diff options
| author | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-15 12:08:53 -0400 |
|---|---|---|
| committer | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-15 12:08:53 -0400 |
| commit | e07c62b1fab2f2dbc9981458c0697829b287b01e (patch) | |
| tree | a86e3317796b70844449eefd8f7adb7d98f63b3b /tools/cuda-ab/push_battery.sh | |
| parent | 02249afd91f4ee02589a07657d130b9b9411debd (diff) | |
| download | open-iov-e07c62b1fab2f2dbc9981458c0697829b287b01e.tar.gz open-iov-e07c62b1fab2f2dbc9981458c0697829b287b01e.zip | |
vgsp-sema: m154 drop injected pins that collide with a live channel ring
r153 root cause (3rd-client userspace spin for the rest of the boot): the
guest scanner's merged CE-window run (va=0x121000000 len=0x40000; the
merged length varies per session) covered a CE channel's GPFIFO ring VA
0x121010000. svc_ipin_store took precedence in the ring read path, so the
ring read the guest page at the wrong PA (0x102e02000): an all-zero entry
was silently consumed, the pool release was never authored
(pushes frozen at 1643, crel frozen), and victory_matmul spun in
userspace for 50+ min. The ring VA translation must come from the
channel's own discovery path; an injected pin inside any live channel's
ring range is always wrong - drop it (counted + logged, first 8 per
session). Validated on the next cycle: 'injected pin ... DROPPED' lines
plus 'entry[1] raw!=0', advancing pushes, MATMUL bad=0 STATUS OK.
Diffstat (limited to 'tools/cuda-ab/push_battery.sh')
0 files changed, 0 insertions, 0 deletions
