Commit e99e7aa4 began passing start > 0 to indexed draw calls rather than keeping start at 0 and manually advancing ib->ptr. This should work fine, however, there have been instances of software fallbacks not handling things right.
vbo_sw_primitive_restart had a bug where it was ignoring "start" and always calling find_sub_primitives with start = 0 and end = ib->count. This meant that when start > 0, it was analyzing the wrong part of the index buffer when finding subprimitives.
In theory, each _mesa_prim can have a different "start" value. But the code only calls find_sub_primitives once, because it wants to map, analyze, and unmap the index buffer before calling ctx->Draw, as some drivers don't support drawing with the index buffer mapped.
To handle this, we break vbo_sw_primitive_restart calls into sections where "start" matches across all the primitives, similar to how I handled the issue in tnl in commit bd6120f5.
In the common case, start matches and we handle it in one pass anyway.
Fixes Piglit's primitive-restart VBO_COMBINED_VERTEX_AND_INDEX test and KHR-GL33.pipeline_statistics_query_tests_ARB.functional_primitives_vertices_submitted_and_clipping_input_output_primitives on Intel Ivybridge and older (which don't do arbitrary cut indices).
Closes: #4052 (closed)