From 2302fc09080bad51c73f293294e19fd4db464eb0 Mon Sep 17 00:00:00 2001 From: Open-IOV Date: Wed, 23 Sep 2026 05:44:08 -0400 Subject: Open-IOV: initial public release Open-IOV virtualizes NVIDIA GPUs so that unmodified guest drivers run with real GPU functionality - CUDA first, 3D and video to follow - on unmodified hosts, without a proprietary vGPU license and without patching any driver, firmware or hypervisor. Core principle: emulate the interface, pass through the work. kernel/ open-iov-vfio.ko - host VFIO mdev driver: virtual GPU device (PCI config space, BAR shadows, MSI-X), GSP boot emulation, GSP-RM message-queue/RPC emulation, memory model (GPU-VA to guest-PA discovery) and the semaphore-completion service that advances guest UVM progress. userspace/ libiov.so management API and examples. tools/ guest diagnostics, firmware analysis wrappers, RM probes. scripts/ stack manager, VM harness, build/load/test automation. config/ hardware/version profiles (the portability surface). docs/ documentation tree - start at docs/README.md. wiki/ long-form firmware and protocol deep dives. Status: initialization works end to end for a stock 570.144 Linux guest on Turing (TU104): driver probe, nvidia-smi, the full GSP-RM control battery, object creation and the early CUDA/UVM start-up path. GPU work forwarding - the step that makes CUDA kernels execute on real hardware - is the active work item; see docs/04-implementation/01-known-knowns-and-unknowns.md. License: BSD-3-Clause for the project; GPL-2.0 for kernel modules that link GPL-only kernel interfaces. See LICENSE and docs/09-reference/legal-and-licensing.md. --- tools/guest-diag/vmcycle.sh | 46 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) create mode 100755 tools/guest-diag/vmcycle.sh (limited to 'tools/guest-diag/vmcycle.sh') diff --git a/tools/guest-diag/vmcycle.sh b/tools/guest-diag/vmcycle.sh new file mode 100755 index 0000000..6faaa75 --- /dev/null +++ b/tools/guest-diag/vmcycle.sh @@ -0,0 +1,46 @@ +#!/bin/bash +# vmcycle.sh - reload cycle for the emulated vGPU stack: +# stop QEMU -> remove mdevs -> rmmod/insmod open-iov-vfio.ko -> create a +# fresh mdev -> patch its UUID into the runtime launch script -> relaunch. +# +# ALL artifacts stay inside this directory (tools/guest-diag/) so nothing is +# lost on reboot: +# launch_qemu_rootport.sh - template QEMU command line (root-port fix) +# launch_qemu_rootport.run.sh - runtime copy with the current mdev UUID +# run/qemu.log - QEMU stderr/stdout of the last launch +# +# Usage: tools/guest-diag/vmcycle.sh +# Env: MDEV_PARENT (default: 0000:01:00.0) +# MDEV_TYPE (default: nvidia-nvidia-vgpu-turing) +set -e + +HERE="$(cd "$(dirname "$0")" && pwd)" +TEMPLATE="$HERE/launch_qemu_rootport.sh" +QEMU_SCRIPT="${QEMU_SCRIPT:-$HERE/launch_qemu_rootport.run.sh}" +MODULE="${MODULE:-$HERE/../../kernel/open-iov-vfio.ko}" +MDEV_PARENT="${MDEV_PARENT:-0000:01:00.0}" +MDEV_TYPE="${MDEV_TYPE:-nvidia-nvidia-vgpu-turing}" +RUNDIR="$HERE/run" + +mkdir -p "$RUNDIR" +[ -f "$QEMU_SCRIPT" ] || cp "$TEMPLATE" "$QEMU_SCRIPT" + +pkill -f qemu-system-x86_64 2>/dev/null || true +sleep 4 +for m in /sys/bus/mdev/devices/*; do + [ -d "$m" ] && echo 1 | sudo tee "$m/remove" >/dev/null +done +sudo rmmod open_iov_vfio 2>/dev/null || true +sudo insmod "$MODULE" +U=$(uuidgen) +echo "$U" | sudo tee "/sys/class/mdev_bus/$MDEV_PARENT/mdev_supported_types/$MDEV_TYPE/create" >/dev/null +sed -i "s|/sys/bus/mdev/devices/[0-9a-f-]*|/sys/bus/mdev/devices/$U|" "$QEMU_SCRIPT" +mkdir -p /tmp/sockets/e726ba0b-204f-4ec9-91da-983ed7f41d06 +rm -f /tmp/qemu-guest-agent.sock /tmp/qemu-qmp.sock +(setsid nohup "$QEMU_SCRIPT" > "$RUNDIR/qemu.log" 2>&1 &) +sleep 6 +if pgrep -f qemu-system-x86_64 >/dev/null; then + echo "VM up (mdev $U) [qemu log: $RUNDIR/qemu.log]" +else + echo "VM FAILED"; tail -3 "$RUNDIR/qemu.log"; exit 1 +fi -- cgit v1.2.3