Mesa (master): i965: Use negative relocation deltas to minimse vertex uploads

[Chris Wilson]

Module: Mesa
Branch: master
Commit: 900a5c91eeb3acae7ee0ad331154531c4dba96e1
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=900a5c91eeb3acae7ee0ad331154531c4dba96e1

Author: Chris Wilson <chris at chris-wilson.co.uk>
Date:   Tue Mar  1 14:46:50 2011 +0000

i965: Use negative relocation deltas to minimse vertex uploads

With relaxed relocation checking in the kernel, we can specify a
negative delta (i.e. pointing outside of the target bo) in order to fake
a range in a large buffer. We only then need to upload the elements used
and adjust the buffer offset such that they correspond with the indices
used in the DrawArrays.

(Depends on libdrm 0209428b3918c4336018da9293cdcbf7f8fedfb6)

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>

---

 src/mesa/drivers/dri/i965/brw_context.h     |    2 +-
 src/mesa/drivers/dri/i965/brw_draw_upload.c |   21 ++++++++++++++-------
 src/mesa/drivers/dri/intel/intel_screen.c   |   11 +++++++++++
 src/mesa/drivers/dri/intel/intel_screen.h   |    1 +
 4 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_context.h b/src/mesa/drivers/dri/i965/brw_context.h
index 2e8561d..897220b 100644
--- a/src/mesa/drivers/dri/i965/brw_context.h
+++ b/src/mesa/drivers/dri/i965/brw_context.h
@@ -460,7 +460,7 @@ struct brw_context
    GLboolean has_negative_rhw_bug;
    GLboolean has_aa_line_parameters;
    GLboolean has_pln;
-;
+
    struct {
       struct brw_state_flags dirty;
 
diff --git a/src/mesa/drivers/dri/i965/brw_draw_upload.c b/src/mesa/drivers/dri/i965/brw_draw_upload.c
index 1e129f9..185f1ff 100644
--- a/src/mesa/drivers/dri/i965/brw_draw_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_draw_upload.c
@@ -278,7 +278,7 @@ static void brw_prepare_vertices(struct brw_context *brw)
    GLuint interleaved = 0, total_size = 0;
    unsigned int min_index = brw->vb.min_index;
    unsigned int max_index = brw->vb.max_index;
-   int i, j;
+   int delta, i, j;
 
    struct brw_vertex_element *upload[VERT_ATTRIB_MAX];
    GLuint nr_uploads = 0;
@@ -401,21 +401,25 @@ static void brw_prepare_vertices(struct brw_context *brw)
     * only the used elements [min_index, max_index] so long as we adjust all
     * the values used in the 3DPRIMITIVE i.e. by setting the vertex bias.
     */
+   brw->vb.start_vertex_bias = 0;
+   delta = min_index;
    if (nr_uploads == brw->vb.nr_enabled) {
-      brw->vb.start_vertex_bias = min_index;
-   } else {
-      brw->vb.start_vertex_bias = 0;
-      min_index = 0;
+      brw->vb.start_vertex_bias = -delta;
+      delta = 0;
    }
+   if (delta && !brw->intel.intelScreen->relaxed_relocations)
+      min_index = delta = 0;
 
    /* Handle any arrays to be uploaded. */
    if (nr_uploads > 1) {
       if (interleaved && interleaved <= 2*total_size) {
+	 struct brw_vertex_buffer *buffer = &brw->vb.buffers[j];
 	 /* All uploads are interleaved, so upload the arrays together as
 	  * interleaved.  First, upload the contents and set up upload[0].
 	  */
 	 copy_array_to_vbo_array(brw, upload[0], min_index, max_index,
-				 &brw->vb.buffers[j], interleaved);
+				 buffer, interleaved);
+	 buffer->offset -= delta * interleaved;
 
 	 for (i = 0; i < nr_uploads; i++) {
 	    /* Then, just point upload[i] at upload[0]'s buffer. */
@@ -462,14 +466,17 @@ static void brw_prepare_vertices(struct brw_context *brw)
 	 intel_upload_unmap(&brw->intel, map, offset * count, offset,
 			    &buffer->bo, &buffer->offset);
 	 buffer->stride = offset;
+	 buffer->offset -= delta * offset;
 
 	 nr_uploads = 0;
       }
    }
    /* Upload non-interleaved arrays */
    for (i = 0; i < nr_uploads; i++) {
+      struct brw_vertex_buffer *buffer = &brw->vb.buffers[j];
       copy_array_to_vbo_array(brw, upload[i], min_index, max_index,
-			      &brw->vb.buffers[j], upload[i]->element_size);
+			      buffer, upload[i]->element_size);
+      buffer->offset -= delta * buffer->stride;
       upload[i]->buffer = j++;
       upload[i]->offset = 0;
    }
diff --git a/src/mesa/drivers/dri/intel/intel_screen.c b/src/mesa/drivers/dri/intel/intel_screen.c
index 746da46..5c95c72 100644
--- a/src/mesa/drivers/dri/intel/intel_screen.c
+++ b/src/mesa/drivers/dri/intel/intel_screen.c
@@ -309,6 +309,13 @@ intel_get_param(__DRIscreen *psp, int param, int *value)
    return GL_TRUE;
 }
 
+static GLboolean
+intel_get_boolean(__DRIscreen *psp, int param)
+{
+   int value = 0;
+   return intel_get_param(psp, param, &value) && value;
+}
+
 static void
 nop_callback(GLuint key, void *data, void *userData)
 {
@@ -482,6 +489,10 @@ intel_init_bufmgr(struct intel_screen *intelScreen)
 
    intelScreen->named_regions = _mesa_NewHashTable();
 
+   intelScreen->relaxed_relocations = 0;
+   intelScreen->relaxed_relocations |=
+      intel_get_boolean(spriv, I915_PARAM_HAS_RELAXED_DELTA) << 0;
+
    return GL_TRUE;
 }
 
diff --git a/src/mesa/drivers/dri/intel/intel_screen.h b/src/mesa/drivers/dri/intel/intel_screen.h
index 5863093..0f0b5be 100644
--- a/src/mesa/drivers/dri/intel/intel_screen.h
+++ b/src/mesa/drivers/dri/intel/intel_screen.h
@@ -43,6 +43,7 @@ struct intel_screen
    __DRIscreen *driScrnPriv;
 
    GLboolean no_hw;
+   GLuint relaxed_relocations;
 
    GLboolean no_vbo;
    dri_bufmgr *bufmgr;