From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from dpdk.org (dpdk.org [92.243.14.124]) by inbox.dpdk.org (Postfix) with ESMTP id 8022FA04FF; Tue, 14 Jan 2020 16:04:36 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 38B8C1BFA0; Tue, 14 Jan 2020 16:04:36 +0100 (CET) Received: from us-smtp-1.mimecast.com (us-smtp-delivery-1.mimecast.com [205.139.110.120]) by dpdk.org (Postfix) with ESMTP id DD7C31BF8C for ; Tue, 14 Jan 2020 16:04:34 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1579014274; 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: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:autocrypt:autocrypt; bh=yLBkeW/4lRP/PWFAZUuBetAbczgm3Ga3GkvVXgS+iHw=; b=HC/UWPTzHkzaN2cDB0gnsDySLp15xzv86CSRLuuxEtRvl6hX2OqDoTub5ZwYN+GcS4wgRV 60EZNw6ZZoAmf+p+8xOwJEOgtQMdc57315alZAFzLORx5cJq22WuElVP6sCG4ZQP5xFenp OhfOS7LQjbFvyl2yriGUtpFxkqLIqbw= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-374-TRfBAO6oPEOEu59HB9XPzg-1; Tue, 14 Jan 2020 10:04:30 -0500 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 4ACA1593A5; Tue, 14 Jan 2020 15:04:29 +0000 (UTC) Received: from [10.36.112.13] (unknown [10.36.112.13]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 049645D9E5; Tue, 14 Jan 2020 15:04:26 +0000 (UTC) To: Xuan Ding , tiwei.bie@intel.com, zhihong.wang@intel.com, yong.liu@intel.com, xiaolong.ye@intel.com Cc: dev@dpdk.org, stable@dpdk.org References: <20191218022406.86245-1-xuan.ding@intel.com> <20191223072519.18899-1-xuan.ding@intel.com> From: Maxime Coquelin Autocrypt: addr=maxime.coquelin@redhat.com; keydata= mQINBFOEQQIBEADjNLYZZqghYuWv1nlLisptPJp+TSxE/KuP7x47e1Gr5/oMDJ1OKNG8rlNg kLgBQUki3voWhUbMb69ybqdMUHOl21DGCj0BTU3lXwapYXOAnsh8q6RRM+deUpasyT+Jvf3a gU35dgZcomRh5HPmKMU4KfeA38cVUebsFec1HuJAWzOb/UdtQkYyZR4rbzw8SbsOemtMtwOx YdXodneQD7KuRU9IhJKiEfipwqk2pufm2VSGl570l5ANyWMA/XADNhcEXhpkZ1Iwj3TWO7XR uH4xfvPl8nBsLo/EbEI7fbuUULcAnHfowQslPUm6/yaGv6cT5160SPXT1t8U9QDO6aTSo59N jH519JS8oeKZB1n1eLDslCfBpIpWkW8ZElGkOGWAN0vmpLfdyiqBNNyS3eGAfMkJ6b1A24un /TKc6j2QxM0QK4yZGfAxDxtvDv9LFXec8ENJYsbiR6WHRHq7wXl/n8guyh5AuBNQ3LIK44x0 KjGXP1FJkUhUuruGyZsMrDLBRHYi+hhDAgRjqHgoXi5XGETA1PAiNBNnQwMf5aubt+mE2Q5r qLNTgwSo2dpTU3+mJ3y3KlsIfoaxYI7XNsPRXGnZi4hbxmeb2NSXgdCXhX3nELUNYm4ArKBP LugOIT/zRwk0H0+RVwL2zHdMO1Tht1UOFGfOZpvuBF60jhMzbQARAQABtCxNYXhpbWUgQ29x dWVsaW4gPG1heGltZS5jb3F1ZWxpbkByZWRoYXQuY29tPokCOAQTAQIAIgUCV3u/5QIbAwYL CQgHAwIGFQgCCQoLBBYCAwECHgECF4AACgkQyjiNKEaHD4ma2g/+P+Hg9WkONPaY1J4AR7Uf kBneosS4NO3CRy0x4WYmUSLYMLx1I3VH6SVjqZ6uBoYy6Fs6TbF6SHNc7QbB6Qjo3neqnQR1 71Ua1MFvIob8vUEl3jAR/+oaE1UJKrxjWztpppQTukIk4oJOmXbL0nj3d8dA2QgHdTyttZ1H xzZJWWz6vqxCrUqHU7RSH9iWg9R2iuTzii4/vk1oi4Qz7y/q8ONOq6ffOy/t5xSZOMtZCspu Mll2Szzpc/trFO0pLH4LZZfz/nXh2uuUbk8qRIJBIjZH3ZQfACffgfNefLe2PxMqJZ8mFJXc RQO0ONZvwoOoHL6CcnFZp2i0P5ddduzwPdGsPq1bnIXnZqJSl3dUfh3xG5ArkliZ/++zGF1O wvpGvpIuOgLqjyCNNRoR7cP7y8F24gWE/HqJBXs1qzdj/5Hr68NVPV1Tu/l2D1KMOcL5sOrz 2jLXauqDWn1Okk9hkXAP7+0Cmi6QwAPuBT3i6t2e8UdtMtCE4sLesWS/XohnSFFscZR6Vaf3 gKdWiJ/fW64L6b9gjkWtHd4jAJBAIAx1JM6xcA1xMbAFsD8gA2oDBWogHGYcScY/4riDNKXi lw92d6IEHnSf6y7KJCKq8F+Jrj2BwRJiFKTJ6ChbOpyyR6nGTckzsLgday2KxBIyuh4w+hMq TGDSp2rmWGJjASq5Ag0EVPSbkwEQAMkaNc084Qvql+XW+wcUIY+Dn9A2D1gMr2BVwdSfVDN7 0ZYxo9PvSkzh6eQmnZNQtl8WSHl3VG3IEDQzsMQ2ftZn2sxjcCadexrQQv3Lu60Tgj7YVYRM H+fLYt9W5YuWduJ+FPLbjIKynBf6JCRMWr75QAOhhhaI0tsie3eDsKQBA0w7WCuPiZiheJaL 4MDe9hcH4rM3ybnRW7K2dLszWNhHVoYSFlZGYh+MGpuODeQKDS035+4H2rEWgg+iaOwqD7bg CQXwTZ1kSrm8NxIRVD3MBtzp9SZdUHLfmBl/tLVwDSZvHZhhvJHC6Lj6VL4jPXF5K2+Nn/Su CQmEBisOmwnXZhhu8ulAZ7S2tcl94DCo60ReheDoPBU8PR2TLg8rS5f9w6mLYarvQWL7cDtT d2eX3Z6TggfNINr/RTFrrAd7NHl5h3OnlXj7PQ1f0kfufduOeCQddJN4gsQfxo/qvWVB7PaE 1WTIggPmWS+Xxijk7xG6x9McTdmGhYaPZBpAxewK8ypl5+yubVsE9yOOhKMVo9DoVCjh5To5 aph7CQWfQsV7cd9PfSJjI2lXI0dhEXhQ7lRCFpf3V3mD6CyrhpcJpV6XVGjxJvGUale7+IOp sQIbPKUHpB2F+ZUPWds9yyVxGwDxD8WLqKKy0WLIjkkSsOb9UBNzgRyzrEC9lgQ/ABEBAAGJ Ah8EGAECAAkFAlT0m5MCGwwACgkQyjiNKEaHD4nU8hAAtt0xFJAy0sOWqSmyxTc7FUcX+pbD KVyPlpl6urKKMk1XtVMUPuae/+UwvIt0urk1mXi6DnrAN50TmQqvdjcPTQ6uoZ8zjgGeASZg jj0/bJGhgUr9U7oG7Hh2F8vzpOqZrdd65MRkxmc7bWj1k81tOU2woR/Gy8xLzi0k0KUa8ueB iYOcZcIGTcs9CssVwQjYaXRoeT65LJnTxYZif2pfNxfINFzCGw42s3EtZFteczClKcVSJ1+L +QUY/J24x0/ocQX/M1PwtZbB4c/2Pg/t5FS+s6UB1Ce08xsJDcwyOPIH6O3tccZuriHgvqKP yKz/Ble76+NFlTK1mpUlfM7PVhD5XzrDUEHWRTeTJSvJ8TIPL4uyfzhjHhlkCU0mw7Pscyxn DE8G0UYMEaNgaZap8dcGMYH/96EfE5s/nTX0M6MXV0yots7U2BDb4soLCxLOJz4tAFDtNFtA wLBhXRSvWhdBJZiig/9CG3dXmKfi2H+wdUCSvEFHRpgo7GK8/Kh3vGhgKmnnxhl8ACBaGy9n fxjSxjSO6rj4/MeenmlJw1yebzkX8ZmaSi8BHe+n6jTGEFNrbiOdWpJgc5yHIZZnwXaW54QT UhhSjDL1rV2B4F28w30jYmlRmm2RdN7iCZfbyP3dvFQTzQ4ySquuPkIGcOOHrvZzxbRjzMx1 Mwqu3GQ= Message-ID: <14e25591-ed6e-6a1d-c20a-ab967c23b7c8@redhat.com> Date: Tue, 14 Jan 2020 16:04:24 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101 Thunderbird/68.1.0 MIME-Version: 1.0 In-Reply-To: <20191223072519.18899-1-xuan.ding@intel.com> Content-Language: en-US X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 X-MC-Unique: TRfBAO6oPEOEu59HB9XPzg-1 X-Mimecast-Spam-Score: 0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: quoted-printable Subject: Re: [dpdk-dev] [PATCH v4] net/virtio-user: fix packed ring server mode X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 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" On 12/23/19 8:25 AM, Xuan Ding wrote: > This patch fixes the situation where datapath does not work properly when > vhost reconnects to virtio in server mode with packed ring. >=20 > Currently, virtio and vhost share memory of vring. For split ring, vhost > can read the status of discriptors directly from the available ring and s/discriptors/descriptors/ > the used ring during reconnection. Therefore, the datapath can continue. >=20 > But for packed ring, when reconnecting to virtio, vhost cannot get the > status of discriptors only through the descriptor ring. By resetting Tx s/discriptor only through/descriptor via/ > and Rx queues, the datapath can restart from the beginning. >=20 > Fixes: 4c3f5822eb214 ("net/virtio: add packed virtqueue defines") > Cc: stable@dpdk.org >=20 > Signed-off-by: Xuan Ding > --- >=20 > v4: > * Moved change log below '---' marker. >=20 > v3: > * Removed an extra asterisk from a comment. > * Renamed device reset function and moved it to virtio_user_ethdev.c. >=20 > v2: > * Renamed queue reset functions and moved them to virtqueue.c. >=20 > drivers/net/virtio/virtio_ethdev.c | 4 +- > drivers/net/virtio/virtio_user_ethdev.c | 40 ++++++++++++++ > drivers/net/virtio/virtqueue.c | 71 +++++++++++++++++++++++++ > drivers/net/virtio/virtqueue.h | 4 ++ > 4 files changed, 117 insertions(+), 2 deletions(-) >=20 > diff --git a/drivers/net/virtio/virtio_ethdev.c b/drivers/net/virtio/virt= io_ethdev.c > index 044eb10a7..f9d0ea70d 100644 > --- a/drivers/net/virtio/virtio_ethdev.c > +++ b/drivers/net/virtio/virtio_ethdev.c > @@ -1913,6 +1913,8 @@ eth_virtio_dev_init(struct rte_eth_dev *eth_dev) > =09=09=09goto err_vtpci_init; > =09} > =20 > +=09rte_spinlock_init(&hw->state_lock); > + > =09/* reset device and negotiate default features */ > =09ret =3D virtio_init_device(eth_dev, VIRTIO_PMD_DEFAULT_GUEST_FEATURES= ); > =09if (ret < 0) > @@ -2155,8 +2157,6 @@ virtio_dev_configure(struct rte_eth_dev *dev) > =09=09=09return -EBUSY; > =09=09} > =20 > -=09rte_spinlock_init(&hw->state_lock); > - > =09hw->use_simple_rx =3D 1; > =20 > =09if (vtpci_with_feature(hw, VIRTIO_F_IN_ORDER)) { > diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio= /virtio_user_ethdev.c > index 3fc172573..425f48230 100644 > --- a/drivers/net/virtio/virtio_user_ethdev.c > +++ b/drivers/net/virtio/virtio_user_ethdev.c > @@ -25,12 +25,48 @@ > #define virtio_user_get_dev(hw) \ > =09((struct virtio_user_dev *)(hw)->virtio_user_dev) > =20 > +static void > +virtio_user_reset_queues_packed(struct rte_eth_dev *dev) > +{ > +=09struct virtio_hw *hw =3D dev->data->dev_private; > +=09struct virtnet_rx *rxvq; > +=09struct virtnet_tx *txvq; > +=09uint16_t i; > + > +=09/* Add lock to avoid queue contention. */ > +=09rte_spinlock_lock(&hw->state_lock); > +=09hw->started =3D 0; > + > +=09/* > +=09 * Waitting for datapath to complete before resetting queues. > +=09 * 1 ms should be enough for the ongoing Tx/Rx function to finish. > +=09 */ > +=09rte_delay_ms(1); > + > +=09/* Vring reset for each Tx queue and Rx queue. */ > +=09for (i =3D 0; i < dev->data->nb_rx_queues; i++) { > +=09=09rxvq =3D dev->data->rx_queues[i]; > +=09=09virtqueue_rxvq_reset_packed(rxvq->vq); > +=09=09virtio_dev_rx_queue_setup_finish(dev, i); > +=09} > + > +=09for (i =3D 0; i < dev->data->nb_tx_queues; i++) { > +=09=09txvq =3D dev->data->tx_queues[i]; > +=09=09virtqueue_txvq_reset_packed(txvq->vq); > +=09} > + > +=09hw->started =3D 1; > +=09rte_spinlock_unlock(&hw->state_lock); > +} > + > + > static int > virtio_user_server_reconnect(struct virtio_user_dev *dev) > { > =09int ret; > =09int connectfd; > =09struct rte_eth_dev *eth_dev =3D &rte_eth_devices[dev->port_id]; > +=09struct virtio_hw *hw =3D eth_dev->data->dev_private; > =20 > =09connectfd =3D accept(dev->listenfd, NULL, NULL); > =09if (connectfd < 0) > @@ -51,6 +87,10 @@ virtio_user_server_reconnect(struct virtio_user_dev *d= ev) > =20 > =09dev->features &=3D dev->device_features; > =20 > +=09/* For packed ring, resetting queues is required in reconnection. */ > +=09if (vtpci_packed_queue(hw)) > +=09=09virtio_user_reset_queues_packed(eth_dev); I think we should log an error here to state that some packets are likely to be dropped. Other than that, I don't think we have other choices than doing that right now, so I'll ack your patch once commit message is fixed and error message is printed on vrings reset. Thanks, Maxime