i965/blorp: Use 8k chunk size for urb allocation

Previously, we hardcoded "VS URB Starting Address" to 2 (in 8kB chunks),
which meant VS URB data would start at an offset of 16kB.

However, on Haswell GT3 and Gen8+, we allocate the first 32kB for the
push constant region.  This means that the PS push constant and VS URB
data regions overlap, which can lead to corruption.

v2 (Ken): Better description of the change, and do not change vs_size
          from 2 to 1.

Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/gen7_blorp.cpp b/src/mesa/drivers/dri/i965/gen7_blorp.cpp
index 4debeb305ade8fd48db9db6ffa1b14769622446c..5d66232e4e44666a0c8dc0c892c87b2877664fae 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_blorp.cpp
+++ b/src/mesa/drivers/dri/i965/gen7_blorp.cpp
@@ -47,8 +47,17 @@
 static void
 gen7_blorp_emit_urb_config(struct brw_context *brw)
 {
+   /* URB allocations must be done in 8k chunks. */
+   const unsigned chunk_size_bytes = 8192;
    const unsigned urb_size =
       (brw->gen >= 8 || (brw->is_haswell && brw->gt == 3)) ? 32 : 16;
+   const unsigned push_constant_bytes = 1024 * urb_size;
+   const unsigned push_constant_chunks =
+      push_constant_bytes / chunk_size_bytes;
+   const unsigned vs_size = 2;
+   const unsigned vs_start = push_constant_chunks;
+   const unsigned vs_chunks =
+      DIV_ROUND_UP(brw->urb.min_vs_entries * vs_size * 64, chunk_size_bytes);
 
    gen7_emit_push_constant_state(brw,
                                  urb_size / 2 /* vs_size */,
@@ -59,17 +68,17 @@ gen7_blorp_emit_urb_config(struct brw_context *brw)
 
    gen7_emit_urb_state(brw,
                        brw->urb.min_vs_entries /* num_vs_entries */,
-                       2 /* vs_size */,
-                       2 /* vs_start */,
+                       vs_size,
+                       vs_start,
                        0 /* num_hs_entries */,
                        1 /* hs_size */,
-                       2 /* hs_start */,
+                       vs_start + vs_chunks /* hs_start */,
                        0 /* num_ds_entries */,
                        1 /* ds_size */,
-                       2 /* ds_start */,
+                       vs_start + vs_chunks /* ds_start */,
                        0 /* num_gs_entries */,
                        1 /* gs_size */,
-                       2 /* gs_start */);
+                       vs_start + vs_chunks /* gs_start */);
 }