Merge tag 'defconfig-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc

[linux-2.6-microblaze.git] / drivers / gpu / drm / amd / amdkfd / kfd_chardev.c

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index e48acdd..86afd37 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -1393,6 +1393,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
        long err = 0;
        int i;
        uint32_t *devices_arr = NULL;
+       bool table_freed = false;
 
        dev = kfd_device_by_id(GET_GPU_ID(args->handle));
        if (!dev)
@@ -1450,7 +1451,8 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
                        goto get_mem_obj_from_handle_failed;
                }
                err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
-                       peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
+                       peer->kgd, (struct kgd_mem *)mem,
+                       peer_pdd->drm_priv, &table_freed);
                if (err) {
                        pr_err("Failed to map to gpu %d/%d\n",
                               i, args->n_devices);
@@ -1468,16 +1470,17 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
        }
 
        /* Flush TLBs after waiting for the page table updates to complete */
-       for (i = 0; i < args->n_devices; i++) {
-               peer = kfd_device_by_id(devices_arr[i]);
-               if (WARN_ON_ONCE(!peer))
-                       continue;
-               peer_pdd = kfd_get_process_device_data(peer, p);
-               if (WARN_ON_ONCE(!peer_pdd))
-                       continue;
-               kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+       if (table_freed) {
+               for (i = 0; i < args->n_devices; i++) {
+                       peer = kfd_device_by_id(devices_arr[i]);
+                       if (WARN_ON_ONCE(!peer))
+                               continue;
+                       peer_pdd = kfd_get_process_device_data(peer, p);
+                       if (WARN_ON_ONCE(!peer_pdd))
+                               continue;
+                       kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
+               }
        }
-
        kfree(devices_arr);
 
        return err;
@@ -1565,10 +1568,29 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep,
                }
                args->n_success = i+1;
        }
-       kfree(devices_arr);
-
        mutex_unlock(&p->mutex);
 
+       if (dev->device_info->asic_family == CHIP_ALDEBARAN) {
+               err = amdgpu_amdkfd_gpuvm_sync_memory(dev->kgd,
+                               (struct kgd_mem *) mem, true);
+               if (err) {
+                       pr_debug("Sync memory failed, wait interrupted by user signal\n");
+                       goto sync_memory_failed;
+               }
+
+               /* Flush TLBs after waiting for the page table updates to complete */
+               for (i = 0; i < args->n_devices; i++) {
+                       peer = kfd_device_by_id(devices_arr[i]);
+                       if (WARN_ON_ONCE(!peer))
+                               continue;
+                       peer_pdd = kfd_get_process_device_data(peer, p);
+                       if (WARN_ON_ONCE(!peer_pdd))
+                               continue;
+                       kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
+               }
+       }
+       kfree(devices_arr);
+
        return 0;
 
 bind_process_to_device_failed:
@@ -1576,6 +1598,7 @@ get_mem_obj_from_handle_failed:
 unmap_memory_from_gpu_failed:
        mutex_unlock(&p->mutex);
 copy_from_user_failed:
+sync_memory_failed:
        kfree(devices_arr);
        return err;
 }