diff options
| author | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-06 23:50:00 -0400 |
|---|---|---|
| committer | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-06 23:50:00 -0400 |
| commit | e6e6dcddf9bc109885bcf4211c31aa82d67f5f2f (patch) | |
| tree | d91b1f5c5ee86b61d76d0eb7409dbbdea84156dd /userspace/cuda/docs/07-version-upgrade-playbook.md | |
| parent | fe163078694a9bf870e7aff1fe161a87fb63d137 (diff) | |
| download | open-iov-e6e6dcddf9bc109885bcf4211c31aa82d67f5f2f.tar.gz open-iov-e6e6dcddf9bc109885bcf4211c31aa82d67f5f2f.zip | |
vgsp: m69 - window-0 shadow pool for the QMD program/param pages
m68 proved the program page's shadow copy contains real SASS (SASS_version
0x75) and the prefetch pair is fixed, yet the engine still never completes
and never writes its release anywhere - including a window-0 module sem.
Best remaining suspect: the window-1 scratch VA range (PT chain installed by
DMA_UPDATE_PDE_2 pdeIndex=1) has never been proven readable by the GR engine
core, unlike the window-0 GPFIFO/PB/QMDWIN small-PT line. m69 plants 8
module pages at VAs 0x108000..0x10f000 (slots 0x108..0x10f, same 128 B PT
fetch line, planted before first fetch like qmdwin), copies the resolved
program/param page content into them at launch and rewrites the QMD pointer
pairs there (param=32, program=48). Param: gsp_phys_rmcall_gr_shadow_win0.
Diffstat (limited to 'userspace/cuda/docs/07-version-upgrade-playbook.md')
0 files changed, 0 insertions, 0 deletions