Merge branch 'gallium-polygon-stipple'

[mesa.git] / src / mesa / drivers / dri / i965 / brw_draw_upload.c

diff --git a/src/mesa/drivers/dri/i965/brw_draw_upload.c b/src/mesa/drivers/dri/i965/brw_draw_upload.c
index 185f1ffa598b2d7c9105273a2e8645e4c5af1007..56a46ced6e3cf4759990348e2bbea2b1ba758678 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_draw_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_draw_upload.c
@@ -207,8 +207,12 @@ static GLuint get_surface_type( GLenum type, GLuint size,
       case GL_UNSIGNED_INT: return uint_types_scale[size];
       case GL_UNSIGNED_SHORT: return ushort_types_scale[size];
       case GL_UNSIGNED_BYTE: return ubyte_types_scale[size];
+      /* This produces GL_FIXED inputs as values between INT32_MIN and
+       * INT32_MAX, which will be scaled down by 1/65536 by the VS.
+       */
+      case GL_FIXED: return int_types_scale[size];
       default: assert(0); return 0;
-      }      
+      }
    }
 }
 
@@ -225,11 +229,12 @@ static GLuint get_size( GLenum type )
    case GL_UNSIGNED_INT: return sizeof(GLuint);
    case GL_UNSIGNED_SHORT: return sizeof(GLushort);
    case GL_UNSIGNED_BYTE: return sizeof(GLubyte);
-   default: return 0;
-   }      
+   case GL_FIXED: return sizeof(GLuint);
+   default: assert(0); return 0;
+   }
 }
 
-static GLuint get_index_type(GLenum type) 
+static GLuint get_index_type(GLenum type)
 {
    switch (type) {
    case GL_UNSIGNED_BYTE:  return BRW_INDEX_BYTE;
@@ -273,6 +278,7 @@ static void brw_prepare_vertices(struct brw_context *brw)
 {
    struct gl_context *ctx = &brw->intel.ctx;
    struct intel_context *intel = intel_context(ctx);
+   /* CACHE_NEW_VS_PROG */
    GLbitfield vs_inputs = brw->vs.prog_data->inputs_read;
    const unsigned char *ptr = NULL;
    GLuint interleaved = 0, total_size = 0;
@@ -291,11 +297,12 @@ static void brw_prepare_vertices(struct brw_context *brw)
    /* Accumulate the list of enabled arrays. */
    brw->vb.nr_enabled = 0;
    while (vs_inputs) {
-      GLuint i = _mesa_ffsll(vs_inputs) - 1;
+      GLuint i = ffs(vs_inputs) - 1;
       struct brw_vertex_element *input = &brw->vb.inputs[i];
 
       vs_inputs &= ~(1 << i);
-      brw->vb.enabled[brw->vb.nr_enabled++] = input;
+      if (input->glarray->Size && get_size(input->glarray->Type))
+         brw->vb.enabled[brw->vb.nr_enabled++] = input;
    }
 
    if (brw->vb.nr_enabled == 0)
@@ -342,7 +349,8 @@ static void brw_prepare_vertices(struct brw_context *brw)
            struct brw_vertex_buffer *buffer = &brw->vb.buffers[j];
 
            /* Named buffer object: Just reference its contents directly. */
-           buffer->bo = intel_bufferobj_source(intel, intel_buffer,
+            buffer->bo = intel_bufferobj_source(intel,
+                                                intel_buffer, type_size,
                                                &buffer->offset);
            drm_intel_bo_reference(buffer->bo);
            buffer->offset += (uintptr_t)glarray->Ptr;
@@ -482,7 +490,7 @@ static void brw_prepare_vertices(struct brw_context *brw)
    }
 
    /* can we simply extend the current vb? */
-   if (0 && j == brw->vb.nr_current_buffers) {
+   if (j == brw->vb.nr_current_buffers) {
       int delta = 0;
       for (i = 0; i < j; i++) {
         int d;
@@ -492,7 +500,9 @@ static void brw_prepare_vertices(struct brw_context *brw)
            break;
 
         d = brw->vb.buffers[i].offset - brw->vb.current_buffers[i].offset;
-        if (delta == 0)
+        if (d < 0)
+           break;
+        if (i == 0)
            delta = d / brw->vb.current_buffers[i].stride;
         if (delta * brw->vb.current_buffers[i].stride != d)
            break;
@@ -532,7 +542,7 @@ static void brw_emit_vertices(struct brw_context *brw)
     */
    if (brw->vb.nr_enabled == 0) {
       BEGIN_BATCH(3);
-      OUT_BATCH((CMD_VERTEX_ELEMENT << 16) | 1);
+      OUT_BATCH((_3DSTATE_VERTEX_ELEMENTS << 16) | 1);
       if (intel->gen >= 6) {
         OUT_BATCH((0 << GEN6_VE0_INDEX_SHIFT) |
                   GEN6_VE0_VALID |
@@ -557,7 +567,7 @@ static void brw_emit_vertices(struct brw_context *brw)
 
    if (brw->vb.nr_buffers) {
       BEGIN_BATCH(1 + 4*brw->vb.nr_buffers);
-      OUT_BATCH((CMD_VERTEX_BUFFER << 16) | (4*brw->vb.nr_buffers - 1));
+      OUT_BATCH((_3DSTATE_VERTEX_BUFFERS << 16) | (4*brw->vb.nr_buffers - 1));
       for (i = 0; i < brw->vb.nr_buffers; i++) {
         struct brw_vertex_buffer *buffer = &brw->vb.buffers[i];
         uint32_t dw0;
@@ -568,12 +578,15 @@ static void brw_emit_vertices(struct brw_context *brw)
            dw0 = BRW_VB0_ACCESS_VERTEXDATA | (i << BRW_VB0_INDEX_SHIFT);
         }
 
+        if (intel->gen >= 7)
+           dw0 |= GEN7_VB0_ADDRESS_MODIFYENABLE;
+
         OUT_BATCH(dw0 | (buffer->stride << BRW_VB0_PITCH_SHIFT));
         OUT_RELOC(buffer->bo, I915_GEM_DOMAIN_VERTEX, 0, buffer->offset);
         if (intel->gen >= 5) {
            OUT_RELOC(buffer->bo, I915_GEM_DOMAIN_VERTEX, 0, buffer->bo->size - 1);
         } else
-           OUT_BATCH(buffer->bo->size / buffer->stride);
+           OUT_BATCH(0);
         OUT_BATCH(0); /* Instance data step rate */
 
         brw->vb.current_buffers[i].handle = buffer->bo->handle;
@@ -585,7 +598,7 @@ static void brw_emit_vertices(struct brw_context *brw)
    }
 
    BEGIN_BATCH(1 + brw->vb.nr_enabled * 2);
-   OUT_BATCH((CMD_VERTEX_ELEMENT << 16) | (2*brw->vb.nr_enabled - 1));
+   OUT_BATCH((_3DSTATE_VERTEX_ELEMENTS << 16) | (2*brw->vb.nr_enabled - 1));
    for (i = 0; i < brw->vb.nr_enabled; i++) {
       struct brw_vertex_element *input = brw->vb.enabled[i];
       uint32_t format = get_surface_type(input->glarray->Type,
@@ -636,7 +649,7 @@ const struct brw_tracked_state brw_vertices = {
    .dirty = {
       .mesa = 0,
       .brw = BRW_NEW_BATCH | BRW_NEW_VERTICES,
-      .cache = 0,
+      .cache = CACHE_NEW_VS_PROG,
    },
    .prepare = brw_prepare_vertices,
    .emit = brw_emit_vertices,
@@ -669,7 +682,6 @@ static void brw_prepare_indices(struct brw_context *brw)
       intel_upload_data(&brw->intel, index_buffer->ptr, ib_size, ib_type_size,
                        &bo, &offset);
       brw->ib.start_vertex_offset = offset / ib_type_size;
-      offset = 0;
    } else {
       offset = (GLuint) (unsigned long) index_buffer->ptr;
 
@@ -686,7 +698,6 @@ static void brw_prepare_indices(struct brw_context *brw)
           intel_upload_data(&brw->intel, map, ib_size, ib_type_size,
                             &bo, &offset);
           brw->ib.start_vertex_offset = offset / ib_type_size;
-          offset = 0;
 
            ctx->Driver.UnmapBuffer(ctx, GL_ELEMENT_ARRAY_BUFFER_ARB, bufferobj);
        } else {
@@ -696,22 +707,30 @@ static void brw_prepare_indices(struct brw_context *brw)
           */
          brw->ib.start_vertex_offset = offset / ib_type_size;
 
-         bo = intel_bufferobj_source(intel, intel_buffer_object(bufferobj),
+         bo = intel_bufferobj_source(intel,
+                                     intel_buffer_object(bufferobj),
+                                     ib_type_size,
                                      &offset);
          drm_intel_bo_reference(bo);
+
+         brw->ib.start_vertex_offset += offset / ib_type_size;
        }
    }
 
-   if (brw->ib.bo != bo || brw->ib.offset != offset) {
+   if (brw->ib.bo != bo) {
       drm_intel_bo_unreference(brw->ib.bo);
       brw->ib.bo = bo;
-      brw->ib.offset = offset;
 
       brw_add_validated_bo(brw, brw->ib.bo);
       brw->state.dirty.brw |= BRW_NEW_INDEX_BUFFER;
    } else {
       drm_intel_bo_unreference(bo);
    }
+
+   if (index_buffer->type != brw->ib.type) {
+      brw->ib.type = index_buffer->type;
+      brw->state.dirty.brw |= BRW_NEW_INDEX_BUFFER;
+   }
 }
 
 const struct brw_tracked_state brw_indices = {
@@ -738,7 +757,7 @@ static void brw_emit_index_buffer(struct brw_context *brw)
              1);
    OUT_RELOC(brw->ib.bo,
              I915_GEM_DOMAIN_VERTEX, 0,
-             brw->ib.offset);
+             0);
    OUT_RELOC(brw->ib.bo,
              I915_GEM_DOMAIN_VERTEX, 0,
             brw->ib.bo->size - 1);