From patchwork Sun Feb 14 03:21:34 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Xueming Li X-Patchwork-Id: 87912 X-Patchwork-Delegate: ferruh.yigit@amd.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 96CF4A0546; Sun, 14 Feb 2021 04:23:37 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 081BB22A246; Sun, 14 Feb 2021 04:23:35 +0100 (CET) Received: from mellanox.co.il (mail-il-dmz.mellanox.com [193.47.165.129]) by mails.dpdk.org (Postfix) with ESMTP id 6171422A246 for ; Sun, 14 Feb 2021 04:23:33 +0100 (CET) Received: from Internal Mail-Server by MTLPINE1 (envelope-from xuemingl@nvidia.com) with SMTP; 14 Feb 2021 05:23:29 +0200 Received: from nvidia.com (pegasus05.mtr.labs.mlnx [10.210.16.100]) by labmailer.mlnx (8.13.8/8.13.8) with ESMTP id 11E3MYvQ008525; Sun, 14 Feb 2021 05:23:29 +0200 From: Xueming Li To: Cc: dev@dpdk.org, Viacheslav Ovsiienko , xuemingl@nvidia.com, Asaf Penso , Thomas Monjalon , Ferruh Yigit , Andrew Rybchenko Date: Sun, 14 Feb 2021 03:21:34 +0000 Message-Id: <1613272907-22563-5-git-send-email-xuemingl@nvidia.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1613272907-22563-1-git-send-email-xuemingl@nvidia.com> References: <1613272907-22563-1-git-send-email-xuemingl@nvidia.com> In-Reply-To: <1608303356-13089-2-git-send-email-xuemingl@nvidia.com> References: <1608303356-13089-2-git-send-email-xuemingl@nvidia.com> Subject: [dpdk-dev] [PATCH v6 4/9] ethdev: support sub function representor X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" SubFunction is a portion of the PCI device, created on demand, a SF netdev has its own dedicated queues(txq, rxq). A SF netdev supports eswitch representation offload similar to existing PF and VF representors. To support SF representor, this patch introduces new devargs syntax, examples: representor=sf0 - single SubFunction representor representor=sf[1,3,5] - single list representor=sf[0-3], - single range representor=sf[0,2-6,8,10-12] - list with singles and ranges Signed-off-by: Xueming Li Acked-by: Viacheslav Ovsiienko Acked-by: Thomas Monjalon Acked-by: Andrew Rybchenko --- doc/guides/prog_guide/poll_mode_drv.rst | 4 +++ .../prog_guide/switch_representation.rst | 35 +++++++++++++------ lib/librte_ethdev/ethdev_private.c | 11 ++++-- lib/librte_ethdev/rte_ethdev.h | 1 + 4 files changed, 39 insertions(+), 12 deletions(-) diff --git a/doc/guides/prog_guide/poll_mode_drv.rst b/doc/guides/prog_guide/poll_mode_drv.rst index 0117c2af07..86e5867f1b 100644 --- a/doc/guides/prog_guide/poll_mode_drv.rst +++ b/doc/guides/prog_guide/poll_mode_drv.rst @@ -378,6 +378,10 @@ parameters to those ports. -a DBDF,representor=vf[0,4,6,9] -a DBDF,representor=vf[0-31] -a DBDF,representor=vf[0,2-4,7,9-11] + -a DBDF,representor=sf0 + -a DBDF,representor=sf[1,3,5] + -a DBDF,representor=sf[0-1023] + -a DBDF,representor=sf[0,2-4,7,9-11] Note: PMDs are not required to support the standard device arguments and users should consult the relevant PMD documentation to see support devargs. diff --git a/doc/guides/prog_guide/switch_representation.rst b/doc/guides/prog_guide/switch_representation.rst index 07ba12bea6..ff6aa91c80 100644 --- a/doc/guides/prog_guide/switch_representation.rst +++ b/doc/guides/prog_guide/switch_representation.rst @@ -13,7 +13,7 @@ Introduction Network adapters with multiple physical ports and/or SR-IOV capabilities usually support the offload of traffic steering rules between their virtual -functions (VFs), physical functions (PFs) and ports. +functions (VFs), sub functions (SFs), physical functions (PFs) and ports. Like for standard Ethernet switches, this involves a combination of automatic MAC learning and manual configuration. For most purposes it is @@ -24,7 +24,7 @@ layer 2 (L2) traffic (such as OVS) need to steer traffic themselves according on their own criteria. Without a standard software interface to manage traffic steering rules -between VFs, PFs and the various physical ports of a given device, +between VFs, SFs, PFs and the various physical ports of a given device, applications cannot take advantage of these offloads; software processing is mandatory even for traffic which ends up re-injected into the device it originates from. @@ -34,6 +34,17 @@ the DPDK flow API (**rte_flow**), with emphasis on the SR-IOV use case (PF/VF steering) using a single physical port for clarity, however the same logic applies to any number of ports without necessarily involving SR-IOV. +Sub Function +------------ +Besides SR-IOV, Sub function is a portion of the PCI device, a SF netdev +has its own dedicated queues(txq, rxq). A SF netdev supports E-Switch +representation offload similar to existing PF and VF representors. +A SF shares PCI level resources with other SFs and/or with its parent PCI +function. + +Sub function is created on-demand, coexists with VFs. Number of SFs is +limited by hardware resources. + Port Representors ----------------- @@ -42,15 +53,16 @@ applications usually have to process a bit of traffic in software before thinking about offloading specific flows to hardware. Applications therefore need the ability to receive and inject traffic to -various device endpoints (other VFs, PFs or physical ports) before +various device endpoints (other VFs, SFs, PFs or physical ports) before connecting them together. Device drivers must provide means to hook the "other end" of these endpoints and to refer them when configuring flow rules. This role is left to so-called "port representors" (also known as "VF -representors" in the specific context of VFs), which are to DPDK what the -Ethernet switch device driver model (**switchdev**) [1]_ is to Linux, and -which can be thought as a software "patch panel" front-end for applications. +representors" in the specific context of VFs, "SF representors" in the +specific context of SFs), which are to DPDK what the Ethernet switch +device driver model (**switchdev**) [1]_ is to Linux, and which can be +thought as a software "patch panel" front-end for applications. - DPDK port representors are implemented as additional virtual Ethernet device (**ethdev**) instances, spawned on an as needed basis through @@ -59,9 +71,12 @@ which can be thought as a software "patch panel" front-end for applications. :: - -a pci:dbdf,representor=0 - -a pci:dbdf,representor=[0-3] - -a pci:dbdf,representor=[0,5-11] + -a pci:dbdf,representor=vf0 + -a pci:dbdf,representor=vf[0-3] + -a pci:dbdf,representor=vf[0,5-11] + -a pci:dbdf,representor=sf1 + -a pci:dbdf,representor=sf[0-1023] + -a pci:dbdf,representor=sf[0,2-1023] - As virtual devices, they may be more limited than their physical counterparts, for instance by exposing only a subset of device @@ -360,7 +375,7 @@ Compared to creating a brand new dedicated interface, **rte_flow** was deemed flexible enough to manage representor traffic only with minor extensions: -- Using physical ports, PF, VF or port representors as targets. +- Using physical ports, PF, SF, VF or port representors as targets. - Affecting traffic that is not necessarily addressed to the DPDK port ID a flow rule is associated with (e.g. forcing VF traffic redirection to PF). diff --git a/lib/librte_ethdev/ethdev_private.c b/lib/librte_ethdev/ethdev_private.c index 4bb3879859..13c191192e 100644 --- a/lib/librte_ethdev/ethdev_private.c +++ b/lib/librte_ethdev/ethdev_private.c @@ -119,6 +119,7 @@ rte_eth_devargs_process_list(char *str, uint16_t *list, uint16_t *len_list, * Representor format: * #: range or single number of VF representor - legacy * vf#: VF port representor/s + * sf#: SF port representor/s * * Examples of #: * 2 - single @@ -130,9 +131,15 @@ rte_eth_devargs_parse_representor_ports(char *str, void *data) { struct rte_eth_devargs *eth_da = data; - eth_da->type = RTE_ETH_REPRESENTOR_VF; - if (str[0] == 'v' && str[1] == 'f') + if (str[0] == 'v' && str[1] == 'f') { + eth_da->type = RTE_ETH_REPRESENTOR_VF; str += 2; + } else if (str[0] == 's' && str[1] == 'f') { + eth_da->type = RTE_ETH_REPRESENTOR_SF; + str += 2; + } else { + eth_da->type = RTE_ETH_REPRESENTOR_VF; + } str = rte_eth_devargs_process_list(str, eth_da->representor_ports, ð_da->nb_representor_ports, RTE_DIM(eth_da->representor_ports)); diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib/librte_ethdev/rte_ethdev.h index 1f378958ca..26b5e109c3 100644 --- a/lib/librte_ethdev/rte_ethdev.h +++ b/lib/librte_ethdev/rte_ethdev.h @@ -1512,6 +1512,7 @@ struct rte_eth_rxseg_capa { enum rte_eth_representor_type { RTE_ETH_REPRESENTOR_NONE, /**< not a representor. */ RTE_ETH_REPRESENTOR_VF, /**< representor of Virtual Function. */ + RTE_ETH_REPRESENTOR_SF, /**< representor of Sub Function. */ }; /**