_list);
+	} else {
+		list_add_tail(&adev->reset_list, &device_list);
+	}
 
 	if (adev->pcie_reset_ctx.swus)
 		link_dev = adev->pcie_reset_ctx.swus;
@@ -7099,19 +7108,13 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev)
 	reset_context.reset_req_dev = adev;
 	set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
 	set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags);
-	INIT_LIST_HEAD(&device_list);
 
-	hive = amdgpu_get_xgmi_hive(adev);
 	if (hive) {
-		mutex_lock(&hive->hive_lock);
 		reset_context.hive = hive;
-		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+		list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head)
 			tmp_adev->pcie_reset_ctx.in_link_reset = true;
-			list_add_tail(&tmp_adev->reset_list, &device_list);
-		}
 	} else {
 		set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags);
-		list_add_tail(&adev->reset_list, &device_list);
 	}
 
 	r = amdgpu_device_asic_reset(adev, &device_list, &reset_context);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
index 6e8aad91bcd3..0d3c18f04ac3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
@@ -332,13 +332,13 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	if (!context || !context->initialized) {
 		dev_err(adev->dev, "TA is not initialized\n");
 		ret = -EINVAL;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	if (!psp->ta_funcs || !psp->ta_funcs->fn_ta_invoke) {
 		dev_err(adev->dev, "Unsupported function to invoke TA\n");
 		ret = -EOPNOTSUPP;
-		goto err_free_shared_buf;
+		goto free_shared_buf;
 	}
 
 	context->session_id = ta_id;
@@ -346,7 +346,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 	mutex_lock(&psp->ras_context.mutex);
 	ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len);
 	if (ret)
-		goto err_free_shared_buf;
+		goto unlock;
 
 	ret = psp_fn_ta_invoke(psp, cmd_id);
 	if (ret || context->resp_status) {
@@ -354,15 +354,17 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
 			ret, context->resp_status);
 		if (!ret) {
 			ret = -EINVAL;
-			goto err_free_shared_buf;
+			goto unlock;
 		}
 	}
 
 	if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len))
 		ret = -EFAULT;
 
-err_free_shared_buf:
+unlock:
 	mutex_unlock(&psp->ras_context.mutex);
+
+free_shared_buf:
 	kfree(shared_buf);
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index 8013260e29dc..7e9cf1868cc9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -35,6 +35,8 @@
 static const struct dma_fence_ops amdgpu_userq_fence_ops;
 static struct kmem_cache *amdgpu_userq_fence_slab;
 
+#define AMDGPU_USERQ_MAX_HANDLES	(1U << 16)
+
 int amdgpu_userq_fence_slab_init(void)
 {
 	amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence",
@@ -478,6 +480,11 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (args->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    args->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_syncobj_handles = args->num_syncobj_handles;
 	syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles),
 				      size_mul(sizeof(u32), num_syncobj_handles));
@@ -664,6 +671,11 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 	if (!amdgpu_userq_enabled(dev))
 		return -ENOTSUPP;
 
+	if (wait_info->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES ||
+	    wait_info->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES)
+		return -EINVAL;
+
 	num_read_bo_handles = wait_info->num_bo_read_handles;
 	bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles),
 				      size_mul(sizeof(u32), num_read_bo_handles));
@@ -833,7 +845,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_read[i]->resv,
 						DMA_RESV_USAGE_READ, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -850,7 +862,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 
 			dma_resv_for_each_fence(&resv_cursor, gobj_write[i]->resv,
 						DMA_RESV_USAGE_WRITE, fence) {
-				if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+				if (num_fences >= wait_info->num_fences) {
 					r = -EINVAL;
 					goto free_fences;
 				}
@@ -874,8 +886,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 					goto free_fences;
 
 				dma_fence_unwrap_for_each(f, &iter, fence) {
-					if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+					if (num_fences >= wait_info->num_fences) {
 						r = -EINVAL;
+						dma_fence_put(fence);
 						goto free_fences;
 					}
 
@@ -898,8 +911,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data,
 			if (r)
 				goto free_fences;
 
-			if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) {
+			if (num_fences >= wait_info->num_fences) {
 				r = -EINVAL;
+				dma_fence_put(fence);
 				goto free_fences;
 			}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 09ebb13ca5e8..a926a330700e 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -720,11 +720,6 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes)
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
 	mes_set_hw_res_pkt.oversubscription_timer = 50;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x7f)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(mes->adev->dev,
-			      "MES FW version must be >= 0x7f to enable LR compute workaround.\n");
 
 	if (amdgpu_mes_log_enable) {
 		mes_set_hw_res_pkt.enable_mes_event_int_logging = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index b1c864dc79a8..5bfa5d1d0b36 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -779,11 +779,6 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe)
 	mes_set_hw_res_pkt.use_different_vmid_compute = 1;
 	mes_set_hw_res_pkt.enable_reg_active_poll = 1;
 	mes_set_hw_res_pkt.enable_level_process_quantum_check = 1;
-	if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x82)
-		mes_set_hw_res_pkt.enable_lr_compute_wa = 1;
-	else
-		dev_info_once(adev->dev,
-			      "MES FW version must be >= 0x82 to enable LR compute workaround.\n");
 
 	/*
 	 * Keep oversubscribe timer for sdma . When we have unmapped doorbell
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
index 0202df5db1e1..6109124f852e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
@@ -174,6 +174,10 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block)
 		fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE);
 		fw_shared->sq.is_enabled = 1;
 
+		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SMU_DPM_INTERFACE_FLAG);
+		fw_shared->smu_dpm_interface.smu_interface_type = (adev->flags & AMD_IS_APU) ?
+			AMDGPU_VCN_SMU_DPM_INTERFACE_APU : AMDGPU_VCN_SMU_DPM_INTERFACE_DGPU;
+
 		if (amdgpu_vcnfw_log)
 			amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]);
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 246893d80f1f..baf820e6eae8 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -170,11 +170,11 @@ struct dc_stream_state *dc_create_stream_for_sink(
 	if (sink == NULL)
 		goto fail;
 
-	stream = kzalloc_obj(struct dc_stream_state);
+	stream = kzalloc_obj(struct dc_stream_state, GFP_ATOMIC);
 	if (stream == NULL)
 		goto fail;
 
-	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_KERNEL);
+	stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_ATOMIC);
 	if (stream->update_scratch == NULL)
 		goto fail;