From 68cdd7728a7cc6715bbbff7decfe2b11c3bdf558 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. --- kernel/Makefile | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) create mode 100644 kernel/Makefile (limited to 'kernel/Makefile') diff --git a/kernel/Makefile b/kernel/Makefile new file mode 100644 index 0000000..8562430 --- /dev/null +++ b/kernel/Makefile @@ -0,0 +1,43 @@ +obj-m += open-iov-vfio.o + +open-iov-vfio-y := \ + main.o \ + bar_init.o \ + bar_emulation.o \ + gsp_comm.o \ + gsp_emulation.o \ + gsp_rm_emulation.o \ + gsp_sema_service.o \ + gsp_rpc_client.o \ + gsp_rpc_integration.o \ + memory.o \ + irq.o \ + migration.o \ + ioctl.o \ + firmware_analyzer.o \ + dynamic_rpc_dispatcher.o \ + architecture/architecture.o \ + version/version.o + +ccflags-y := -I$(src)/include -I$(src)/architecture -I$(src)/version -Wall -Wextra -Wno-error -Wno-unused-parameter -Wno-unused-function + +# mdev dependencies +KBUILD_MODPOST_WARN := 1 + +# Use symbols from host nvidia.ko (path resolved relative to this repo) +KBUILD_EXTRA_SYMBOLS := $(abspath $(src)/../nvidia-open-gpu-kernel-modules/kernel-open/Module.symvers) + +# Use $(CURDIR), NOT $(PWD): when invoked via the top-level Makefile +# (make -C kernel), $(PWD) still points at the caller's directory and kbuild +# silently builds nothing (the "stale .ko" trap). +all: + $(MAKE) -C /lib/modules/$(shell uname -r)/build M=$(CURDIR) modules + +clean: + $(MAKE) -C /lib/modules/$(shell uname -r)/build M=$(CURDIR) clean + +install: + $(MAKE) -C /lib/modules/$(shell uname -r)/build M=$(CURDIR) modules_install + depmod -a + +.PHONY: all clean install \ No newline at end of file -- cgit v1.2.3