This prevents RA failures the results of reading multiple textures that
require less than 4 channels, as seen in a number of GL 3 WebRender shaders.
Closes: #3342
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reported-by: Icecream95 <ixn@keemail.me>
Tested-by: Icecream95 <ixn@keemail.me>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6144>
midgard_instruction st;
+ /* Note: it's important to match the mask of the spill
+ * with the mask of the instruction whose destination
+ * we're spilling, or otherwise we'll read invalid
+ * components and can fail RA in a subsequent iteration
+ */
+
if (is_special_w) {
st = v_mov(spill_node, spill_slot);
st.no_spill |= (1 << spill_class);
+ st.mask = ins->mask;
+ st.dest_type = st.src_types[0] = ins->dest_type;
} else {
ins->dest = spill_index++;
ins->no_spill |= (1 << spill_class);