i965: Use I915_EXEC_NO_RELOC

If we correctly fill the batch with the right relocation value, and that
matches the expected location of the object, we can then tell the kernel
it can forgo checking each individual relocation by only checking
whether the object moved.

v2: Rebase to apply ahead of I915_EXEC_HANDLE_LUT

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/intel_batchbuffer.c b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
index 58482ecac9fc22bf3d1382215bbeba0f8ed730ff..dcc6f90238cf3a98d64784739769a270f867b987 100644 (file)
--- a/src/mesa/drivers/dri/i965/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
@@ -637,7 +637,19 @@ do_flush_locked(struct brw_context *brw, int in_fence_fd, int *out_fence_fd)
    }
 
    if (!brw->screen->no_hw) {
-      int flags = 0;
+      /* The requirement for using I915_EXEC_NO_RELOC are:
+       *
+       *   The addresses written in the objects must match the corresponding
+       *   reloc.presumed_offset which in turn must match the corresponding
+       *   execobject.offset.
+       *
+       *   Any render targets written to in the batch must be flagged with
+       *   EXEC_OBJECT_WRITE.
+       *
+       *   To avoid stalling, execobject.offset should match the current
+       *   address of that object within the active context.
+       */
+      int flags = I915_EXEC_NO_RELOC;
 
       if (brw->gen >= 6 && batch->ring == BLT_RING) {
          flags |= I915_EXEC_BLT;
@@ -767,8 +779,6 @@ brw_emit_reloc(struct intel_batchbuffer *batch, uint32_t batch_offset,
 {
    assert(target != NULL);
 
-   uint64_t offset64;
-
    if (batch->reloc_count == batch->reloc_array_size) {
       batch->reloc_array_size *= 2;
       batch->relocs = realloc(batch->relocs,
@@ -780,16 +790,32 @@ brw_emit_reloc(struct intel_batchbuffer *batch, uint32_t batch_offset,
    assert(batch_offset <= BATCH_SZ - sizeof(uint32_t));
    assert(_mesa_bitcount(write_domain) <= 1);
 
-   if (target != batch->bo)
-      add_exec_bo(batch, target);
+   uint64_t offset64;
+   if (target != batch->bo) {
+      unsigned int index = add_exec_bo(batch, target);
+      struct drm_i915_gem_exec_object2 *entry = &batch->validation_list[index];
+
+      if (write_domain) {
+         entry->flags |= EXEC_OBJECT_WRITE;
+
+         /* PIPECONTROL needs a w/a on gen6 */
+         if (write_domain == I915_GEM_DOMAIN_INSTRUCTION) {
+            struct brw_context *brw = container_of(batch, brw, batch);
+            if (brw->gen == 6)
+               entry->flags |= EXEC_OBJECT_NEEDS_GTT;
+         }
+      }
+
+      offset64 = entry->offset;
+   } else {
+      offset64 = target->offset64;
+   }
 
    struct drm_i915_gem_relocation_entry *reloc =
       &batch->relocs[batch->reloc_count];
 
    batch->reloc_count++;
 
-   /* ensure gcc doesn't reload */
-   offset64 = *((volatile uint64_t *)&target->offset64);
    reloc->offset = batch_offset;
    reloc->delta = target_offset;
    reloc->target_handle = target->gem_handle;