drm/ttm/dma: Only call set_pages_array_wb when the page is not in WB pool.

Otherwise we are doing redundant work. Especially since the 'unbind'
and 'unpopulate' have been merged and nouveau driver ends up calling
it quite excessivly. On a GeForce 8600 GT with Gnome Shell (GNOME 3)
we end up spending about 54% CPU time in __change_page_attr_set_clr
checking the page flags.

The callgraph (annotated) looks as so before this patch:

    53.29%  gnome-shell  [kernel.kallsyms]                   [k] static_protections
            |
            --- static_protections
               |
               |--91.80%-- __change_page_attr_set_clr
               |          change_page_attr_set_clr
               |          set_pages_array_wb
               |          |
               |          |--96.55%-- ttm_dma_unpopulate
               |          |          nouveau_ttm_tt_unpopulate
               |          |          ttm_tt_destroy
               |          |          ttm_bo_cleanup_memtype_use
               |          |          ttm_bo_release
               |          |          kref_put
               |          |          ttm_bo_unref
               |          |          nouveau_gem_object_del
               |          |          drm_gem_object_free
               |          |          kref_put
               |          |          drm_gem_object_unreference_unlocked
               |          |          drm_gem_object_handle_unreference_unlocked.part.1
               |          |          drm_gem_handle_delete
               |          |          drm_gem_close_ioctl
               |          |          drm_ioctl
               |          |          do_vfs_ioctl
               |          |          sys_ioctl
               |          |          system_call_fastpath
               |          |          __GI___ioctl
               |          |
               |           --3.45%-- ttm_dma_pages_put
               |                     ttm_dma_page_pool_free
               |                     ttm_dma_unpopulate
               |                     nouveau_ttm_tt_unpopulate
               |                     ttm_tt_destroy
               |                     ttm_bo_cleanup_memtype_use
               |                     ttm_bo_release
               |                     kref_put
               |                     ttm_bo_unref
               |                     nouveau_gem_object_del
               |                     drm_gem_object_free
               |                     kref_put
               |                     drm_gem_object_unreference_unlocked
               |                     drm_gem_object_handle_unreference_unlocked.part.1
               |                     drm_gem_handle_delete
               |                     drm_gem_close_ioctl
               |                     drm_ioctl
               |                     do_vfs_ioctl
               |                     sys_ioctl
               |                     system_call_fastpath
               |                     __GI___ioctl
               |
                --8.20%-- change_page_attr_set_clr
                          set_pages_array_wb
                          |
                          |--93.76%-- ttm_dma_unpopulate
                          |          nouveau_ttm_tt_unpopulate
                          |          ttm_tt_destroy
                          |          ttm_bo_cleanup_memtype_use
                          |          ttm_bo_release
                          |          kref_put
                          |          ttm_bo_unref
                          |          nouveau_gem_object_del
                          |          drm_gem_object_free
                          |          kref_put
                          |          drm_gem_object_unreference_unlocked
                          |          drm_gem_object_handle_unreference_unlocked.part.1
                          |          drm_gem_handle_delete
                          |          drm_gem_close_ioctl
                          |          drm_ioctl
                          |          do_vfs_ioctl
                          |          sys_ioctl
                          |          system_call_fastpath
                          |          __GI___ioctl
                          |
                           --6.24%-- ttm_dma_pages_put
                                     ttm_dma_page_pool_free
                                     ttm_dma_unpopulate
                                     nouveau_ttm_tt_unpopulate
                                     ttm_tt_destroy
                                     ttm_bo_cleanup_memtype_use
                                     ttm_bo_release
                                     kref_put
                                     ttm_bo_unref
                                     nouveau_gem_object_del
                                     drm_gem_object_free
                                     kref_put
                                     drm_gem_object_unreference_unlocked
                                     drm_gem_object_handle_unreference_unlocked.part.1
                                     drm_gem_handle_delete
                                     drm_gem_close_ioctl
                                     drm_ioctl
                                     do_vfs_ioctl
                                     sys_ioctl
                                     system_call_fastpath
                                     __GI___ioctl

and after this patch all of that disappears.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 6678abca0d98a2e751e45d5121eb14c95189e3b1..6c06d0b601f95842f55a04b43a195f0b547f3ef1 100644 (file)
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -384,7 +384,9 @@ static void ttm_dma_pages_put(struct dma_pool *pool, struct list_head *d_pages,
 {
        struct dma_page *d_page, *tmp;
 
-       if (npages && set_pages_array_wb(pages, npages))
+       /* Don't set WB on WB page pool. */
+       if (npages && !(pool->type & IS_CACHED) &&
+           set_pages_array_wb(pages, npages))
                pr_err(TTM_PFX "%s: Failed to set %d pages to wb!\n",
                        pool->dev_name, npages);
 
@@ -396,7 +398,8 @@ static void ttm_dma_pages_put(struct dma_pool *pool, struct list_head *d_pages,
 
 static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
 {
-       if (set_pages_array_wb(&d_page->p, 1))
+       /* Don't set WB on WB page pool. */
+       if (!(pool->type & IS_CACHED) && set_pages_array_wb(&d_page->p, 1))
                pr_err(TTM_PFX "%s: Failed to set %d pages to wb!\n",
                        pool->dev_name, 1);