drm/amdgpu: user temporary GTT as bounce buffer

Currently, we have a limitted GTT memory size and need a bounce buffer
when doing buffer migration between VRAM and SYSTEM domain.

The problem is under GTT memory pressure we can't do buffer migration
between VRAM and SYSTEM domain. But in some cases we really need that.
Eespecially when validating a VRAM backing store BO which resides in
SYSTEM domain.

v2: still account temporary GTT allocations
v3 (chk): revert to the simpler change for now

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Nirmoy Das <nirmoy.das@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210622162339.761651-2-andrey.grodzovsky@amd.com

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index ec96e0b..3b45208 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -132,14 +132,15 @@ static int amdgpu_gtt_mgr_new(struct ttm_resource_manager *man,
        struct amdgpu_gtt_node *node;
        int r;
 
-       spin_lock(&mgr->lock);
-       if (tbo->resource && tbo->resource->mem_type != TTM_PL_TT &&
-           atomic64_read(&mgr->available) < num_pages) {
+       if (!(place->flags & TTM_PL_FLAG_TEMPORARY)) {
+               spin_lock(&mgr->lock);
+               if (atomic64_read(&mgr->available) < num_pages) {
+                       spin_unlock(&mgr->lock);
+                       return -ENOSPC;
+               }
+               atomic64_sub(num_pages, &mgr->available);
                spin_unlock(&mgr->lock);
-               return -ENOSPC;
        }
-       atomic64_sub(num_pages, &mgr->available);
-       spin_unlock(&mgr->lock);
 
        node = kzalloc(struct_size(node, base.mm_nodes, 1), GFP_KERNEL);
        if (!node) {
@@ -175,7 +176,8 @@ err_free:
        kfree(node);
 
 err_out:
-       atomic64_add(num_pages, &mgr->available);
+       if (!(place->flags & TTM_PL_FLAG_TEMPORARY))
+               atomic64_add(num_pages, &mgr->available);
 
        return r;
 }
@@ -198,7 +200,9 @@ static void amdgpu_gtt_mgr_del(struct ttm_resource_manager *man,
        if (drm_mm_node_allocated(&node->base.mm_nodes[0]))
                drm_mm_remove_node(&node->base.mm_nodes[0]);
        spin_unlock(&mgr->lock);
-       atomic64_add(res->num_pages, &mgr->available);
+
+       if (!(res->placement & TTM_PL_FLAG_TEMPORARY))
+               atomic64_add(res->num_pages, &mgr->available);
 
        kfree(node);
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 80dff29..79f8757 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -521,7 +521,7 @@ static int amdgpu_bo_move(struct ttm_buffer_object *bo, bool evict,
                        hop->fpfn = 0;
                        hop->lpfn = 0;
                        hop->mem_type = TTM_PL_TT;
-                       hop->flags = 0;
+                       hop->flags = TTM_PL_FLAG_TEMPORARY;
                        return -EMULTIHOP;
                }