drm/vmwgfx: Fix cpu updates of coherent multisample surfaces

In cases where the dirty linear memory range spans multiple sample sheets
in a surface, the dirty surface region is incorrectly computed.
To do this correctly and in an optimized fashion  we would have to compute
the dirty region of each sample sheet and compute the union of those
regions.

But assuming that cpu writing to a multisample surface is rather a corner
case than a common case, just set the dirty region to the full surface.

This fixes OpenGL piglit errors with SVGA_FORCE_COHERENT=1
and the piglit test:

fbo-depthstencil blit default_fb -samples=2 -auto

Fixes: 9ca7d19ff8ba ("drm/vmwgfx: Add surface dirty-tracking callbacks")
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Signed-off-by: Zack Rusin <zackr@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210505035740.286923-4-zackr@vmware.com

1 files changed, 13 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index c3e55c1376eb..beab3e19d8e2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1804,6 +1804,19 @@ static void vmw_surface_tex_dirty_range_add(struct vmw_resource *res,
 	svga3dsurface_get_loc(cache, &loc2, end - 1);
 	svga3dsurface_inc_loc(cache, &loc2);
 
+	if (loc1.sheet != loc2.sheet) {
+		u32 sub_res;
+
+		/*
+		 * Multiple multisample sheets. To do this in an optimized
+		 * fashion, compute the dirty region for each sheet and the
+		 * resulting union. Since this is not a common case, just dirty
+		 * the whole surface.
+		 */
+		for (sub_res = 0; sub_res < dirty->num_subres; ++sub_res)
+			vmw_subres_dirty_full(dirty, sub_res);
+		return;
+	}
 	if (loc1.sub_resource + 1 == loc2.sub_resource) {
 		/* Dirty range covers a single sub-resource */
 		vmw_subres_dirty_add(dirty, &loc1, &loc2);