i965/fs: Relax fs_builder channel group assertion when force_writemask_all is on.

This assertion was meant to catch code inadvertently escaping the
control flow jail determined by the group of channel enable signals
selected by some caller, however it seems useful to be able to
increase the default execution size as long as force_writemask_all is
enabled, because force_writemask_all is an explicit indication that
there is no longer a one-to-one correspondence between channels and
SIMD components so the restriction doesn't apply.

In addition reorder the calls to fs_builder::group and ::exec_all in a
couple of places to make sure that we don't temporarily break this
invariant in the future for instructions with exec_size higher than
the dispatch width.

Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>

src/mesa/drivers/dri/i965/brw_fs.cpp

@@ -2915,7 +2915,7 @@ fs_visitor::lower_load_payload()
       if (dst.file == MRF)
          dst.reg = dst.reg & ~BRW_MRF_COMPR4;
 
-      const fs_builder hbld = bld.group(8, 0).exec_all().at(block, inst);
+      const fs_builder hbld = bld.exec_all().group(8, 0).at(block, inst);
 
       for (uint8_t i = 0; i < inst->header_size; i++) {
          if (inst->src[i].file != BAD_FILE) {
@@ -2926,8 +2926,8 @@ fs_visitor::lower_load_payload()
          dst = offset(dst, hbld, 1);
       }
 
-      const fs_builder ibld = bld.group(inst->exec_size, inst->force_sechalf)
-                                 .exec_all(inst->force_writemask_all)
+      const fs_builder ibld = bld.exec_all(inst->force_writemask_all)
+                                 .group(inst->exec_size, inst->force_sechalf)
                                  .at(block, inst);
 
       if (inst->dst.file == MRF && (inst->dst.reg & BRW_MRF_COMPR4) &&

src/mesa/drivers/dri/i965/brw_fs_builder.h

@@ -99,8 +99,8 @@ namespace brw {
       fs_builder
       group(unsigned n, unsigned i) const
       {
-         assert(n <= dispatch_width() &&
-                i < dispatch_width() / n);
+         assert(force_writemask_all ||
+                (n <= dispatch_width() && i < dispatch_width() / n));
          fs_builder bld = *this;
          bld._dispatch_width = n;
          bld._group += i * n;

src/mesa/drivers/dri/i965/brw_fs_cse.cpp

@@ -180,8 +180,8 @@ create_copy_instr(const fs_builder &bld, fs_inst *inst, fs_reg src, bool negate)
 {
    int written = inst->regs_written;
    int dst_width = inst->exec_size / 8;
-   const fs_builder ubld = bld.group(inst->exec_size, inst->force_sechalf)
-                              .exec_all(inst->force_writemask_all);
+   const fs_builder ubld = bld.exec_all(inst->force_writemask_all)
+                              .group(inst->exec_size, inst->force_sechalf);
    fs_inst *copy;
 
    if (written > dst_width) {