Open-IOV vGPU-IO: host-side GSP emulation for unmodified NVIDIA guest drivers https://git.vgpu.io/open-iov.git/atom?h=master 2026-10-08T15:49:48+00:00 2026-10-08T15:49:48+00:00 Arthur Hanson Rasmusson arthur@vgpu.io 2026-10-08T15:49:48+00:00 urn:sha1:25d23d32f53a1beb8d2302d6f589cef04d105c48 2026-10-08T08:15:24+00:00 Arthur Hanson Rasmusson arthur@vgpu.io 2026-10-08T08:15:24+00:00 urn:sha1:5bb2d53ec14f0d802726bc879b994c0286f85415 guest_pin_stream.py now resolves translations entirely from guest truth via /proc/kcore + a manual page-table walk (no QMP races): the CE semaphore pool and pushbuffer memory from the UVM rm_mem structures, and each channel's GPFIFO ring + GPPUT from the tracking semaphore's embedding uvm_channel_t (channel_info located by its gpFifoGpuVa value). This removes the watcher pipeline's flakiness on the cudaMalloc stall class (missing pool/pushbuffer pins). gsp_sema_service.c: svc_gr_ring_autopin tries the guest-registered USERD memdesc base as a ring candidate (the fixed FB convention only matches when the guest's VRAM allocator happens to reproduce the old layout), plus an optional (gsp_sema_dbg) one-shot FB scan + raw-word diagnostics when every candidate fails. tools/cuda-ab/p2: self-checking arbitrary-kernel acceptance suite (10 programs: sequential launches, shapes, params, smem/GEMM, streams, malloc churn, printf+error, FMA benchmark, mixed, managed probe) with host oracle expectations and a guest runner.