i965: Be more careful with the interleaved user array upload optimization

The checks to determine when the data can be uploaded in an interleaved
fashion can be tricked by certain data layouts.  For example,

    float data[...];

    glVertexAttribPointer(0, 4, GL_FLOAT, GL_FALSE, 16, &data[0]);
    glVertexAttribPointer(1, 4, GL_FLOAT, GL_FALSE, 16, &data[4]);
    glDrawArrays(GL_POINTS, 0, 1);

will hit the interleaved path with an incorrect size (16 bytes instead
of 32 bytes).  As a result, the data for attribute 1 never gets
uploaded.  The single element draw case is the only sensible case I can
think of for non-interleaved-that-looks-like-interleaved data, but there
may be others as well.

To fix this, make sure that the end of the element in the array being
checked is within the stride "window."  Previously the code would check
that the begining of the element was within the window.

NOTE: This is a candidate for stable branches.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_draw_upload.c b/src/mesa/drivers/dri/i965/brw_draw_upload.c
index 2ded14b0de7b2e29a60c296c71f18a6114b46ab6..74c9e2f40d447c5a7f17f633c8845f28ec2bae83 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_draw_upload.c
+++ b/src/mesa/drivers/dri/i965/brw_draw_upload.c
@@ -506,8 +506,24 @@ static void brw_prepare_vertices(struct brw_context *brw)
            ptr = glarray->Ptr;
         }
         else if (interleaved != glarray->StrideB ||
-                 (uintptr_t)(glarray->Ptr - ptr) > interleaved)
+                  glarray->Ptr < ptr ||
+                  (uintptr_t)(glarray->Ptr - ptr) + glarray->_ElementSize > interleaved)
         {
+            /* If our stride is different from the first attribute's stride,
+             * or if the first attribute's stride didn't cover our element,
+             * disable the interleaved upload optimization.  The second case
+             * can most commonly occur in cases where there is a single vertex
+             * and, for example, the data is stored on the application's
+             * stack.
+             *
+             * NOTE: This will also disable the optimization in cases where
+             * the data is in a different order than the array indices.
+             * Something like:
+             *
+             *     float data[...];
+             *     glVertexAttribPointer(0, 4, GL_FLOAT, 32, &data[4]);
+             *     glVertexAttribPointer(1, 4, GL_FLOAT, 32, &data[0]);
+             */
            interleaved = 0;
         }