Merge tag 'amd-drm-next-6.18-2025-09-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.18-2025-09-09:

amdgpu:
- Add CRIU support for gem objects
- SI UVD fix
- SI DPM fixes
- Misc code cleanups
- RAS updates
- GPUVM debugfs fixes
- Cyan Skillfish updates
- UserQ updates
- OEM i2c fix
- SMU 13.0.x updates
- DPCD probe quirk fix
- Make vbios build number available in sysfs
- HDCP updates
- Brightness curve fixes
- eDP updates
- Vblank fixes
- DCN 3.5 PG fix
- PBN calcution fix

amdkfd:
- Add CRIU support for gem objects
- Flexible array fix
- P2P topology fix
- APU memlimit fixes
- Misc code cleanups

UAPI:
- Add CRIU support for gem objects
  Proposed userspace: https://github.com/checkpoint-restore/criu/pull/2613

radeon:
- Use dev_warn_once() in CS parsers

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

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20250909161928.942785-1-alexander.deucher@amd.com

1 files changed, 65 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 135598502c8d..5bf9be073cdd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -191,6 +191,20 @@ int amdgpu_mes_init(struct amdgpu_device *adev)
 	if (r)
 		goto error_doorbell;
 
+	if (adev->mes.hung_queue_db_array_size) {
+		r = amdgpu_bo_create_kernel(adev,
+					    adev->mes.hung_queue_db_array_size * sizeof(u32),
+					    PAGE_SIZE,
+					    AMDGPU_GEM_DOMAIN_GTT,
+					    &adev->mes.hung_queue_db_array_gpu_obj,
+					    &adev->mes.hung_queue_db_array_gpu_addr,
+					    &adev->mes.hung_queue_db_array_cpu_addr);
+		if (r) {
+			dev_warn(adev->dev, "failed to create MES hung db array buffer (%d)", r);
+			goto error_doorbell;
+		}
+	}
+
 	return 0;
 
 error_doorbell:
@@ -216,6 +230,10 @@ void amdgpu_mes_fini(struct amdgpu_device *adev)
 {
 	int i;
 
+	amdgpu_bo_free_kernel(&adev->mes.hung_queue_db_array_gpu_obj,
+			      &adev->mes.hung_queue_db_array_gpu_addr,
+			      &adev->mes.hung_queue_db_array_cpu_addr);
+
 	amdgpu_bo_free_kernel(&adev->mes.event_log_gpu_obj,
 			      &adev->mes.event_log_gpu_addr,
 			      &adev->mes.event_log_cpu_addr);
@@ -366,6 +384,53 @@ int amdgpu_mes_reset_legacy_queue(struct amdgpu_device *adev,
 	return r;
 }
 
+int amdgpu_mes_get_hung_queue_db_array_size(struct amdgpu_device *adev)
+{
+	return adev->mes.hung_queue_db_array_size;
+}
+
+int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev,
+					    int queue_type,
+					    bool detect_only,
+					    unsigned int *hung_db_num,
+					    u32 *hung_db_array)
+
+{
+	struct mes_detect_and_reset_queue_input input;
+	u32 *db_array = adev->mes.hung_queue_db_array_cpu_addr;
+	int r, i;
+
+	if (!hung_db_num || !hung_db_array)
+		return -EINVAL;
+
+	if ((queue_type != AMDGPU_RING_TYPE_GFX) &&
+	    (queue_type != AMDGPU_RING_TYPE_COMPUTE) &&
+	    (queue_type != AMDGPU_RING_TYPE_SDMA))
+		return -EINVAL;
+
+	/* Clear the doorbell array before detection */
+	memset(adev->mes.hung_queue_db_array_cpu_addr, 0,
+		adev->mes.hung_queue_db_array_size * sizeof(u32));
+	input.queue_type = queue_type;
+	input.detect_only = detect_only;
+
+	r = adev->mes.funcs->detect_and_reset_hung_queues(&adev->mes,
+							  &input);
+	if (r) {
+		dev_err(adev->dev, "failed to detect and reset\n");
+	} else {
+		*hung_db_num = 0;
+		for (i = 0; i < adev->mes.hung_queue_db_array_size; i++) {
+			if (db_array[i] != AMDGPU_MES_INVALID_DB_OFFSET) {
+				hung_db_array[i] = db_array[i];
+				*hung_db_num += 1;
+			}
+		}
+	}
+
+	return r;
+}
+
 uint32_t amdgpu_mes_rreg(struct amdgpu_device *adev, uint32_t reg)
 {
 	struct mes_misc_op_input op_input;