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 68302C07E9D for ; Thu, 29 Sep 2022 07:40:44 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235365AbiI2Hkn (ORCPT ); Thu, 29 Sep 2022 03:40:43 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:49360 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235364AbiI2Hke (ORCPT ); Thu, 29 Sep 2022 03:40:34 -0400 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 4F8187F11D for ; Thu, 29 Sep 2022 00:40:24 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1664437223; 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=oaCFqrQ5GzdKP7AhOQ10Zj7koIi79amAnF/+mMQ81sg=; b=b4YfKYj08HJibCovZfAlzY12sCe0/NHnIU3gVzbJfhTovGDLxhA9iCLu3YSSJygfvLb8gH 3rlxcv8zN4UKPkDZMKH+v3DhSvCl1Db0sGW4hZLki8HgAHlzo/LIRMkcO/xXW/FEQCk9pO 34lkHUMat4GskCyzXKEf8VWHqrBiGx4= Received: from mail-qk1-f200.google.com (mail-qk1-f200.google.com [209.85.222.200]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_128_GCM_SHA256) id us-mta-67-veOYiquaOYyPx7DyCjlpaw-1; Thu, 29 Sep 2022 03:40:21 -0400 X-MC-Unique: veOYiquaOYyPx7DyCjlpaw-1 Received: by mail-qk1-f200.google.com with SMTP id i7-20020a05620a404700b006ced0d02b68so488529qko.10 for ; Thu, 29 Sep 2022 00:40:21 -0700 (PDT) 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; bh=oaCFqrQ5GzdKP7AhOQ10Zj7koIi79amAnF/+mMQ81sg=; b=5Ug9c6dLGeWit/nXfIU9NBK/YiTNjBM/t4s+5bfLbhsA+GGv7w/vWAlfVOxdu7ym74 GHWXvxT6EEEOa125inGOpTpHaaIF9WOIwvvKo3J/cp1Y6Q+htMKPqFZ++sfoVW1w11oM oC0CFROfAB6f+/z0J7AgzrdMOugjZZQ5u2py+oP7cYLDTyTqra40/zURGj9tA6BTASgL xuXuCSCrrpOxWvV3QXuiYSg3obS00QywTtbdBgraBrM+Hhjq6psi+SflKEpZhyokvvGf etRKNndb3bID1vK3OQbu/ip1AEsTa0EadgWtFJNgi0C+yMkAHc2EeRJTVLKjNKmfdrZt 7ifA== X-Gm-Message-State: ACrzQf0I4vsjW4qip/mllv8dx5BxindjgvYznfJZ8KcJkAwnZK4FHaIY LT3VgSXZnEasEkxLybFDfIpOlceOy+pzUR1iXLPUc4NaFCXJiXwhPisrqu2YAqZ6Rd4Smv1ogwf 0ti8hhw4ajPG8iHeB X-Received: by 2002:a05:620a:c15:b0:6ce:d1db:f7dc with SMTP id l21-20020a05620a0c1500b006ced1dbf7dcmr1200823qki.259.1664437221183; Thu, 29 Sep 2022 00:40:21 -0700 (PDT) X-Google-Smtp-Source: AMsMyM7ojPjmY7apjIi1WK+7gxu/7NwTtehomIcT45iZfLQ6HJTQ6dVYty87P02i03q/EK/PFipsQA== X-Received: by 2002:a05:620a:c15:b0:6ce:d1db:f7dc with SMTP id l21-20020a05620a0c1500b006ced1dbf7dcmr1200814qki.259.1664437220936; Thu, 29 Sep 2022 00:40:20 -0700 (PDT) Received: from sgarzare-redhat (host-79-46-200-222.retail.telecomitalia.it. [79.46.200.222]) by smtp.gmail.com with ESMTPSA id x11-20020a05620a258b00b006bac157ec19sm5392848qko.123.2022.09.29.00.40.17 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 29 Sep 2022 00:40:20 -0700 (PDT) Date: Thu, 29 Sep 2022 09:40:10 +0200 From: Stefano Garzarella To: "Michael S. Tsirkin" Cc: Junichi Uekawa , Stefan Hajnoczi , Jason Wang , Eric Dumazet , davem@davemloft.net, netdev@vger.kernel.org, Jakub Kicinski , virtualization@lists.linux-foundation.org, kvm@vger.kernel.org, Paolo Abeni , linux-kernel@vger.kernel.org, Bobby Eshleman Subject: Re: [PATCH] vhost/vsock: Use kvmalloc/kvfree for larger packets. Message-ID: <20220929074010.37mksjmwr3l4wlwt@sgarzare-redhat> References: <20220928064538.667678-1-uekawa@chromium.org> <20220928082823.wyxplop5wtpuurwo@sgarzare-redhat> <20220928052738-mutt-send-email-mst@kernel.org> <20220928151135.pvrlsylg6j3hzh74@sgarzare-redhat> <20220928160116-mutt-send-email-mst@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Disposition: inline In-Reply-To: <20220928160116-mutt-send-email-mst@kernel.org> Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org On Wed, Sep 28, 2022 at 04:02:12PM -0400, Michael S. Tsirkin wrote: >On Wed, Sep 28, 2022 at 05:11:35PM +0200, Stefano Garzarella wrote: >> On Wed, Sep 28, 2022 at 05:31:58AM -0400, Michael S. Tsirkin wrote: >> > On Wed, Sep 28, 2022 at 10:28:23AM +0200, Stefano Garzarella wrote: >> > > On Wed, Sep 28, 2022 at 03:45:38PM +0900, Junichi Uekawa wrote: >> > > > When copying a large file over sftp over vsock, data size is usually 32kB, >> > > > and kmalloc seems to fail to try to allocate 32 32kB regions. >> > > > >> > > > Call Trace: >> > > > [] dump_stack+0x97/0xdb >> > > > [] warn_alloc_failed+0x10f/0x138 >> > > > [] ? __alloc_pages_direct_compact+0x38/0xc8 >> > > > [] __alloc_pages_nodemask+0x84c/0x90d >> > > > [] alloc_kmem_pages+0x17/0x19 >> > > > [] kmalloc_order_trace+0x2b/0xdb >> > > > [] __kmalloc+0x177/0x1f7 >> > > > [] ? copy_from_iter+0x8d/0x31d >> > > > [] vhost_vsock_handle_tx_kick+0x1fa/0x301 [vhost_vsock] >> > > > [] vhost_worker+0xf7/0x157 [vhost] >> > > > [] kthread+0xfd/0x105 >> > > > [] ? vhost_dev_set_owner+0x22e/0x22e [vhost] >> > > > [] ? flush_kthread_worker+0xf3/0xf3 >> > > > [] ret_from_fork+0x4e/0x80 >> > > > [] ? flush_kthread_worker+0xf3/0xf3 >> > > > >> > > > Work around by doing kvmalloc instead. >> > > > >> > > > Signed-off-by: Junichi Uekawa >> > >> > My worry here is that this in more of a work around. >> > It would be better to not allocate memory so aggressively: >> > if we are so short on memory we should probably process >> > packets one at a time. Is that very hard to implement? >> >> Currently the "virtio_vsock_pkt" is allocated in the "handle_kick" callback >> of TX virtqueue. Then the packet is multiplexed on the right socket queue, >> then the user space can de-queue it whenever they want. >> >> So maybe we can stop processing the virtqueue if we are short on memory, but >> when can we restart the TX virtqueue processing? > >Assuming you added at least one buffer, the time to restart would be >after that buffer has been used. Yes, but we still might not have as many continuous pages to allocate, so I would use kvmalloc the same. I agree that we should do better, I hope that moving to sk_buff will allow us to better manage allocation. Maybe after we merge that part we should spend some time to solve these problems. Thanks, Stefano