From 1306a73b1958ab54a501fa23146ef85fa68d2d5d Mon Sep 17 00:00:00 2001 From: Elena Agostini Date: Tue, 16 Nov 2021 22:50:18 +0000 Subject: [PATCH] gpu/cuda: introduce CUDA driver This is the CUDA implementation of the gpudev library. Functionalities implemented through CUDA Driver API are: - Device probe and remove - Manage device memory allocations - Register/unregister external CPU memory in the device memory area Signed-off-by: Elena Agostini --- MAINTAINERS | 9 + doc/guides/gpus/cuda.rst | 152 ++++ doc/guides/gpus/index.rst | 1 + doc/guides/rel_notes/release_21_11.rst | 2 + drivers/gpu/cuda/cuda.c | 1162 ++++++++++++++++++++++++ drivers/gpu/cuda/meson.build | 21 + drivers/gpu/cuda/version.map | 3 + drivers/gpu/meson.build | 2 +- 8 files changed, 1351 insertions(+), 1 deletion(-) create mode 100644 doc/guides/gpus/cuda.rst create mode 100644 drivers/gpu/cuda/cuda.c create mode 100644 drivers/gpu/cuda/meson.build create mode 100644 drivers/gpu/cuda/version.map diff --git a/MAINTAINERS b/MAINTAINERS index 2a3c68e818..387aa25511 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1344,6 +1344,15 @@ F: drivers/baseband/la12xx/ F: doc/guides/bbdevs/la12xx.rst +GPU Drivers +----------- + +NVIDIA CUDA +M: Elena Agostini +F: drivers/gpu/cuda/ +F: doc/guides/gpus/cuda.rst + + Rawdev Drivers -------------- diff --git a/doc/guides/gpus/cuda.rst b/doc/guides/gpus/cuda.rst new file mode 100644 index 0000000000..38e22dc2c0 --- /dev/null +++ b/doc/guides/gpus/cuda.rst @@ -0,0 +1,152 @@ +.. SPDX-License-Identifier: BSD-3-Clause + Copyright (c) 2021 NVIDIA Corporation & Affiliates + +CUDA GPU driver +=============== + +The CUDA GPU driver library (**librte_gpu_cuda**) provides support for NVIDIA GPUs. +Information and documentation about these devices can be found on the +`NVIDIA website `_. Help is also provided by the +`NVIDIA CUDA Toolkit developer zone `_. + +Build dependencies +------------------ + +The CUDA GPU driver library has an header-only dependency on ``cuda.h`` and ``cudaTypedefs.h``. +To get these headers there are two options: + +- Install `CUDA Toolkit `_ + (either regular or stubs installation). +- Download these two headers from this `CUDA headers + `_ repository. + +You need to indicate to meson where CUDA headers files are through the CFLAGS variable. +Three ways: + +- Set ``export CFLAGS=-I/usr/local/cuda/include`` before building +- Add CFLAGS in the meson command line ``CFLAGS=-I/usr/local/cuda/include meson build`` +- Add the ``-Dc_args`` in meson command line ``meson build -Dc_args=-I/usr/local/cuda/include`` + +If headers are not found, the CUDA GPU driver library is not built. + +CUDA Shared Library +------------------- + +To avoid any system configuration issue, the CUDA API **libcuda.so** shared library +is not linked at building time because of a Meson bug that looks +for `cudart` module even if the `meson.build` file only requires default `cuda` module. + +**libcuda.so** is loaded at runtime in the ``cuda_gpu_probe`` function through ``dlopen`` +when the very first GPU is detected. +If CUDA installation resides in a custom directory, +the environment variable ``CUDA_PATH_L`` should specify where ``dlopen`` +can look for **libcuda.so**. + +All CUDA API symbols are loaded at runtime as well. +For this reason, to build the CUDA driver library, +no need to install the CUDA library. + +Design +------ + +**librte_gpu_cuda** relies on CUDA Driver API (no need for CUDA Runtime API). + +Goal of this driver library is not to provide a wrapper for the whole CUDA Driver API. +Instead, the scope is to implement the generic features of gpudev API. +For a CUDA application, integrating the gpudev library functions +using the CUDA driver library is quite straightforward +and doesn't create any compatibility problem. + +Initialization +~~~~~~~~~~~~~~ + +During initialization, CUDA driver library detects NVIDIA physical GPUs +on the system or specified via EAL device options (e.g. ``-a b6:00.0``). +The driver initializes the CUDA driver environment through ``cuInit(0)`` function. +For this reason, it's required to set any CUDA environment configuration before +calling ``rte_eal_init`` function in the DPDK application. + +If the CUDA driver environment has been already initialized, the ``cuInit(0)`` +in CUDA driver library has no effect. + +CUDA Driver sub-contexts +~~~~~~~~~~~~~~~~~~~~~~~~ + +After initialization, a CUDA application can create multiple sub-contexts +on GPU physical devices. +Through gpudev library, is possible to register these sub-contexts +in the CUDA driver library as child devices having as parent a GPU physical device. + +CUDA driver library also supports `MPS +`__. + +GPU memory management +~~~~~~~~~~~~~~~~~~~~~ + +The CUDA driver library maintains a table of GPU memory addresses allocated +and CPU memory addresses registered associated to the input CUDA context. +Whenever the application tried to deallocate or deregister a memory address, +if the address is not in the table the CUDA driver library will return an error. + +Features +-------- + +- Register new child devices aka new CUDA Driver contexts. +- Allocate memory on the GPU. +- Register CPU memory to make it visible from GPU. + +Minimal requirements +-------------------- + +Minimal requirements to enable the CUDA driver library are: + +- NVIDIA GPU Ampere or Volta +- CUDA 11.4 Driver API or newer + +`GPUDirect RDMA Technology `_ +allows compatible network cards (e.g. Mellanox) to directly send and receive packets +using GPU memory instead of additional memory copies through the CPU system memory. +To enable this technology, system requirements are: + +- `nvidia-peermem `_ + module running on the system; +- Mellanox network card ConnectX-5 or newer (BlueField models included); +- DPDK mlx5 PMD enabled; +- To reach the best performance, an additional PCIe switch between GPU and NIC is recommended. + +Limitations +----------- + +Supported only on Linux. + +Supported GPUs +-------------- + +The following NVIDIA GPU devices are supported by this CUDA driver library: + +- NVIDIA A100 80GB PCIe +- NVIDIA A100 40GB PCIe +- NVIDIA A30 24GB +- NVIDIA A10 24GB +- NVIDIA V100 32GB PCIe +- NVIDIA V100 16GB PCIe + +External references +------------------- + +A good example of how to use the GPU CUDA driver library through the gpudev library +is the l2fwd-nv application that can be found `here `_. + +The application is based on vanilla DPDK example l2fwd +and is enhanced with GPU memory managed through gpudev library +and CUDA to launch the swap of packets MAC addresses workload on the GPU. + +l2fwd-nv is not intended to be used for performance +(testpmd is the good candidate for this). +The goal is to show different use-cases about how a CUDA application can use DPDK to: + +- Allocate memory on GPU device using gpudev library. +- Use that memory to create an external GPU memory mempool. +- Receive packets directly in GPU memory. +- Coordinate the workload on the GPU with the network and CPU activity to receive packets. +- Send modified packets directly from the GPU memory. diff --git a/doc/guides/gpus/index.rst b/doc/guides/gpus/index.rst index 1878423239..4b7a420556 100644 --- a/doc/guides/gpus/index.rst +++ b/doc/guides/gpus/index.rst @@ -9,3 +9,4 @@ General-Purpose Graphics Processing Unit Drivers :numbered: overview + cuda diff --git a/doc/guides/rel_notes/release_21_11.rst b/doc/guides/rel_notes/release_21_11.rst index 677353f2d2..850ea5605e 100644 --- a/doc/guides/rel_notes/release_21_11.rst +++ b/doc/guides/rel_notes/release_21_11.rst @@ -111,6 +111,8 @@ New Features * Memory management * Communication flag & list +* **Added NVIDIA GPU driver implemented with CUDA library.** + * **Added new RSS offload types for IPv4/L4 checksum in RSS flow.** Added macros ETH_RSS_IPV4_CHKSUM and ETH_RSS_L4_CHKSUM, now IPv4 and diff --git a/drivers/gpu/cuda/cuda.c b/drivers/gpu/cuda/cuda.c new file mode 100644 index 0000000000..24ae630d04 --- /dev/null +++ b/drivers/gpu/cuda/cuda.c @@ -0,0 +1,1162 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright (c) 2021 NVIDIA Corporation & Affiliates + */ + +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +#define CUDA_DRIVER_MIN_VERSION 11040 +#define CUDA_API_MIN_VERSION 3020 + +/* CUDA Driver functions loaded with dlsym() */ +static CUresult CUDAAPI (*sym_cuInit)(unsigned int flags); +static CUresult CUDAAPI (*sym_cuDriverGetVersion)(int *driverVersion); +static CUresult CUDAAPI (*sym_cuGetProcAddress)(const char *symbol, + void **pfn, int cudaVersion, uint64_t flags); + +/* CUDA Driver functions loaded with cuGetProcAddress for versioning */ +static PFN_cuGetErrorString pfn_cuGetErrorString; +static PFN_cuGetErrorName pfn_cuGetErrorName; +static PFN_cuPointerSetAttribute pfn_cuPointerSetAttribute; +static PFN_cuDeviceGetAttribute pfn_cuDeviceGetAttribute; +static PFN_cuDeviceGetByPCIBusId pfn_cuDeviceGetByPCIBusId; +static PFN_cuDevicePrimaryCtxRetain pfn_cuDevicePrimaryCtxRetain; +static PFN_cuDevicePrimaryCtxRelease pfn_cuDevicePrimaryCtxRelease; +static PFN_cuDeviceTotalMem pfn_cuDeviceTotalMem; +static PFN_cuDeviceGetName pfn_cuDeviceGetName; +static PFN_cuCtxGetApiVersion pfn_cuCtxGetApiVersion; +static PFN_cuCtxSetCurrent pfn_cuCtxSetCurrent; +static PFN_cuCtxGetCurrent pfn_cuCtxGetCurrent; +static PFN_cuCtxGetDevice pfn_cuCtxGetDevice; +static PFN_cuCtxGetExecAffinity pfn_cuCtxGetExecAffinity; +static PFN_cuMemAlloc pfn_cuMemAlloc; +static PFN_cuMemFree pfn_cuMemFree; +static PFN_cuMemHostRegister pfn_cuMemHostRegister; +static PFN_cuMemHostUnregister pfn_cuMemHostUnregister; +static PFN_cuMemHostGetDevicePointer pfn_cuMemHostGetDevicePointer; +static PFN_cuFlushGPUDirectRDMAWrites pfn_cuFlushGPUDirectRDMAWrites; + +static void *cudalib; +static unsigned int cuda_api_version; +static int cuda_driver_version; + +/* NVIDIA GPU vendor */ +#define NVIDIA_GPU_VENDOR_ID (0x10de) + +/* NVIDIA GPU device IDs */ +#define NVIDIA_GPU_A100_40GB_DEVICE_ID (0x20f1) +#define NVIDIA_GPU_A100_80GB_DEVICE_ID (0x20b5) + +#define NVIDIA_GPU_A30_24GB_DEVICE_ID (0x20b7) +#define NVIDIA_GPU_A10_24GB_DEVICE_ID (0x2236) + +#define NVIDIA_GPU_V100_32GB_DEVICE_ID (0x1db6) +#define NVIDIA_GPU_V100_16GB_DEVICE_ID (0x1db4) + +#define NVIDIA_GPU_T4_16GB_DEVICE_ID (0x1eb8) + +#define CUDA_MAX_ALLOCATION_NUM 512 + +#define GPU_PAGE_SHIFT 16 +#define GPU_PAGE_SIZE (1UL << GPU_PAGE_SHIFT) + +static RTE_LOG_REGISTER_DEFAULT(cuda_logtype, NOTICE); + +/* Helper macro for logging */ +#define rte_cuda_log(level, fmt, ...) \ + rte_log(RTE_LOG_ ## level, cuda_logtype, fmt "\n", ##__VA_ARGS__) + +#define rte_cuda_debug(fmt, ...) \ + rte_cuda_log(DEBUG, RTE_STR(__LINE__) ":%s() " fmt, __func__, \ + ##__VA_ARGS__) + +/* NVIDIA GPU address map */ +static const struct rte_pci_id pci_id_cuda_map[] = { + { + RTE_PCI_DEVICE(NVIDIA_GPU_VENDOR_ID, + NVIDIA_GPU_A100_40GB_DEVICE_ID) + }, + { + RTE_PCI_DEVICE(NVIDIA_GPU_VENDOR_ID, + NVIDIA_GPU_A100_80GB_DEVICE_ID) + }, + { + RTE_PCI_DEVICE(NVIDIA_GPU_VENDOR_ID, + NVIDIA_GPU_A30_24GB_DEVICE_ID) + }, + { + RTE_PCI_DEVICE(NVIDIA_GPU_VENDOR_ID, + NVIDIA_GPU_A10_24GB_DEVICE_ID) + }, + { + RTE_PCI_DEVICE(NVIDIA_GPU_VENDOR_ID, + NVIDIA_GPU_V100_32GB_DEVICE_ID) + }, + { + RTE_PCI_DEVICE(NVIDIA_GPU_VENDOR_ID, + NVIDIA_GPU_V100_16GB_DEVICE_ID) + }, + { + RTE_PCI_DEVICE(NVIDIA_GPU_VENDOR_ID, + NVIDIA_GPU_T4_16GB_DEVICE_ID) + }, + { + .device_id = 0 + } +}; + +/* Device private info */ +struct cuda_info { + char gpu_name[RTE_DEV_NAME_MAX_LEN]; + CUdevice cu_dev; + int gdr_supported; + int gdr_write_ordering; + int gdr_flush_type; +}; + +/* Type of memory allocated by CUDA driver */ +enum mem_type { + GPU_MEM = 0, + CPU_REGISTERED, + GPU_REGISTERED /* Not used yet */ +}; + +/* key associated to a memory address */ +typedef uintptr_t cuda_ptr_key; + +/* Single entry of the memory list */ +struct mem_entry { + CUdeviceptr ptr_d; + void *ptr_h; + size_t size; + struct rte_gpu *dev; + CUcontext ctx; + cuda_ptr_key pkey; + enum mem_type mtype; + struct mem_entry *prev; + struct mem_entry *next; +}; + +static struct mem_entry *mem_alloc_list_head; +static struct mem_entry *mem_alloc_list_tail; +static uint32_t mem_alloc_list_last_elem; + +/* Load the CUDA symbols */ + +static int +cuda_loader(void) +{ + char cuda_path[1024]; + + if (getenv("CUDA_PATH_L") == NULL) + snprintf(cuda_path, 1024, "%s", "libcuda.so"); + else + snprintf(cuda_path, 1024, "%s%s", getenv("CUDA_PATH_L"), "libcuda.so"); + + cudalib = dlopen(cuda_path, RTLD_LAZY); + if (cudalib == NULL) { + rte_cuda_log(ERR, "Failed to find CUDA library in %s (CUDA_PATH_L=%s)", + cuda_path, getenv("CUDA_PATH_L")); + return -1; + } + + return 0; +} + +static int +cuda_sym_func_loader(void) +{ + if (cudalib == NULL) + return -1; + + sym_cuInit = dlsym(cudalib, "cuInit"); + if (sym_cuInit == NULL) { + rte_cuda_log(ERR, "Failed to load CUDA missing symbol cuInit"); + return -1; + } + + sym_cuDriverGetVersion = dlsym(cudalib, "cuDriverGetVersion"); + if (sym_cuDriverGetVersion == NULL) { + rte_cuda_log(ERR, "Failed to load CUDA missing symbol cuDriverGetVersion"); + return -1; + } + + sym_cuGetProcAddress = dlsym(cudalib, "cuGetProcAddress"); + if (sym_cuGetProcAddress == NULL) { + rte_cuda_log(ERR, "Failed to load CUDA missing symbol cuGetProcAddress"); + return -1; + } + + return 0; +} + +static int +cuda_pfn_func_loader(void) +{ + CUresult res; + + res = sym_cuGetProcAddress("cuGetErrorString", + (void **) (&pfn_cuGetErrorString), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuGetErrorString failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuGetErrorName", + (void **)(&pfn_cuGetErrorName), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuGetErrorName failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuPointerSetAttribute", + (void **)(&pfn_cuPointerSetAttribute), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuPointerSetAttribute failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuDeviceGetAttribute", + (void **)(&pfn_cuDeviceGetAttribute), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuDeviceGetAttribute failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuDeviceGetByPCIBusId", + (void **)(&pfn_cuDeviceGetByPCIBusId), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuDeviceGetByPCIBusId failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuDeviceGetName", + (void **)(&pfn_cuDeviceGetName), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuDeviceGetName failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuDevicePrimaryCtxRetain", + (void **)(&pfn_cuDevicePrimaryCtxRetain), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuDevicePrimaryCtxRetain failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuDevicePrimaryCtxRelease", + (void **)(&pfn_cuDevicePrimaryCtxRelease), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuDevicePrimaryCtxRelease failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuDeviceTotalMem", + (void **)(&pfn_cuDeviceTotalMem), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuDeviceTotalMem failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuCtxGetApiVersion", + (void **)(&pfn_cuCtxGetApiVersion), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuCtxGetApiVersion failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuCtxGetDevice", + (void **)(&pfn_cuCtxGetDevice), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuCtxGetDevice failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuCtxSetCurrent", + (void **)(&pfn_cuCtxSetCurrent), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuCtxSetCurrent failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuCtxGetCurrent", + (void **)(&pfn_cuCtxGetCurrent), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuCtxGetCurrent failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuCtxGetExecAffinity", + (void **)(&pfn_cuCtxGetExecAffinity), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuCtxGetExecAffinity failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuMemAlloc", + (void **)(&pfn_cuMemAlloc), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuMemAlloc failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuMemFree", + (void **)(&pfn_cuMemFree), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuMemFree failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuMemHostRegister", + (void **)(&pfn_cuMemHostRegister), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuMemHostRegister failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuMemHostUnregister", + (void **)(&pfn_cuMemHostUnregister), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuMemHostUnregister failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuMemHostGetDevicePointer", + (void **)(&pfn_cuMemHostGetDevicePointer), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve pfn_cuMemHostGetDevicePointer failed with %d", res); + return -1; + } + + res = sym_cuGetProcAddress("cuFlushGPUDirectRDMAWrites", + (void **)(&pfn_cuFlushGPUDirectRDMAWrites), cuda_driver_version, 0); + if (res != 0) { + rte_cuda_log(ERR, "Retrieve cuFlushGPUDirectRDMAWrites failed with %d", res); + return -1; + } + + return 0; +} + +/* Generate a key from a memory pointer */ +static cuda_ptr_key +get_hash_from_ptr(void *ptr) +{ + return (uintptr_t)ptr; +} + +static uint32_t +mem_list_count_item(void) +{ + return mem_alloc_list_last_elem; +} + +/* Initiate list of memory allocations if not done yet */ +static struct mem_entry * +mem_list_add_item(void) +{ + /* Initiate list of memory allocations if not done yet */ + if (mem_alloc_list_head == NULL) { + mem_alloc_list_head = rte_zmalloc(NULL, + sizeof(struct mem_entry), + RTE_CACHE_LINE_SIZE); + if (mem_alloc_list_head == NULL) { + rte_cuda_log(ERR, "Failed to allocate memory for memory list"); + return NULL; + } + + mem_alloc_list_head->next = NULL; + mem_alloc_list_head->prev = NULL; + mem_alloc_list_tail = mem_alloc_list_head; + } else { + struct mem_entry *mem_alloc_list_cur = rte_zmalloc(NULL, + sizeof(struct mem_entry), + RTE_CACHE_LINE_SIZE); + + if (mem_alloc_list_cur == NULL) { + rte_cuda_log(ERR, "Failed to allocate memory for memory list"); + return NULL; + } + + mem_alloc_list_tail->next = mem_alloc_list_cur; + mem_alloc_list_cur->prev = mem_alloc_list_tail; + mem_alloc_list_tail = mem_alloc_list_tail->next; + mem_alloc_list_tail->next = NULL; + } + + mem_alloc_list_last_elem++; + + return mem_alloc_list_tail; +} + +static struct mem_entry * +mem_list_find_item(cuda_ptr_key pk) +{ + struct mem_entry *mem_alloc_list_cur = NULL; + + if (mem_alloc_list_head == NULL) { + rte_cuda_log(ERR, "Memory list doesn't exist"); + return NULL; + } + + if (mem_list_count_item() == 0) { + rte_cuda_log(ERR, "No items in memory list"); + return NULL; + } + + mem_alloc_list_cur = mem_alloc_list_head; + + while (mem_alloc_list_cur != NULL) { + if (mem_alloc_list_cur->pkey == pk) + return mem_alloc_list_cur; + mem_alloc_list_cur = mem_alloc_list_cur->next; + } + + return mem_alloc_list_cur; +} + +static int +mem_list_del_item(cuda_ptr_key pk) +{ + struct mem_entry *mem_alloc_list_cur = NULL; + + mem_alloc_list_cur = mem_list_find_item(pk); + if (mem_alloc_list_cur == NULL) + return -EINVAL; + + /* if key is in head */ + if (mem_alloc_list_cur->prev == NULL) + mem_alloc_list_head = mem_alloc_list_cur->next; + else { + mem_alloc_list_cur->prev->next = mem_alloc_list_cur->next; + if (mem_alloc_list_cur->next != NULL) + mem_alloc_list_cur->next->prev = mem_alloc_list_cur->prev; + } + + rte_free(mem_alloc_list_cur); + + mem_alloc_list_last_elem--; + + return 0; +} + +static int +cuda_dev_info_get(struct rte_gpu *dev, struct rte_gpu_info *info) +{ + int ret = 0; + CUresult res; + struct rte_gpu_info parent_info; + CUexecAffinityParam affinityPrm; + const char *err_string; + struct cuda_info *private; + CUcontext current_ctx; + CUcontext input_ctx; + + if (dev == NULL) + return -ENODEV; + + /* Child initialization time probably called by rte_gpu_add_child() */ + if (dev->mpshared->info.parent != RTE_GPU_ID_NONE && + dev->mpshared->dev_private == NULL) { + /* Store current ctx */ + res = pfn_cuCtxGetCurrent(¤t_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxGetCurrent failed with %s", + err_string); + return -EPERM; + } + + /* Set child ctx as current ctx */ + input_ctx = (CUcontext)((uintptr_t)dev->mpshared->info.context); + res = pfn_cuCtxSetCurrent(input_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent input failed with %s", + err_string); + return -EPERM; + } + + /* + * Ctx capacity info + */ + + /* MPS compatible */ + res = pfn_cuCtxGetExecAffinity(&affinityPrm, + CU_EXEC_AFFINITY_TYPE_SM_COUNT); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxGetExecAffinity failed with %s", + err_string); + } + dev->mpshared->info.processor_count = + (uint32_t)affinityPrm.param.smCount.val; + + ret = rte_gpu_info_get(dev->mpshared->info.parent, &parent_info); + if (ret) + return -ENODEV; + dev->mpshared->info.total_memory = parent_info.total_memory; + + /* + * GPU Device private info + */ + dev->mpshared->dev_private = rte_zmalloc(NULL, + sizeof(struct cuda_info), + RTE_CACHE_LINE_SIZE); + if (dev->mpshared->dev_private == NULL) { + rte_cuda_log(ERR, "Failed to allocate memory for GPU process private"); + return -EPERM; + } + + private = (struct cuda_info *)dev->mpshared->dev_private; + + res = pfn_cuCtxGetDevice(&(private->cu_dev)); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxGetDevice failed with %s", + err_string); + return -EPERM; + } + + res = pfn_cuDeviceGetName(private->gpu_name, + RTE_DEV_NAME_MAX_LEN, private->cu_dev); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceGetName failed with %s", + err_string); + return -EPERM; + } + + /* Restore original ctx as current ctx */ + res = pfn_cuCtxSetCurrent(current_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent current failed with %s", + err_string); + return -EPERM; + } + } + + *info = dev->mpshared->info; + + return 0; +} + +/* + * GPU Memory + */ + +static int +cuda_mem_alloc(struct rte_gpu *dev, size_t size, void **ptr) +{ + CUresult res; + const char *err_string; + CUcontext current_ctx; + CUcontext input_ctx; + unsigned int flag = 1; + + if (dev == NULL) + return -ENODEV; + if (size == 0) + return -EINVAL; + + /* Store current ctx */ + res = pfn_cuCtxGetCurrent(¤t_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxGetCurrent failed with %s", + err_string); + return -EPERM; + } + + /* Set child ctx as current ctx */ + input_ctx = (CUcontext)((uintptr_t)dev->mpshared->info.context); + res = pfn_cuCtxSetCurrent(input_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent input failed with %s", + err_string); + return -EPERM; + } + + /* Get next memory list item */ + mem_alloc_list_tail = mem_list_add_item(); + if (mem_alloc_list_tail == NULL) + return -ENOMEM; + + /* Allocate memory */ + mem_alloc_list_tail->size = size; + res = pfn_cuMemAlloc(&(mem_alloc_list_tail->ptr_d), + mem_alloc_list_tail->size); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent current failed with %s", + err_string); + return -EPERM; + } + + /* GPUDirect RDMA attribute required */ + res = pfn_cuPointerSetAttribute(&flag, + CU_POINTER_ATTRIBUTE_SYNC_MEMOPS, + mem_alloc_list_tail->ptr_d); + if (res != 0) { + rte_cuda_log(ERR, "Could not set SYNC MEMOP attribute for " + "GPU memory at %"PRIu32", err %d", + (uint32_t)mem_alloc_list_tail->ptr_d, res); + return -EPERM; + } + + mem_alloc_list_tail->pkey = get_hash_from_ptr((void *)mem_alloc_list_tail->ptr_d); + mem_alloc_list_tail->ptr_h = NULL; + mem_alloc_list_tail->size = size; + mem_alloc_list_tail->dev = dev; + mem_alloc_list_tail->ctx = (CUcontext)((uintptr_t)dev->mpshared->info.context); + mem_alloc_list_tail->mtype = GPU_MEM; + + /* Restore original ctx as current ctx */ + res = pfn_cuCtxSetCurrent(current_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent current failed with %s", + err_string); + return -EPERM; + } + + *ptr = (void *)mem_alloc_list_tail->ptr_d; + + return 0; +} + +static int +cuda_mem_register(struct rte_gpu *dev, size_t size, void *ptr) +{ + CUresult res; + const char *err_string; + CUcontext current_ctx; + CUcontext input_ctx; + unsigned int flag = 1; + int use_ptr_h = 0; + + if (dev == NULL) + return -ENODEV; + + if (size == 0 || ptr == NULL) + return -EINVAL; + + /* Store current ctx */ + res = pfn_cuCtxGetCurrent(¤t_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxGetCurrent failed with %s", + err_string); + return -EPERM; + } + + /* Set child ctx as current ctx */ + input_ctx = (CUcontext)((uintptr_t)dev->mpshared->info.context); + res = pfn_cuCtxSetCurrent(input_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent input failed with %s", + err_string); + return -EPERM; + } + + /* Get next memory list item */ + mem_alloc_list_tail = mem_list_add_item(); + if (mem_alloc_list_tail == NULL) + return -ENOMEM; + + /* Allocate memory */ + mem_alloc_list_tail->size = size; + mem_alloc_list_tail->ptr_h = ptr; + + res = pfn_cuMemHostRegister(mem_alloc_list_tail->ptr_h, + mem_alloc_list_tail->size, + CU_MEMHOSTREGISTER_PORTABLE | + CU_MEMHOSTREGISTER_DEVICEMAP); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuMemHostRegister failed with %s ptr %p size %zd", + err_string, + mem_alloc_list_tail->ptr_h, + mem_alloc_list_tail->size); + return -EPERM; + } + + res = pfn_cuDeviceGetAttribute(&(use_ptr_h), + CU_DEVICE_ATTRIBUTE_CAN_USE_HOST_POINTER_FOR_REGISTERED_MEM, + ((struct cuda_info *)(dev->mpshared->dev_private))->cu_dev); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceGetAttribute failed with %s", + err_string); + return -EPERM; + } + + if (use_ptr_h == 0) { + res = pfn_cuMemHostGetDevicePointer(&(mem_alloc_list_tail->ptr_d), + mem_alloc_list_tail->ptr_h, 0); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuMemHostGetDevicePointer failed with %s", + err_string); + return -EPERM; + } + + if ((uintptr_t)mem_alloc_list_tail->ptr_d != + (uintptr_t)mem_alloc_list_tail->ptr_h) { + rte_cuda_log(ERR, "Host input pointer is different wrt GPU registered pointer"); + return -ENOTSUP; + } + } else { + mem_alloc_list_tail->ptr_d = (CUdeviceptr)mem_alloc_list_tail->ptr_h; + } + + /* GPUDirect RDMA attribute required */ + res = pfn_cuPointerSetAttribute(&flag, + CU_POINTER_ATTRIBUTE_SYNC_MEMOPS, + mem_alloc_list_tail->ptr_d); + if (res != 0) { + rte_cuda_log(ERR, "Could not set SYNC MEMOP attribute for GPU memory at %"PRIu32 + ", err %d", (uint32_t)mem_alloc_list_tail->ptr_d, res); + return -EPERM; + } + + mem_alloc_list_tail->pkey = get_hash_from_ptr((void *)mem_alloc_list_tail->ptr_h); + mem_alloc_list_tail->size = size; + mem_alloc_list_tail->dev = dev; + mem_alloc_list_tail->ctx = (CUcontext)((uintptr_t)dev->mpshared->info.context); + mem_alloc_list_tail->mtype = CPU_REGISTERED; + + /* Restore original ctx as current ctx */ + res = pfn_cuCtxSetCurrent(current_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent current failed with %s", + err_string); + return -EPERM; + } + + return 0; +} + +static int +cuda_mem_free(struct rte_gpu *dev, void *ptr) +{ + CUresult res; + struct mem_entry *mem_item; + const char *err_string; + cuda_ptr_key hk; + + if (dev == NULL) + return -ENODEV; + + if (ptr == NULL) + return -EINVAL; + + hk = get_hash_from_ptr((void *)ptr); + + mem_item = mem_list_find_item(hk); + if (mem_item == NULL) { + rte_cuda_log(ERR, "Memory address 0x%p not found in driver memory", ptr); + return -EPERM; + } + + if (mem_item->mtype == GPU_MEM) { + res = pfn_cuMemFree(mem_item->ptr_d); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuMemFree current failed with %s", + err_string); + return -EPERM; + } + + return mem_list_del_item(hk); + } + + rte_cuda_log(ERR, "Memory type %d not supported", mem_item->mtype); + + return -EPERM; +} + +static int +cuda_mem_unregister(struct rte_gpu *dev, void *ptr) +{ + CUresult res; + struct mem_entry *mem_item; + const char *err_string; + cuda_ptr_key hk; + + if (dev == NULL) + return -ENODEV; + + if (ptr == NULL) + return -EINVAL; + + hk = get_hash_from_ptr((void *)ptr); + + mem_item = mem_list_find_item(hk); + if (mem_item == NULL) { + rte_cuda_log(ERR, "Memory address 0x%p not found in driver memory", ptr); + return -EPERM; + } + + if (mem_item->mtype == CPU_REGISTERED) { + res = pfn_cuMemHostUnregister(ptr); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuMemHostUnregister current failed with %s", + err_string); + return -EPERM; + } + + return mem_list_del_item(hk); + } + + rte_cuda_log(ERR, "Memory type %d not supported", mem_item->mtype); + + return -EPERM; +} + +static int +cuda_dev_close(struct rte_gpu *dev) +{ + if (dev == NULL) + return -EINVAL; + + rte_free(dev->mpshared->dev_private); + + return 0; +} + +static int +cuda_wmb(struct rte_gpu *dev) +{ + CUresult res; + const char *err_string; + CUcontext current_ctx; + CUcontext input_ctx; + struct cuda_info *private; + + if (dev == NULL) + return -ENODEV; + + private = (struct cuda_info *)dev->mpshared->dev_private; + + if (private->gdr_write_ordering != CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE) { + /* + * No need to explicitly force the write ordering because + * the device natively supports it + */ + return 0; + } + + if (private->gdr_flush_type != CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST) { + /* + * Can't flush GDR writes with cuFlushGPUDirectRDMAWrites CUDA function. + * Application needs to use alternative methods. + */ + rte_cuda_log(WARNING, "Can't flush GDR writes with cuFlushGPUDirectRDMAWrites CUDA function." + "Application needs to use alternative methods."); + return -ENOTSUP; + } + + /* Store current ctx */ + res = pfn_cuCtxGetCurrent(¤t_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxGetCurrent failed with %s", + err_string); + return -EPERM; + } + + /* Set child ctx as current ctx */ + input_ctx = (CUcontext)((uintptr_t)dev->mpshared->info.context); + res = pfn_cuCtxSetCurrent(input_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent input failed with %s", + err_string); + return -EPERM; + } + + res = pfn_cuFlushGPUDirectRDMAWrites(CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TARGET_CURRENT_CTX, + CU_FLUSH_GPU_DIRECT_RDMA_WRITES_TO_ALL_DEVICES); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuFlushGPUDirectRDMAWrites current failed with %s", + err_string); + return -EPERM; + } + + /* Restore original ctx as current ctx */ + res = pfn_cuCtxSetCurrent(current_ctx); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuCtxSetCurrent current failed with %s", + err_string); + return -EPERM; + } + + return 0; +} + +static int +cuda_gpu_probe(__rte_unused struct rte_pci_driver *pci_drv, struct rte_pci_device *pci_dev) +{ + struct rte_gpu *dev = NULL; + CUresult res; + CUdevice cu_dev_id; + CUcontext pctx; + char dev_name[RTE_DEV_NAME_MAX_LEN]; + const char *err_string; + int processor_count = 0; + struct cuda_info *private; + + if (pci_dev == NULL) { + rte_cuda_log(ERR, "NULL PCI device"); + return -EINVAL; + } + + rte_pci_device_name(&pci_dev->addr, dev_name, sizeof(dev_name)); + + /* Allocate memory to be used privately by drivers */ + dev = rte_gpu_allocate(pci_dev->device.name); + if (dev == NULL) + return -ENODEV; + + /* Initialize values only for the first CUDA driver call */ + if (dev->mpshared->info.dev_id == 0) { + mem_alloc_list_head = NULL; + mem_alloc_list_tail = NULL; + mem_alloc_list_last_elem = 0; + + /* Load libcuda.so library */ + if (cuda_loader()) { + rte_cuda_log(ERR, "CUDA Driver library not found"); + return -ENOTSUP; + } + + /* Load initial CUDA functions */ + if (cuda_sym_func_loader()) { + rte_cuda_log(ERR, "CUDA functions not found in library"); + return -ENOTSUP; + } + + /* + * Required to initialize the CUDA Driver. + * Multiple calls of cuInit() will return immediately + * without making any relevant change + */ + sym_cuInit(0); + + res = sym_cuDriverGetVersion(&cuda_driver_version); + if (res != 0) { + rte_cuda_log(ERR, "cuDriverGetVersion failed with %d", res); + return -ENOTSUP; + } + + if (cuda_driver_version < CUDA_DRIVER_MIN_VERSION) { + rte_cuda_log(ERR, "CUDA Driver version found is %d. " + "Minimum requirement is %d", + cuda_driver_version, + CUDA_DRIVER_MIN_VERSION); + return -ENOTSUP; + } + + if (cuda_pfn_func_loader()) { + rte_cuda_log(ERR, "CUDA PFN functions not found in library"); + return -ENOTSUP; + } + } + + /* Fill HW specific part of device structure */ + dev->device = &pci_dev->device; + dev->mpshared->info.numa_node = pci_dev->device.numa_node; + + /* Get NVIDIA GPU Device descriptor */ + res = pfn_cuDeviceGetByPCIBusId(&cu_dev_id, dev->device->name); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceGetByPCIBusId name %s failed with %d: %s", + dev->device->name, res, err_string); + return -EPERM; + } + + res = pfn_cuDevicePrimaryCtxRetain(&pctx, cu_dev_id); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDevicePrimaryCtxRetain name %s failed with %d: %s", + dev->device->name, res, err_string); + return -EPERM; + } + + res = pfn_cuCtxGetApiVersion(pctx, &cuda_api_version); + if (res != 0) { + rte_cuda_log(ERR, "cuCtxGetApiVersion failed with %d", res); + return -ENOTSUP; + } + + if (cuda_api_version < CUDA_API_MIN_VERSION) { + rte_cuda_log(ERR, "CUDA API version found is %d Minimum requirement is %d", + cuda_api_version, CUDA_API_MIN_VERSION); + return -ENOTSUP; + } + + dev->mpshared->info.context = (uint64_t)pctx; + + /* + * GPU Device generic info + */ + + /* Processor count */ + res = pfn_cuDeviceGetAttribute(&(processor_count), + CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT, + cu_dev_id); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceGetAttribute failed with %s", + err_string); + return -EPERM; + } + dev->mpshared->info.processor_count = (uint32_t)processor_count; + + /* Total memory */ + res = pfn_cuDeviceTotalMem(&dev->mpshared->info.total_memory, cu_dev_id); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceTotalMem failed with %s", + err_string); + return -EPERM; + } + + /* + * GPU Device private info + */ + dev->mpshared->dev_private = rte_zmalloc(NULL, + sizeof(struct cuda_info), + RTE_CACHE_LINE_SIZE); + if (dev->mpshared->dev_private == NULL) { + rte_cuda_log(ERR, "Failed to allocate memory for GPU process private"); + return -ENOMEM; + } + + private = (struct cuda_info *)dev->mpshared->dev_private; + private->cu_dev = cu_dev_id; + res = pfn_cuDeviceGetName(private->gpu_name, + RTE_DEV_NAME_MAX_LEN, + cu_dev_id); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceGetName failed with %s", + err_string); + return -EPERM; + } + + res = pfn_cuDeviceGetAttribute(&(private->gdr_supported), + CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_SUPPORTED, + cu_dev_id); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceGetAttribute failed with %s", + err_string); + return -EPERM; + } + + if (private->gdr_supported == 0) + rte_cuda_log(WARNING, "GPU %s doesn't support GPUDirect RDMA", + pci_dev->device.name); + + res = pfn_cuDeviceGetAttribute(&(private->gdr_write_ordering), + CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_WRITES_ORDERING, + cu_dev_id); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, + "cuDeviceGetAttribute failed with %s", + err_string); + return -EPERM; + } + + if (private->gdr_write_ordering == CU_GPU_DIRECT_RDMA_WRITES_ORDERING_NONE) { + res = pfn_cuDeviceGetAttribute(&(private->gdr_flush_type), + CU_DEVICE_ATTRIBUTE_GPU_DIRECT_RDMA_FLUSH_WRITES_OPTIONS, + cu_dev_id); + if (res != 0) { + pfn_cuGetErrorString(res, &(err_string)); + rte_cuda_log(ERR, "cuDeviceGetAttribute failed with %s", + err_string); + return -EPERM; + } + + if (private->gdr_flush_type != CU_FLUSH_GPU_DIRECT_RDMA_WRITES_OPTION_HOST) + rte_cuda_log(ERR, "GPUDirect RDMA flush writes API is not supported"); + } + + dev->ops.dev_info_get = cuda_dev_info_get; + dev->ops.dev_close = cuda_dev_close; + dev->ops.mem_alloc = cuda_mem_alloc; + dev->ops.mem_free = cuda_mem_free; + dev->ops.mem_register = cuda_mem_register; + dev->ops.mem_unregister = cuda_mem_unregister; + dev->ops.wmb = cuda_wmb; + + rte_gpu_complete_new(dev); + + rte_cuda_debug("dev id = %u name = %s", + dev->mpshared->info.dev_id, private->gpu_name); + + return 0; +} + +static int +cuda_gpu_remove(struct rte_pci_device *pci_dev) +{ + struct rte_gpu *dev; + int ret; + uint8_t gpu_id; + + if (pci_dev == NULL) + return -EINVAL; + + dev = rte_gpu_get_by_name(pci_dev->device.name); + if (dev == NULL) { + rte_cuda_log(ERR, "Couldn't find HW dev \"%s\" to uninitialise it", + pci_dev->device.name); + return -ENODEV; + } + gpu_id = dev->mpshared->info.dev_id; + + /* release dev from library */ + ret = rte_gpu_release(dev); + if (ret) + rte_cuda_log(ERR, "Device %i failed to uninit: %i", gpu_id, ret); + + rte_cuda_debug("Destroyed dev = %u", gpu_id); + + return 0; +} + +static struct rte_pci_driver rte_cuda_driver = { + .id_table = pci_id_cuda_map, + .drv_flags = RTE_PCI_DRV_WC_ACTIVATE, + .probe = cuda_gpu_probe, + .remove = cuda_gpu_remove, +}; + +RTE_PMD_REGISTER_PCI(gpu_cuda, rte_cuda_driver); +RTE_PMD_REGISTER_PCI_TABLE(gpu_cuda, pci_id_cuda_map); +RTE_PMD_REGISTER_KMOD_DEP(gpu_cuda, "* nvidia & (nv_peer_mem | nvpeer_mem)"); diff --git a/drivers/gpu/cuda/meson.build b/drivers/gpu/cuda/meson.build new file mode 100644 index 0000000000..3fe20929fa --- /dev/null +++ b/drivers/gpu/cuda/meson.build @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright (c) 2021 NVIDIA Corporation & Affiliates + +if not is_linux + build = false + reason = 'only supported on Linux' + subdir_done() +endif +if not cc.has_header('cuda.h') + build = false + reason = 'missing dependency, "cuda.h"' + subdir_done() +endif +if not cc.has_header('cudaTypedefs.h') + build = false + reason = 'missing dependency, "cudaTypedefs.h"' + subdir_done() +endif + +deps += ['gpudev', 'pci', 'bus_pci'] +sources = files('cuda.c') diff --git a/drivers/gpu/cuda/version.map b/drivers/gpu/cuda/version.map new file mode 100644 index 0000000000..c2e0723b4c --- /dev/null +++ b/drivers/gpu/cuda/version.map @@ -0,0 +1,3 @@ +DPDK_22 { + local: *; +}; diff --git a/drivers/gpu/meson.build b/drivers/gpu/meson.build index e51ad3381b..601bedcd61 100644 --- a/drivers/gpu/meson.build +++ b/drivers/gpu/meson.build @@ -1,4 +1,4 @@ # SPDX-License-Identifier: BSD-3-Clause # Copyright (c) 2021 NVIDIA Corporation & Affiliates -drivers = [] +drivers = [ 'cuda' ]