From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 59DC9424CD; Thu, 20 Jun 2024 14:01:32 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 41C3B42E47; Thu, 20 Jun 2024 14:01:32 +0200 (CEST) Received: from mail-qt1-f182.google.com (mail-qt1-f182.google.com [209.85.160.182]) by mails.dpdk.org (Postfix) with ESMTP id F10DA402D2 for ; Thu, 20 Jun 2024 14:01:30 +0200 (CEST) Received: by mail-qt1-f182.google.com with SMTP id d75a77b69052e-44055ca3103so3513651cf.3 for ; Thu, 20 Jun 2024 05:01:30 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1718884890; x=1719489690; darn=dpdk.org; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:from:to:cc:subject:date :message-id:reply-to; bh=rDBYvB4a8HhcSxq0cG+zopLXXt99g8DxDOgdJAnF+18=; b=mmP/shUENHx9Ev5IwHsBc46i8OmLN2tP5hRtWSmJ/I5WHqIDR/7sYqCKEAYMQ19WoM bPLsx+LnR75mYJpA4wciksepQnyCSniwF7UD0lRru3/QPk0j6kd8twUyw7HyhQV/yx5z gAKK0qCcIs+RjjaKZMFYHFOoUvAIZJ6VL1WpNY73cjhEGV7PzPl9Fr10OjmTyJ6N6/mN qiOE1Bf9gxTO2NLM/PbJQojJDY+tyx54vvWHzrKB8K5TUuyTo19mLZpvlPvjL6Krw+Er plbSnpKPw7/Slp95ZbDavDsQ0UctyqCUhiYuT8UlUlVr8LpDF8Bi82kr3a+ARFLXZ5dD e05w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1718884890; x=1719489690; h=content-transfer-encoding:cc:to:subject:message-id:date:from :in-reply-to:references:mime-version:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=rDBYvB4a8HhcSxq0cG+zopLXXt99g8DxDOgdJAnF+18=; b=mhBQyV77FZ3qRwuKH2I79muZBgRBr0Ffx1FzEz/pEWp7DHBNRedmrElyZhK+R8+8zo bLmDDa8R2m4j/4eL5N54ayZn8eNuJQb0Hyyz7U6rIlRmufUGq4gfReuCKTAirtsSjsZ1 MEeuWls1VKF+n9P3hnb+Ko0lZsoEimeBy9v7DT2RpioyzKtOFnqIp5n1NbRt4HJ+W8FC Ij3G0/rMVTWozYFeGyTF9AdVacaiQOdUGw9NFkIq9d3v/aCpYU4alqzRJzUOKYwrRDef h5AtEc4Q+w98tMs9TeFYeOmwnESwaCJNyDOGZyUcFX9OQ6eEXxdPWEVJy3tCbgKHMxxR FZHw== X-Gm-Message-State: AOJu0YzvPCa1ByK/McTP9PacQDnbNiscs6O+l+AFH0N/iWPckG+3y7Le zhelTAKOtPhPn6tbMb6JY78rXzKVzQlAnueRccK2Qfvc3qIFkEkR3ngHI4GDMKIVGLRFukV/fZW U2eSHpGbJipMwKh4qGLAJZ+UomtY= X-Google-Smtp-Source: AGHT+IH7OMClzA19J4e/Dsvu6tpqgs4m3l6VFYG9WHO4C6RBv74+VwZ2KE41d2N7Aaue7Feh6w8ef5i0NN29u5gpIro= X-Received: by 2002:a05:622a:1209:b0:441:3395:ece0 with SMTP id d75a77b69052e-444a79df931mr60010261cf.37.1718884889937; Thu, 20 Jun 2024 05:01:29 -0700 (PDT) MIME-Version: 1.0 References: <20240501194620.1199357-2-abdullah.sevincer@intel.com> <20240619210106.253239-1-abdullah.sevincer@intel.com> <20240619210106.253239-2-abdullah.sevincer@intel.com> In-Reply-To: <20240619210106.253239-2-abdullah.sevincer@intel.com> From: Jerin Jacob Date: Thu, 20 Jun 2024 17:31:03 +0530 Message-ID: Subject: Re: [PATCH v5 1/5] event/dlb2: add support for HW delayed token To: Abdullah Sevincer Cc: dev@dpdk.org, jerinj@marvell.com, mike.ximing.chen@intel.com, tirthendu.sarkar@intel.com, pravin.pathak@intel.com, shivani.doneria@intel.com Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable 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 On Thu, Jun 20, 2024 at 2:37=E2=80=AFAM Abdullah Sevincer wrote: > > In DLB 2.5, hardware assist is available, complementing the Delayed > token POP software implementation. When it is enabled, the feature > works as follows: > > It stops CQ scheduling when the inflight limit associated with the CQ > is reached. So the feature is activated only if the core is > congested. If the core can handle multiple atomic flows, DLB will not > try to switch them. This is an improvement over SW implementation > which always switches the flows. > > The feature will resume CQ scheduling when the number of pending > completions fall below a configured threshold. To emulate older 2.0 > behavior, this threshold is set to 1 by old APIs. SW sets CQ to > auto-pop mode for token return, as tokens withholding is not > necessary now. As HW counts completions and not tokens, events equal > to HL (History List) entries will be scheduled to DLB before the > feature activates and stops CQ scheduling. > > Signed-off-by: Abdullah Sevincer > > +/** Set inflight threshold for flow migration */ > +#define RTE_PMD_DLB2_FLOW_MIGRATION_THRESHOLD RTE_BIT64(0) > + > +/** Set port history list */ > +#define RTE_PMD_DLB2_SET_PORT_HL RTE_BIT64(1) > + Missing Doxygen comment > +struct rte_pmd_dlb2_port_params { > + uint16_t inflight_threshold : 12; Missing Doxygen comment > +}; > + > +/*! > + * @warning > + * @b EXPERIMENTAL: this API may change, or be removed, without prior no= tice > + * > + * Configure various port parameters. > + * AUTO_POP. This function must be called before calling rte_event_port_= setup() > + * for the port, but after calling rte_event_dev_configure(). > + * > + * @param dev_id > + * The identifier of the event device. > + * @param port_id > + * The identifier of the event port. > + * @param flags > + * Bitmask of the parameters being set. > + * @param params > + * Structure coantaining the values of parameters being set. > + * > + * @return > + * - 0: Success > + * - EINVAL: Invalid dev_id, port_id, or mode > + * - EINVAL: The DLB2 is not configured, is already running, or the port= is > + * already setup > + */ > +__rte_experimental > +int > +rte_pmd_dlb2_set_port_params(uint8_t dev_id, > + uint8_t port_id, > + uint64_t flags, > + struct rte_pmd_dlb2_port_params *params); > +