amdgpu_gfx_reset_mes_compute combines two features into one:
1) hung queue/pipe reset - suspend all/queue reset/resume all
2) bad queue removal - suspend_all/remove_queue/resume_all
GPU recovery aims on 1)resetting hung queues/pipes. When gpu_recovery is
disabled, we need to keep 2) going. Therefore move the gpu_recovery
check from KFD's reset_queues_mes into amdgpu_gfx_reset_mes_compute
where queue reset is done.

Signed-off-by: Amber Lin <[email protected]>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c               | 10 +++++++---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c |  9 +++------
 2 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index c5a2dcff5058..c30fecc653b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -2594,14 +2594,17 @@ int amdgpu_gfx_reset_mes_compute(struct amdgpu_device 
*adev,
         * reset detect will return the array of bad queue doorbells
         */
        r = amdgpu_mes_suspend(adev, xcc_id);
+       dev_dbg(adev->dev, "Suspend all returns %d. xcc_id %d\n", r, xcc_id);
+
+       if (!amdgpu_gpu_recovery)
+               goto after_reset;
+
        /* if suspend all success, it should no hang queue */
-       if (!r) {
-               dev_dbg(adev->dev, "Suspend all succeeds. xcc_id %d\n", xcc_id);
+       if (!r)
                /* always reset the KCQ/userq since we need to signal the fence
                 * and we could be stuck in a loop which is preemptable.
                 */
                goto fence_reset;
-       }
        r = amdgpu_mes_detect_and_reset_hung_queues(adev, 
AMDGPU_RING_TYPE_COMPUTE,
                                                    true, &num_hung, 
adev->gfx.mec.mes_hung_db_array, xcc_id);
        if (r) {
@@ -2662,6 +2665,7 @@ int amdgpu_gfx_reset_mes_compute(struct amdgpu_device 
*adev,
                        goto out;
        }
 
+after_reset:
        /* MES doesn't detect any hung queue but we have a known bad queue
         * and it is not KCQ
         */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c 
b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 86b70748617b..b77cfd8ba907 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -471,11 +471,6 @@ static int reset_queues_mes(struct device_queue_manager 
*dqm, struct queue *q)
        if (WARN_ON(dqm->detect_hang_count > 0))
                return 0;
 
-       if (!amdgpu_gpu_recovery) {
-               r = -ENOTRECOVERABLE;
-               goto fail;
-       }
-
        memset(&queue_input, 0x0, sizeof(struct mes_remove_queue_input));
        queue_input.doorbell_offset = q->properties.doorbell_off;
        queue_input.gang_context_addr = q->gang_ctx_gpu_addr;
@@ -3609,7 +3604,9 @@ int kfd_dqm_suspend_bad_queue_mes(struct kfd_node *knode, 
u32 pasid, u32 doorbel
 
                list_for_each_entry(q, &qpd->queues_list, list) {
                        if (q->doorbell_id == doorbell_id && 
q->properties.is_active) {
-                               reset_queues_mes(dqm, q);
+                               if (reset_queues_mes(dqm, q))
+                                       dev_dbg(knode->adev->dev,
+                                       "Fail to remove bad queue. doorbell_id 
0x%x\n", q->doorbell_id);
                                q->properties.is_evicted = true;
                                q->properties.is_active = false;
                                decrement_queue_count(dqm, qpd, q);
-- 
2.43.0

Reply via email to