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 83AF7A04FA; Tue, 17 Dec 2019 08:18:48 +0100 (CET) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 573502C17; Tue, 17 Dec 2019 08:18:48 +0100 (CET) Received: from us-smtp-1.mimecast.com (us-smtp-1.mimecast.com [205.139.110.61]) by dpdk.org (Postfix) with ESMTP id E137B330 for ; Tue, 17 Dec 2019 08:18:46 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1576567126; 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=Me6tEIOgCqa20uuN2gPMjqzAlg2BYuX4VI65cRqy1NE=; b=GFRCejMAH5UW7m9L/TYnP9mJCs1nbXEljoDegkfaSrE1c6p/FedVwmZ7sMf25WF+63A/Pe 1TMmKEdVmzsoyb/+9lZP9FdfMrbiyeED5k7+B9weW0MPtRaHWhUvKCBD50hroOrWFcw9ij 4ogbNumn+RBIzAAbsr2+3XH9dAvs2CE= 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-18-pM2UnQehPmWux1Sk2H3wPw-1; Tue, 17 Dec 2019 02:18:42 -0500 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.phx2.redhat.com [10.5.11.15]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id AA73F593A3; Tue, 17 Dec 2019 07:18:41 +0000 (UTC) Received: from [10.36.112.19] (ovpn-112-19.ams2.redhat.com [10.36.112.19]) by smtp.corp.redhat.com (Postfix) with ESMTPS id CAB5067015; Tue, 17 Dec 2019 07:18:39 +0000 (UTC) To: Jiayu Hu , dev@dpdk.org Cc: tiwei.bie@intel.com, zhihong.wang@intel.com References: <1569507973-247570-1-git-send-email-jiayu.hu@intel.com> <1569507973-247570-2-git-send-email-jiayu.hu@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: Date: Tue, 17 Dec 2019 08:18:37 +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: <1569507973-247570-2-git-send-email-jiayu.hu@intel.com> Content-Language: en-US X-Scanned-By: MIMEDefang 2.79 on 10.5.11.15 X-MC-Unique: pM2UnQehPmWux1Sk2H3wPw-1 X-Mimecast-Spam-Score: 0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Subject: Re: [dpdk-dev] [RFC 1/2] vhost: populate guest memory for DMA-accelerated vhost-user 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 9/26/19 4:26 PM, Jiayu Hu wrote: > DMA engines, like I/OAT, are efficient in moving large data > within memory. Offloading large copies in vhost side to DMA > engines can save precious CPU cycles and improve vhost > performance. >=20 > However, using the DMA engine requires to populate guest's > memory. This patch is to enable DMA-accelerated vhost-user > to populate guest's memory. >=20 > Signed-off-by: Jiayu Hu > --- > lib/librte_vhost/rte_vhost.h | 1 + > lib/librte_vhost/socket.c | 10 ++++++++++ > lib/librte_vhost/vhost.h | 2 ++ > lib/librte_vhost/vhost_user.c | 3 ++- > 4 files changed, 15 insertions(+), 1 deletion(-) >=20 > diff --git a/lib/librte_vhost/rte_vhost.h b/lib/librte_vhost/rte_vhost.h > index 7fb1729..61f8bef 100644 > --- a/lib/librte_vhost/rte_vhost.h > +++ b/lib/librte_vhost/rte_vhost.h > @@ -30,6 +30,7 @@ extern "C" { > #define RTE_VHOST_USER_DEQUEUE_ZERO_COPY=09(1ULL << 2) > #define RTE_VHOST_USER_IOMMU_SUPPORT=09(1ULL << 3) > #define RTE_VHOST_USER_POSTCOPY_SUPPORT=09=09(1ULL << 4) > +#define RTE_VHOST_USER_DMA_COPY=09=09(1ULL << 5) > =20 > /** Protocol features. */ > #ifndef VHOST_USER_PROTOCOL_F_MQ > diff --git a/lib/librte_vhost/socket.c b/lib/librte_vhost/socket.c > index 274988c..55498c4 100644 > --- a/lib/librte_vhost/socket.c > +++ b/lib/librte_vhost/socket.c > @@ -60,6 +60,8 @@ struct vhost_user_socket { > =09 */ > =09int vdpa_dev_id; > =20 > +=09bool dma_enabled; > + > =09struct vhost_device_ops const *notify_ops; > }; > =20 > @@ -232,6 +234,13 @@ vhost_user_add_connection(int fd, struct vhost_user_= socket *vsocket) > =09if (vsocket->dequeue_zero_copy) > =09=09vhost_enable_dequeue_zero_copy(vid); > =20 > +=09if (vsocket->dma_enabled) { > +=09=09struct virtio_net *dev; > + > +=09=09dev =3D get_device(vid); > +=09=09dev->dma_enabled =3D true; > +=09} > + > =09RTE_LOG(INFO, VHOST_CONFIG, "new device, handle is %d\n", vid); > =20 > =09if (vsocket->notify_ops->new_connection) { > @@ -870,6 +879,7 @@ rte_vhost_driver_register(const char *path, uint64_t = flags) > =09=09goto out_free; > =09} > =09vsocket->dequeue_zero_copy =3D flags & RTE_VHOST_USER_DEQUEUE_ZERO_CO= PY; > +=09vsocket->dma_enabled =3D flags & RTE_VHOST_USER_DMA_COPY; > =20 > =09/* > =09 * Set the supported features correctly for the builtin vhost-user I think you also need to disable VHOST_USER_PROTOCOL_F_PAGEFAULT from the supported protocol features if DMA is enabled, since it requires MAP_POPULATE which is not compatible with postcopy. > diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h > index 884befa..8f564f1 100644 > --- a/lib/librte_vhost/vhost.h > +++ b/lib/librte_vhost/vhost.h > @@ -329,6 +329,8 @@ struct virtio_net { > =09 */ > =09int=09=09=09vdpa_dev_id; > =20 > +=09bool=09=09=09dma_enabled; > + > =09/* context data for the external message handlers */ > =09void=09=09=09*extern_data; > =09/* pre and post vhost user message handlers for the device */ > diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.= c > index 0b72648..6a4969b 100644 > --- a/lib/librte_vhost/vhost_user.c > +++ b/lib/librte_vhost/vhost_user.c > @@ -990,7 +990,8 @@ vhost_user_set_mem_table(struct virtio_net **pdev, st= ruct VhostUserMsg *msg, > =09=09} > =09=09mmap_size =3D RTE_ALIGN_CEIL(mmap_size, alignment); > =20 > -=09=09populate =3D (dev->dequeue_zero_copy) ? MAP_POPULATE : 0; > +=09=09populate =3D (dev->dequeue_zero_copy || dev->dma_enabled) ? > +=09=09=09MAP_POPULATE : 0; > =09=09mmap_addr =3D mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, > =09=09=09=09 MAP_SHARED | populate, fd, 0); > =20 >=20