diff options
| author | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-24 01:38:07 -0400 |
|---|---|---|
| committer | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-24 01:38:07 -0400 |
| commit | f3225a81ca384248180d77f78c3614c73dcf289d (patch) | |
| tree | ca4735c63659bd201d8cf5a2b31858cf73bf92e7 /userspace/include/libvgpu.h | |
| parent | a61041edf3de9c63d3ac08aed2d613df45d0219b (diff) | |
| download | open-iov-f3225a81ca384248180d77f78c3614c73dcf289d.tar.gz open-iov-f3225a81ca384248180d77f78c3614c73dcf289d.zip | |
vgsp-gr r590b: the stream-order watermark must watch every ring, not engine_type!=0
The r591 draw reproduced the r568 signature (VADD bad=32735 csum=8139264,
c = a + 0) with ceback=0: the driver submits its relocation/H2D copies on
a COMPUTE channel (h=0x5c000059 registers eng=0), so the engine_type
filter skipped exactly the backlog the guard exists for.
Consider every other channel of the device (the launching channel is
excluded: its own ring legitimately runs ahead with future entries), and
read each one's live USERD GP_PUT against this pass's consumed position.
r590's validated part is unchanged: same pass snapshot, same bounded
defer, historical forward at the absolute cap (never a refusal).
Diffstat (limited to 'userspace/include/libvgpu.h')
0 files changed, 0 insertions, 0 deletions