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, 73 insertions, 0 deletions

diff --git a/tools/guest-diag/sysc_shim.c b/tools/guest-diag/sysc_shim.c
new file mode 100644
index 0000000..9b07e4c
--- /dev/null
+++ b/tools/guest-diag/sysc_shim.c
@@ -0,0 +1,73 @@
+/* sysc_shim.c - intercept syscall() so we can dump ioctl buffer *results*
+ * for UVM ioctls (libcuda calls syscall(SYS_ioctl, ...) directly, so an
+ * ioctl() wrapper is bypassed but syscall() is not).
+ * Build in guest: gcc -shared -fPIC -O1 -o /tmp/sysc.so sysc_shim.c -ldl
+ * Run: LD_PRELOAD=/tmp/sysc.so /tmp/cdt
+ */
+#define _GNU_SOURCE
+#include <dlfcn.h>
+#include <stdarg.h>
+#include <stddef.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+static long (*real_syscall)(long, ...);
+
+static void dump(const char *tag, unsigned long req, void *arg, long ret)
+{
+	unsigned int *p = (unsigned int *)arg;
+	char buf[512];
+	int n, i;
+	long *vp = (long *)arg;
+
+	if (!p)
+		return;
+	n = 0;
+	n += __builtin_snprintf(buf + n, sizeof(buf) - n,
+				"SYSC[%s] req=0x%lx ret=%ld dwords: ", tag, req,
+				ret);
+	for (i = 0; i < 16 && n < (int)sizeof(buf) - 16; i++)
+		n += __builtin_snprintf(buf + n, sizeof(buf) - n, "%08x ",
+					p[i]);
+	(void)vp;
+	write(2, buf, n);
+	write(2, "\n", 1);
+}
+
+long syscall(long nr, ...)
+{
+	va_list ap;
+	long a1, a2, a3, a4, a5, a6;
+	long ret;
+
+	if (!real_syscall)
+		real_syscall = dlsym(RTLD_NEXT, "syscall");
+
+	va_start(ap, nr);
+	a1 = va_arg(ap, long);
+	a2 = va_arg(ap, long);
+	a3 = va_arg(ap, long);
+	a4 = va_arg(ap, long);
+	a5 = va_arg(ap, long);
+	a6 = va_arg(ap, long);
+	va_end(ap);
+
+	ret = real_syscall(nr, a1, a2, a3, a4, a5, a6);
+
+	if (nr == SYS_ioctl) {
+		unsigned long req = (unsigned long)a2;
+		switch (req) {
+		case 0x1:  /* UVM_RESERVE_VA */
+		case 0x2:  /* UVM_RELEASE_VA */
+		case 0x25: /* UVM_REGISTER_GPU */
+		case 0x27: /* UVM_PAGEABLE_MEM_ACCESS */
+		case 0x17: /* UVM_EVENT_CTRL */
+		case 0x19: /* UVM_REGISTER_MPS_CLIENT */
+			dump("uvmioctl", req, (void *)a3, ret);
+			break;
+		default:
+			break;
+		}
+	}
+	return ret;
+}