drm/amdgpu: move VM page tables to the LRU end on CS v2

This makes it less likely to run into an ENOMEM because
VM page tables are evicted last.

v2: move the BOs in the LRU tail after validation

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

3 files changed, 35 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 003959f99251..313b0cc8d676 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -987,6 +987,8 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 			 struct list_head *validated,
 			 struct amdgpu_bo_list_entry *entry);
 void amdgpu_vm_get_pt_bos(struct amdgpu_vm *vm, struct list_head *duplicates);
+void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev,
+				  struct amdgpu_vm *vm);
 int amdgpu_vm_grab_id(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 		      struct amdgpu_sync *sync);
 void amdgpu_vm_flush(struct amdgpu_ring *ring,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index ce0254d4dcd7..1fffc338f69d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -428,8 +428,10 @@ static int amdgpu_cs_parser_relocs(struct amdgpu_cs_parser *p)
 	r = amdgpu_cs_list_validate(p->adev, &fpriv->vm, &duplicates);
 
 error_validate:
-	if (r)
+	if (r) {
+		amdgpu_vm_move_pt_bos_in_lru(p->adev, &fpriv->vm);
 		ttm_eu_backoff_reservation(&p->ticket, &p->validated);
+	}
 
 error_reserve:
 	if (need_mmap_lock)
@@ -473,8 +475,11 @@ static int cmp_size_smaller_first(void *priv, struct list_head *a,
  **/
 static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error, bool backoff)
 {
+	struct amdgpu_fpriv *fpriv = parser->filp->driver_priv;
 	unsigned i;
 
+	amdgpu_vm_move_pt_bos_in_lru(parser->adev, &fpriv->vm);
+
 	if (!error) {
 		/* Sort the buffer list from the smallest to largest buffer,
 		 * which affects the order of buffers in the LRU list.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 8f7688e598a1..aefc668e6b5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -119,6 +119,33 @@ void amdgpu_vm_get_pt_bos(struct amdgpu_vm *vm, struct list_head *duplicates)
 
 		list_add(&entry->tv.head, duplicates);
 	}
+
+}
+
+/**
+ * amdgpu_vm_move_pt_bos_in_lru - move the PT BOs to the LRU tail
+ *
+ * @adev: amdgpu device instance
+ * @vm: vm providing the BOs
+ *
+ * Move the PT BOs to the tail of the LRU.
+ */
+void amdgpu_vm_move_pt_bos_in_lru(struct amdgpu_device *adev,
+				  struct amdgpu_vm *vm)
+{
+	struct ttm_bo_global *glob = adev->mman.bdev.glob;
+	unsigned i;
+
+	spin_lock(&glob->lru_lock);
+	for (i = 0; i <= vm->max_pde_used; ++i) {
+		struct amdgpu_bo_list_entry *entry = &vm->page_tables[i].entry;
+
+		if (!entry->robj)
+			continue;
+
+		ttm_bo_move_to_lru_tail(&entry->robj->tbo);
+	}
+	spin_unlock(&glob->lru_lock);
 }
 
 /**