i965: intel_texture_barrier reimplemented

Fixes:
GL44-CTS.texture_barrier_ARB.same-texel-rw-multipass

On Haswell, Broadwell and Skylake (note that in order to execute that
test, it is needed to override GL and GLSL versions).

On gen6 this test was already working without this change. It keeps
working after it.

This commit replaces the call to brw_emit_mi_flush for gen6+ with two
calls to brw_emit_pipe_control_flush:

 * The first one with RENDER_TARGET_FLUSH and CS_STALL set to initiate
   a render cache flush after any concurrent rendering completes and
   cause the CS to stop parsing commands until the render cache
   becomes coherent with memory.

 * The second one have TEXTURE_CACHE_INVALIDATE set (and no CS stall)
   to clean up any stale data from the sampler caches before rendering
   continues.

Didn't touch gen4-5, basically because I don't have a way to test
them.

More info on commits:
0aa4f99f562a05880a779707cbcd46be459863bf
72473658c51d5e074ce219c1e6385a4cce29f467

Thanks to Curro to help to tracking this down, as the root case was a
hw race condition.

v2: use two calls to pipe_control_flush instead of a combination of
    gen7_emit_cs_stall_flush and brw_emit_mi_flush calls (Curro)
v3: no need to const cache invalidation (Curro)

Reviewed-by: Francisco Jerez <[email protected]>

1 files changed, 20 insertions, 1 deletions

diff --git a/src/mesa/drivers/dri/i965/intel_tex.c b/src/mesa/drivers/dri/i965/intel_tex.c
index cac33ac64a7..a802d5a9186 100644
--- a/src/mesa/drivers/dri/i965/intel_tex.c
+++ b/src/mesa/drivers/dri/i965/intel_tex.c
@@ -9,6 +9,7 @@
 #include "intel_mipmap_tree.h"
 #include "intel_tex.h"
 #include "intel_fbo.h"
+#include "intel_reg.h"
 
 #define FILE_DEBUG_FLAG DEBUG_TEXTURE
 
@@ -362,7 +363,25 @@ intel_texture_barrier(struct gl_context *ctx)
 {
    struct brw_context *brw = brw_context(ctx);
 
-   brw_emit_mi_flush(brw);
+   if (brw->gen >= 6) {
+      if (brw->gen == 6) {
+         /* [Dev-SNB{W/A}]: Before a PIPE_CONTROL with Write Cache
+          * Flush Enable = 1, a PIPE_CONTROL with any non-zero
+          * post-sync-op is required.
+          */
+         brw_emit_post_sync_nonzero_flush(brw);
+      }
+
+      brw_emit_pipe_control_flush(brw,
+                                  PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+                                  PIPE_CONTROL_RENDER_TARGET_FLUSH |
+                                  PIPE_CONTROL_CS_STALL);
+
+      brw_emit_pipe_control_flush(brw,
+                                  PIPE_CONTROL_TEXTURE_CACHE_INVALIDATE);
+   } else {
+      brw_emit_mi_flush(brw);
+   }
 }
 
 void