1 files changed, 53 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index bf79b73e1538..be80a4a68d7b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -323,6 +323,7 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
         struct amdgpu_bo *bo;
         enum ttm_bo_type type;
         unsigned long page_align;
+        u64 initial_bytes_moved;
         size_t acc_size;
         int r;
 
@@ -363,11 +364,33 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
 
         bo->flags = flags;
 
+#ifdef CONFIG_X86_32
+        /* XXX: Write-combined CPU mappings of GTT seem broken on 32-bit
+         * See https://bugs.freedesktop.org/show_bug.cgi?id=84627
+         */
+        bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#elif defined(CONFIG_X86) && !defined(CONFIG_X86_PAT)
+        /* Don't try to enable write-combining when it can't work, or things
+         * may be slow
+         * See https://bugs.freedesktop.org/show_bug.cgi?id=88758
+         */
+
+#ifndef CONFIG_COMPILE_TEST
+#warning Please enable CONFIG_MTRR and CONFIG_X86_PAT for better performance \
+         thanks to write-combining
+#endif
+
+        if (bo->flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC)
+                DRM_INFO_ONCE("Please enable CONFIG_MTRR and CONFIG_X86_PAT for "
+                              "better performance thanks to write-combining\n");
+        bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#else
         /* For architectures that don't support WC memory,
          * mask out the WC flag from the BO
          */
         if (!drm_arch_can_wc_memory())
                 bo->flags &= ~AMDGPU_GEM_CREATE_CPU_GTT_USWC;
+#endif
 
         amdgpu_fill_placement_to_bo(bo, placement);
         /* Kernel allocation are uninterruptible */
@@ -379,12 +402,25 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
                 locked = ww_mutex_trylock(&bo->tbo.ttm_resv.lock);
                 WARN_ON(!locked);
         }
+
+        initial_bytes_moved = atomic64_read(&adev->num_bytes_moved);
         r = ttm_bo_init(&adev->mman.bdev, &bo->tbo, size, type,
                         &bo->placement, page_align, !kernel, NULL,
                         acc_size, sg, resv ? resv : &bo->tbo.ttm_resv,
                         &amdgpu_ttm_bo_destroy);
-        if (unlikely(r != 0))
+        amdgpu_cs_report_moved_bytes(adev,
+                atomic64_read(&adev->num_bytes_moved) - initial_bytes_moved);
+
+        if (unlikely(r != 0)) {
+                if (!resv)
+                        ww_mutex_unlock(&bo->tbo.resv->lock);
                 return r;
+        }
+
+        bo->tbo.priority = ilog2(bo->tbo.num_pages);
+        if (kernel)
+                bo->tbo.priority *= 2;
+        bo->tbo.priority = min(bo->tbo.priority, (unsigned)(TTM_MAX_BO_PRIORITY - 1));
 
         if (flags & AMDGPU_GEM_CREATE_VRAM_CLEARED &&
             bo->tbo.mem.placement & TTM_PL_FLAG_VRAM) {
@@ -408,7 +444,8 @@ int amdgpu_bo_create_restricted(struct amdgpu_device *adev,
         return 0;
 
 fail_unreserve:
-        ww_mutex_unlock(&bo->tbo.resv->lock);
+        if (!resv)
+                ww_mutex_unlock(&bo->tbo.resv->lock);
         amdgpu_bo_unref(&bo);
         return r;
 }
@@ -472,7 +509,16 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
                 return r;
 
         if (amdgpu_need_backup(adev) && (flags & AMDGPU_GEM_CREATE_SHADOW)) {
+                if (!resv) {
+                        r = ww_mutex_lock(&(*bo_ptr)->tbo.resv->lock, NULL);
+                        WARN_ON(r != 0);
+                }
+
                 r = amdgpu_bo_create_shadow(adev, size, byte_align, (*bo_ptr));
+
+                if (!resv)
+                        ww_mutex_unlock(&(*bo_ptr)->tbo.resv->lock);
+
                 if (r)
                         amdgpu_bo_unref(bo_ptr);
         }
@@ -849,6 +895,7 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 }
 
 void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
+                           bool evict,
                            struct ttm_mem_reg *new_mem)
 {
         struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
@@ -861,6 +908,10 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
         abo = container_of(bo, struct amdgpu_bo, tbo);
         amdgpu_vm_bo_invalidate(adev, abo);
 
+        /* remember the eviction */
+        if (evict)
+                atomic64_inc(&adev->num_evictions);
+
         /* update statistics */
         if (!new_mem)
                 return;