drm/amdkfd: relax checks for over allocation of save area

Over allocation of save area is not fatal, only under allocation is.
ROCm has various components that independently claim authority over save
area size.

Unless KFD decides to claim single authority, relax size checks.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Philip Yang <philip.yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 15bd4958fe38e763bc17b607ba55155254a01f55)
Cc: stable@vger.kernel.org

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index a65c67cf56ff3776b521faa616a9dea15ac3a80f..f1e7583650c41677931ac12140c047fac5ffcd1d 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -297,16 +297,16 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
                goto out_err_unreserve;
        }
 
-       if (properties->ctx_save_restore_area_size != topo_dev->node_props.cwsr_size) {
-               pr_debug("queue cwsr size 0x%x not equal to node cwsr size 0x%x\n",
+       if (properties->ctx_save_restore_area_size < topo_dev->node_props.cwsr_size) {
+               pr_debug("queue cwsr size 0x%x not sufficient for node cwsr size 0x%x\n",
                        properties->ctx_save_restore_area_size,
                        topo_dev->node_props.cwsr_size);
                err = -EINVAL;
                goto out_err_unreserve;
        }
 
-       total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
-                         * NUM_XCC(pdd->dev->xcc_mask);
+       total_cwsr_size = (properties->ctx_save_restore_area_size +
+                          topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask);
        total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
 
        err = kfd_queue_buffer_get(vm, (void *)properties->ctx_save_restore_area_address,
@@ -352,8 +352,8 @@ int kfd_queue_release_buffers(struct kfd_process_device *pdd, struct queue_prope
        topo_dev = kfd_topology_device_by_id(pdd->dev->id);
        if (!topo_dev)
                return -EINVAL;
-       total_cwsr_size = (topo_dev->node_props.cwsr_size + topo_dev->node_props.debug_memory_size)
-                         * NUM_XCC(pdd->dev->xcc_mask);
+       total_cwsr_size = (properties->ctx_save_restore_area_size +
+                          topo_dev->node_props.debug_memory_size) * NUM_XCC(pdd->dev->xcc_mask);
        total_cwsr_size = ALIGN(total_cwsr_size, PAGE_SIZE);
 
        kfd_queue_buffer_svm_put(pdd, properties->ctx_save_restore_area_address, total_cwsr_size);