From patchwork Mon Nov 23 17:53:02 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Xiong, Jianxin" X-Patchwork-Id: 11925841 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id DBB41C63798 for ; Mon, 23 Nov 2020 17:39:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A269620756 for ; Mon, 23 Nov 2020 17:39:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2390419AbgKWRjK (ORCPT ); Mon, 23 Nov 2020 12:39:10 -0500 Received: from mga11.intel.com ([192.55.52.93]:51712 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2390359AbgKWRjK (ORCPT ); Mon, 23 Nov 2020 12:39:10 -0500 IronPort-SDR: +V7y9INig1jvbO79eEuK4iMWD61VSVzenBks1qxq7f1DMo8BQrkO1AIbcwARcB9ABXU6kxbuyk eLRWobf0nH8A== X-IronPort-AV: E=McAfee;i="6000,8403,9814"; a="168301222" X-IronPort-AV: E=Sophos;i="5.78,364,1599548400"; d="scan'208";a="168301222" X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga004.fm.intel.com ([10.253.24.48]) by fmsmga102.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 23 Nov 2020 09:39:10 -0800 IronPort-SDR: 9vils/WBwvnYkMVY6uFUzvlVAqGTQOlBYNR3BgVlnfcFzsZOOHUL5Bx62n9fAzH74NBJKIp/AU kdDImGrG5y9w== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.78,364,1599548400"; d="scan'208";a="361525796" Received: from cst-dev.jf.intel.com ([10.23.221.69]) by fmsmga004.fm.intel.com with ESMTP; 23 Nov 2020 09:39:09 -0800 From: Jianxin Xiong To: linux-rdma@vger.kernel.org, dri-devel@lists.freedesktop.org Cc: Jianxin Xiong , Doug Ledford , Jason Gunthorpe , Leon Romanovsky , Sumit Semwal , Christian Koenig , Daniel Vetter Subject: [PATCH rdma-core 3/5] pyverbs: Add dma-buf based MR support Date: Mon, 23 Nov 2020 09:53:02 -0800 Message-Id: <1606153984-104583-4-git-send-email-jianxin.xiong@intel.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1606153984-104583-1-git-send-email-jianxin.xiong@intel.com> References: <1606153984-104583-1-git-send-email-jianxin.xiong@intel.com> Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org Define a new sub-class of 'MR' that uses dma-buf object for the memory region. Define a new class 'DmaBuf' for dma-buf object allocation. Signed-off-by: Jianxin Xiong --- pyverbs/CMakeLists.txt | 2 ++ pyverbs/dmabuf.pxd | 13 +++++++++ pyverbs/dmabuf.pyx | 58 +++++++++++++++++++++++++++++++++++++ pyverbs/libibverbs.pxd | 2 ++ pyverbs/mr.pxd | 5 ++++ pyverbs/mr.pyx | 77 ++++++++++++++++++++++++++++++++++++++++++++++++-- 6 files changed, 155 insertions(+), 2 deletions(-) create mode 100644 pyverbs/dmabuf.pxd create mode 100644 pyverbs/dmabuf.pyx diff --git a/pyverbs/CMakeLists.txt b/pyverbs/CMakeLists.txt index 9542c4b..5aee02b 100644 --- a/pyverbs/CMakeLists.txt +++ b/pyverbs/CMakeLists.txt @@ -1,5 +1,6 @@ # SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) # Copyright (c) 2019, Mellanox Technologies. All rights reserved. See COPYING file +# Copyright (c) 2020, Intel Corporation. All rights reserved. rdma_cython_module(pyverbs "" addr.pyx @@ -16,6 +17,7 @@ rdma_cython_module(pyverbs "" wr.pyx xrcd.pyx srq.pyx + dmabuf.pyx ) rdma_python_module(pyverbs diff --git a/pyverbs/dmabuf.pxd b/pyverbs/dmabuf.pxd new file mode 100644 index 0000000..040db4b --- /dev/null +++ b/pyverbs/dmabuf.pxd @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) +# Copyright (c) 2020, Intel Corporation. All rights reserved. + +#cython: language_level=3 + +cdef class DmaBuf: + cdef int dri_fd + cdef int handle + cdef int fd + cdef unsigned long size + cdef unsigned long map_offset + cdef object dmabuf_mrs + cdef add_ref(self, obj) diff --git a/pyverbs/dmabuf.pyx b/pyverbs/dmabuf.pyx new file mode 100644 index 0000000..6c7622d --- /dev/null +++ b/pyverbs/dmabuf.pyx @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) +# Copyright (c) 2020, Intel Corporation. All rights reserved. + +#cython: language_level=3 + +import weakref + +from os import open, close, O_RDWR +from fcntl import ioctl +from struct import pack_into, unpack +from pyverbs.base cimport close_weakrefs +from pyverbs.mr cimport DmaBufMR + +cdef extern from "drm/drm.h": + cdef int DRM_IOCTL_MODE_CREATE_DUMB + cdef int DRM_IOCTL_MODE_MAP_DUMB + cdef int DRM_IOCTL_MODE_DESTROY_DUMB + cdef int DRM_IOCTL_PRIME_HANDLE_TO_FD + +cdef class DmaBuf: + def __init__(self, size, unit=0): + """ + Allocate DmaBuf object from a GPU device. This is done through the + DRI device interface (/dev/dri/card*). Usually this requires the + effective user id being root or being a member of the 'video' group. + :param size: The size (in number of bytes) of the buffer. + :param unit: The unit number of the GPU to allocate the buffer from. + :return: The newly created DmaBuf object on success. + """ + self.dmabuf_mrs = weakref.WeakSet() + self.dri_fd = open('/dev/dri/card'+str(unit), O_RDWR) + + args = bytearray(32) + pack_into('=iiiiiiq', args, 0, 1, size, 8, 0, 0, 0, 0) + ioctl(self.dri_fd, DRM_IOCTL_MODE_CREATE_DUMB, args) + a, b, c, d, self.handle, e, self.size = unpack('=iiiiiiq', args) + + args = bytearray(12) + pack_into('=iii', args, 0, self.handle, O_RDWR, 0) + ioctl(self.dri_fd, DRM_IOCTL_PRIME_HANDLE_TO_FD, args) + a, b, self.fd = unpack('=iii', args) + + args = bytearray(16) + pack_into('=iiq', args, 0, self.handle, 0, 0) + ioctl(self.dri_fd, DRM_IOCTL_MODE_MAP_DUMB, args); + a, b, self.map_offset = unpack('=iiq', args); + + def __dealloc__(self): + close_weakrefs([self.dmabuf_mrs]) + args = bytearray(4) + pack_into('=i', args, 0, self.handle) + ioctl(self.dri_fd, DRM_IOCTL_MODE_DESTROY_DUMB, args) + close(self.dri_fd) + + cdef add_ref(self, obj): + if isinstance(obj, DmaBufMR): + self.dmabuf_mrs.add(obj) + diff --git a/pyverbs/libibverbs.pxd b/pyverbs/libibverbs.pxd index 6fbba54..95e51e1 100644 --- a/pyverbs/libibverbs.pxd +++ b/pyverbs/libibverbs.pxd @@ -507,6 +507,8 @@ cdef extern from 'infiniband/verbs.h': ibv_pd *ibv_alloc_pd(ibv_context *context) int ibv_dealloc_pd(ibv_pd *pd) ibv_mr *ibv_reg_mr(ibv_pd *pd, void *addr, size_t length, int access) + ibv_mr *ibv_reg_dmabuf_mr(ibv_pd *pd, uint64_t offset, size_t length, + int fd, int access) int ibv_dereg_mr(ibv_mr *mr) int ibv_advise_mr(ibv_pd *pd, uint32_t advice, uint32_t flags, ibv_sge *sg_list, uint32_t num_sge) diff --git a/pyverbs/mr.pxd b/pyverbs/mr.pxd index ebe8ada..b89cf02 100644 --- a/pyverbs/mr.pxd +++ b/pyverbs/mr.pxd @@ -1,5 +1,6 @@ # SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) # Copyright (c) 2019, Mellanox Technologies. All rights reserved. See COPYING file +# Copyright (c) 2020, Intel Corporation. All rights reserved. #cython: language_level=3 @@ -33,3 +34,7 @@ cdef class MW(PyverbsCM): cdef class DMMR(MR): cdef object dm + +cdef class DmaBufMR(MR): + cdef object dmabuf + cdef unsigned long offset diff --git a/pyverbs/mr.pyx b/pyverbs/mr.pyx index 7011da1..4102d3c 100644 --- a/pyverbs/mr.pyx +++ b/pyverbs/mr.pyx @@ -1,11 +1,12 @@ # SPDX-License-Identifier: (GPL-2.0 OR Linux-OpenIB) # Copyright (c) 2019, Mellanox Technologies. All rights reserved. See COPYING file +# Copyright (c) 2020, Intel Corporation. All rights reserved. import resource import logging from posix.mman cimport mmap, munmap, MAP_PRIVATE, PROT_READ, PROT_WRITE, \ - MAP_ANONYMOUS, MAP_HUGETLB + MAP_ANONYMOUS, MAP_HUGETLB, MAP_SHARED from pyverbs.pyverbs_error import PyverbsError, PyverbsRDMAError, \ PyverbsUserError from libc.stdint cimport uintptr_t, SIZE_MAX @@ -14,9 +15,10 @@ from posix.stdlib cimport posix_memalign from libc.string cimport memcpy, memset cimport pyverbs.libibverbs_enums as e from pyverbs.device cimport DM -from libc.stdlib cimport free +from libc.stdlib cimport free, malloc from .cmid cimport CMID from .pd cimport PD +from .dmabuf cimport DmaBuf cdef extern from 'sys/mman.h': cdef void* MAP_FAILED @@ -348,6 +350,77 @@ cdef class DMMR(MR): cpdef read(self, length, offset): return self.dm.copy_from_dm(offset, length) +cdef class DmaBufMR(MR): + def __init__(self, PD pd not None, length=0, access=0, DmaBuf dmabuf=None, offset=0): + """ + Initializes a DmaBufMR (DMA-BUF Memory Region) of the given length + and access flags using the given PD and DmaBuf objects. + :param pd: A PD object + :param length: Length in bytes + :param access: Access flags, see ibv_access_flags enum + :param dmabuf: A DmaBuf object + :param offset: Byte offset from the beginning of the dma-buf + :return: The newly create DMABUFMR + """ + self.logger = logging.getLogger(self.__class__.__name__) + if dmabuf is None: + dmabuf = DmaBuf(length + offset) + self.mr = v.ibv_reg_dmabuf_mr(pd.pd, offset, length, dmabuf.fd, access) + if self.mr == NULL: + raise PyverbsRDMAErrno('Failed to register a dma-buf MR. length: {len}, access flags: {flags}'. + format(len=length, flags=access,)) + super().__init__(pd, length, access) + self.pd = pd + self.dmabuf = dmabuf + self.offset = offset + pd.add_ref(self) + dmabuf.add_ref(self) + self.logger.debug('Registered dma-buf ibv_mr. Length: {len}, access flags {flags}'. + format(len=length, flags=access)) + + def write(self, data, length, offset=0): + """ + Write user data to the dma-buf backing the MR + :param data: User data to write + :param length: Length of the data to write + :param offset: Writing offset + :return: None + """ + if isinstance(data, str): + data = data.encode() + # can't access the attributes if self.dmabuf is used w/o cast + dmabuf = self.dmabuf + cdef int off = offset + self.offset + cdef void *buf = mmap(NULL, length + off, PROT_READ | PROT_WRITE, + MAP_SHARED, dmabuf.dri_fd, dmabuf.map_offset) + if buf == MAP_FAILED: + raise PyverbsError('Failed to map dma-buf of size {l}'. + format(l=length)) + memcpy((buf + off), data, length) + munmap(buf, length + off) + + cpdef read(self, length, offset): + """ + Reads data from the dma-buf backing the MR + :param length: Length of data to read + :param offset: Reading offset + :return: The data on the buffer in the requested offset + """ + # can't access the attributes if self.dmabuf is used w/o cast + dmabuf = self.dmabuf + cdef int off = offset + self.offset + cdef void *buf = mmap(NULL, length + off, PROT_READ | PROT_WRITE, + MAP_SHARED, dmabuf.dri_fd, dmabuf.map_offset) + if buf == MAP_FAILED: + raise PyverbsError('Failed to map dma-buf of size {l}'. + format(l=length)) + cdef char *data =malloc(length) + memset(data, 0, length) + memcpy(data, (buf + off), length) + munmap(buf, length + off) + res = data[:length] + free(data) + return res def mwtype2str(mw_type): mw_types = {1:'IBV_MW_TYPE_1', 2:'IBV_MW_TYPE_2'}