[Mesa-dev] [PATCH 1/2] i965/fs: fix offset when loading double vector input varyings

[Samuel Iglesias Gonsálvez]

When we are not packing a double input varying, we might need to
read its data in a non-aligned to 64-bit offset, so we read
the wrong data. This is happening when using explicit locations
in varyings because Mesa disables packing varying for that case.

const_index is in 32-bit size units but offset() is multiplying
it by destination type size units. When operating with double
input varyings, const_index value could be not aligned to 64 bits.
To fix it, we load the double vector as if it was a float based vector
with twice the number of components.

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias at igalia.com>
---
 src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
index e7e0ee1..084301a 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp
@@ -3669,9 +3669,21 @@ fs_visitor::nir_emit_intrinsic(const fs_builder &bld, nir_intrinsic_instr *instr
 
    case nir_intrinsic_load_input: {
       fs_reg src;
+      unsigned num_components = instr->num_components;
+      enum brw_reg_type type = dest.type;
+
       if (stage == MESA_SHADER_VERTEX) {
          src = fs_reg(ATTR, instr->const_index[0], dest.type);
       } else {
+         assert(type_sz(type) >= 4);
+         if (type == BRW_REGISTER_TYPE_DF) {
+            /* const_index is in 32-bit type size units that could not be aligned
+             * with DF. We need to read the double vector as if it was a float
+             * vector of twice the number of components to fetch the right data.
+             */
+            dest = retype(dest, BRW_REGISTER_TYPE_F);
+            num_components *= 2;
+         }
          src = offset(retype(nir_inputs, dest.type), bld,
                       instr->const_index[0]);
       }
@@ -3680,10 +3692,18 @@ fs_visitor::nir_emit_intrinsic(const fs_builder &bld, nir_intrinsic_instr *instr
       assert(const_offset && "Indirect input loads not allowed");
       src = offset(src, bld, const_offset->u32[0]);
 
-      for (unsigned j = 0; j < instr->num_components; j++) {
+      for (unsigned j = 0; j < num_components; j++) {
          bld.MOV(offset(dest, bld, j), offset(src, bld, j));
       }
 
+      if (type == BRW_REGISTER_TYPE_DF) {
+         /* Once the double vector is read, set again its original register
+          * type to continue with normal execution.
+          */
+         src = retype(src, type);
+         dest = retype(dest, type);
+      }
+
       if (type_sz(src.type) == 8) {
          shuffle_32bit_load_result_to_64bit_data(bld,
                                                  dest,
-- 
2.8.1