| commit | 163f8526123ffa38783fc911b5f7a19debce7f73 | [log] [tgz] |
|---|---|---|
| author | Ben Skeggs <skeggsb@gmail.com> | Mon Jul 02 19:31:18 2007 +1000 |
| committer | Ben Skeggs <skeggsb@gmail.com> | Mon Jul 09 16:16:44 2007 +1000 |
| tree | 361850d429808f9a3baf2228b2067160b6bc0fe1 | |
| parent | d57b7f02d2e525e5600e5d77370d7ad2b4c9b265 [diff] |
nouveau: rewrite gpu object code Allows multiple references to a single object, needed to support PCI(E)GART scatter-gather DMA objects which would quickly fill PRAMIN if each channel had its own. Handle per-channel private instmem areas. This is needed to support NV50, but might be something we want to do on earlier chipsets at some point? Everything that touches PRAMIN is a GPU object.