vc4: Handle a couple of the transfer map flags.

This is part of fixing extremely long runtimes on some piglit tests that
involve streaming vertex reuploads due to format conversions, and will
similarly be important for X performance, which relies on these flags.

2 files changed, 12 insertions, 4 deletions

diff --git a/src/gallium/drivers/vc4/vc4_bufmgr.h b/src/gallium/drivers/vc4/vc4_bufmgr.h
index 14bfa2466df..00ea149bd5f 100644
--- a/src/gallium/drivers/vc4/vc4_bufmgr.h
+++ b/src/gallium/drivers/vc4/vc4_bufmgr.h
@@ -70,6 +70,9 @@ vc4_bo_reference(struct vc4_bo *bo)
 static inline void
 vc4_bo_unreference(struct vc4_bo **bo)
 {
+        if (!*bo)
+                return;
+
         if (pipe_reference(&(*bo)->reference, NULL))
                 vc4_bo_free(*bo);
         *bo = NULL;
diff --git a/src/gallium/drivers/vc4/vc4_resource.c b/src/gallium/drivers/vc4/vc4_resource.c
index 98c8f89fdec..a71ae5bab13 100644
--- a/src/gallium/drivers/vc4/vc4_resource.c
+++ b/src/gallium/drivers/vc4/vc4_resource.c
@@ -73,15 +73,20 @@ vc4_resource_transfer_map(struct pipe_context *pctx,
         enum pipe_format format = prsc->format;
         char *buf;
 
-        vc4_flush_for_bo(pctx, rsc->bo);
+        if (usage & PIPE_TRANSFER_DISCARD_WHOLE_RESOURCE) {
+                uint32_t size = rsc->bo->size;
+                vc4_bo_unreference(&rsc->bo);
+                rsc->bo = vc4_bo_alloc(vc4->screen, size, "resource");
+        }
+
+        if (!(usage & PIPE_TRANSFER_UNSYNCHRONIZED))
+                vc4_flush_for_bo(pctx, rsc->bo);
 
         trans = util_slab_alloc(&vc4->transfer_pool);
         if (!trans)
                 return NULL;
 
-        /* XXX: Handle DISCARD_WHOLE_RESOURCE, DONTBLOCK, UNSYNCHRONIZED,
-         * DISCARD_WHOLE_RESOURCE, PERSISTENT, COHERENT.
-         */
+        /* XXX: Handle DONTBLOCK, DISCARD_RANGE, PERSISTENT, COHERENT. */
 
         /* util_slab_alloc() doesn't zero: */
         memset(trans, 0, sizeof(*trans));