i965: Fix the SF Vertex URB Read Length calculation for Gen7 platforms.
Ivybridge doesn't appear to have the same errata as Sandybridge; no
corruption was observed by setting it to more than the minimal correct
value. It's possible that we were simply lucky, since the URB entries
are 1024-bit on Ivybridge vs. 512-bit Sandybridge. Or perhaps the
underlying hardware issue is fixed.
Either way, we may as well program the minimum value since it's now
readily available, likely to be more efficient, and possibly more
correct.
v2: Use GEN7_SBE_* defines rather than GEN6_SF_*. (A copy and paste
mistake.) They're the same, but using the right names is better.
Reviewed-by: Paul Berry <stereotype441@gmail.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
(cherry picked from commit 44aa2e15f692965be76229e67f919bf967fc7d67)
diff --git a/src/mesa/drivers/dri/i965/gen7_sf_state.c b/src/mesa/drivers/dri/i965/gen7_sf_state.c
index b801b96..9171eff 100644
--- a/src/mesa/drivers/dri/i965/gen7_sf_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sf_state.c
@@ -34,7 +34,6 @@
{
struct intel_context *intel = &brw->intel;
struct gl_context *ctx = &intel->ctx;
- uint32_t urb_entry_read_length;
/* BRW_NEW_FRAGMENT_PROGRAM */
uint32_t num_outputs = _mesa_bitcount_64(brw->fragment_program->Base.InputsRead);
/* _NEW_LIGHT */
@@ -48,22 +47,8 @@
bool render_to_fbo = _mesa_is_user_fbo(ctx->DrawBuffer);
uint32_t point_sprite_origin;
- /* CACHE_NEW_VS_PROG */
- urb_entry_read_length = ((brw->vs.prog_data->vue_map.num_slots + 1) / 2 -
- urb_entry_read_offset);
- if (urb_entry_read_length == 0) {
- /* Setting the URB entry read length to 0 causes undefined behavior, so
- * if we have no URB data to read, set it to 1.
- */
- urb_entry_read_length = 1;
- }
-
/* FINISHME: Attribute Swizzle Control Mode? */
- dw1 =
- GEN7_SBE_SWIZZLE_ENABLE |
- num_outputs << GEN7_SBE_NUM_OUTPUTS_SHIFT |
- urb_entry_read_length << GEN7_SBE_URB_ENTRY_READ_LENGTH_SHIFT |
- urb_entry_read_offset << GEN7_SBE_URB_ENTRY_READ_OFFSET_SHIFT;
+ dw1 = GEN7_SBE_SWIZZLE_ENABLE | num_outputs << GEN7_SBE_NUM_OUTPUTS_SHIFT;
/* _NEW_POINT
*
@@ -123,6 +108,21 @@
&max_source_attr);
}
+ /* From the Ivy Bridge PRM, Volume 2, Part 1, documentation for
+ * 3DSTATE_SBE DWord 1 bits 15:11, "Vertex URB Entry Read Length":
+ *
+ * "This field should be set to the minimum length required to read the
+ * maximum source attribute. The maximum source attribute is indicated
+ * by the maximum value of the enabled Attribute # Source Attribute if
+ * Attribute Swizzle Enable is set, Number of Output Attributes-1 if
+ * enable is not set.
+ *
+ * read_length = ceiling((max_source_attr + 1) / 2)"
+ */
+ uint32_t urb_entry_read_length = ALIGN(max_source_attr + 1, 2) / 2;
+ dw1 |= urb_entry_read_length << GEN7_SBE_URB_ENTRY_READ_LENGTH_SHIFT |
+ urb_entry_read_offset << GEN7_SBE_URB_ENTRY_READ_OFFSET_SHIFT;
+
for (; input_index < FRAG_ATTRIB_MAX; input_index++)
attr_overrides[input_index] = 0;
