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.

1 files changed, 75 insertions, 0 deletions

diff --git a/scripts/test_guest_driver.sh b/scripts/test_guest_driver.sh
new file mode 100755
index 0000000..f391d64
--- /dev/null
+++ b/scripts/test_guest_driver.sh
@@ -0,0 +1,75 @@
+#!/bin/bash
+# Guest Driver Validation Suite
+# Tests the guest NVIDIA driver with vGPU
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+OPEN_IOV_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+echo "=== Guest Driver Validation Suite ==="
+echo "Open-IOV root: $OPEN_IOV_ROOT"
+
+# Check if we're root
+if [ "$EUID" -ne 0 ]; then
+    echo "ERROR: This script must be run as root"
+    exit 1
+fi
+
+# Check if mdev exists
+MDEV_DEVICES=$(ls /sys/bus/mdev/devices/ 2>/dev/null | wc -l)
+if [ "$MDEV_DEVICES" -eq 0 ]; then
+    echo "ERROR: No mdev devices found. Run create_mdev.sh first."
+    exit 1
+fi
+
+echo "Found $MDEV_DEVICES mdev device(s)"
+
+# Launch QEMU with vGPU
+echo "Launching QEMU with vGPU..."
+"$SCRIPT_DIR/launch_qemu_vgpu.sh" &
+QEMU_PID=$!
+
+# Wait for QEMU to start
+sleep 10
+
+# Check if QEMU is running
+if ! kill -0 $QEMU_PID 2>/dev/null; then
+    echo "ERROR: QEMU failed to start"
+    exit 1
+fi
+
+echo "QEMU started with PID $QEMU_PID"
+echo "Guest should be booting..."
+
+# Wait for guest to boot and SSH to be available
+echo "Waiting for guest SSH (timeout 120s)..."
+for i in {1..24}; do
+    if ssh -o ConnectTimeout=5 -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null root@localhost -p 2222 "echo 'SSH ready'" 2>/dev/null; then
+        echo "Guest SSH is ready"
+        break
+    fi
+    sleep 5
+done
+
+# Run guest driver setup
+echo "Setting up guest NVIDIA driver..."
+ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null root@localhost -p 2222 \
+    "bash -s" < "$SCRIPT_DIR/setup_guest_driver.sh"
+
+# Test nvidia-smi
+echo "Testing nvidia-smi..."
+ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null root@localhost -p 2222 \
+    "nvidia-smi"
+
+# Test CUDA
+echo "Testing CUDA vectorAdd..."
+ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null root@localhost -p 2222 \
+    "cd /usr/local/cuda/samples/1_Utilities/vectorAdd && make && ./vectorAdd"
+
+# Cleanup
+echo "Shutting down QEMU..."
+kill $QEMU_PID 2>/dev/null || true
+wait $QEMU_PID 2>/dev/null || true
+
+echo "=== Guest Driver Validation Complete ==="
\ No newline at end of file