nvc0/ir: don't check the format for surface stores on Kepler

Initially to make sure the format doesn't mismatch and won't produce
out-of-bounds access, we checked that both formats have exactly the same
number of bytes, but this should not be checked for type stores.

This fixes serious rendering issues in the UE4 demos (tested with
realistic and reflections).

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
index 0a3964c..43a6e5f 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
@@ -1834,18 +1834,17 @@ NVC0LoweringPass::processSurfaceCoordsNVE4(TexInstruction *su)
                 TYPE_U32, bld.mkImm(0),
                 loadSuInfo32(ind, base + NVE4_SU_INFO_ADDR));
 
-   if (su->tex.format) {
+   if (su->op != OP_SUSTP && su->tex.format) {
       const TexInstruction::ImgFormatDesc *format = su->tex.format;
       int blockwidth = format->bits[0] + format->bits[1] +
                        format->bits[2] + format->bits[3];
 
-      if (blockwidth >= 8) {
-         // make sure that the format doesn't mismatch
-         bld.mkCmp(OP_SET_OR, CC_NE, TYPE_U32, pred1->getDef(0),
-                   TYPE_U32, bld.loadImm(NULL, blockwidth / 8),
-                   loadSuInfo32(ind, base + NVE4_SU_INFO_BSIZE),
-                   pred1->getDef(0));
-      }
+      // make sure that the format doesn't mismatch
+      assert(format->components != 0);
+      bld.mkCmp(OP_SET_OR, CC_NE, TYPE_U32, pred1->getDef(0),
+                TYPE_U32, bld.loadImm(NULL, blockwidth / 8),
+                loadSuInfo32(ind, base + NVE4_SU_INFO_BSIZE),
+                pred1->getDef(0));
    }
    su->setPredicate(CC_NOT_P, pred1->getDef(0));