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, 68 insertions, 0 deletions

diff --git a/userspace/tests/test_host_init.c b/userspace/tests/test_host_init.c
new file mode 100644
index 0000000..a08fe33
--- /dev/null
+++ b/userspace/tests/test_host_init.c
@@ -0,0 +1,68 @@
+/*
+ * Test for host vGPU initialization
+ */
+#include <gvm/apis.h>
+#include <gvm/nvidia/manager.h>
+#include <gvm/nvidia/creator.h>
+#include <gvm/nvidia/open/signature.h>
+#include <utils/configs.h>
+
+#include <stdio.h>
+#include <stdlib.h>
+
+int main(int argc, char *argv[])
+{
+    int ret = 0;
+    enum SupportedGpus selected_gpu = Nvidia;
+    const struct ManagerAPI *api = MANAGER_APIS[selected_gpu];
+    struct NvManager *mgr = NULL;
+
+    printf("Testing host vGPU initialization...\n");
+
+    mgr = calloc(1, sizeof(struct NvManager));
+    if (!mgr) {
+        printf("Failed to allocate manager\n");
+        return 1;
+    }
+
+    mgr->ignore_version_check = 1;
+    mgr->create_signature = nvidia_open_create_signature;
+    mgr->use_vmiop = 1;
+    mgr->vmiop_plugin = "/usr/lib/x86_64-linux-gnu/libnvidia-vgpu.so";
+
+    if (api->init(mgr)) {
+        printf("FAIL: Manager initialization failed\n");
+        ret = 1;
+        goto cleanup;
+    }
+
+    printf("PASS: Manager initialized successfully\n");
+
+    if (!api->running(mgr)) {
+        printf("FAIL: Manager not running\n");
+        ret = 1;
+        goto cleanup;
+    }
+
+    printf("PASS: Manager is running\n");
+
+    if (mgr->vmiop) {
+        printf("PASS: VMIOP initialized\n");
+    } else {
+        printf("FAIL: VMIOP not initialized\n");
+        ret = 1;
+    }
+
+cleanup:
+    if (mgr) {
+        api->stop(mgr);
+        free(mgr);
+    }
+
+    if (ret == 0)
+        printf("\nAll host initialization tests PASSED\n");
+    else
+        printf("\nSome host initialization tests FAILED\n");
+
+    return ret;
+}
\ No newline at end of file