drm/xe: Skip VMAs pin when requesting signal to the last XE_EXEC

[ Upstream commit dd8a07f06dfd946e0eea1a3323d52e7c28a6ed80 ]

Doing a XE_EXEC with num_batch_buffer == 0 makes signals passed as
argument to be signaled when the last real XE_EXEC is completed.
But to do that it was first pinning all VMAs in drm_gpuvm_exec_lock(),
this patch remove this pinning as it is not required.

This change also help Mesa implementing memory over-commiting recovery
as it needs to unbind not needed VMAs when the whole VM can't fit
in GPU memory but it can only do the unbiding when the last XE_EXEC
is completed.
So with this change Mesa can get the signal it want without getting
out-of-memory errors.

Fixes: eb9702ad2986 ("drm/xe: Allow num_batch_buffer / num_binds == 0 in IOCTLs")
Cc: Thomas Hellstrom <thomas.hellstrom@linux.intel.com>
Co-developed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240313171318.121066-1-jose.souza@intel.com
(cherry picked from commit 58480c1c912ff8146d067301a0d04cca318b4a66)
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 17f26952e6656b8a077eb51161acbfd96638db2c..222209b0d6904d78089750af82829f69c29e9e43 100644 (file)
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -196,6 +196,29 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
                        goto err_unlock_list;
        }
 
+       if (!args->num_batch_buffer) {
+               err = xe_vm_lock(vm, true);
+               if (err)
+                       goto err_unlock_list;
+
+               if (!xe_vm_in_lr_mode(vm)) {
+                       struct dma_fence *fence;
+
+                       fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);
+                       if (IS_ERR(fence)) {
+                               err = PTR_ERR(fence);
+                               goto err_unlock_list;
+                       }
+                       for (i = 0; i < num_syncs; i++)
+                               xe_sync_entry_signal(&syncs[i], NULL, fence);
+                       xe_exec_queue_last_fence_set(q, vm, fence);
+                       dma_fence_put(fence);
+               }
+
+               xe_vm_unlock(vm);
+               goto err_unlock_list;
+       }
+
        vm_exec.vm = &vm->gpuvm;
        vm_exec.num_fences = 1 + vm->xe->info.tile_count;
        vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT;
@@ -216,24 +239,6 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
                goto err_exec;
        }
 
-       if (!args->num_batch_buffer) {
-               if (!xe_vm_in_lr_mode(vm)) {
-                       struct dma_fence *fence;
-
-                       fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm);
-                       if (IS_ERR(fence)) {
-                               err = PTR_ERR(fence);
-                               goto err_exec;
-                       }
-                       for (i = 0; i < num_syncs; i++)
-                               xe_sync_entry_signal(&syncs[i], NULL, fence);
-                       xe_exec_queue_last_fence_set(q, vm, fence);
-                       dma_fence_put(fence);
-               }
-
-               goto err_exec;
-       }
-
        if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) {
                err = -EWOULDBLOCK;     /* Aliased to -EAGAIN */
                skip_retry = true;