i965/gen7: Skip resetting SOL offsets at batch start with HW contexts.

The software-tracked transform feedback offsets (svbi_0_starting_index)
are incorrect in the presence of primitive restart, so we can't reliably
compute offsets for our buffer pointers after a batch flush.  Thanks to HW
contexts, our transform feedback offsets are now saved, so we can just
keep using the ones from before the batch wrap.

Fixes piglit OpenGL 3.1/primitive-restart-xfb flush
Reviewed-by: Paul Berry <stereotype441@gmail.com>
NOTE: This is a candidate for the 9.1 branch.
(cherry picked from commit 62a18da34153dd0e167a2944fc00812c1471c0fb)

2 files changed, 21 insertions, 6 deletions

diff --git a/src/mesa/drivers/dri/i965/gen6_sol.c b/src/mesa/drivers/dri/i965/gen6_sol.c
index 9c09adee00b..a7b63f67e87 100644
--- a/src/mesa/drivers/dri/i965/gen6_sol.c
+++ b/src/mesa/drivers/dri/i965/gen6_sol.c
@@ -159,6 +159,7 @@ brw_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
 			     struct gl_transform_feedback_object *obj)
 {
    struct brw_context *brw = brw_context(ctx);
+   struct intel_context *intel = &brw->intel;
    const struct gl_shader_program *vs_prog =
       ctx->Shader.CurrentVertexProgram;
    const struct gl_transform_feedback_info *linked_xfb_info =
@@ -180,6 +181,14 @@ brw_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
    brw->sol.svbi_0_starting_index = 0;
    brw->sol.svbi_0_max_index = max_index;
    brw->sol.offset_0_batch_start = 0;
+
+   if (intel->gen >= 7) {
+      /* Ask the kernel to reset the SO offsets for any previous transform
+       * feedback, so we start at the start of the user's buffer. (note: these
+       * are not the query counters)
+       */
+      intel->batch.needs_sol_reset = true;
+   }
 }
 
 void
diff --git a/src/mesa/drivers/dri/i965/gen7_sol_state.c b/src/mesa/drivers/dri/i965/gen7_sol_state.c
index 28cecf2d5cd..c725fb67b68 100644
--- a/src/mesa/drivers/dri/i965/gen7_sol_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sol_state.c
@@ -82,12 +82,14 @@ upload_3dstate_so_buffers(struct brw_context *brw)
       end = ALIGN(start + xfb_obj->Size[i], 4);
       assert(end <= bo->size);
 
-      /* Offset the starting offset by the current vertex index into the
-       * feedback buffer, offset register is always set to 0 at the start of the
-       * batchbuffer.
+      /* If we don't have hardware contexts, then we reset our offsets at the
+       * start of every batch, so we track the number of vertices written in
+       * software and increment our pointers by that many.
        */
-      start += brw->sol.offset_0_batch_start * stride;
-      assert(start <= end);
+      if (!intel->hw_ctx) {
+         start += brw->sol.offset_0_batch_start * stride;
+         assert(start <= end);
+      }
 
       BEGIN_BATCH(4);
       OUT_BATCH(_3DSTATE_SO_BUFFER << 16 | (4 - 2));
@@ -244,7 +246,11 @@ upload_sol_state(struct brw_context *brw)
       /* CACHE_NEW_VS_PROG */
       upload_3dstate_so_decl_list(brw, &brw->vs.prog_data->vue_map);
 
-      intel->batch.needs_sol_reset = true;
+      /* If we don't have hardware contexts, then some other client may have
+       * changed the SO write offsets, and we need to rewrite them.
+       */
+      if (!intel->hw_ctx)
+         intel->batch.needs_sol_reset = true;
    }
 
    /* Finally, set up the SOL stage.  This command must always follow updates to