Merge branch 'gallium-userbuf'

Conflicts:
	src/gallium/docs/source/screen.rst
	src/gallium/drivers/nv50/nv50_state.c
	src/gallium/include/pipe/p_defines.h
	src/mesa/state_tracker/st_draw.c

9 files changed, 125 insertions, 69 deletions

diff --git a/src/gallium/auxiliary/util/u_draw.c b/src/gallium/auxiliary/util/u_draw.c
index d16575b7340..1f3eb887959 100644
--- a/src/gallium/auxiliary/util/u_draw.c
+++ b/src/gallium/auxiliary/util/u_draw.c
@@ -62,6 +62,10 @@ util_draw_max_index(
       const struct util_format_description *format_desc;
       unsigned format_size;
 
+      if (!buffer->buffer) {
+         continue;
+      }
+
       assert(buffer->buffer->height0 == 1);
       assert(buffer->buffer->depth0 == 1);
       buffer_size = buffer->buffer->width0;
diff --git a/src/gallium/auxiliary/util/u_draw_quad.c b/src/gallium/auxiliary/util/u_draw_quad.c
index 590fa0c36bb..469c874988d 100644
--- a/src/gallium/auxiliary/util/u_draw_quad.c
+++ b/src/gallium/auxiliary/util/u_draw_quad.c
@@ -69,6 +69,27 @@ util_draw_vertex_buffer(struct pipe_context *pipe,
 }
 
 
+/**
+ * Draw a simple vertex buffer / primitive.
+ * Limited to float[4] vertex attribs, tightly packed.
+ */
+void
+util_draw_user_vertex_buffer(struct cso_context *cso, void *buffer,
+                             uint prim_type, uint num_verts, uint num_attribs)
+{
+   struct pipe_vertex_buffer vbuffer = {0};
+
+   assert(num_attribs <= PIPE_MAX_ATTRIBS);
+
+   vbuffer.user_buffer = buffer;
+   vbuffer.stride = num_attribs * 4 * sizeof(float);  /* vertex size */
+
+   /* note: vertex elements already set by caller */
+
+   cso_set_vertex_buffers(cso, 1, &vbuffer);
+   cso_draw_arrays(cso, prim_type, 0, num_verts);
+}
+
 
 /**
  * Draw screen-aligned textured quad.
@@ -118,10 +139,11 @@ util_draw_texquad(struct pipe_context *pipe, struct cso_context *cso,
    v[28] = 0.0;
    v[29] = 1.0;
 	 
-   vbuf = pipe_user_buffer_create(pipe->screen, v, vertexBytes,
-				  PIPE_BIND_VERTEX_BUFFER);
+   vbuf = pipe_buffer_create(pipe->screen, PIPE_BIND_VERTEX_BUFFER,
+                             PIPE_USAGE_STAGING, vertexBytes);
    if (!vbuf)
       goto out;
+   pipe_buffer_write(pipe, vbuf, 0, vertexBytes, v);
 
    util_draw_vertex_buffer(pipe, cso, vbuf, 0, PIPE_PRIM_TRIANGLE_FAN, 4, 2);
 
diff --git a/src/gallium/auxiliary/util/u_draw_quad.h b/src/gallium/auxiliary/util/u_draw_quad.h
index f1167786f0e..2834a4a8115 100644
--- a/src/gallium/auxiliary/util/u_draw_quad.h
+++ b/src/gallium/auxiliary/util/u_draw_quad.h
@@ -47,6 +47,9 @@ util_draw_vertex_buffer(struct pipe_context *pipe, struct cso_context *cso,
                         struct pipe_resource *vbuf, uint offset,
                         uint num_attribs, uint num_verts, uint prim_type);
 
+void
+util_draw_user_vertex_buffer(struct cso_context *cso, void *buffer,
+                             uint prim_type, uint num_verts, uint num_attribs);
 
 extern void 
 util_draw_texquad(struct pipe_context *pipe, struct cso_context *cso,
diff --git a/src/gallium/auxiliary/util/u_index_modify.c b/src/gallium/auxiliary/util/u_index_modify.c
index d0a28b5fdfa..5e3fd463eb4 100644
--- a/src/gallium/auxiliary/util/u_index_modify.c
+++ b/src/gallium/auxiliary/util/u_index_modify.c
@@ -27,21 +27,25 @@
 /* Ubyte indices. */
 
 void util_shorten_ubyte_elts_to_userptr(struct pipe_context *context,
-					struct pipe_resource *elts,
+					struct pipe_index_buffer *ib,
 					int index_bias,
 					unsigned start,
 					unsigned count,
 					void *out)
 {
-    struct pipe_transfer *src_transfer;
-    unsigned char *in_map;
+    struct pipe_transfer *src_transfer = NULL;
+    const unsigned char *in_map;
     unsigned short *out_map = out;
     unsigned i;
 
-    in_map = pipe_buffer_map(context, elts,
-                             PIPE_TRANSFER_READ |
-                             PIPE_TRANSFER_UNSYNCHRONIZED,
-                             &src_transfer);
+    if (ib->user_buffer) {
+       in_map = ib->user_buffer;
+    } else {
+       in_map = pipe_buffer_map(context, ib->buffer,
+                                PIPE_TRANSFER_READ |
+                                PIPE_TRANSFER_UNSYNCHRONIZED,
+                                &src_transfer);
+    }
     in_map += start;
 
     for (i = 0; i < count; i++) {
@@ -50,11 +54,13 @@ void util_shorten_ubyte_elts_to_userptr(struct pipe_context *context,
         out_map++;
     }
 
-    pipe_buffer_unmap(context, src_transfer);
+    if (src_transfer)
+       pipe_buffer_unmap(context, src_transfer);
 }
 
 void util_shorten_ubyte_elts(struct pipe_context *context,
-			     struct pipe_resource **elts,
+			     struct pipe_index_buffer *ib,
+			     struct pipe_resource **out_buf,
 			     int index_bias,
 			     unsigned start,
 			     unsigned count)
@@ -70,31 +76,36 @@ void util_shorten_ubyte_elts(struct pipe_context *context,
 
     out_map = pipe_buffer_map(context, new_elts, PIPE_TRANSFER_WRITE,
                               &dst_transfer);
-    util_shorten_ubyte_elts_to_userptr(context, *elts, index_bias,
+    util_shorten_ubyte_elts_to_userptr(context, ib, index_bias,
                                        start, count, out_map);
     pipe_buffer_unmap(context, dst_transfer);
 
-    *elts = new_elts;
+    pipe_resource_reference(out_buf, NULL);
+    *out_buf = new_elts;
 }
 
 
 /* Ushort indices. */
 
 void util_rebuild_ushort_elts_to_userptr(struct pipe_context *context,
-					 struct pipe_resource *elts,
+					 struct pipe_index_buffer *ib,
 					 int index_bias,
 					 unsigned start, unsigned count,
 					 void *out)
 {
     struct pipe_transfer *in_transfer = NULL;
-    unsigned short *in_map;
+    const unsigned short *in_map;
     unsigned short *out_map = out;
     unsigned i;
 
-    in_map = pipe_buffer_map(context, elts,
-                             PIPE_TRANSFER_READ |
-                             PIPE_TRANSFER_UNSYNCHRONIZED,
-                             &in_transfer);
+    if (ib->user_buffer) {
+       in_map = ib->user_buffer;
+    } else {
+       in_map = pipe_buffer_map(context, ib->buffer,
+                                PIPE_TRANSFER_READ |
+                                PIPE_TRANSFER_UNSYNCHRONIZED,
+                                &in_transfer);
+    }
     in_map += start;
 
     for (i = 0; i < count; i++) {
@@ -103,11 +114,13 @@ void util_rebuild_ushort_elts_to_userptr(struct pipe_context *context,
         out_map++;
     }
 
-    pipe_buffer_unmap(context, in_transfer);
+    if (in_transfer)
+       pipe_buffer_unmap(context, in_transfer);
 }
 
 void util_rebuild_ushort_elts(struct pipe_context *context,
-			      struct pipe_resource **elts,
+			      struct pipe_index_buffer *ib,
+			      struct pipe_resource **out_buf,
 			      int index_bias,
 			      unsigned start, unsigned count)
 {
@@ -122,31 +135,36 @@ void util_rebuild_ushort_elts(struct pipe_context *context,
 
     out_map = pipe_buffer_map(context, new_elts,
                               PIPE_TRANSFER_WRITE, &out_transfer);
-    util_rebuild_ushort_elts_to_userptr(context, *elts, index_bias,
+    util_rebuild_ushort_elts_to_userptr(context, ib, index_bias,
                                         start, count, out_map);
     pipe_buffer_unmap(context, out_transfer);
 
-    *elts = new_elts;
+    pipe_resource_reference(out_buf, NULL);
+    *out_buf = new_elts;
 }
 
 
 /* Uint indices. */
 
 void util_rebuild_uint_elts_to_userptr(struct pipe_context *context,
-				       struct pipe_resource *elts,
+				       struct pipe_index_buffer *ib,
 				       int index_bias,
 				       unsigned start, unsigned count,
 				       void *out)
 {
     struct pipe_transfer *in_transfer = NULL;
-    unsigned int *in_map;
+    const unsigned int *in_map;
     unsigned int *out_map = out;
     unsigned i;
 
-    in_map = pipe_buffer_map(context, elts,
-                             PIPE_TRANSFER_READ |
-                             PIPE_TRANSFER_UNSYNCHRONIZED,
-                             &in_transfer);
+    if (ib->user_buffer) {
+       in_map = ib->user_buffer;
+    } else {
+       in_map = pipe_buffer_map(context, ib->buffer,
+                                PIPE_TRANSFER_READ |
+                                PIPE_TRANSFER_UNSYNCHRONIZED,
+                                &in_transfer);
+    }
     in_map += start;
 
     for (i = 0; i < count; i++) {
@@ -155,11 +173,13 @@ void util_rebuild_uint_elts_to_userptr(struct pipe_context *context,
         out_map++;
     }
 
-    pipe_buffer_unmap(context, in_transfer);
+    if (in_transfer)
+       pipe_buffer_unmap(context, in_transfer);
 }
 
 void util_rebuild_uint_elts(struct pipe_context *context,
-			    struct pipe_resource **elts,
+			    struct pipe_index_buffer *ib,
+			    struct pipe_resource **out_buf,
 			    int index_bias,
 			    unsigned start, unsigned count)
 {
@@ -174,9 +194,10 @@ void util_rebuild_uint_elts(struct pipe_context *context,
 
     out_map = pipe_buffer_map(context, new_elts,
                               PIPE_TRANSFER_WRITE, &out_transfer);
-    util_rebuild_uint_elts_to_userptr(context, *elts, index_bias,
+    util_rebuild_uint_elts_to_userptr(context, ib, index_bias,
                                       start, count, out_map);
     pipe_buffer_unmap(context, out_transfer);
 
-    *elts = new_elts;
+    pipe_resource_reference(out_buf, NULL);
+    *out_buf = new_elts;
 }
diff --git a/src/gallium/auxiliary/util/u_index_modify.h b/src/gallium/auxiliary/util/u_index_modify.h
index 1e9de3dfac8..6afce50b984 100644
--- a/src/gallium/auxiliary/util/u_index_modify.h
+++ b/src/gallium/auxiliary/util/u_index_modify.h
@@ -25,16 +25,18 @@
 
 struct pipe_context;
 struct pipe_resource;
+struct pipe_index_buffer;
 
 void util_shorten_ubyte_elts_to_userptr(struct pipe_context *context,
-					struct pipe_resource *elts,
+					struct pipe_index_buffer *ib,
 					int index_bias,
 					unsigned start,
 					unsigned count,
 					void *out);
 
 void util_shorten_ubyte_elts(struct pipe_context *context,
-			     struct pipe_resource **elts,
+			     struct pipe_index_buffer *ib,
+			     struct pipe_resource **out_buf,
 			     int index_bias,
 			     unsigned start,
 			     unsigned count);
@@ -42,26 +44,28 @@ void util_shorten_ubyte_elts(struct pipe_context *context,
 
 
 void util_rebuild_ushort_elts_to_userptr(struct pipe_context *context,
-					 struct pipe_resource *elts,
+					 struct pipe_index_buffer *ib,
 					 int index_bias,
 					 unsigned start, unsigned count,
 					 void *out);
 
 void util_rebuild_ushort_elts(struct pipe_context *context,
-			      struct pipe_resource **elts,
+			      struct pipe_index_buffer *ib,
+			      struct pipe_resource **out_buf,
 			      int index_bias,
 			      unsigned start, unsigned count);
 
 
 
 void util_rebuild_uint_elts_to_userptr(struct pipe_context *context,
-				       struct pipe_resource *elts,
+				       struct pipe_index_buffer *ib,
 				       int index_bias,
 				       unsigned start, unsigned count,
 				       void *out);
 
 void util_rebuild_uint_elts(struct pipe_context *context,
-			    struct pipe_resource **elts,
+			    struct pipe_index_buffer *ib,
+			    struct pipe_resource **out_buf,
 			    int index_bias,
 			    unsigned start, unsigned count);
 
diff --git a/src/gallium/auxiliary/util/u_inlines.h b/src/gallium/auxiliary/util/u_inlines.h
index 49b4531dbac..651f7c2d727 100644
--- a/src/gallium/auxiliary/util/u_inlines.h
+++ b/src/gallium/auxiliary/util/u_inlines.h
@@ -437,6 +437,21 @@ pipe_transfer_destroy( struct pipe_context *context,
    context->transfer_destroy(context, transfer);
 }
 
+static INLINE void
+pipe_set_constant_buffer(struct pipe_context *pipe, uint shader, uint index,
+                         struct pipe_resource *buf)
+{
+   if (buf) {
+      struct pipe_constant_buffer cb;
+      cb.buffer = buf;
+      cb.buffer_offset = 0;
+      cb.buffer_size = buf->width0;
+      pipe->set_constant_buffer(pipe, shader, index, &cb);
+   } else {
+      pipe->set_constant_buffer(pipe, shader, index, NULL);
+   }
+}
+
 
 static INLINE boolean util_get_offset( 
    const struct pipe_rasterizer_state *templ,
diff --git a/src/gallium/auxiliary/util/u_transfer.c b/src/gallium/auxiliary/util/u_transfer.c
index 673a984fcb2..0b2679ffdb4 100644
--- a/src/gallium/auxiliary/util/u_transfer.c
+++ b/src/gallium/auxiliary/util/u_transfer.c
@@ -125,11 +125,3 @@ void u_default_transfer_destroy(struct pipe_context *pipe,
 {
    FREE(transfer);
 }
-
-void u_default_redefine_user_buffer(struct pipe_context *ctx,
-                                    struct pipe_resource *resource,
-                                    unsigned offset,
-                                    unsigned size)
-{
-   resource->width0 = MAX2(resource->width0, offset + size);
-}
diff --git a/src/gallium/auxiliary/util/u_transfer.h b/src/gallium/auxiliary/util/u_transfer.h
index 5b5ddeb4aba..f4fdf9a4840 100644
--- a/src/gallium/auxiliary/util/u_transfer.h
+++ b/src/gallium/auxiliary/util/u_transfer.h
@@ -124,9 +124,4 @@ void u_transfer_inline_write_vtbl( struct pipe_context *rm_ctx,
                                    unsigned stride,
                                    unsigned layer_stride);
 
-void u_default_redefine_user_buffer(struct pipe_context *ctx,
-                                    struct pipe_resource *resource,
-                                    unsigned offset,
-                                    unsigned size);
-
 #endif
diff --git a/src/gallium/auxiliary/util/u_vbuf.c b/src/gallium/auxiliary/util/u_vbuf.c
index 401c8a4a850..4141ba536fd 100644
--- a/src/gallium/auxiliary/util/u_vbuf.c
+++ b/src/gallium/auxiliary/util/u_vbuf.c
@@ -277,8 +277,8 @@ u_vbuf_translate_buffers(struct u_vbuf *mgr, struct translate_key *key,
          unsigned offset = vb->buffer_offset + vb->stride * start_vertex;
          uint8_t *map;
 
-         if (vb->buffer->user_ptr) {
-            map = vb->buffer->user_ptr + offset;
+         if (vb->user_buffer) {
+            map = (uint8_t*)vb->user_buffer + offset;
          } else {
             unsigned size = vb->stride ? num_vertices * vb->stride
                                        : sizeof(double)*4;
@@ -307,10 +307,10 @@ u_vbuf_translate_buffers(struct u_vbuf *mgr, struct translate_key *key,
       unsigned offset = ib->offset + start_index * ib->index_size;
       uint8_t *map;
 
-      assert(ib->buffer && ib->index_size);
+      assert((ib->buffer || ib->user_buffer) && ib->index_size);
 
-      if (ib->buffer->user_ptr) {
-         map = ib->buffer->user_ptr + offset;
+      if (ib->user_buffer) {
+         map = (uint8_t*)ib->user_buffer + offset;
       } else {
          map = pipe_buffer_map_range(mgr->pipe, ib->buffer, offset,
                                      num_indices * ib->index_size,
@@ -713,15 +713,17 @@ void u_vbuf_set_vertex_buffers(struct u_vbuf *mgr, unsigned count,
       struct pipe_vertex_buffer *real_vb = &mgr->real_vertex_buffer[i];
 
       pipe_resource_reference(&orig_vb->buffer, vb->buffer);
+      orig_vb->user_buffer = vb->user_buffer;
 
       real_vb->buffer_offset = orig_vb->buffer_offset = vb->buffer_offset;
       real_vb->stride = orig_vb->stride = vb->stride;
+      real_vb->user_buffer = NULL;
 
       if (vb->stride) {
          mgr->nonzero_stride_vb_mask |= 1 << i;
       }
 
-      if (!vb->buffer) {
+      if (!vb->buffer && !vb->user_buffer) {
          pipe_resource_reference(&real_vb->buffer, NULL);
          continue;
       }
@@ -733,13 +735,14 @@ void u_vbuf_set_vertex_buffers(struct u_vbuf *mgr, unsigned count,
          continue;
       }
 
-      if (!mgr->caps.user_vertex_buffers && vb->buffer->user_ptr) {
+      if (!mgr->caps.user_vertex_buffers && vb->user_buffer) {
          mgr->user_vb_mask |= 1 << i;
          pipe_resource_reference(&real_vb->buffer, NULL);
          continue;
       }
 
       pipe_resource_reference(&real_vb->buffer, vb->buffer);
+      real_vb->user_buffer = vb->user_buffer;
    }
 
    for (i = count; i < mgr->nr_vertex_buffers; i++) {
@@ -759,11 +762,10 @@ void u_vbuf_set_index_buffer(struct u_vbuf *mgr,
 {
    struct pipe_context *pipe = mgr->pipe;
 
-   if (ib && ib->buffer) {
+   if (ib) {
       assert(ib->offset % ib->index_size == 0);
       pipe_resource_reference(&mgr->index_buffer.buffer, ib->buffer);
-      mgr->index_buffer.offset = ib->offset;
-      mgr->index_buffer.index_size = ib->index_size;
+      memcpy(&mgr->index_buffer, ib, sizeof(*ib));
    } else {
       pipe_resource_reference(&mgr->index_buffer.buffer, NULL);
    }
@@ -798,9 +800,7 @@ u_vbuf_upload_buffers(struct u_vbuf *mgr,
          continue;
       }
 
-      assert(vb->buffer);
-
-      if (!vb->buffer->user_ptr) {
+      if (!vb->user_buffer) {
          continue;
       }
 
@@ -837,7 +837,7 @@ u_vbuf_upload_buffers(struct u_vbuf *mgr,
    for (i = 0; i < nr_vbufs; i++) {
       unsigned start, end = end_offset[i];
       struct pipe_vertex_buffer *real_vb;
-      uint8_t *ptr;
+      const uint8_t *ptr;
 
       if (!end) {
          continue;
@@ -847,7 +847,7 @@ u_vbuf_upload_buffers(struct u_vbuf *mgr,
       assert(start < end);
 
       real_vb = &mgr->real_vertex_buffer[i];
-      ptr = mgr->vertex_buffer[i].buffer->user_ptr;
+      ptr = mgr->vertex_buffer[i].user_buffer;
 
       u_upload_data(mgr->uploader, start, end - start, ptr + start,
                     &real_vb->buffer_offset, &real_vb->buffer);
@@ -888,8 +888,8 @@ static void u_vbuf_get_minmax_index(struct pipe_context *pipe,
    unsigned i;
    unsigned restart_index = info->restart_index;
 
-   if (ib->buffer->user_ptr) {
-      indices = ib->buffer->user_ptr +
+   if (ib->user_buffer) {
+      indices = (uint8_t*)ib->user_buffer +
                 ib->offset + info->start * ib->index_size;
    } else {
       indices = pipe_buffer_map_range(pipe, ib->buffer,