diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp
index 545e1bf18b1..fc34800df72 100644
--- a/src/intel/compiler/brw_fs_nir.cpp
+++ b/src/intel/compiler/brw_fs_nir.cpp
@@ -567,8 +567,46 @@ optimize_extract_to_float(nir_to_brw_state &ntb, const fs_builder &bld,
    op0.type = brw_type_for_nir_type(devinfo,
       (nir_alu_type)(nir_op_infos[src0->op].input_types[0] |
                      nir_src_bit_size(src0->src[0].src)));
+
+   /* It is not documented in the Bspec, but DG2 and newer platforms cannot do
+    * direct byte-to-float conversions from scalars. MR !30140 has more
+    * details. If the optimization is applied in cases that would require
+    * lower_regioning to do some lowering, the code generated will be much,
+    * much worse.
+    */
+   if (devinfo->verx10 >= 125 && bytes == 1) {
+      /* If the source truly scalar, for example from the UNIFORM file, skip
+       * the optimize_extract_to_float optimization.
+       *
+       * Note: is_scalar values won't have zero stride until after the call to
+       * offset() below that applies the swizzle.
+       */
+      if (is_uniform(op0))
+         return false;
+
+      /* If the dispatch width matches the scalar allocation width, then
+       * is_scalar can be demoted to non-is_scalar. This prevents offset() and
+       * component() (both called below) from setting the stride to zero, and
+       * that avoids the awful code generated by lower_regioning.
+       */
+      if (op0.is_scalar) {
+         const unsigned allocation_width = 8 * reg_unit(ntb.devinfo);
+         if (ntb.bld.dispatch_width() != allocation_width)
+            return false;
+
+         assert(bld.dispatch_width() == allocation_width);
+         op0.is_scalar = false;
+      }
+   }
+
    op0 = offset(op0, bld, src0->src[0].swizzle[0]);
 
+   /* If the dispatch width matches the scalar allocation width, offset() will
+    * not modify the stride, but having source stride <0;1,0> is advantageous.
+    */
+   if (op0.is_scalar)
+      op0 = component(op0, 0);
+
    /* Bspec "Register Region Restrictions" for Xe says:
     *
     *    "In case of all float point data types used in destination