From patchwork Thu Jul 17 10:25:14 2014 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Anders Roxell X-Patchwork-Id: 33779 Return-Path: X-Original-To: linaro@patches.linaro.org Delivered-To: linaro@patches.linaro.org Received: from mail-pd0-f200.google.com (mail-pd0-f200.google.com [209.85.192.200]) by ip-10-151-82-157.ec2.internal (Postfix) with ESMTPS id 3596020CA0 for ; Thu, 17 Jul 2014 10:25:43 +0000 (UTC) Received: by mail-pd0-f200.google.com with SMTP id w10sf7148904pde.7 for ; Thu, 17 Jul 2014 03:25:42 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:delivered-to:date:from:to:message-id:references :mime-version:in-reply-to:user-agent:cc:subject:precedence:list-id :list-unsubscribe:list-archive:list-post:list-help:list-subscribe :errors-to:sender:x-original-sender :x-original-authentication-results:mailing-list:content-disposition :content-type:content-transfer-encoding; bh=hDw5YYkWZk4SFF5jJKD05jX3OVaBXC2iVNb49e1dVPo=; b=ckcQ18UuE54TriM/AcB++eriPcOjpS207P9wZ+3zexzT7jpbVfSYUIJg5BzBEaTiL8 sMtbjUehS3TmQhSIoX2fJqXtDg3VCcJHbx18u00lCABCmcpqTFPIoXPSqwMcubTIur95 eRJ1qrZrIBsAX+cT35x7QcAIPC7kgka1yyBbsWpOmopYrGRZ6kTOu/0oRfbSHoPEAjBT rgCzqint7idD301U91guV/0iyldCbnJXE3licIdIvysRJBNeV3CqzulPPWyM3CXwNtej 4noPArFTRyBPHKo79ddA5ELXfdkEMU8lnUFUbsvTl1+zR84+Du4mCi9xa5qsFZdgFkhJ nsuQ== X-Gm-Message-State: ALoCoQnT7GBhHiHlynWPRwFM8bw1lXlJ7FXgC6AoiDpjhKMMv0jVH4d4gPcPPTXE23PhMfyxsb59 X-Received: by 10.68.107.33 with SMTP id gz1mr16935656pbb.5.1405592742452; Thu, 17 Jul 2014 03:25:42 -0700 (PDT) X-BeenThere: patchwork-forward@linaro.org Received: by 10.140.95.193 with SMTP id i59ls657213qge.20.gmail; Thu, 17 Jul 2014 03:25:42 -0700 (PDT) X-Received: by 10.53.5.162 with SMTP id cn2mr15282072vdd.23.1405592742206; Thu, 17 Jul 2014 03:25:42 -0700 (PDT) Received: from mail-vc0-f182.google.com (mail-vc0-f182.google.com [209.85.220.182]) by mx.google.com with ESMTPS id nu8si1672849vcb.16.2014.07.17.03.25.42 for (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Thu, 17 Jul 2014 03:25:42 -0700 (PDT) Received-SPF: pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 209.85.220.182 as permitted sender) client-ip=209.85.220.182; Received: by mail-vc0-f182.google.com with SMTP id hy4so4213727vcb.27 for ; Thu, 17 Jul 2014 03:25:42 -0700 (PDT) X-Received: by 10.220.118.136 with SMTP id v8mr12316730vcq.50.1405592742034; Thu, 17 Jul 2014 03:25:42 -0700 (PDT) X-Forwarded-To: patchwork-forward@linaro.org X-Forwarded-For: patch@linaro.org patchwork-forward@linaro.org Delivered-To: patch@linaro.org Received: by 10.221.37.5 with SMTP id tc5csp23508vcb; Thu, 17 Jul 2014 03:25:41 -0700 (PDT) X-Received: by 10.224.134.201 with SMTP id k9mr55271082qat.59.1405592740670; Thu, 17 Jul 2014 03:25:40 -0700 (PDT) Received: from ip-10-141-164-156.ec2.internal (lists.linaro.org. [54.225.227.206]) by mx.google.com with ESMTPS id v6si4289211qat.51.2014.07.17.03.25.39 for (version=TLSv1 cipher=RC4-SHA bits=128/128); Thu, 17 Jul 2014 03:25:40 -0700 (PDT) Received-SPF: none (google.com: lng-odp-bounces@lists.linaro.org does not designate permitted sender hosts) client-ip=54.225.227.206; Received: from localhost ([127.0.0.1] helo=ip-10-141-164-156.ec2.internal) by ip-10-141-164-156.ec2.internal with esmtp (Exim 4.76) (envelope-from ) id 1X7iqF-0000UF-Q5; Thu, 17 Jul 2014 10:23:11 +0000 Received: from mail-la0-f51.google.com ([209.85.215.51]) by ip-10-141-164-156.ec2.internal with esmtp (Exim 4.76) (envelope-from ) id 1X7iq2-0000U2-Rg for lng-odp@lists.linaro.org; Thu, 17 Jul 2014 10:22:59 +0000 Received: by mail-la0-f51.google.com with SMTP id el20so1536314lab.38 for ; Thu, 17 Jul 2014 03:25:20 -0700 (PDT) X-Received: by 10.112.56.148 with SMTP id a20mr14071847lbq.72.1405592719977; Thu, 17 Jul 2014 03:25:19 -0700 (PDT) Received: from 8470w (c-853670d5.07-21-73746f28.cust.bredbandsbolaget.se. [213.112.54.133]) by mx.google.com with ESMTPSA id tj1sm2664475lbb.40.2014.07.17.03.25.18 for (version=TLSv1.2 cipher=RC4-SHA bits=128/128); Thu, 17 Jul 2014 03:25:18 -0700 (PDT) Date: Thu, 17 Jul 2014 12:25:14 +0200 From: Anders Roxell To: venkatesh.vivekanandan@linaro.org Message-ID: <20140717102514.GA18656@8470w> References: <1405506215-26817-1-git-send-email-venkatesh.vivekanandan@linaro.org> MIME-Version: 1.0 In-Reply-To: <1405506215-26817-1-git-send-email-venkatesh.vivekanandan@linaro.org> User-Agent: Mutt/1.5.21 (2010-09-15) X-Topics: patch Cc: Vincent Hsu , lng-odp@lists.linaro.org Subject: Re: [lng-odp] [PATCH v4 1/2] Initial odp-dpdk port X-BeenThere: lng-odp@lists.linaro.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: , List-Help: , List-Subscribe: , Errors-To: lng-odp-bounces@lists.linaro.org Sender: lng-odp-bounces@lists.linaro.org X-Removed-Original-Auth: Dkim didn't pass. X-Original-Sender: anders.roxell@linaro.org X-Original-Authentication-Results: mx.google.com; spf=pass (google.com: domain of patch+caf_=patchwork-forward=linaro.org@linaro.org designates 209.85.220.182 as permitted sender) smtp.mail=patch+caf_=patchwork-forward=linaro.org@linaro.org Mailing-list: list patchwork-forward@linaro.org; contact patchwork-forward+owners@linaro.org X-Google-Group-Id: 836684582541 Content-Disposition: inline Hi Venkatesh, I've started to look into your patches. I haven't reviewed all, just started. On 2014-07-16 15:53, venkatesh.vivekanandan@linaro.org wrote: > From: Vincent Hsu > > Signed-off-by: Vincent Hsu > > - Add/modify files to support linux-dpdk compilation in new automake > environment. > * Modified configure.ac > * Added platform/linux-dpdk/Makefile.am > * Moved all files from platform/linux-dpdk/source to > platform/linux-dpdk/. > > - Added platform/linux-dpdk/README on how to clone, compile DPDK and > commands to execute on ODP. > - Made ODP_BUFFER_ consistent with linux-generic. > - Removed odp_buffer_is_scatter API to be inline with linux-generic. > - Added platform/linux-dpdk/odp_linux.c to supply the function > and argument to the pthread created by dpdk. > > Signed-off-by: Venkatesh Vivekanandan > --- > configure.ac | 2 + > platform/linux-dpdk/Makefile.am | 100 ++++ > platform/linux-dpdk/README | 70 +++ > platform/linux-dpdk/include/api/odp_buffer.h | 94 ++++ > platform/linux-dpdk/include/api/odp_buffer_pool.h | 99 ++++ > platform/linux-dpdk/include/api/odp_packet.h | 228 +++++++++ > platform/linux-dpdk/include/api/odp_pktio_types.h | 45 ++ > platform/linux-dpdk/include/odp_buffer_internal.h | 72 +++ > .../linux-dpdk/include/odp_buffer_pool_internal.h | 90 ++++ > platform/linux-dpdk/include/odp_packet_dpdk.h | 87 ++++ > platform/linux-dpdk/include/odp_packet_internal.h | 139 +++++ > .../linux-dpdk/include/odp_packet_io_internal.h | 51 ++ > platform/linux-dpdk/odp_buffer.c | 90 ++++ > platform/linux-dpdk/odp_buffer_pool.c | 156 ++++++ > platform/linux-dpdk/odp_init.c | 113 +++++ > platform/linux-dpdk/odp_linux.c | 96 ++++ > platform/linux-dpdk/odp_packet.c | 374 ++++++++++++++ > platform/linux-dpdk/odp_packet_dpdk.c | 189 +++++++ > platform/linux-dpdk/odp_packet_io.c | 561 +++++++++++++++++++++ I did a diff between this file and platform/linux-generic/odp_packet_io.c and basically the only changes that is are 6 case for ODP_PKTIO_TYPE_DPDK, is it possible to factorise this somehow so we don't need to copy this much code? I haven't looked in any other files. > platform/linux-dpdk/odp_queue.c | 435 ++++++++++++++++ > 20 files changed, 3091 insertions(+) > create mode 100644 platform/linux-dpdk/Makefile.am > create mode 100644 platform/linux-dpdk/README > create mode 100644 platform/linux-dpdk/include/api/odp_buffer.h > create mode 100644 platform/linux-dpdk/include/api/odp_buffer_pool.h > create mode 100644 platform/linux-dpdk/include/api/odp_packet.h > create mode 100644 platform/linux-dpdk/include/api/odp_pktio_types.h > create mode 100644 platform/linux-dpdk/include/odp_buffer_internal.h > create mode 100644 platform/linux-dpdk/include/odp_buffer_pool_internal.h > create mode 100644 platform/linux-dpdk/include/odp_packet_dpdk.h > create mode 100644 platform/linux-dpdk/include/odp_packet_internal.h > create mode 100644 platform/linux-dpdk/include/odp_packet_io_internal.h > create mode 100644 platform/linux-dpdk/odp_buffer.c > create mode 100644 platform/linux-dpdk/odp_buffer_pool.c > create mode 100644 platform/linux-dpdk/odp_init.c > create mode 100644 platform/linux-dpdk/odp_linux.c > create mode 100644 platform/linux-dpdk/odp_packet.c > create mode 100644 platform/linux-dpdk/odp_packet_dpdk.c > create mode 100644 platform/linux-dpdk/odp_packet_io.c > create mode 100644 platform/linux-dpdk/odp_queue.c > > diff --git a/configure.ac b/configure.ac > index 873ea9e..3d8481f 100644 > --- a/configure.ac > +++ b/configure.ac > @@ -51,6 +51,7 @@ AC_ARG_WITH([platform], > > AM_CONDITIONAL([ODP_PLATFORM_GENERIC], [test "x$with_platform" = xlinux-generic]) > AM_CONDITIONAL([ODP_PLATFORM_KEYSTONE2], [test "x$with_platform" = xlinux-keystone2]) > +AM_CONDITIONAL([ODP_PLATFORM_DPDK], [test "x$with_platform" = xlinux-dpdk]) > > AC_SUBST([with_platform]) > > @@ -111,6 +112,7 @@ AC_CONFIG_FILES([Makefile > platform/Makefile > platform/linux-generic/Makefile > platform/linux-keystone2/Makefile > + platform/linux-dpdk/Makefile > test/Makefile > test/api_test/Makefile > test/example/Makefile > diff --git a/platform/linux-dpdk/Makefile.am b/platform/linux-dpdk/Makefile.am > new file mode 100644 > index 0000000..067c0bb > --- /dev/null > +++ b/platform/linux-dpdk/Makefile.am > @@ -0,0 +1,100 @@ > +include $(top_srcdir)/Makefile.inc > +LIB = $(top_builddir)/lib > + > +dist_pkgdata_DATA = $(LIB)/libodp.la > + > +pkgconfigdir = pkgconfig > +nodist_pkgconfig_DATA = $(top_builddir)/pkgconfig/libodp.pc > + > +.PHONY: pkgconfig/libodp.pc > + > +RTE_SDK ?= $(top_srcdir)/../dpdk > +RTE_OUTPUT ?= $(RTE_SDK)/build > +RTE_LIB ?= $(RTE_OUTPUT)/lib > + > +PLAT_CFLAGS = -include $(RTE_OUTPUT)/include/rte_config.h why do you need to specify this like that? > +PLAT_CFLAGS += -I$(RTE_OUTPUT)/include > +PLAT_CFLAGS += -I$(RTE_OUTPUT)/include/arch > +PLAT_CFLAGS += -I$(RTE_OUTPUT)/include/exec-env Remove this... too hardcoded... do as ks2 Something like this: $ ./configure --with-platform=linux-dpdk LDFLAGS=-L/home/anders/src/dpdk/build/lib CFLAGS="-include /home/anders/src/for_dpdk/build/include/rte_config.h -I/home/anders/src/for_dpdk/build/include -I/home/anders/src/for_dpdk/build/include/arch -I/home/anders/src/for_dpdk/build/include/exec-env" I used build instead of my_sdk_build_dir that was stated in the README $ gitt df > + > +$ cd ./dpdk > +# Only for the first time > +$ make config T=x86_64-default-linuxapp-gcc O=my_sdk_build_dir The O= you should be able to set that to whatever you want right? s|my_sdk_build_dir|| > +set CONFIG_RTE_BUILD_COMBINE_LIBS=y in my_sdk_build_dir/.config Maybe change s|set|# set| > + > +Note: If not-intel SFP's are used in NIC, then go to my_sdk_build_dir/.config and set CONFIG_RTE_LIBRTE_IXGBE_ALLOW_UNSUPPORTED_SFP=y > + > +$ cd my_sdk_build_dir/ s|my_sdk_build_dir|| > +$ make clean; make > + > +# To reserve huge pages which is needed for dpdk execute following command > +$ echo 1024 > /sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages > +# If you are running on a multi-node machine then, hugepages should be reserved on each node > +$ echo 1024 > /sys/devices/system/node/node1/hugepages/hugepages-2048kB/nr_hugepages > + > +$ sudo mkdir /mnt/huge > +$ sudo mount -t hugetlbfs nodev /mnt/huge > +# To load uio driver > +$ sudo /sbin/modprobe uio > +$ ulimit -Sn 2048 > + > +# sudo insmod igb_uio.ko > +$ cd ./dpdk > +$ insmod ./build/build/lib/librte_eal/linuxapp/igb_uio/igb_uio.ko > + > +$ rmmod ixgbe > +$ modprobe ixgbe > +# If the SFP's used are non-intel, then > +$ modprobe ixgbe allow_unsupported_sfp=1 > + > +$ cd ./dpdk > +$ ./tools/igb_uio_bind.py --status > + > +Now you should look for pci id listed and give it in the following command in > +place of 42:00.0 > + > +# To give the interfaces to dpdk, use following command > +$ sudo ./tools/igb_uio_bind.py --bind=igb_uio 42:00.0 > +$ sudo ./tools/igb_uio_bind.py --bind=igb_uio 42:00.1 > +# To restore it back to kernel, use following command > +$ sudo ./tools/igb_uio_bind.py --bind=ixgbe 42:00.0 > +$ sudo ./tools/igb_uio_bind.py --bind=ixgbe 42:00.1 > + > +# To compile ODP with linux-dpdk > +$ ./bootstrap > +$ ./configure --with-platform=linux-dpdk And maybe add to the ./configure command: LDFLAGS=-L/lib CFLAGS="-include /include/rte_config.h -I/include -I/include/arch -I/include/exec-env" Cheers, Anders > +$ make clean > +$ make > + > +# Commands to test > +l2fwding app - ./test/l2fwd/odp_l2fwd -i 0,1 -t 5 -m 0 -c 2 > +loopback app - ./test/packet/odp_pktio -i 0,1 -t 5 -m 0 -c 2 > + > + -i 0,1 - interface number > + -t 5 - dpdk type > + -m 0 - burst mode > + -c 2 - number of cpus > diff --git a/platform/linux-dpdk/include/api/odp_buffer.h b/platform/linux-dpdk/include/api/odp_buffer.h > new file mode 100644 > index 0000000..9ea1ed8 > --- /dev/null > +++ b/platform/linux-dpdk/include/api/odp_buffer.h > @@ -0,0 +1,94 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > + > +/** > + * @file > + * > + * ODP buffer descriptor > + */ > + > +#ifndef ODP_BUFFER_H_ > +#define ODP_BUFFER_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > + > + > +#include > + > + > + > + > + > +/** > + * ODP buffer > + */ > +typedef unsigned long odp_buffer_t; > + > + > +#define ODP_BUFFER_INVALID (0xffffffff) /**< Invalid buffer */ > + > + > +/** > + * Buffer start address > + * > + * @param buf Buffer handle > + * > + * @return Buffer start address > + */ > +void *odp_buffer_addr(odp_buffer_t buf); > + > +/** > + * Buffer maximum data size > + * > + * @param buf Buffer handle > + * > + * @return Buffer maximum data size > + */ > +size_t odp_buffer_size(odp_buffer_t buf); > + > +/** > + * Buffer type > + * > + * @param buf Buffer handle > + * > + * @return Buffer type > + */ > +int odp_buffer_type(odp_buffer_t buf); > + > +#define ODP_BUFFER_TYPE_INVALID (-1) /**< Buffer type invalid */ > +#define ODP_BUFFER_TYPE_ANY 0 /**< Buffer that can hold any other > + buffer type */ > +#define ODP_BUFFER_TYPE_RAW 1 /**< Raw buffer, no additional metadata */ > +#define ODP_BUFFER_TYPE_PACKET 2 /**< Packet buffer */ > +#define ODP_BUFFER_TYPE_TIMEOUT 3 /**< Timeout buffer */ > + > +/** > + * Tests if buffer is valid > + * > + * @param buf Buffer handle > + * > + * @return 1 if valid, otherwise 0 > + */ > +int odp_buffer_is_valid(odp_buffer_t buf); > + > +/** > + * Print buffer metadata to STDOUT > + * > + * @param buf Buffer handle > + * > + */ > +void odp_buffer_print(odp_buffer_t buf); > + > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/include/api/odp_buffer_pool.h b/platform/linux-dpdk/include/api/odp_buffer_pool.h > new file mode 100644 > index 0000000..4b75cf5 > --- /dev/null > +++ b/platform/linux-dpdk/include/api/odp_buffer_pool.h > @@ -0,0 +1,99 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > + > +/** > + * @file > + * > + * ODP buffer pool > + */ > + > +#ifndef ODP_BUFFER_POOL_H_ > +#define ODP_BUFFER_POOL_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > + > + > +#include > +#include > + > +/** Maximum queue name lenght in chars */ > +#define ODP_BUFFER_POOL_NAME_LEN 32 > + > +/** Invalid buffer pool */ > +#define ODP_BUFFER_POOL_INVALID (0xffffffff) > + > +/** ODP buffer pool */ > +typedef unsigned long odp_buffer_pool_t; > + > + > +/** > + * Create a buffer pool > + * > + * @param name Name of the pool (max ODP_BUFFER_POOL_NAME_LEN - 1 chars) > + * @param base_addr Pool base address > + * @param size Pool size in bytes > + * @param buf_size Buffer size in bytes > + * @param buf_align Minimum buffer alignment > + * @param buf_type Buffer type > + * > + * @return Buffer pool handle > + */ > +odp_buffer_pool_t odp_buffer_pool_create(const char *name, > + void *base_addr, uint64_t size, > + size_t buf_size, size_t buf_align, > + int buf_type); > + > + > +/** > + * Find a buffer pool by name > + * > + * @param name Name of the pool > + * > + * @return Buffer pool handle, or ODP_BUFFER_POOL_INVALID if not found. > + */ > +odp_buffer_pool_t odp_buffer_pool_lookup(const char *name); > + > + > +/** > + * Print buffer pool info > + * > + * @param pool Pool handle > + * > + */ > +void odp_buffer_pool_print(odp_buffer_pool_t pool); > + > + > + > +/** > + * Buffer alloc > + * > + * @param pool Pool handle > + * > + * @return Buffer handle or ODP_BUFFER_INVALID > + */ > +odp_buffer_t odp_buffer_alloc(odp_buffer_pool_t pool); > + > + > +/** > + * Buffer free > + * > + * @param buf Buffer handle > + * > + */ > +void odp_buffer_free(odp_buffer_t buf); > + > + > + > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/include/api/odp_packet.h b/platform/linux-dpdk/include/api/odp_packet.h > new file mode 100644 > index 0000000..bdb3417 > --- /dev/null > +++ b/platform/linux-dpdk/include/api/odp_packet.h > @@ -0,0 +1,228 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > + > +/** > + * @file > + * > + * ODP packet descriptor > + */ > + > +#ifndef ODP_PACKET_H_ > +#define ODP_PACKET_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +#include > + > + > +/** > + * ODP packet descriptor > + */ > +typedef unsigned long odp_packet_t; > + > + > +/** Invalid packet */ > +#define ODP_PACKET_INVALID ODP_BUFFER_INVALID > + > +/** Invalid offset */ > +#define ODP_PACKET_OFFSET_INVALID ((size_t)-1) > + > + > +/** > + * Initialize the packet > + * > + * Needs to be called if the user allocates a packet buffer, i.e. the packet > + * has not been received from I/O through ODP. > + * > + * @param pkt Packet handle > + */ > +void odp_packet_init(odp_packet_t pkt); > + > +/** > + * Convert from packet handle to buffer handle > + * > + * @param buf Buffer handle > + * > + * @return Packet handle > + */ > +odp_packet_t odp_packet_from_buffer(odp_buffer_t buf); > + > +/** > + * Convert from buffer handle to packet handle > + * > + * @param pkt Packet handle > + * > + * @return Buffer handle > + */ > +odp_buffer_t odp_buffer_from_packet(odp_packet_t pkt); > + > +/** > + * Set the packet length > + * > + * @param pkt Packet handle > + * @param len Length of packet in bytes > + */ > +void odp_packet_set_len(odp_packet_t pkt, size_t len); > + > +/** > + * Get the packet length > + * > + * @param pkt Packet handle > + * > + * @return Packet length in bytes > + */ > +size_t odp_packet_get_len(odp_packet_t pkt); > + > +/** > + * Get address to the start of the packet buffer > + * > + * The address of the packet buffer is not necessarily the same as the start > + * address of the received frame, e.g. an eth frame may be offset by 2 or 6 > + * bytes to ensure 32 or 64-bit alignment of the IP header. > + * Use odp_packet_l2(pkt) to get the start address of a received valid frame > + * or odp_packet_start(pkt) to get the start address even if no valid L2 header > + * could be found. > + * > + * @param pkt Packet handle > + * > + * @return Pointer to the start of the packet buffer > + * > + * @see odp_packet_l2(), odp_packet_start() > + */ > +uint8_t *odp_packet_buf_addr(odp_packet_t pkt); > + > +/** > + * Get pointer to the start of the received frame > + * > + * The address of the packet buffer is not necessarily the same as the start > + * address of the received frame, e.g. an eth frame may be offset by 2 or 6 > + * bytes to ensure 32 or 64-bit alignment of the IP header. > + * Use odp_packet_l2(pkt) to get the start address of a received valid eth frame > + * > + * odp_packet_start() will always return a pointer to the start of the frame, > + * even if the frame is unrecognized and no valid L2 header could be found. > + * > + * @param pkt Packet handle > + * > + * @return Pointer to the start of the received frame > + * > + * @see odp_packet_l2(), odp_packet_buf_addr() > + */ > +uint8_t *odp_packet_start(odp_packet_t pkt); > + > +/** > + * Get pointer to the start of the L2 frame > + * > + * The L2 frame header address is not necessarily the same as the address of the > + * packet buffer, see odp_packet_buf_addr() > + * > + * @param pkt Packet handle > + * > + * @return Pointer to L2 header or NULL if not found > + * > + * @see odp_packet_buf_addr(), odp_packet_start() > + */ > +uint8_t *odp_packet_l2(odp_packet_t pkt); > + > +/** > + * Return the byte offset from the packet buffer to the L2 frame > + * > + * @param pkt Packet handle > + * > + * @return L2 byte offset or ODP_PACKET_OFFSET_INVALID if not found > + */ > +size_t odp_packet_l2_offset(odp_packet_t pkt); > + > +/** > + * Set the byte offset to the L2 frame > + * > + * @param pkt Packet handle > + * @param offset L2 byte offset > + */ > +void odp_packet_set_l2_offset(odp_packet_t pkt, size_t offset); > + > + > +/** > + * Get pointer to the start of the L3 packet > + * > + * @param pkt Packet handle > + * > + * @return Pointer to L3 packet or NULL if not found > + * > + */ > +uint8_t *odp_packet_l3(odp_packet_t pkt); > + > +/** > + * Return the byte offset from the packet buffer to the L3 packet > + * > + * @param pkt Packet handle > + * > + * @return L3 byte offset or ODP_PACKET_OFFSET_INVALID if not found > + */ > +size_t odp_packet_l3_offset(odp_packet_t pkt); > + > +/** > + * Set the byte offset to the L3 packet > + * > + * @param pkt Packet handle > + * @param offset L3 byte offset > + */ > +void odp_packet_set_l3_offset(odp_packet_t pkt, size_t offset); > + > + > +/** > + * Get pointer to the start of the L4 packet > + * > + * @param pkt Packet handle > + * > + * @return Pointer to L4 packet or NULL if not found > + * > + */ > +uint8_t *odp_packet_l4(odp_packet_t pkt); > + > +/** > + * Return the byte offset from the packet buffer to the L4 packet > + * > + * @param pkt Packet handle > + * > + * @return L4 byte offset or ODP_PACKET_OFFSET_INVALID if not found > + */ > +size_t odp_packet_l4_offset(odp_packet_t pkt); > + > +/** > + * Set the byte offset to the L4 packet > + * > + * @param pkt Packet handle > + * @param offset L4 byte offset > + */ > +void odp_packet_set_l4_offset(odp_packet_t pkt, size_t offset); > + > +/** > + * Print (debug) information about the packet > + * > + * @param pkt Packet handle > + */ > +void odp_packet_print(odp_packet_t pkt); > + > +/** > + * Copy contents and metadata from pkt_src to pkt_dst > + * Useful when creating copies of packets > + * > + * @param pkt_dst Destination packet > + * @param pkt_src Source packet > + * > + * @return 0 if successful > + */ > +int odp_packet_copy(odp_packet_t pkt_dst, odp_packet_t pkt_src); > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/include/api/odp_pktio_types.h b/platform/linux-dpdk/include/api/odp_pktio_types.h > new file mode 100644 > index 0000000..b23e6da > --- /dev/null > +++ b/platform/linux-dpdk/include/api/odp_pktio_types.h > @@ -0,0 +1,45 @@ > + > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#ifndef ODP_PKTIO_TYPES_H > +#define ODP_PKTIO_TYPES_H > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +/* We should ensure that future enum values will never overlap, otherwise > + * applications that want netmap suport might get in trouble if the odp lib > + * was not built with netmap support and there are more types define below > + */ > + > +typedef enum { > + ODP_PKTIO_TYPE_SOCKET_BASIC = 0x1, > + ODP_PKTIO_TYPE_SOCKET_MMSG, > + ODP_PKTIO_TYPE_SOCKET_MMAP, > + ODP_PKTIO_TYPE_NETMAP, > + ODP_PKTIO_TYPE_DPDK, > +} odp_pktio_type_t; > + > +#include > +#ifdef ODP_HAVE_NETMAP > +#include > +#endif > + > +typedef union odp_pktio_params_t { > + odp_pktio_type_t type; > + socket_params_t sock_params; > +#ifdef ODP_HAVE_NETMAP > + netmap_params_t nm_params; > +#endif > +} odp_pktio_params_t; > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/include/odp_buffer_internal.h b/platform/linux-dpdk/include/odp_buffer_internal.h > new file mode 100644 > index 0000000..f87ec80 > --- /dev/null > +++ b/platform/linux-dpdk/include/odp_buffer_internal.h > @@ -0,0 +1,72 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > + > +/** > + * @file > + * > + * ODP buffer descriptor - implementation internal > + */ > + > +#ifndef ODP_BUFFER_INTERNAL_H_ > +#define ODP_BUFFER_INTERNAL_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +/* TODO: move these to correct files */ > + > +typedef uint64_t odp_phys_addr_t; > + > +#define ODP_BUFFER_MAX_INDEX (ODP_BUFFER_MAX_BUFFERS - 2) > +#define ODP_BUFFER_INVALID_INDEX (ODP_BUFFER_MAX_BUFFERS - 1) > + > +#define ODP_BUFS_PER_CHUNK 16 > +#define ODP_BUFS_PER_SCATTER 4 > + > +#define ODP_BUFFER_TYPE_CHUNK 0xffff > + > + > +#define ODP_BUFFER_POOL_BITS 4 > +#define ODP_BUFFER_INDEX_BITS (32 - ODP_BUFFER_POOL_BITS) > +#define ODP_BUFFER_MAX_POOLS (1 << ODP_BUFFER_POOL_BITS) > +#define ODP_BUFFER_MAX_BUFFERS (1 << ODP_BUFFER_INDEX_BITS) > + > +typedef union odp_buffer_bits_t { > + uint32_t u32; > + odp_buffer_t handle; > + > + struct { > + uint32_t pool:ODP_BUFFER_POOL_BITS; > + uint32_t index:ODP_BUFFER_INDEX_BITS; > + }; > +} odp_buffer_bits_t; > + > + > +/* forward declaration */ > +struct odp_buffer_hdr_t; > + > + > +typedef struct rte_mbuf odp_buffer_hdr_t; > + > + > +int odp_buffer_snprint(char *str, size_t n, odp_buffer_t buf); > + > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/include/odp_buffer_pool_internal.h b/platform/linux-dpdk/include/odp_buffer_pool_internal.h > new file mode 100644 > index 0000000..1a36655 > --- /dev/null > +++ b/platform/linux-dpdk/include/odp_buffer_pool_internal.h > @@ -0,0 +1,90 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > + > +/** > + * @file > + * > + * ODP buffer pool - internal header > + */ > + > +#ifndef ODP_BUFFER_POOL_INTERNAL_H_ > +#define ODP_BUFFER_POOL_INTERNAL_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +/* for DPDK */ > +#include > + > +/* Use ticketlock instead of spinlock */ > +#define POOL_USE_TICKETLOCK > + > +/* Extra error checks */ > +/* #define POOL_ERROR_CHECK */ > + > + > +#ifdef POOL_USE_TICKETLOCK > +#include > +#else > +#include > +#endif > + > + > +struct pool_entry_s { > +#ifdef POOL_USE_TICKETLOCK > + odp_ticketlock_t lock ODP_ALIGNED_CACHE; > +#else > + odp_spinlock_t lock ODP_ALIGNED_CACHE; > +#endif > + > + uint64_t free_bufs; > + char name[ODP_BUFFER_POOL_NAME_LEN]; > + > + > + odp_buffer_pool_t pool ODP_ALIGNED_CACHE; > + uintptr_t buf_base; > + size_t buf_size; > + size_t buf_offset; > + uint64_t num_bufs; > + void *pool_base_addr; > + uint64_t pool_size; > + size_t payload_size; > + size_t payload_align; > + int buf_type; > + size_t hdr_size; > +}; > + > + > +extern void *pool_entry_ptr[]; > + > + > +static inline void *get_pool_entry(odp_buffer_pool_t pool_id) > +{ > + return pool_entry_ptr[pool_id]; > +} > + > + > +static inline odp_buffer_hdr_t *odp_buf_to_hdr(odp_buffer_t buf) > +{ > + return (odp_buffer_hdr_t *)buf; > +} > + > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/include/odp_packet_dpdk.h b/platform/linux-dpdk/include/odp_packet_dpdk.h > new file mode 100644 > index 0000000..bcbe9e8 > --- /dev/null > +++ b/platform/linux-dpdk/include/odp_packet_dpdk.h > @@ -0,0 +1,87 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#ifndef ODP_PACKET_DPDK_H > +#define ODP_PACKET_DPDK_H > + > +#include > +#include > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > + > +#define ODP_DPDK_MODE_HW 0 > +#define ODP_DPDK_MODE_SW 1 > + > +#define DPDK_BLOCKING_IO > + > +/** Packet socket using dpdk mmaped rings for both Rx and Tx */ > +typedef struct { > + odp_buffer_pool_t pool; > + > + /********************************/ > + char ifname[32]; > + uint8_t portid; > + uint16_t queueid; > +} pkt_dpdk_t; > + > +/** > + * Configure an interface to work in dpdk mode > + */ > +int setup_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk, const char *netdev, > + odp_buffer_pool_t pool); > + > +/** > + * Switch interface from dpdk mode to normal mode > + */ > +int close_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk); > + > +/** > + * Receive packets using dpdk > + */ > +int recv_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk, odp_packet_t pkt_table[], > + unsigned len); > + > +/** > + * Send packets using dpdk > + */ > +int send_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk, odp_packet_t pkt_table[], > + unsigned len); > + > +int odp_init_dpdk(void); > +#endif > diff --git a/platform/linux-dpdk/include/odp_packet_internal.h b/platform/linux-dpdk/include/odp_packet_internal.h > new file mode 100644 > index 0000000..0f798c1 > --- /dev/null > +++ b/platform/linux-dpdk/include/odp_packet_internal.h > @@ -0,0 +1,139 @@ > +/* Copyright (c) 2014, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > + > +/** > + * @file > + * > + * ODP packet descriptor - implementation internal > + */ > + > +#ifndef ODP_PACKET_INTERNAL_H_ > +#define ODP_PACKET_INTERNAL_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +#include > +#include > +#include > +#include > +#include > +#include > + > +/** > + * Packet input & protocol flags > + */ > +typedef union { > + /* All input flags */ > + uint32_t all; > + > + struct { > + /* Bitfield flags for each protocol */ > + uint32_t l2:1; /**< known L2 protocol present */ > + uint32_t l3:1; /**< known L3 protocol present */ > + uint32_t l4:1; /**< known L4 protocol present */ > + > + uint32_t eth:1; /**< Ethernet */ > + uint32_t jumbo:1; /**< Jumbo frame */ > + uint32_t vlan:1; /**< VLAN hdr found */ > + uint32_t vlan_qinq:1; /**< Stacked VLAN found, QinQ */ > + > + uint32_t arp:1; /**< ARP */ > + > + uint32_t ipv4:1; /**< IPv4 */ > + uint32_t ipv6:1; /**< IPv6 */ > + uint32_t ipfrag:1; /**< IP fragment */ > + uint32_t ipopt:1; /**< IP optional headers */ > + uint32_t ipsec:1; /**< IPSec decryption may be needed */ > + > + uint32_t udp:1; /**< UDP */ > + uint32_t tcp:1; /**< TCP */ > + uint32_t sctp:1; /**< SCTP */ > + uint32_t icmp:1; /**< ICMP */ > + }; > +} input_flags_t; > + > +ODP_ASSERT(sizeof(input_flags_t) == sizeof(uint32_t), INPUT_FLAGS_SIZE_ERROR); > + > +/** > + * Packet error flags > + */ > +typedef union { > + /* All error flags */ > + uint32_t all; > + > + struct { > + /* Bitfield flags for each detected error */ > + uint32_t frame_len:1; /**< Frame length error */ > + uint32_t l2_chksum:1; /**< L2 checksum error, checks TBD */ > + uint32_t ip_err:1; /**< IP error, checks TBD */ > + uint32_t tcp_err:1; /**< TCP error, checks TBD */ > + uint32_t udp_err:1; /**< UDP error, checks TBD */ > + }; > +} error_flags_t; > + > +ODP_ASSERT(sizeof(error_flags_t) == sizeof(uint32_t), ERROR_FLAGS_SIZE_ERROR); > + > +/** > + * Packet output flags > + */ > +typedef union { > + /* All output flags */ > + uint32_t all; > + > + struct { > + /* Bitfield flags for each output option */ > + uint32_t l4_chksum:1; /**< Request L4 checksum calculation */ > + }; > +} output_flags_t; > + > +ODP_ASSERT(sizeof(output_flags_t) == sizeof(uint32_t), OUTPUT_FLAGS_SIZE_ERROR); > + > +/** > + * Internal Packet header > + */ > +typedef struct { > + /* common buffer header */ > + odp_buffer_hdr_t buf_hdr; > + > + input_flags_t input_flags; > + error_flags_t error_flags; > + output_flags_t output_flags; > + > + uint32_t frame_offset; /**< offset to start of frame, even on error */ > + uint32_t l2_offset; /**< offset to L2 hdr, e.g. Eth */ > + uint32_t l3_offset; /**< offset to L3 hdr, e.g. IPv4, IPv6 */ > + uint32_t l4_offset; /**< offset to L4 hdr (TCP, UDP, SCTP, also ICMP) */ > + > + uint32_t frame_len; > + > + odp_pktio_t input; > + > + uint32_t pad; > + uint8_t payload[]; > + > +} odp_packet_hdr_t; > + > +/** > + * Return the packet header > + */ > +static inline odp_packet_hdr_t *odp_packet_hdr(odp_packet_t pkt) > +{ > + return (odp_packet_hdr_t *)pkt; > +} > + > +/** > + * Parse packet and set internal metadata > + */ > +void odp_packet_parse(odp_packet_t pkt, size_t len, size_t l2_offset); > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/include/odp_packet_io_internal.h b/platform/linux-dpdk/include/odp_packet_io_internal.h > new file mode 100644 > index 0000000..08abea7 > --- /dev/null > +++ b/platform/linux-dpdk/include/odp_packet_io_internal.h > @@ -0,0 +1,51 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > + > +/** > + * @file > + * > + * ODP packet IO - implementation internal > + */ > + > +#ifndef ODP_PACKET_IO_INTERNAL_H_ > +#define ODP_PACKET_IO_INTERNAL_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +#include > +#include > +#ifdef ODP_HAVE_NETMAP > +#include > +#endif > +#include > + > +struct pktio_entry { > + odp_spinlock_t lock; /**< entry spinlock */ > + int taken; /**< is entry taken(1) or free(0) */ > + odp_queue_t inq_default; /**< default input queue, if set */ > + odp_queue_t outq_default; /**< default out queue */ > + odp_pktio_params_t params; /**< pktio parameters */ > + pkt_sock_t pkt_sock; /**< using socket API for IO */ > + pkt_sock_mmap_t pkt_sock_mmap; /**< using socket mmap API for IO */ > +#ifdef ODP_HAVE_NETMAP > + pkt_netmap_t pkt_nm; /**< using netmap API for IO */ > +#endif > + pkt_dpdk_t pkt_dpdk; /**< using DPDK API for IO */ > +}; > + > +typedef union { > + struct pktio_entry s; > + uint8_t pad[ODP_CACHE_LINE_SIZE_ROUNDUP(sizeof(struct pktio_entry))]; > +} pktio_entry_t; > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif > diff --git a/platform/linux-dpdk/odp_buffer.c b/platform/linux-dpdk/odp_buffer.c > new file mode 100644 > index 0000000..e2f8942 > --- /dev/null > +++ b/platform/linux-dpdk/odp_buffer.c > @@ -0,0 +1,90 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#include > +#include > +#include > + > +#include > +#include > + > + > +void *odp_buffer_addr(odp_buffer_t buf) > +{ > + odp_buffer_hdr_t *hdr = odp_buf_to_hdr(buf); > + > + return hdr->buf_addr; > +} > + > + > +size_t odp_buffer_size(odp_buffer_t buf) > +{ > + odp_buffer_hdr_t *hdr = odp_buf_to_hdr(buf); > + > + return hdr->buf_len; > +} > + > + > +int odp_buffer_type(odp_buffer_t buf) > +{ > + odp_buffer_hdr_t *hdr = odp_buf_to_hdr(buf); > + > + return hdr->type; > +} > + > + > +int odp_buffer_is_valid(odp_buffer_t buf) > +{ > + odp_buffer_bits_t handle; > + > + handle.u32 = buf; > + > + return (handle.index != ODP_BUFFER_INVALID_INDEX); > +} > + > + > +int odp_buffer_snprint(char *str, size_t n, odp_buffer_t buf) > +{ > + odp_buffer_hdr_t *hdr; > + int len = 0; > + > + if (!odp_buffer_is_valid(buf)) { > + printf("Buffer is not valid.\n"); > + return len; > + } > + > + hdr = odp_buf_to_hdr(buf); > + > + len += snprintf(&str[len], n-len, > + "Buffer\n"); > + len += snprintf(&str[len], n-len, > + " pool %"PRIu64"\n", (int64_t) hdr->pool); > + len += snprintf(&str[len], n-len, > + " phy_addr %"PRIu64"\n", hdr->buf_physaddr); > + len += snprintf(&str[len], n-len, > + " addr %p\n", hdr->buf_addr); > + len += snprintf(&str[len], n-len, > + " size %u\n", hdr->buf_len); > + len += snprintf(&str[len], n-len, > + " ref_count %i\n", hdr->refcnt); > + len += snprintf(&str[len], n-len, > + " type %i\n", hdr->type); > + > + return len; > +} > + > + > +void odp_buffer_print(odp_buffer_t buf) > +{ > + int max_len = 512; > + char str[max_len]; > + int len; > + > + len = odp_buffer_snprint(str, max_len-1, buf); > + str[len] = 0; > + > + printf("\n%s\n", str); > +} > diff --git a/platform/linux-dpdk/odp_buffer_pool.c b/platform/linux-dpdk/odp_buffer_pool.c > new file mode 100644 > index 0000000..de90275 > --- /dev/null > +++ b/platform/linux-dpdk/odp_buffer_pool.c > @@ -0,0 +1,156 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include > +#include > + > +/* for DPDK */ > +#include > + > +#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) > +#define NB_MBUF 8192 > + > +#ifdef POOL_USE_TICKETLOCK > +#include > +#define LOCK(a) odp_ticketlock_lock(a) > +#define UNLOCK(a) odp_ticketlock_unlock(a) > +#define LOCK_INIT(a) odp_ticketlock_init(a) > +#else > +#include > +#define LOCK(a) odp_spinlock_lock(a) > +#define UNLOCK(a) odp_spinlock_unlock(a) > +#define LOCK_INIT(a) odp_spinlock_init(a) > +#endif > + > + > +#if ODP_CONFIG_BUFFER_POOLS > ODP_BUFFER_MAX_POOLS > +#error ODP_CONFIG_BUFFER_POOLS > ODP_BUFFER_MAX_POOLS > +#endif > + > +#define NULL_INDEX ((uint32_t)-1) > + > + > +typedef union pool_entry_u { > + struct pool_entry_s s; > + > + uint8_t pad[ODP_CACHE_LINE_SIZE_ROUNDUP(sizeof(struct pool_entry_s))]; > + > +} pool_entry_t; > + > + > +typedef struct pool_table_t { > + pool_entry_t pool[ODP_CONFIG_BUFFER_POOLS]; > + > +} pool_table_t; > + > + > +/* The pool table */ > +static pool_table_t *pool_tbl; > + > +/* Pool entry pointers (for inlining) */ > +void *pool_entry_ptr[ODP_CONFIG_BUFFER_POOLS]; > + > + > +int odp_buffer_pool_init_global(void) > +{ > + odp_buffer_pool_t i; > + > + pool_tbl = odp_shm_reserve("odp_buffer_pools", > + sizeof(pool_table_t), > + sizeof(pool_entry_t)); > + > + if (pool_tbl == NULL) > + return -1; > + > + memset(pool_tbl, 0, sizeof(pool_table_t)); > + > + > + for (i = 0; i < ODP_CONFIG_BUFFER_POOLS; i++) { > + /* init locks */ > + pool_entry_t *pool = &pool_tbl->pool[i]; > + LOCK_INIT(&pool->s.lock); > + pool->s.pool = i; > + > + pool_entry_ptr[i] = pool; > + } > + > + ODP_DBG("\nBuffer pool init global\n"); > + ODP_DBG(" pool_entry_s size %zu\n", sizeof(struct pool_entry_s)); > + ODP_DBG(" pool_entry_t size %zu\n", sizeof(pool_entry_t)); > + ODP_DBG(" odp_buffer_hdr_t size %zu\n", sizeof(odp_buffer_hdr_t)); > + ODP_DBG("\n"); > + > + return 0; > +} > + > + > +odp_buffer_pool_t odp_buffer_pool_create(const char *name, > + void *base_addr, uint64_t size, > + size_t buf_size, size_t buf_align, > + int buf_type) > +{ > + struct rte_mempool *pktmbuf_pool = NULL; > + ODP_DBG("odp_buffer_pool_create: %s, %lx, %u, %u, %u, %d\n", name, > + (uint64_t) base_addr, (unsigned) size, > + (unsigned) buf_size, (unsigned) buf_align, > + buf_type); > + > + pktmbuf_pool = > + rte_mempool_create(name, NB_MBUF, > + MBUF_SIZE, 32, > + sizeof(struct rte_pktmbuf_pool_private), > + rte_pktmbuf_pool_init, NULL, > + rte_pktmbuf_init, NULL, > + rte_socket_id(), 0); > + if (pktmbuf_pool == NULL) { > + ODP_ERR("Cannot init DPDK mbuf pool\n"); > + return -1; > + } > + > + return (odp_buffer_pool_t) pktmbuf_pool; > +} > + > + > +odp_buffer_pool_t odp_buffer_pool_lookup(const char *name) > +{ > + struct rte_mempool *mp = NULL; > + > + mp = rte_mempool_lookup(name); > + if (mp == NULL) > + return ODP_BUFFER_POOL_INVALID; > + > + return (odp_buffer_pool_t)mp; > +} > + > + > +odp_buffer_t odp_buffer_alloc(odp_buffer_pool_t pool_id) > +{ > + return (odp_buffer_t)rte_pktmbuf_alloc((struct rte_mempool *)pool_id); > +} > + > + > +void odp_buffer_free(odp_buffer_t buf) > +{ > + rte_pktmbuf_free((struct rte_mbuf *)buf); > +} > + > + > +void odp_buffer_pool_print(odp_buffer_pool_t pool_id) > +{ > + rte_mempool_dump((const struct rte_mempool *)pool_id); > +} > diff --git a/platform/linux-dpdk/odp_init.c b/platform/linux-dpdk/odp_init.c > new file mode 100644 > index 0000000..ecc2066 > --- /dev/null > +++ b/platform/linux-dpdk/odp_init.c > @@ -0,0 +1,113 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#include > +#include > +#include > +#include > + > +int odp_init_dpdk(void) > +{ > + int test_argc = 5; > + char *test_argv[6]; > + int core_count, i, num_cores = 0; > + char core_mask[8]; > + > + core_count = odp_sys_core_count(); > + for (i = 0; i < core_count; i++) > + num_cores += (0x1 << i); > + sprintf(core_mask, "%x", num_cores); > + > + test_argv[0] = malloc(sizeof("odp_dpdk")); > + strcpy(test_argv[0], "odp_dpdk"); > + test_argv[1] = malloc(sizeof("-c")); > + strcpy(test_argv[1], "-c"); > + test_argv[2] = malloc(sizeof(core_mask)); > + strcpy(test_argv[2], core_mask); > + test_argv[3] = malloc(sizeof("-n")); > + strcpy(test_argv[3], "-n"); > + test_argv[4] = malloc(sizeof("3")); > + strcpy(test_argv[4], "3"); > + > + if (rte_eal_init(test_argc, (char **)test_argv) < 0) { > + ODP_ERR("Cannot init the Intel DPDK EAL!"); > + return -1; > + } > + > + if (rte_pmd_init_all() < 0) { > + ODP_ERR("Cannot init pmd\n"); > + return -1; > + } > + > + if (rte_eal_pci_probe() < 0) { > + ODP_ERR("Cannot probe PCI\n"); > + return -1; > + } > + > + return 0; > +} > + > +int odp_init_global(void) > +{ > + odp_thread_init_global(); > + > + odp_system_info_init(); > + > + if (odp_init_dpdk()) { > + ODP_ERR("ODP dpdk init failed.\n"); > + return -1; > + } > + > + if (odp_shm_init_global()) { > + ODP_ERR("ODP shm init failed.\n"); > + return -1; > + } > + > + if (odp_buffer_pool_init_global()) { > + ODP_ERR("ODP buffer pool init failed.\n"); > + return -1; > + } > + > + if (odp_queue_init_global()) { > + ODP_ERR("ODP queue init failed.\n"); > + return -1; > + } > + > + if (odp_schedule_init_global()) { > + ODP_ERR("ODP schedule init failed.\n"); > + return -1; > + } > + > + if (odp_pktio_init_global()) { > + ODP_ERR("ODP packet io init failed.\n"); > + return -1; > + } > + > + if (odp_timer_init_global()) { > + ODP_ERR("ODP timer init failed.\n"); > + return -1; > + } > + > + return 0; > +} > + > + > +int odp_init_local(int thr_id) > +{ > + odp_thread_init_local(thr_id); > + > + if (odp_pktio_init_local()) { > + ODP_ERR("ODP packet io local init failed.\n"); > + return -1; > + } > + > + if (odp_schedule_init_local()) { > + ODP_ERR("ODP schedule local init failed.\n"); > + return -1; > + } > + > + return 0; > +} > diff --git a/platform/linux-dpdk/odp_linux.c b/platform/linux-dpdk/odp_linux.c > new file mode 100644 > index 0000000..067bd99 > --- /dev/null > +++ b/platform/linux-dpdk/odp_linux.c > @@ -0,0 +1,96 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#ifndef _GNU_SOURCE > +#define _GNU_SOURCE > +#endif > +#include > + > +#include > +#include > +#include > +#include > + > +#include > +#include > +#include > +#include > +#include > + > +#include > + > +typedef struct { > + int thr_id; > + void *(*start_routine) (void *); > + void *arg; > + > +} odp_start_args_t; > + > + > +static void *odp_run_start_routine(void *arg) > +{ > + odp_start_args_t *start_args = arg; > + > + /* ODP thread local init */ > + odp_init_local(start_args->thr_id); > + > + return start_args->start_routine(start_args->arg); > +} > + > + > +void odp_linux_pthread_create(odp_linux_pthread_t *thread_tbl, int num, > + int first_core, void *(*start_routine) (void *), void *arg) > +{ > + int i; > + cpu_set_t cpu_set; > + odp_start_args_t *start_args; > + int core_count; > + int cpu; > + > + (void) cpu_set; > + (void) thread_tbl; > + > + core_count = odp_sys_core_count(); > + > + assert((first_core >= 0) && (first_core < core_count)); > + assert((num >= 0) && (num <= core_count)); > + > + for (i = 0; i < num; i++) { > + cpu = (first_core + i) % core_count; > + > + start_args = malloc(sizeof(odp_start_args_t)); > + memset(start_args, 0, sizeof(odp_start_args_t)); > + start_args->start_routine = start_routine; > + start_args->arg = arg; > + > + odp_thread_create(cpu); > + start_args->thr_id = cpu; > + /* If not master core */ > + if (cpu != 0) { > + rte_eal_remote_launch( > + (int(*)(void *))odp_run_start_routine, > + start_args, cpu); > + } else { > + lcore_config[cpu].ret = (int)(uint64_t) > + odp_run_start_routine(start_args); > + lcore_config[cpu].state = FINISHED; > + } > + } > +} > + > + > +void odp_linux_pthread_join(odp_linux_pthread_t *thread_tbl, int num) > +{ > + uint32_t lcore_id; > + > + (void) thread_tbl; > + (void) num; > + > + RTE_LCORE_FOREACH_SLAVE(lcore_id) { > + if (rte_eal_wait_lcore(lcore_id) < 0) > + return; > + } > +} > diff --git a/platform/linux-dpdk/odp_packet.c b/platform/linux-dpdk/odp_packet.c > new file mode 100644 > index 0000000..c34e626 > --- /dev/null > +++ b/platform/linux-dpdk/odp_packet.c > @@ -0,0 +1,374 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#include > +#include > +#include > +#include > + > +#include > +#include > + > +#include > +#include > + > +static inline uint8_t parse_ipv4(odp_packet_hdr_t *pkt_hdr, odp_ipv4hdr_t *ipv4, > + size_t *offset_out); > +static inline uint8_t parse_ipv6(odp_packet_hdr_t *pkt_hdr, odp_ipv6hdr_t *ipv6, > + size_t *offset_out); > + > +void odp_packet_init(odp_packet_t pkt) > +{ > + odp_packet_hdr_t *const pkt_hdr = odp_packet_hdr(pkt); > + const size_t start_offset = ODP_FIELD_SIZEOF(odp_packet_hdr_t, buf_hdr); > + uint8_t *start; > + size_t len; > + > + start = (uint8_t *)pkt_hdr + start_offset; > + len = ODP_OFFSETOF(odp_packet_hdr_t, payload) - start_offset; > + memset(start, 0, len); > + > + pkt_hdr->l2_offset = (uint32_t) ODP_PACKET_OFFSET_INVALID; > + pkt_hdr->l3_offset = (uint32_t) ODP_PACKET_OFFSET_INVALID; > + pkt_hdr->l4_offset = (uint32_t) ODP_PACKET_OFFSET_INVALID; > +} > + > +odp_packet_t odp_packet_from_buffer(odp_buffer_t buf) > +{ > + return (odp_packet_t)buf; > +} > + > +odp_buffer_t odp_buffer_from_packet(odp_packet_t pkt) > +{ > + return (odp_buffer_t)pkt; > +} > + > +void odp_packet_set_len(odp_packet_t pkt, size_t len) > +{ > + /* for rte_pktmbuf */ > + odp_buffer_hdr_t *buf_hdr = odp_buf_to_hdr(odp_buffer_from_packet(pkt)); > + buf_hdr->pkt.data_len = len; > + > + odp_packet_hdr(pkt)->frame_len = len; > +} > + > +size_t odp_packet_get_len(odp_packet_t pkt) > +{ > + return odp_packet_hdr(pkt)->frame_len; > +} > + > +uint8_t *odp_packet_buf_addr(odp_packet_t pkt) > +{ > + return odp_buffer_addr(odp_buffer_from_packet(pkt)); > +} > + > +uint8_t *odp_packet_start(odp_packet_t pkt) > +{ > + return odp_packet_buf_addr(pkt) + odp_packet_hdr(pkt)->frame_offset; > +} > + > + > +uint8_t *odp_packet_l2(odp_packet_t pkt) > +{ > + const size_t offset = odp_packet_l2_offset(pkt); > + > + if (odp_unlikely(offset == ODP_PACKET_OFFSET_INVALID)) > + return NULL; > + > + return odp_packet_buf_addr(pkt) + offset; > +} > + > +size_t odp_packet_l2_offset(odp_packet_t pkt) > +{ > + return odp_packet_hdr(pkt)->l2_offset; > +} > + > +void odp_packet_set_l2_offset(odp_packet_t pkt, size_t offset) > +{ > + odp_packet_hdr(pkt)->l2_offset = offset; > +} > + > +uint8_t *odp_packet_l3(odp_packet_t pkt) > +{ > + const size_t offset = odp_packet_l3_offset(pkt); > + > + if (odp_unlikely(offset == ODP_PACKET_OFFSET_INVALID)) > + return NULL; > + > + return odp_packet_buf_addr(pkt) + offset; > +} > + > +size_t odp_packet_l3_offset(odp_packet_t pkt) > +{ > + return odp_packet_hdr(pkt)->l3_offset; > +} > + > +void odp_packet_set_l3_offset(odp_packet_t pkt, size_t offset) > +{ > + odp_packet_hdr(pkt)->l3_offset = offset; > +} > + > +uint8_t *odp_packet_l4(odp_packet_t pkt) > +{ > + const size_t offset = odp_packet_l4_offset(pkt); > + > + if (odp_unlikely(offset == ODP_PACKET_OFFSET_INVALID)) > + return NULL; > + > + return odp_packet_buf_addr(pkt) + offset; > +} > + > +size_t odp_packet_l4_offset(odp_packet_t pkt) > +{ > + return odp_packet_hdr(pkt)->l4_offset; > +} > + > +void odp_packet_set_l4_offset(odp_packet_t pkt, size_t offset) > +{ > + odp_packet_hdr(pkt)->l4_offset = offset; > +} > + > +/** > + * Simple packet parser: eth, VLAN, IP, TCP/UDP/ICMP > + * > + * Internal function: caller is resposible for passing only valid packet handles > + * , lengths and offsets (usually done&called in packet input). > + * > + * @param pkt Packet handle > + * @param len Packet length in bytes > + * @param frame_offset Byte offset to L2 header > + */ > +void odp_packet_parse(odp_packet_t pkt, size_t len, size_t frame_offset) > +{ > + odp_packet_hdr_t *const pkt_hdr = odp_packet_hdr(pkt); > + odp_ethhdr_t *eth; > + odp_vlanhdr_t *vlan; > + odp_ipv4hdr_t *ipv4; > + odp_ipv6hdr_t *ipv6; > + uint16_t ethtype; > + size_t offset = 0; > + uint8_t ip_proto = 0; > + > + pkt_hdr->input_flags.eth = 1; > + pkt_hdr->frame_offset = frame_offset; > + pkt_hdr->frame_len = len; > + > + if (odp_unlikely(len < ODP_ETH_LEN_MIN)) { > + pkt_hdr->error_flags.frame_len = 1; > + return; > + } else if (len > ODP_ETH_LEN_MAX) { > + pkt_hdr->input_flags.jumbo = 1; > + } > + > + /* Assume valid L2 header, no CRC/FCS check in SW */ > + pkt_hdr->input_flags.l2 = 1; > + pkt_hdr->l2_offset = frame_offset; > + > + eth = (odp_ethhdr_t *)odp_packet_start(pkt); > + ethtype = odp_be_to_cpu_16(eth->type); > + vlan = (odp_vlanhdr_t *)ð->type; > + > + if (ethtype == ODP_ETHTYPE_VLAN_OUTER) { > + pkt_hdr->input_flags.vlan_qinq = 1; > + ethtype = odp_be_to_cpu_16(vlan->tpid); > + offset += sizeof(odp_vlanhdr_t); > + vlan = &vlan[1]; > + } > + > + if (ethtype == ODP_ETHTYPE_VLAN) { > + pkt_hdr->input_flags.vlan = 1; > + ethtype = odp_be_to_cpu_16(vlan->tpid); > + offset += sizeof(odp_vlanhdr_t); > + } > + > + /* Set l3_offset+flag only for known ethtypes */ > + switch (ethtype) { > + case ODP_ETHTYPE_IPV4: > + pkt_hdr->input_flags.ipv4 = 1; > + pkt_hdr->input_flags.l3 = 1; > + pkt_hdr->l3_offset = frame_offset + ODP_ETHHDR_LEN + offset; > + ipv4 = (odp_ipv4hdr_t *)odp_packet_l3(pkt); > + ip_proto = parse_ipv4(pkt_hdr, ipv4, &offset); > + break; > + case ODP_ETHTYPE_IPV6: > + pkt_hdr->input_flags.ipv6 = 1; > + pkt_hdr->input_flags.l3 = 1; > + pkt_hdr->l3_offset = frame_offset + ODP_ETHHDR_LEN + offset; > + ipv6 = (odp_ipv6hdr_t *)odp_packet_l3(pkt); > + ip_proto = parse_ipv6(pkt_hdr, ipv6, &offset); > + break; > + case ODP_ETHTYPE_ARP: > + pkt_hdr->input_flags.arp = 1; > + /* fall through */ > + default: > + ip_proto = 0; > + break; > + } > + > + switch (ip_proto) { > + case ODP_IPPROTO_UDP: > + pkt_hdr->input_flags.udp = 1; > + pkt_hdr->input_flags.l4 = 1; > + pkt_hdr->l4_offset = pkt_hdr->l3_offset + offset; > + break; > + case ODP_IPPROTO_TCP: > + pkt_hdr->input_flags.tcp = 1; > + pkt_hdr->input_flags.l4 = 1; > + pkt_hdr->l4_offset = pkt_hdr->l3_offset + offset; > + break; > + case ODP_IPPROTO_SCTP: > + pkt_hdr->input_flags.sctp = 1; > + pkt_hdr->input_flags.l4 = 1; > + pkt_hdr->l4_offset = pkt_hdr->l3_offset + offset; > + break; > + case ODP_IPPROTO_ICMP: > + pkt_hdr->input_flags.icmp = 1; > + pkt_hdr->input_flags.l4 = 1; > + pkt_hdr->l4_offset = pkt_hdr->l3_offset + offset; > + break; > + default: > + /* 0 or unhandled IP protocols, don't set L4 flag+offset */ > + if (pkt_hdr->input_flags.ipv6) { > + /* IPv6 next_hdr is not L4, mark as IP-option instead */ > + pkt_hdr->input_flags.ipopt = 1; > + } > + break; > + } > +} > + > +static inline uint8_t parse_ipv4(odp_packet_hdr_t *pkt_hdr, odp_ipv4hdr_t *ipv4, > + size_t *offset_out) > +{ > + uint8_t ihl; > + uint16_t frag_offset; > + > + ihl = ODP_IPV4HDR_IHL(ipv4->ver_ihl); > + if (odp_unlikely(ihl < ODP_IPV4HDR_IHL_MIN)) { > + pkt_hdr->error_flags.ip_err = 1; > + return 0; > + } > + > + if (odp_unlikely(ihl > ODP_IPV4HDR_IHL_MIN)) { > + pkt_hdr->input_flags.ipopt = 1; > + return 0; > + } > + > + /* A packet is a fragment if: > + * "more fragments" flag is set (all fragments except the last) > + * OR > + * "fragment offset" field is nonzero (all fragments except the first) > + */ > + frag_offset = odp_be_to_cpu_16(ipv4->frag_offset); > + if (odp_unlikely(ODP_IPV4HDR_IS_FRAGMENT(frag_offset))) { > + pkt_hdr->input_flags.ipfrag = 1; > + return 0; > + } > + > + if (ipv4->proto == ODP_IPPROTO_ESP || > + ipv4->proto == ODP_IPPROTO_AH) { > + pkt_hdr->input_flags.ipsec = 1; > + return 0; > + } > + > + /* Set pkt_hdr->input_flags.ipopt when checking L4 hdrs after return */ > + > + *offset_out = sizeof(uint32_t) * ihl; > + return ipv4->proto; > +} > + > +static inline uint8_t parse_ipv6(odp_packet_hdr_t *pkt_hdr, odp_ipv6hdr_t *ipv6, > + size_t *offset_out) > +{ > + if (ipv6->next_hdr == ODP_IPPROTO_ESP || > + ipv6->next_hdr == ODP_IPPROTO_AH) { > + pkt_hdr->input_flags.ipopt = 1; > + pkt_hdr->input_flags.ipsec = 1; > + return 0; > + } > + > + if (odp_unlikely(ipv6->next_hdr == ODP_IPPROTO_FRAG)) { > + pkt_hdr->input_flags.ipopt = 1; > + pkt_hdr->input_flags.ipfrag = 1; > + return 0; > + } > + > + /* Don't step through more extensions */ > + *offset_out = ODP_IPV6HDR_LEN; > + return ipv6->next_hdr; > +} > + > +void odp_packet_print(odp_packet_t pkt) > +{ > + int max_len = 512; > + char str[max_len]; > + int len = 0; > + int n = max_len-1; > + odp_packet_hdr_t *hdr = odp_packet_hdr(pkt); > + > + len += snprintf(&str[len], n-len, "Packet "); > + len += odp_buffer_snprint(&str[len], n-len, (odp_buffer_t) pkt); > + len += snprintf(&str[len], n-len, > + " input_flags 0x%x\n", hdr->input_flags.all); > + len += snprintf(&str[len], n-len, > + " error_flags 0x%x\n", hdr->error_flags.all); > + len += snprintf(&str[len], n-len, > + " output_flags 0x%x\n", hdr->output_flags.all); > + len += snprintf(&str[len], n-len, > + " frame_offset %u\n", hdr->frame_offset); > + len += snprintf(&str[len], n-len, > + " l2_offset %u\n", hdr->l2_offset); > + len += snprintf(&str[len], n-len, > + " l3_offset %u\n", hdr->l3_offset); > + len += snprintf(&str[len], n-len, > + " l4_offset %u\n", hdr->l4_offset); > + len += snprintf(&str[len], n-len, > + " frame_len %u\n", hdr->frame_len); > + len += snprintf(&str[len], n-len, > + " input %u\n", hdr->input); > + str[len] = '\0'; > + > + printf("\n%s\n", str); > +} > + > +int odp_packet_copy(odp_packet_t pkt_dst, odp_packet_t pkt_src) > +{ > + odp_packet_hdr_t *const pkt_hdr_dst = odp_packet_hdr(pkt_dst); > + odp_packet_hdr_t *const pkt_hdr_src = odp_packet_hdr(pkt_src); > + const size_t start_offset = ODP_FIELD_SIZEOF(odp_packet_hdr_t, buf_hdr); > + uint8_t *start_src; > + uint8_t *start_dst; > + size_t len; > + > + if (pkt_dst == ODP_PACKET_INVALID || pkt_src == ODP_PACKET_INVALID) > + return -1; > + > + /* if (pkt_hdr_dst->buf_hdr.size < */ > + /* pkt_hdr_src->frame_len + pkt_hdr_src->frame_offset) */ > + if (pkt_hdr_dst->buf_hdr.buf_len < > + pkt_hdr_src->frame_len + pkt_hdr_src->frame_offset) > + return -1; > + > + /* Copy packet header */ > + start_dst = (uint8_t *)pkt_hdr_dst + start_offset; > + start_src = (uint8_t *)pkt_hdr_src + start_offset; > + len = ODP_OFFSETOF(odp_packet_hdr_t, payload) - start_offset; > + memcpy(start_dst, start_src, len); > + > + /* Copy frame payload */ > + start_dst = (uint8_t *)odp_packet_start(pkt_dst); > + start_src = (uint8_t *)odp_packet_start(pkt_src); > + len = pkt_hdr_src->frame_len; > + memcpy(start_dst, start_src, len); > + > + /* Copy useful things from the buffer header */ > + /* pkt_hdr_dst->buf_hdr.cur_offset = pkt_hdr_src->buf_hdr.cur_offset; */ > + > + /* Create a copy of the scatter list */ > + /* odp_buffer_copy_scatter(odp_buffer_from_packet(pkt_dst), */ > + /* odp_buffer_from_packet(pkt_src)); */ > + > + return 0; > +} > diff --git a/platform/linux-dpdk/odp_packet_dpdk.c b/platform/linux-dpdk/odp_packet_dpdk.c > new file mode 100644 > index 0000000..31bfa30 > --- /dev/null > +++ b/platform/linux-dpdk/odp_packet_dpdk.c > @@ -0,0 +1,189 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#define _GNU_SOURCE > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include > +#include > + > +#include > +#include > + > +#include > +#include > + > +/* > + * RX and TX Prefetch, Host, and Write-back threshold values should be > + * carefully set for optimal performance. Consult the network > + * controller's datasheet and supporting DPDK documentation for guidance > + * on how these parameters should be set. > + */ > +#define RX_PTHRESH 8 /**< Default values of RX prefetch threshold reg. */ > +#define RX_HTHRESH 8 /**< Default values of RX host threshold reg. */ > +#define RX_WTHRESH 4 /**< Default values of RX write-back threshold reg. */ > + > +/* > + * These default values are optimized for use with the Intel(R) 82599 10 GbE > + * Controller and the DPDK ixgbe PMD. Consider using other values for other > + * network controllers and/or network drivers. > + */ > +#define TX_PTHRESH 36 /**< Default values of TX prefetch threshold reg. */ > +#define TX_HTHRESH 0 /**< Default values of TX host threshold reg. */ > +#define TX_WTHRESH 0 /**< Default values of TX write-back threshold reg. */ > + > +#define MAX_PKT_BURST 16 > +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ > +#define RTE_TEST_RX_DESC_DEFAULT 128 > +#define RTE_TEST_TX_DESC_DEFAULT 512 > +static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT; > +static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT; > + > +static const struct rte_eth_conf port_conf = { > + .rxmode = { > + .split_hdr_size = 0, > + .header_split = 0, /**< Header Split disabled */ > + .hw_ip_checksum = 0, /**< IP checksum offload disabled */ > + .hw_vlan_filter = 0, /**< VLAN filtering disabled */ > + .jumbo_frame = 0, /**< Jumbo Frame Support disabled */ > + .hw_strip_crc = 0, /**< CRC stripped by hardware */ > + }, > + .txmode = { > + .mq_mode = ETH_MQ_TX_NONE, > + }, > +}; > + > +static const struct rte_eth_rxconf rx_conf = { > + .rx_thresh = { > + .pthresh = RX_PTHRESH, > + .hthresh = RX_HTHRESH, > + .wthresh = RX_WTHRESH, > + }, > +}; > + > +static const struct rte_eth_txconf tx_conf = { > + .tx_thresh = { > + .pthresh = TX_PTHRESH, > + .hthresh = TX_HTHRESH, > + .wthresh = TX_WTHRESH, > + }, > + .tx_free_thresh = 0, /* Use PMD default values */ > + .tx_rs_thresh = 0, /* Use PMD default values */ > + /* > + * As the example won't handle mult-segments and offload cases, > + * set the flag by default. > + */ > + .txq_flags = ETH_TXQ_FLAGS_NOMULTSEGS | ETH_TXQ_FLAGS_NOOFFLOADS, > +}; > + > +int setup_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk, const char *netdev, > + odp_buffer_pool_t pool) > +{ > + ODP_DBG("setup_pkt_dpdk\n"); > + > + static struct ether_addr eth_addr[RTE_MAX_ETHPORTS]; > + uint8_t portid = 0; > + uint16_t queueid = 0; > + int ret; > + printf("dpdk netdev: %s\n", netdev); > + printf("dpdk pool: %lx\n", pool); > + > + portid = atoi(netdev); > + pkt_dpdk->portid = portid; > + pkt_dpdk->queueid = queueid; > + pkt_dpdk->pool = pool; > + printf("dpdk portid: %u\n", portid); > + > + fflush(stdout); > + ret = rte_eth_dev_configure(portid, 1, 1, &port_conf); > + if (ret < 0) > + ODP_ERR("Cannot configure device: err=%d, port=%u\n", > + ret, (unsigned) portid); > + > + rte_eth_macaddr_get(portid, ð_addr[portid]); > + ODP_DBG("Port %u, MAC address: %02X:%02X:%02X:%02X:%02X:%02X\n\n", > + (unsigned) portid, > + eth_addr[portid].addr_bytes[0], > + eth_addr[portid].addr_bytes[1], > + eth_addr[portid].addr_bytes[2], > + eth_addr[portid].addr_bytes[3], > + eth_addr[portid].addr_bytes[4], > + eth_addr[portid].addr_bytes[5]); > + > + /* init one RX queue on each port */ > + fflush(stdout); > + ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd, > + rte_eth_dev_socket_id(portid), &rx_conf, > + (struct rte_mempool *)pool); > + if (ret < 0) > + ODP_ERR("rte_eth_rx_queue_setup:err=%d, port=%u\n", > + ret, (unsigned) portid); > + ODP_DBG("dpdk rx queue setup done\n"); > + > + /* init one TX queue on each port */ > + fflush(stdout); > + ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd, > + rte_eth_dev_socket_id(portid), &tx_conf); > + if (ret < 0) > + ODP_ERR("rte_eth_tx_queue_setup:err=%d, port=%u\n", > + ret, (unsigned) portid); > + ODP_DBG("dpdk tx queue setup done\n"); > + > + /* Start device */ > + ret = rte_eth_dev_start(portid); > + if (ret < 0) > + ODP_ERR("rte_eth_dev_start:err=%d, port=%u\n", > + ret, (unsigned) portid); > + ODP_DBG("dpdk setup done\n\n"); > + > + > + return 0; > +} > + > +int close_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk) > +{ > + ODP_DBG("close pkt_dpdk, %u\n", pkt_dpdk->portid); > + > + return 0; > +} > + > +int recv_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk, odp_packet_t pkt_table[], > + unsigned len) > +{ > + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; > + uint16_t nb_rx, i = 0; > + > + memset(pkts_burst, 0 , sizeof(pkts_burst)); > + nb_rx = rte_eth_rx_burst((uint8_t)pkt_dpdk->portid, > + (uint16_t)pkt_dpdk->queueid, > + (struct rte_mbuf **)pkts_burst, (uint16_t)len); > + for (i = 0; i < nb_rx; i++) > + pkt_table[i] = (odp_packet_t)pkts_burst[i]; > + return nb_rx; > +} > + > +int send_pkt_dpdk(pkt_dpdk_t * const pkt_dpdk, odp_packet_t pkt_table[], > + unsigned len) > +{ > + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; > + uint16_t i; > + > + for (i = 0; i < len; i++) > + pkts_burst[i] = (struct rte_mbuf *)pkt_table[i]; > + return rte_eth_tx_burst((uint8_t)pkt_dpdk->portid, > + (uint16_t)pkt_dpdk->queueid, > + (struct rte_mbuf **)pkts_burst, (uint16_t)len); > +} > diff --git a/platform/linux-dpdk/odp_packet_io.c b/platform/linux-dpdk/odp_packet_io.c > new file mode 100644 > index 0000000..abea0ec > --- /dev/null > +++ b/platform/linux-dpdk/odp_packet_io.c > @@ -0,0 +1,561 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#ifdef ODP_HAVE_NETMAP > +#include > +#endif > +#include > +#include > +#include > +#include > +#include > + > +#include > +#ifdef ODP_HAVE_NETMAP > +#include > +#endif > + > +#include > + > +typedef struct { > + pktio_entry_t entries[ODP_CONFIG_PKTIO_ENTRIES]; > +} pktio_table_t; > + > +static pktio_table_t *pktio_tbl; > + > + > +static pktio_entry_t *get_entry(odp_pktio_t id) > +{ > + if (odp_unlikely(id == ODP_PKTIO_INVALID || > + id > ODP_CONFIG_PKTIO_ENTRIES)) > + return NULL; > + > + return &pktio_tbl->entries[id - 1]; > +} > + > +int odp_pktio_init_global(void) > +{ > + char name[ODP_QUEUE_NAME_LEN]; > + pktio_entry_t *pktio_entry; > + queue_entry_t *queue_entry; > + odp_queue_t qid; > + int id; > + > + pktio_tbl = odp_shm_reserve("odp_pktio_entries", > + sizeof(pktio_table_t), > + sizeof(pktio_entry_t)); > + if (pktio_tbl == NULL) > + return -1; > + > + memset(pktio_tbl, 0, sizeof(pktio_table_t)); > + > + for (id = 1; id <= ODP_CONFIG_PKTIO_ENTRIES; ++id) { > + pktio_entry = get_entry(id); > + > + odp_spinlock_init(&pktio_entry->s.lock); > + > + /* Create a default output queue for each pktio resource */ > + snprintf(name, sizeof(name), "%i-pktio_outq_default", (int)id); > + name[ODP_QUEUE_NAME_LEN-1] = '\0'; > + > + qid = odp_queue_create(name, ODP_QUEUE_TYPE_PKTOUT, NULL); > + if (qid == ODP_QUEUE_INVALID) > + return -1; > + pktio_entry->s.outq_default = qid; > + > + queue_entry = queue_to_qentry(qid); > + queue_entry->s.pktout = id; > + } > + > + return 0; > +} > + > +int odp_pktio_init_local(void) > +{ > + return 0; > +} > + > +static int is_free(pktio_entry_t *entry) > +{ > + return (entry->s.taken == 0); > +} > + > +static void set_free(pktio_entry_t *entry) > +{ > + entry->s.taken = 0; > +} > + > +static void set_taken(pktio_entry_t *entry) > +{ > + entry->s.taken = 1; > +} > + > +static void lock_entry(pktio_entry_t *entry) > +{ > + odp_spinlock_lock(&entry->s.lock); > +} > + > +static void unlock_entry(pktio_entry_t *entry) > +{ > + odp_spinlock_unlock(&entry->s.lock); > +} > + > +static void init_pktio_entry(pktio_entry_t *entry, odp_pktio_params_t *params) > +{ > + set_taken(entry); > + entry->s.inq_default = ODP_QUEUE_INVALID; > + switch (params->type) { > + case ODP_PKTIO_TYPE_SOCKET_BASIC: > + case ODP_PKTIO_TYPE_SOCKET_MMSG: > + case ODP_PKTIO_TYPE_SOCKET_MMAP: > + memset(&entry->s.pkt_sock, 0, sizeof(entry->s.pkt_sock)); > + memset(&entry->s.pkt_sock_mmap, 0, > + sizeof(entry->s.pkt_sock_mmap)); > + break; > +#ifdef ODP_HAVE_NETMAP > + case ODP_PKTIO_TYPE_NETMAP: > + memset(&entry->s.pkt_nm, 0, sizeof(entry->s.pkt_nm)); > + break; > +#endif > + case ODP_PKTIO_TYPE_DPDK: > + memset(&entry->s.pkt_dpdk, 0, sizeof(entry->s.pkt_dpdk)); > + break; > + default: > + ODP_ERR("Packet I/O type not supported. Please recompile\n"); > + break; > + } > + /* Save pktio parameters, type is the most useful */ > + memcpy(&entry->s.params, params, sizeof(*params)); > +} > + > +static odp_pktio_t alloc_lock_pktio_entry(odp_pktio_params_t *params) > +{ > + odp_pktio_t id; > + pktio_entry_t *entry; > + int i; > + > + for (i = 0; i < ODP_CONFIG_PKTIO_ENTRIES; ++i) { > + entry = &pktio_tbl->entries[i]; > + if (is_free(entry)) { > + lock_entry(entry); > + if (is_free(entry)) { > + init_pktio_entry(entry, params); > + id = i + 1; > + return id; /* return with entry locked! */ > + } > + unlock_entry(entry); > + } > + } > + > + return ODP_PKTIO_INVALID; > +} > + > +static int free_pktio_entry(odp_pktio_t id) > +{ > + pktio_entry_t *entry = get_entry(id); > + > + if (entry == NULL) > + return -1; > + > + set_free(entry); > + > + return 0; > +} > + > +odp_pktio_t odp_pktio_open(const char *dev, odp_buffer_pool_t pool, > + odp_pktio_params_t *params) > +{ > + odp_pktio_t id; > + pktio_entry_t *pktio_entry; > + int res; > + > + if (params == NULL) { > + ODP_ERR("Invalid pktio params\n"); > + return ODP_PKTIO_INVALID; > + } > + > + switch (params->type) { > + case ODP_PKTIO_TYPE_SOCKET_BASIC: > + case ODP_PKTIO_TYPE_SOCKET_MMSG: > + case ODP_PKTIO_TYPE_SOCKET_MMAP: > + ODP_DBG("Allocating socket pktio\n"); > + break; > +#ifdef ODP_HAVE_NETMAP > + case ODP_PKTIO_TYPE_NETMAP: > + ODP_DBG("Allocating netmap pktio\n"); > + break; > +#endif > + case ODP_PKTIO_TYPE_DPDK: > + ODP_DBG("Allocating dpdk pktio\n"); > + break; > + default: > + ODP_ERR("Invalid pktio type: %02x\n", params->type); > + return ODP_PKTIO_INVALID; > + } > + > + id = alloc_lock_pktio_entry(params); > + if (id == ODP_PKTIO_INVALID) { > + ODP_ERR("No resources available.\n"); > + return ODP_PKTIO_INVALID; > + } > + /* if successful, alloc_pktio_entry() returns with the entry locked */ > + > + pktio_entry = get_entry(id); > + > + switch (params->type) { > + case ODP_PKTIO_TYPE_SOCKET_BASIC: > + case ODP_PKTIO_TYPE_SOCKET_MMSG: > + res = setup_pkt_sock(&pktio_entry->s.pkt_sock, dev, pool); > + if (res == -1) { > + close_pkt_sock(&pktio_entry->s.pkt_sock); > + free_pktio_entry(id); > + id = ODP_PKTIO_INVALID; > + } > + break; > + case ODP_PKTIO_TYPE_SOCKET_MMAP: > + res = setup_pkt_sock_mmap(&pktio_entry->s.pkt_sock_mmap, dev, > + pool, params->sock_params.fanout); > + if (res == -1) { > + close_pkt_sock_mmap(&pktio_entry->s.pkt_sock_mmap); > + free_pktio_entry(id); > + id = ODP_PKTIO_INVALID; > + } > + break; > +#ifdef ODP_HAVE_NETMAP > + case ODP_PKTIO_TYPE_NETMAP: > + > + res = setup_pkt_netmap(&pktio_entry->s.pkt_nm, dev, > + pool, ¶ms->nm_params); > + if (res == -1) { > + close_pkt_netmap(&pktio_entry->s.pkt_nm); > + free_pktio_entry(id); > + id = ODP_PKTIO_INVALID; > + } > + break; > +#endif > + case ODP_PKTIO_TYPE_DPDK: > + res = setup_pkt_dpdk(&pktio_entry->s.pkt_dpdk, dev, pool); > + if (res == -1) { > + close_pkt_dpdk(&pktio_entry->s.pkt_dpdk); > + free_pktio_entry(id); > + id = ODP_PKTIO_INVALID; > + } > + break; > + default: > + free_pktio_entry(id); > + id = ODP_PKTIO_INVALID; > + ODP_ERR("Invalid pktio type. Please recompile.\n"); > + break; > + } > + > + unlock_entry(pktio_entry); > + return id; > +} > + > +int odp_pktio_close(odp_pktio_t id) > +{ > + pktio_entry_t *entry; > + int res = -1; > + > + entry = get_entry(id); > + if (entry == NULL) > + return -1; > + > + lock_entry(entry); > + if (!is_free(entry)) { > + switch (entry->s.params.type) { > + case ODP_PKTIO_TYPE_SOCKET_BASIC: > + case ODP_PKTIO_TYPE_SOCKET_MMSG: > + res = close_pkt_sock(&entry->s.pkt_sock); > + break; > + case ODP_PKTIO_TYPE_SOCKET_MMAP: > + res = close_pkt_sock_mmap(&entry->s.pkt_sock_mmap); > + break; > +#ifdef ODP_HAVE_NETMAP > + case ODP_PKTIO_TYPE_NETMAP: > + res = close_pkt_netmap(&entry->s.pkt_nm); > + break; > +#endif > + case ODP_PKTIO_TYPE_DPDK: > + res = close_pkt_dpdk(&entry->s.pkt_dpdk); > + break; > + default: > + break; > + res |= free_pktio_entry(id); > + } > + } > + unlock_entry(entry); > + > + if (res != 0) > + return -1; > + > + return 0; > +} > + > +void odp_pktio_set_input(odp_packet_t pkt, odp_pktio_t pktio) > +{ > + odp_packet_hdr(pkt)->input = pktio; > +} > + > +odp_pktio_t odp_pktio_get_input(odp_packet_t pkt) > +{ > + return odp_packet_hdr(pkt)->input; > +} > + > +int odp_pktio_recv(odp_pktio_t id, odp_packet_t pkt_table[], unsigned len) > +{ > + pktio_entry_t *pktio_entry = get_entry(id); > + int pkts; > + int i; > + > + if (pktio_entry == NULL) > + return -1; > + > + lock_entry(pktio_entry); > + switch (pktio_entry->s.params.type) { > + case ODP_PKTIO_TYPE_SOCKET_BASIC: > + pkts = recv_pkt_sock_basic(&pktio_entry->s.pkt_sock, > + pkt_table, len); > + break; > + case ODP_PKTIO_TYPE_SOCKET_MMSG: > + pkts = recv_pkt_sock_mmsg(&pktio_entry->s.pkt_sock, > + pkt_table, len); > + break; > + case ODP_PKTIO_TYPE_SOCKET_MMAP: > + pkts = recv_pkt_sock_mmap(&pktio_entry->s.pkt_sock_mmap, > + pkt_table, len); > + break; > +#ifdef ODP_HAVE_NETMAP > + case ODP_PKTIO_TYPE_NETMAP: > + pkts = recv_pkt_netmap(&pktio_entry->s.pkt_nm, pkt_table, len); > + break; > +#endif > + case ODP_PKTIO_TYPE_DPDK: > + pkts = recv_pkt_dpdk(&pktio_entry->s.pkt_dpdk, pkt_table, len); > + break; > + default: > + pkts = -1; > + break; > + } > + > + unlock_entry(pktio_entry); > + if (pkts < 0) > + return pkts; > + > + for (i = 0; i < pkts; ++i) > + odp_pktio_set_input(pkt_table[i], id); > + > + return pkts; > +} > + > +int odp_pktio_send(odp_pktio_t id, odp_packet_t pkt_table[], unsigned len) > +{ > + pktio_entry_t *pktio_entry = get_entry(id); > + int pkts; > + > + if (pktio_entry == NULL) > + return -1; > + > + lock_entry(pktio_entry); > + switch (pktio_entry->s.params.type) { > + case ODP_PKTIO_TYPE_SOCKET_BASIC: > + pkts = send_pkt_sock_basic(&pktio_entry->s.pkt_sock, > + pkt_table, len); > + break; > + case ODP_PKTIO_TYPE_SOCKET_MMSG: > + pkts = send_pkt_sock_mmsg(&pktio_entry->s.pkt_sock, > + pkt_table, len); > + break; > + case ODP_PKTIO_TYPE_SOCKET_MMAP: > + pkts = send_pkt_sock_mmap(&pktio_entry->s.pkt_sock_mmap, > + pkt_table, len); > + break; > +#ifdef ODP_HAVE_NETMAP > + case ODP_PKTIO_TYPE_NETMAP: > + pkts = send_pkt_netmap(&pktio_entry->s.pkt_nm, > + pkt_table, len); > + break; > +#endif > + case ODP_PKTIO_TYPE_DPDK: > + pkts = send_pkt_dpdk(&pktio_entry->s.pkt_dpdk, > + pkt_table, len); > + break; > + default: > + pkts = -1; > + } > + unlock_entry(pktio_entry); > + > + return pkts; > +} > + > +int odp_pktio_inq_setdef(odp_pktio_t id, odp_queue_t queue) > +{ > + pktio_entry_t *pktio_entry = get_entry(id); > + queue_entry_t *qentry = queue_to_qentry(queue); > + > + if (pktio_entry == NULL || qentry == NULL) > + return -1; > + > + if (qentry->s.type != ODP_QUEUE_TYPE_PKTIN) > + return -1; > + > + lock_entry(pktio_entry); > + pktio_entry->s.inq_default = queue; > + unlock_entry(pktio_entry); > + > + queue_lock(qentry); > + qentry->s.pktin = id; > + qentry->s.status = QUEUE_STATUS_SCHED; > + queue_unlock(qentry); > + > + odp_schedule_queue(queue, qentry->s.param.sched.prio); > + > + return 0; > +} > + > +int odp_pktio_inq_remdef(odp_pktio_t id) > +{ > + return odp_pktio_inq_setdef(id, ODP_QUEUE_INVALID); > +} > + > +odp_queue_t odp_pktio_inq_getdef(odp_pktio_t id) > +{ > + pktio_entry_t *pktio_entry = get_entry(id); > + > + if (pktio_entry == NULL) > + return ODP_QUEUE_INVALID; > + > + return pktio_entry->s.inq_default; > +} > + > +odp_queue_t odp_pktio_outq_getdef(odp_pktio_t id) > +{ > + pktio_entry_t *pktio_entry = get_entry(id); > + > + if (pktio_entry == NULL) > + return ODP_QUEUE_INVALID; > + > + return pktio_entry->s.outq_default; > +} > + > +int pktout_enqueue(queue_entry_t *qentry, odp_buffer_hdr_t *buf_hdr) > +{ > + odp_packet_t pkt = odp_packet_from_buffer((odp_buffer_t) buf_hdr); > + int len = 1; > + int nbr; > + > + nbr = odp_pktio_send(qentry->s.pktout, &pkt, len); > + return (nbr == len ? 0 : -1); > +} > + > +odp_buffer_hdr_t *pktout_dequeue(queue_entry_t *qentry) > +{ > + (void)qentry; > + return NULL; > +} > + > +int pktout_enq_multi(queue_entry_t *qentry, odp_buffer_hdr_t *buf_hdr[], > + int num) > +{ > + odp_packet_t pkt_tbl[QUEUE_MULTI_MAX]; > + int nbr; > + int i; > + > + for (i = 0; i < num; ++i) > + pkt_tbl[i] = odp_packet_from_buffer((odp_buffer_t) buf_hdr[i]); > + > + nbr = odp_pktio_send(qentry->s.pktout, pkt_tbl, num); > + return (nbr == num ? 0 : -1); > +} > + > +int pktout_deq_multi(queue_entry_t *qentry, odp_buffer_hdr_t *buf_hdr[], > + int num) > +{ > + (void)qentry; > + (void)buf_hdr; > + (void)num; > + > + return 0; > +} > + > +int pktin_enqueue(queue_entry_t *qentry, odp_buffer_hdr_t *buf_hdr) > +{ > + /* Use default action */ > + return queue_enq(qentry, buf_hdr); > +} > + > +odp_buffer_hdr_t *pktin_dequeue(queue_entry_t *qentry) > +{ > + odp_buffer_hdr_t *buf_hdr; > + > + buf_hdr = queue_deq(qentry); > + > + if (buf_hdr == NULL) { > + odp_packet_t pkt; > + odp_buffer_t buf; > + odp_packet_t pkt_tbl[QUEUE_MULTI_MAX]; > + odp_buffer_hdr_t *tmp_hdr_tbl[QUEUE_MULTI_MAX]; > + int pkts, i, j; > + > + pkts = odp_pktio_recv(qentry->s.pktin, pkt_tbl, > + QUEUE_MULTI_MAX); > + > + if (pkts > 0) { > + pkt = pkt_tbl[0]; > + buf = odp_buffer_from_packet(pkt); > + buf_hdr = odp_buf_to_hdr(buf); > + > + for (i = 1, j = 0; i < pkts; ++i) { > + buf = odp_buffer_from_packet(pkt_tbl[i]); > + tmp_hdr_tbl[j++] = odp_buf_to_hdr(buf); > + } > + queue_enq_multi(qentry, tmp_hdr_tbl, j); > + } > + } > + > + return buf_hdr; > +} > + > +int pktin_enq_multi(queue_entry_t *qentry, odp_buffer_hdr_t *buf_hdr[], int num) > +{ > + /* Use default action */ > + return queue_enq_multi(qentry, buf_hdr, num); > +} > + > +int pktin_deq_multi(queue_entry_t *qentry, odp_buffer_hdr_t *buf_hdr[], int num) > +{ > + int nbr; > + > + nbr = queue_deq_multi(qentry, buf_hdr, num); > + > + if (nbr < num) { > + odp_packet_t pkt_tbl[QUEUE_MULTI_MAX]; > + odp_buffer_hdr_t *tmp_hdr_tbl[QUEUE_MULTI_MAX]; > + odp_buffer_t buf; > + int pkts, i; > + > + pkts = odp_pktio_recv(qentry->s.pktin, pkt_tbl, > + QUEUE_MULTI_MAX); > + if (pkts > 0) { > + for (i = 0; i < pkts; ++i) { > + buf = odp_buffer_from_packet(pkt_tbl[i]); > + tmp_hdr_tbl[i] = odp_buf_to_hdr(buf); > + } > + queue_enq_multi(qentry, tmp_hdr_tbl, pkts); > + } > + } > + > + return nbr; > +} > diff --git a/platform/linux-dpdk/odp_queue.c b/platform/linux-dpdk/odp_queue.c > new file mode 100644 > index 0000000..554b8ea > --- /dev/null > +++ b/platform/linux-dpdk/odp_queue.c > @@ -0,0 +1,435 @@ > +/* Copyright (c) 2013, Linaro Limited > + * All rights reserved. > + * > + * SPDX-License-Identifier: BSD-3-Clause > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#ifdef USE_TICKETLOCK > +#include > +#define LOCK(a) odp_ticketlock_lock(a) > +#define UNLOCK(a) odp_ticketlock_unlock(a) > +#define LOCK_INIT(a) odp_ticketlock_init(a) > +#else > +#include > +#define LOCK(a) odp_spinlock_lock(a) > +#define UNLOCK(a) odp_spinlock_unlock(a) > +#define LOCK_INIT(a) odp_spinlock_init(a) > +#endif > + > +#include > + > + > +typedef struct queue_table_t { > + queue_entry_t queue[ODP_CONFIG_QUEUES]; > +} queue_table_t; > + > +static queue_table_t *queue_tbl; > + > + > +queue_entry_t *get_qentry(uint32_t queue_id) > +{ > + return &queue_tbl->queue[queue_id]; > +} > + > +static void queue_init(queue_entry_t *queue, const char *name, > + odp_queue_type_t type, odp_queue_param_t *param) > +{ > + strncpy(queue->s.name, name, ODP_QUEUE_NAME_LEN - 1); > + queue->s.type = type; > + > + if (param) { > + memcpy(&queue->s.param, param, sizeof(odp_queue_param_t)); > + } else { > + /* Defaults */ > + memset(&queue->s.param, 0, sizeof(odp_queue_param_t)); > + queue->s.param.sched.prio = ODP_SCHED_PRIO_DEFAULT; > + queue->s.param.sched.sync = ODP_SCHED_SYNC_DEFAULT; > + queue->s.param.sched.group = ODP_SCHED_GROUP_DEFAULT; > + } > + > + switch (type) { > + case ODP_QUEUE_TYPE_PKTIN: > + queue->s.enqueue = pktin_enqueue; > + queue->s.dequeue = pktin_dequeue; > + queue->s.enqueue_multi = pktin_enq_multi; > + queue->s.dequeue_multi = pktin_deq_multi; > + break; > + case ODP_QUEUE_TYPE_PKTOUT: > + queue->s.enqueue = pktout_enqueue; > + queue->s.dequeue = pktout_dequeue; > + queue->s.enqueue_multi = pktout_enq_multi; > + queue->s.dequeue_multi = pktout_deq_multi; > + break; > + default: > + queue->s.enqueue = queue_enq; > + queue->s.dequeue = queue_deq; > + queue->s.enqueue_multi = queue_enq_multi; > + queue->s.dequeue_multi = queue_deq_multi; > + break; > + } > + > + queue->s.head = NULL; > + queue->s.tail = NULL; > + queue->s.sched_buf = ODP_BUFFER_INVALID; > +} > + > + > +int odp_queue_init_global(void) > +{ > + uint32_t i; > + > + ODP_DBG("Queue init ... "); > + > + queue_tbl = odp_shm_reserve("odp_queues", > + sizeof(queue_table_t), > + sizeof(queue_entry_t)); > + > + if (queue_tbl == NULL) > + return -1; > + > + memset(queue_tbl, 0, sizeof(queue_table_t)); > + > + for (i = 0; i < ODP_CONFIG_QUEUES; i++) { > + /* init locks */ > + queue_entry_t *queue = get_qentry(i); > + LOCK_INIT(&queue->s.lock); > + queue->s.handle = queue_from_id(i); > + } > + > + ODP_DBG("done\n"); > + ODP_DBG("Queue init global\n"); > + ODP_DBG(" struct queue_entry_s size %zu\n", > + sizeof(struct queue_entry_s)); > + ODP_DBG(" queue_entry_t size %zu\n", > + sizeof(queue_entry_t)); > + ODP_DBG("\n"); > + > + return 0; > +} > + > +odp_queue_type_t odp_queue_type(odp_queue_t handle) > +{ > + queue_entry_t *queue; > + > + queue = queue_to_qentry(handle); > + > + return queue->s.type; > +} > + > +odp_schedule_sync_t odp_queue_sched_type(odp_queue_t handle) > +{ > + queue_entry_t *queue; > + > + queue = queue_to_qentry(handle); > + > + return queue->s.param.sched.sync; > +} > + > +odp_queue_t odp_queue_create(const char *name, odp_queue_type_t type, > + odp_queue_param_t *param) > +{ > + uint32_t i; > + queue_entry_t *queue; > + odp_queue_t handle = ODP_QUEUE_INVALID; > + > + for (i = 0; i < ODP_CONFIG_QUEUES; i++) { > + queue = &queue_tbl->queue[i]; > + > + if (queue->s.status != QUEUE_STATUS_FREE) > + continue; > + > + LOCK(&queue->s.lock); > + if (queue->s.status == QUEUE_STATUS_FREE) { > + queue_init(queue, name, type, param); > + > + if (type == ODP_QUEUE_TYPE_SCHED || > + type == ODP_QUEUE_TYPE_PKTIN) > + queue->s.status = QUEUE_STATUS_NOTSCHED; > + else > + queue->s.status = QUEUE_STATUS_READY; > + > + handle = queue->s.handle; > + UNLOCK(&queue->s.lock); > + break; > + } > + UNLOCK(&queue->s.lock); > + } > + > + if (handle != ODP_QUEUE_INVALID && > + (type == ODP_QUEUE_TYPE_SCHED || type == ODP_QUEUE_TYPE_PKTIN)) { > + odp_buffer_t buf; > + > + buf = odp_schedule_buffer_alloc(handle); > + if (buf == ODP_BUFFER_INVALID) { > + ODP_ERR("queue_init: sched buf alloc failed\n"); > + return ODP_QUEUE_INVALID; > + } > + > + queue->s.sched_buf = buf; > + odp_schedule_mask_set(handle, queue->s.param.sched.prio); > + } > + > + return handle; > +} > + > + > +odp_buffer_t queue_sched_buf(odp_queue_t handle) > +{ > + queue_entry_t *queue; > + queue = queue_to_qentry(handle); > + > + return queue->s.sched_buf; > +} > + > + > +int queue_sched_atomic(odp_queue_t handle) > +{ > + queue_entry_t *queue; > + queue = queue_to_qentry(handle); > + > + return queue->s.param.sched.sync == ODP_SCHED_SYNC_ATOMIC; > +} > + > + > +odp_queue_t odp_queue_lookup(const char *name) > +{ > + uint32_t i; > + > + for (i = 0; i < ODP_CONFIG_QUEUES; i++) { > + queue_entry_t *queue = &queue_tbl->queue[i]; > + > + if (queue->s.status == QUEUE_STATUS_FREE) > + continue; > + > + LOCK(&queue->s.lock); > + if (strcmp(name, queue->s.name) == 0) { > + /* found it */ > + UNLOCK(&queue->s.lock); > + return queue->s.handle; > + } > + UNLOCK(&queue->s.lock); > + } > + > + return ODP_QUEUE_INVALID; > +} > + > + > +int queue_enq(queue_entry_t *queue, odp_buffer_hdr_t *buf_hdr) > +{ > + int sched = 0; > + > + LOCK(&queue->s.lock); > + if (queue->s.head == NULL) { > + /* Empty queue */ > + queue->s.head = buf_hdr; > + queue->s.tail = buf_hdr; > + buf_hdr->pkt.next = NULL; > + } else { > + queue->s.tail->pkt.next = buf_hdr; > + queue->s.tail = buf_hdr; > + buf_hdr->pkt.next = NULL; > + } > + > + if (queue->s.status == QUEUE_STATUS_NOTSCHED) { > + queue->s.status = QUEUE_STATUS_SCHED; > + sched = 1; /* retval: schedule queue */ > + } > + UNLOCK(&queue->s.lock); > + > + /* Add queue to scheduling */ > + if (sched == 1) > + odp_schedule_queue(queue->s.handle, queue->s.param.sched.prio); > + > + return 0; > +} > + > + > +int queue_enq_multi(queue_entry_t *queue, odp_buffer_hdr_t *buf_hdr[], int num) > +{ > + int sched = 0; > + int i; > + odp_buffer_hdr_t *tail; > + > + for (i = 0; i < num - 1; i++) > + buf_hdr[i]->pkt.next = buf_hdr[i+1]; > + > + tail = buf_hdr[num-1]; > + buf_hdr[num-1]->pkt.next = NULL; > + > + LOCK(&queue->s.lock); > + /* Empty queue */ > + if (queue->s.head == NULL) > + queue->s.head = buf_hdr[0]; > + else > + queue->s.tail->pkt.next = buf_hdr[0]; > + > + queue->s.tail = tail; > + > + if (queue->s.status == QUEUE_STATUS_NOTSCHED) { > + queue->s.status = QUEUE_STATUS_SCHED; > + sched = 1; /* retval: schedule queue */ > + } > + UNLOCK(&queue->s.lock); > + > + /* Add queue to scheduling */ > + if (sched == 1) > + odp_schedule_queue(queue->s.handle, queue->s.param.sched.prio); > + > + return 0; > +} > + > + > +int odp_queue_enq_multi(odp_queue_t handle, odp_buffer_t buf[], int num) > +{ > + odp_buffer_hdr_t *buf_hdr[QUEUE_MULTI_MAX]; > + queue_entry_t *queue; > + int i; > + > + if (num > QUEUE_MULTI_MAX) > + num = QUEUE_MULTI_MAX; > + > + queue = queue_to_qentry(handle); > + > + for (i = 0; i < num; i++) > + buf_hdr[i] = odp_buf_to_hdr(buf[i]); > + > + return queue->s.enqueue_multi(queue, buf_hdr, num); > +} > + > + > +int odp_queue_enq(odp_queue_t handle, odp_buffer_t buf) > +{ > + odp_buffer_hdr_t *buf_hdr; > + queue_entry_t *queue; > + > + queue = queue_to_qentry(handle); > + buf_hdr = odp_buf_to_hdr(buf); > + > + return queue->s.enqueue(queue, buf_hdr); > +} > + > + > +odp_buffer_hdr_t *queue_deq(queue_entry_t *queue) > +{ > + odp_buffer_hdr_t *buf_hdr = NULL; > + > + LOCK(&queue->s.lock); > + > + if (queue->s.head == NULL) { > + /* Already empty queue */ > + if (queue->s.status == QUEUE_STATUS_SCHED && > + queue->s.type != ODP_QUEUE_TYPE_PKTIN) > + queue->s.status = QUEUE_STATUS_NOTSCHED; > + } else { > + buf_hdr = queue->s.head; > + queue->s.head = buf_hdr->pkt.next; > + buf_hdr->pkt.next = NULL; > + > + if (queue->s.head == NULL) { > + /* Queue is now empty */ > + queue->s.tail = NULL; > + } > + } > + > + UNLOCK(&queue->s.lock); > + > + return buf_hdr; > +} > + > + > +int queue_deq_multi(queue_entry_t *queue, odp_buffer_hdr_t *buf_hdr[], int num) > +{ > + int i = 0; > + > + LOCK(&queue->s.lock); > + > + if (queue->s.head == NULL) { > + /* Already empty queue */ > + if (queue->s.status == QUEUE_STATUS_SCHED && > + queue->s.type != ODP_QUEUE_TYPE_PKTIN) > + queue->s.status = QUEUE_STATUS_NOTSCHED; > + } else { > + odp_buffer_hdr_t *hdr = queue->s.head; > + > + for (; i < num && hdr; i++) { > + buf_hdr[i] = hdr; > + /* odp_prefetch(hdr->addr); */ > + hdr = hdr->pkt.next; > + buf_hdr[i]->pkt.next = NULL; > + } > + > + queue->s.head = hdr; > + > + if (hdr == NULL) { > + /* Queue is now empty */ > + queue->s.tail = NULL; > + } > + } > + > + UNLOCK(&queue->s.lock); > + > + return i; > +} > + > + > +int odp_queue_deq_multi(odp_queue_t handle, odp_buffer_t buf[], int num) > +{ > + queue_entry_t *queue; > + odp_buffer_hdr_t *buf_hdr[QUEUE_MULTI_MAX]; > + int i, ret; > + > + if (num > QUEUE_MULTI_MAX) > + num = QUEUE_MULTI_MAX; > + > + queue = queue_to_qentry(handle); > + > + ret = queue->s.dequeue_multi(queue, buf_hdr, num); > + > + for (i = 0; i < ret; i++) > + buf[i] = (odp_buffer_t) buf_hdr[i]; > + > + return ret; > +} > + > + > +odp_buffer_t odp_queue_deq(odp_queue_t handle) > +{ > + queue_entry_t *queue; > + odp_buffer_hdr_t *buf_hdr; > + > + queue = queue_to_qentry(handle); > + buf_hdr = queue->s.dequeue(queue); > + > + if (buf_hdr) > + return (odp_buffer_t) buf_hdr; > + > + return ODP_BUFFER_INVALID; > +} > + > + > +void queue_lock(queue_entry_t *queue) > +{ > + LOCK(&queue->s.lock); > +} > + > + > +void queue_unlock(queue_entry_t *queue) > +{ > + UNLOCK(&queue->s.lock); > +} > -- > 1.8.1.2 > > > _______________________________________________ > lng-odp mailing list > lng-odp@lists.linaro.org > http://lists.linaro.org/mailman/listinfo/lng-odp diff --git a/platform/linux-dpdk/Makefile.am b/platform/linux-dpdk/Makefile.am index 067c0bb..f9f31c6 100644 --- a/platform/linux-dpdk/Makefile.am +++ b/platform/linux-dpdk/Makefile.am @@ -8,15 +8,7 @@ nodist_pkgconfig_DATA = $(top_builddir)/pkgconfig/libodp.pc .PHONY: pkgconfig/libodp.pc -RTE_SDK ?= $(top_srcdir)/../dpdk -RTE_OUTPUT ?= $(RTE_SDK)/build -RTE_LIB ?= $(RTE_OUTPUT)/lib - -PLAT_CFLAGS = -include $(RTE_OUTPUT)/include/rte_config.h -PLAT_CFLAGS += -I$(RTE_OUTPUT)/include -PLAT_CFLAGS += -I$(RTE_OUTPUT)/include/arch -PLAT_CFLAGS += -I$(RTE_OUTPUT)/include/exec-env -PLAT_CFLAGS += -msse4.2 +PLAT_CFLAGS = -msse4.2 AM_CFLAGS += $(PLAT_CFLAGS) AM_CFLAGS += -I$(srcdir)/include @@ -25,7 +17,6 @@ AM_CFLAGS += -I$(top_srcdir)/platform/linux-generic/include AM_CFLAGS += -I$(top_srcdir)/platform/linux-generic/include/api AM_CFLAGS += -I$(top_srcdir)/include -AM_LDFLAGS += -L$(RTE_LIB) VPATH = $(srcdir) $(builddir) if ODP_PLATFORM_DPDK lib_LTLIBRARIES = $(LIB)/libodp.la > +PLAT_CFLAGS += -msse4.2 > + > +AM_CFLAGS += $(PLAT_CFLAGS) > +AM_CFLAGS += -I$(srcdir)/include > +AM_CFLAGS += -I$(srcdir)/include/api > +AM_CFLAGS += -I$(top_srcdir)/platform/linux-generic/include > +AM_CFLAGS += -I$(top_srcdir)/platform/linux-generic/include/api > +AM_CFLAGS += -I$(top_srcdir)/include > + > +AM_LDFLAGS += -L$(RTE_LIB) > +VPATH = $(srcdir) $(builddir) > +if ODP_PLATFORM_DPDK > +lib_LTLIBRARIES = $(LIB)/libodp.la > +DPDK_LIBS="-lintel_dpdk -ldl" > +LIBS += $(DPDK_LIBS) > + > +include_HEADERS = \ > + $(top_srcdir)/platform/linux-dpdk/include/api/odp_buffer.h \ > + $(top_srcdir)/include/odp.h \ > + $(top_srcdir)/include/odp_align.h \ > + $(top_srcdir)/include/odp_atomic.h \ > + $(top_srcdir)/include/odp_barrier.h \ > + $(top_srcdir)/include/odp_buffer_pool.h \ > + $(top_srcdir)/include/odp_byteorder.h \ > + $(top_srcdir)/include/odp_compiler.h \ > + $(top_srcdir)/include/odp_config.h \ > + $(top_srcdir)/include/odp_coremask.h \ > + $(top_srcdir)/include/odp_debug.h \ > + $(top_srcdir)/include/odp_hints.h \ > + $(top_srcdir)/include/odp_init.h \ > + $(top_srcdir)/include/odp_packet_flags.h \ > + $(top_srcdir)/include/odp_packet.h \ > + $(top_srcdir)/include/odp_packet_io.h \ > + $(top_srcdir)/include/odp_queue.h \ > + $(top_srcdir)/include/odp_rwlock.h \ > + $(top_srcdir)/include/odp_schedule.h \ > + $(top_srcdir)/include/odp_shared_memory.h \ > + $(top_srcdir)/include/odp_spinlock.h \ > + $(top_srcdir)/include/odp_std_types.h \ > + $(top_srcdir)/include/odp_sync.h \ > + $(top_srcdir)/include/odp_system_info.h \ > + $(top_srcdir)/include/odp_thread.h \ > + $(top_srcdir)/include/odp_ticketlock.h \ > + $(top_srcdir)/include/odp_time.h \ > + $(top_srcdir)/include/odp_timer.h \ > + $(top_srcdir)/include/odp_version.h > + > +subdirheadersdir = $(includedir)/helper > +subdirheaders_HEADERS = \ > + $(top_srcdir)/include/helper/odp_chksum.h \ > + $(top_srcdir)/include/helper/odp_eth.h \ > + $(top_srcdir)/include/helper/odp_ip.h \ > + $(top_srcdir)/include/helper/odp_linux.h \ > + $(top_srcdir)/include/helper/odp_packet_helper.h \ > + $(top_srcdir)/include/helper/odp_ring.h \ > + $(top_srcdir)/include/helper/odp_udp.h > + > +__LIB__libodp_la_SOURCES = \ > + ../linux-generic/odp_barrier.c \ > + odp_buffer.c \ > + odp_buffer_pool.c \ > + ../linux-generic/odp_coremask.c \ > + odp_init.c \ > + odp_linux.c \ > + odp_packet.c \ > + odp_packet_dpdk.c \ > + ../linux-generic/odp_packet_flags.c \ > + odp_packet_io.c \ > + ../linux-generic/odp_packet_socket.c \ > + odp_queue.c \ > + ../linux-generic/odp_ring.c \ > + ../linux-generic/odp_rwlock.c \ > + ../linux-generic/odp_schedule.c \ > + ../linux-generic/odp_shared_memory.c \ > + ../linux-generic/odp_spinlock.c \ > + ../linux-generic/odp_system_info.c \ > + ../linux-generic/odp_thread.c \ > + ../linux-generic/odp_ticketlock.c \ > + ../linux-generic/odp_time.c \ > + ../linux-generic/odp_timer.c > + > +endif > diff --git a/platform/linux-dpdk/README b/platform/linux-dpdk/README > new file mode 100644 > index 0000000..69116a7 > --- /dev/null > +++ b/platform/linux-dpdk/README > @@ -0,0 +1,70 @@ > +ODP-DPDK: > +--------- > + This effort is to port ODP on top of DPDK and use dpdk as the > +accelerator for all intel NIC's. Pre-requisite is DPDK should be cloned and > +compiled. > + > +# To Clone DPDK > +$ git clone http://92.243.14.124/git/dpdk ./dpdk > +# Ensure that dpdk is present at the same directory level as odp, that is, ./odp and ./dpdk > +# we support only 1.6.0r2 of dpdk for now > +$ git tag -l -- will list all the tags available > +$ git checkout tags/v1.6.0r2 Oh right I wasn't able to build dpdk I'm using Ubuntu-14.04 with kernel 3.13.0-30-generic I had to do this change to dpdk: $ git df diff --git a/lib/librte_eal/linuxapp/kni/ethtool/igb/kcompat.h b/lib/librte_eal/linuxapp/kni/ethtool/igb/kcompat.h index 19df483..78a794a 100644 --- a/lib/librte_eal/linuxapp/kni/ethtool/igb/kcompat.h +++ b/lib/librte_eal/linuxapp/kni/ethtool/igb/kcompat.h @@ -3845,11 +3845,6 @@ static inline struct sk_buff *__kc__vlan_hwaccel_put_tag(struct sk_buff *skb, #if ( LINUX_VERSION_CODE < KERNEL_VERSION(3,14,0) ) #ifdef NETIF_F_RXHASH #define PKT_HASH_TYPE_L3 0 -static inline void -skb_set_hash(struct sk_buff *skb, __u32 hash, __always_unused int type) -{ - skb->rxhash = hash; -} #endif /* NETIF_F_RXHASH */ #endif /* < 3.14.0 */