From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 93339C433FE for ; Wed, 30 Nov 2022 12:08:56 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233789AbiK3MIx (ORCPT ); Wed, 30 Nov 2022 07:08:53 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:56282 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S233577AbiK3MIj (ORCPT ); Wed, 30 Nov 2022 07:08:39 -0500 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 793A07643 for ; Wed, 30 Nov 2022 04:07:39 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1669810058; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: in-reply-to:in-reply-to:references:references; bh=jnVdlteFV26Z76cEF4gxE55CdPW4P3QACX8nQF2ZXTo=; b=W/dSB4qs5hwMfYN4TjxxFnqFD4auu9K07/woj4RDIZunyWcd9qT2g9XoFZvOSjAqfTe4Ga sPDuA5GKhAnz1PJtE0E805fwucXHtgi6wF0TyYucotzcJnBT4lkI2YNflsI6f5EEvixFEq 5X6WL3hpHvkVlHRo2bXgnkAdSZ4Yo+A= Received: from mail-wm1-f71.google.com (mail-wm1-f71.google.com [209.85.128.71]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_128_GCM_SHA256) id us-mta-518-ez1_AMZFPeC1O7R5m-sHXA-1; Wed, 30 Nov 2022 07:07:37 -0500 X-MC-Unique: ez1_AMZFPeC1O7R5m-sHXA-1 Received: by mail-wm1-f71.google.com with SMTP id l42-20020a05600c1d2a00b003cf8e70c1ecso907959wms.4 for ; Wed, 30 Nov 2022 04:07:37 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:x-gm-message-state:from:to:cc:subject:date :message-id:reply-to; bh=jnVdlteFV26Z76cEF4gxE55CdPW4P3QACX8nQF2ZXTo=; b=OvRGd68qPpLcrxbAV0SetMDJ1tpPjS1VuVr1ZgONPuLznM25q3hZ05BeNa0o4FJFa4 ShEH9ZjuCGEiy35NDZou5PJYykoWrihEfqTfVbgJcdc7715Tp3Y93Mj1xVFRiLW7zjPm g+krT2BhYaO+K0ArwPmzKs4UAdksxw7sw5jN4KrO7CWzNovhPgCgJ35Qv3gl7w4ze2At eiXojWVPk0lKuKcZzxbRwlh0/BwWeVezkho6wc7P55griUr3LxyEcYQD/xC05dgD1M48 wwLGFmTAlUTdch7Rh1P/hVDgoXSGw7Jv/4D14Rd2UZNCPdcwXwwomj9oJ+og2jnKBA1d 6Jhg== X-Gm-Message-State: ANoB5pn3cG47/7BAg6NfRP85Gg6SvT1WrqIAH5AOtjIV7wpHzOfElIP3 ebfthVvpXPz8OPJmS2PUEQiOWfoUs9BfmSX/wAmCruxJ1xodV7hTpgzbgXj3pNPklIGXbI3T+FM XWrWBNQrHjzOsJQgSJBOx X-Received: by 2002:a05:600c:3c8e:b0:3d0:69f4:d3d0 with SMTP id bg14-20020a05600c3c8e00b003d069f4d3d0mr4598111wmb.93.1669810056147; Wed, 30 Nov 2022 04:07:36 -0800 (PST) X-Google-Smtp-Source: AA0mqf4PpVsPubG71ps8rgagttNzK50w8zECDxzJfF2enqQnAPQgsvcgKe3HBaErdsIeSxrgevrHjQ== X-Received: by 2002:a05:600c:3c8e:b0:3d0:69f4:d3d0 with SMTP id bg14-20020a05600c3c8e00b003d069f4d3d0mr4598054wmb.93.1669810055886; Wed, 30 Nov 2022 04:07:35 -0800 (PST) Received: from pc-4.home (2a01cb058918ce00dd1a5a4f9908f2d5.ipv6.abo.wanadoo.fr. [2a01:cb05:8918:ce00:dd1a:5a4f:9908:f2d5]) by smtp.gmail.com with ESMTPSA id j3-20020adfd203000000b002366c3eefccsm1368822wrh.109.2022.11.30.04.07.33 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 30 Nov 2022 04:07:35 -0800 (PST) Date: Wed, 30 Nov 2022 13:07:32 +0100 From: Guillaume Nault To: Benjamin Coddington Cc: Christoph Hellwig , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Philipp Reisner , Lars Ellenberg , Christoph =?iso-8859-1?Q?B=F6hmwalder?= , Jens Axboe , Josef Bacik , Keith Busch , Sagi Grimberg , Lee Duncan , Chris Leech , Mike Christie , "James E.J. Bottomley" , "Martin K. Petersen" , Valentina Manea , Shuah Khan , Greg Kroah-Hartman , David Howells , Marc Dionne , Steve French , Christine Caulfield , David Teigland , Mark Fasheh , Joel Becker , Joseph Qi , Eric Van Hensbergen , Latchesar Ionkov , Dominique Martinet , "David S. Miller" , Eric Dumazet , Jakub Kicinski , Paolo Abeni , Ilya Dryomov , Xiubo Li , Trond Myklebust , Anna Schumaker , Chuck Lever , Jeff Layton , drbd-dev@lists.linbit.com, linux-block@vger.kernel.org, nbd@other.debian.org, linux-nvme@lists.infradead.org, open-iscsi@googlegroups.com, linux-scsi@vger.kernel.org, linux-usb@vger.kernel.org, linux-afs@lists.infradead.org, linux-cifs@vger.kernel.org, samba-technical@lists.samba.org, cluster-devel@redhat.com, ocfs2-devel@oss.oracle.com, v9fs-developer@lists.sourceforge.net, ceph-devel@vger.kernel.org, linux-nfs@vger.kernel.org Subject: Re: [PATCH v1 2/3] Treewide: Stop corrupting socket's task_frag Message-ID: <20221130120732.GB29316@pc-4.home> References: <20221129140242.GA15747@lst.de> <794DBAB0-EDAF-4DA2-A837-C1F99916BC8E@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <794DBAB0-EDAF-4DA2-A837-C1F99916BC8E@redhat.com> Precedence: bulk List-ID: X-Mailing-List: linux-nfs@vger.kernel.org On Tue, Nov 29, 2022 at 11:47:47AM -0500, Benjamin Coddington wrote: > On 29 Nov 2022, at 9:02, Christoph Hellwig wrote: > > > Hmm. Having to set a flag to not accidentally corrupt per-task > > state seems a bit fragile. Wouldn't it make sense to find a way to opt > > into the feature only for sockets created from the syscall layer? > > It's totally fragile, and that's why it's currently broken in production. > The fragile ship sailed when networking decided to depend on users setting > the socket's GFP_ flags correctly to avoid corruption. > > Meantime, this problem needs fixing in a way that makes everyone happy. > This fix doesn't make it less fragile, but it may (hopefully) address the > previous criticisms enough that something gets done to fix it. Also, let's remember that while we're discussing how the kernel sould work in an ideal world, the reality is that production NFS systems crash randomly upon memory reclaim since commit a1231fda7e94 ("SUNRPC: Set memalloc_nofs_save() on all rpciod/xprtiod jobs"). Fixing that is just a matter of re-introducing GFP_NOFS on SUNRPC sockets (which has been proposed several times already). Then we'll have plenty of time to argue about how networking should use the per-task page_frag and how to remove GFP_NOFS in the long term.