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 035FAA0032; Thu, 16 Dec 2021 21:29:03 +0100 (CET) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id B69C940143; Thu, 16 Dec 2021 21:29:02 +0100 (CET) Received: from mail-il1-f195.google.com (mail-il1-f195.google.com [209.85.166.195]) by mails.dpdk.org (Postfix) with ESMTP id 96C784013F for ; Thu, 16 Dec 2021 21:29:01 +0100 (CET) Received: by mail-il1-f195.google.com with SMTP id s11so13396ilv.3 for ; Thu, 16 Dec 2021 12:29:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=mime-version:from:date:message-id:subject:to; bh=nVqnvHxHOvwiOUjVJyFhnkkQPYYPYCm0xkMh4F4qaYI=; b=LP2POpFkKNp8aZXpyYtRstLfTE4mPQFeAi+alukk94el1nV5UZmdilzw7JPRteyzwn EhkHGm6OHgozYjOHeKzaUBaz5JaPq+2ruAkfk6CTwynipTcDvCqFCZyYS9dYHyYo5Jat cuHqcDIo1eJGokhC9RrMjKWsSD8K/SdhsJnxO/7xaXWbjeizFGCOSO39iZR6YprnBzhN gEcfAG0KKjWrp9WB2hbIQ0wXT6Wug0d618OzVDH30IPej+1vqXm/+hNg4m0PLxSYQAhC dmOwMOcdvU9yrWAKmHXDsi1tDa/tgjrTHHaDZSE+nteuGyVU4oPWr6puTsGAT/uAv/FX QdvA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:mime-version:from:date:message-id:subject:to; bh=nVqnvHxHOvwiOUjVJyFhnkkQPYYPYCm0xkMh4F4qaYI=; b=J/HYxzT3kqTWNpUUC68FIzeqoR3JlBwFou5+bBMVguLlUJlaDE6ns5xCosloCuijjw nSC8E7hgV30bbQLbZ9jKk/dMEWe3Sla6NEWOcwqM4096F5GnVs+yTjYGs5h77OyWYLzm dmMbhpTmAftqvhXIVqkPdB1PiTDGdMq+xG69+EGaTZv/2++6mY9kS5RqygrUA/NXsDfX B5hk3DQS4A1kjafLu63zY8b8ypYWZGSy7epUJFTQVYxiZUl32eYkEI8Yl7iNgEHkgc7/ +r7vXmtfrdpAwAU8GrSd9qOEo4kWzqbBMywVxyTCeMDRjXHxyrsH3e5/le3jCXiDHR7S BN7g== X-Gm-Message-State: AOAM5307z+vdfXidHPU17orz2cdXLhnQZtThprQX1InQwH3BiYmhz/jR jfkbB0A2ndkdzqc1J3TMR5CzKBFQyAHtsB+LGhc= X-Google-Smtp-Source: ABdhPJxbQKrqoSeuvj5//WVAtIXjHW+jFsMFmHmPgJosEuSWmnYZt9PCmVQ9EZKIPJ6uTek7siohdTuEkxq0VX2fqHU= X-Received: by 2002:a05:6e02:1529:: with SMTP id i9mr11118568ilu.303.1639686540879; Thu, 16 Dec 2021 12:29:00 -0800 (PST) MIME-Version: 1.0 From: Learn DPDK Date: Thu, 16 Dec 2021 12:28:50 -0800 Message-ID: Subject: When tap PMD is used, memory loss occurs in secondary block To: Learn DPDK , dev@dpdk.org Content-Type: multipart/alternative; boundary="000000000000cfecb305d349455b" 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 --000000000000cfecb305d349455b Content-Type: text/plain; charset="UTF-8" Hello. Thanks a lot in advance for your help and nice support. We use tap PMD to send exception packet to kernel by DPDK primary block. If the secondary block is driven in this state, vdev probe is performed inside rte_eal_init func and memory is allocated using the rte_zmalloc_socket function if it is a secondary block in the rte_pmd_tap_probe (dpdk-20.11/drivers/net/tap/rte_eth_tap.c) function. The secondary block mentioned is used to debug the primary block and is terminated immediately after executing the command so the memory allocated above is not free and is lost. The secondary block does not access the tap interface, is there any way to prevent memory allocation for tap vdev? I am inquiring this because rte_eth_tap.c file copyrighted --000000000000cfecb305d349455b Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable

Hello.Thanks a lot in advance f= or your help and nice support.

We=C2=A0use=C2=A0tap=C2=A0PMD=C2=A0to=C2= =A0send=C2=A0exception=C2=A0packet=C2=A0to=C2=A0kernel=C2=A0by=C2=A0DPDK=C2= =A0primary=C2=A0block.
If=C2=A0the=C2=A0secondary=C2=A0blo= ck=C2=A0is=C2=A0driven=C2=A0in=C2=A0this=C2=A0state,=C2=A0vdev=C2=A0probe= =C2=A0is=C2=A0performed=C2=A0inside=C2=A0rte_eal_init func and=C2=A0memory= =C2=A0is=C2=A0allocated=C2=A0using=C2=A0the=C2=A0rte_zmalloc_socket=C2=A0fu= nction=C2=A0if=C2=A0it=C2=A0is=C2=A0a=C2=A0secondary=C2=A0block=C2=A0in=C2= =A0the=C2=A0rte_pmd_tap_probe=C2=A0(dpdk-20.11/drivers/net/tap/rte_eth_tap.= c)=C2=A0function.
The=C2=A0secondary=C2=A0block=C2=A0menti= oned=C2=A0is=C2=A0used=C2=A0to=C2=A0debug=C2=A0the primary block=C2=A0and= =C2=A0is=C2=A0terminated=C2=A0immediately=C2=A0after=C2=A0executing=C2=A0th= e=C2=A0command so the=C2=A0memory=C2=A0allocated=C2=A0above=C2=A0is=C2=A0no= t=C2=A0free=C2=A0and=C2=A0is=C2=A0lost.
The secondary bloc= k=C2=A0does not=C2=A0access=C2=A0the=C2=A0tap interface, is=C2=A0there=C2= =A0any=C2=A0way=C2=A0to=C2=A0prevent=C2=A0memory=C2=A0allocation for tap vd= ev?
I am=C2=A0inquiring this because=C2=A0rte_eth_tap.c= =C2=A0file copyrighted
--000000000000cfecb305d349455b--