nvc0/ir: make sure to align the second arg of TXD to 4, as we do for TEX

This was handled in handleTEX(), however the way the logic works, those
extra arguments aren't added on by then, so it did nothing. Instead we
must duplicate that bit here. GK110 appears to complain about
MISALIGNED_GPR, however it's reasonable to believe that GK104 has the
same requirements.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=95403
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>

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 1068c210f89442b301d27d1129e4b2273e9c8b98..869b06c2b4c72bb506a197b97c79199f87716dcf 100644 (file)
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_lowering_nvc0.cpp
@@ -993,6 +993,20 @@ NVC0LoweringPass::handleTXD(TexInstruction *txd)
       txd->dPdx[c].set(NULL);
       txd->dPdy[c].set(NULL);
    }
+
+   // In this case we have fewer than 4 "real" arguments, which means that
+   // handleTEX didn't apply any padding. However we have to make sure that
+   // the second "group" of arguments still gets padded up to 4.
+   if (chipset >= NVISA_GK104_CHIPSET) {
+      int s = arg + 2 * dim;
+      if (s >= 4 && s < 7) {
+         if (txd->srcExists(s)) // move potential predicate out of the way
+            txd->moveSources(s, 7 - s);
+         while (s < 7)
+            txd->setSrc(s++, bld.loadImm(NULL, 0));
+      }
+   }
+
    return true;
 }