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, 42 insertions, 0 deletions

diff --git a/tools/module_ops/unload_all.sh b/tools/module_ops/unload_all.sh
new file mode 100755
index 0000000..4c73a0b
--- /dev/null
+++ b/tools/module_ops/unload_all.sh
@@ -0,0 +1,42 @@
+#!/bin/bash
+# Unload all vGPU modules cleanly
+# Usage: sudo ./unload_all.sh
+
+set -euo pipefail
+
+echo "=== Unloading Open-IOV vGPU Stack ==="
+
+# Unload in reverse order of loading
+modules=(
+    "nvidia-vgpu-vfio"
+    "nvidia-drm"
+    "nvidia-modeset"
+    "nvidia-uvm"
+    "nvidia-peermem"
+    "nvidia"
+    "mdev"
+)
+
+for module in "${modules[@]}"; do
+    if lsmod | grep -q "^$module "; then
+        echo "Unloading $module..."
+        if sudo rmmod "$module" 2>/dev/null; then
+            echo "  ✓ $module unloaded"
+        else
+            echo "  ⚠ $module could not be unloaded (may be in use)"
+            # Check refcnt
+            if [[ -f /sys/module/$module/refcnt ]]; then
+                echo "    refcnt: $(cat /sys/module/$module/refcnt)"
+            fi
+            if [[ -f /sys/module/$module/initstate ]]; then
+                echo "    initstate: $(cat /sys/module/$module/initstate)"
+            fi
+        fi
+    else
+        echo "  - $module not loaded"
+    fi
+done
+
+echo ""
+echo "=== Unload Complete ==="
+lsmod | grep -E 'nvidia|mdev' || echo "No NVIDIA/mdev modules loaded"
\ No newline at end of file