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 C2859A3201 for ; Mon, 21 Oct 2019 11:47:17 +0200 (CEST) Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 8E8214CA7; Mon, 21 Oct 2019 11:47:17 +0200 (CEST) Received: from us-smtp-delivery-1.mimecast.com (us-smtp-1.mimecast.com [207.211.31.81]) by dpdk.org (Postfix) with ESMTP id DC72C2D13 for ; Mon, 21 Oct 2019 11:47:15 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1571651235; 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=USvVbTAjAZwoi6wnjb8BzB6M0W5Hf9wgGKKgeqq//pI=; b=ai8zzVVFml/SPJB0MeqkQHmUEoCDyjlV68/oLzBJCgsYQoh3A6/rkphJ05ihwPyDy80/cW +8ElhNlIJm9zThmR0ybGYCrBtPkWajt+iLSBHLfLArFEvVjhtWZMhud2+hIUrfKRLUlz94 zuw8XgQq0/a48XzKz5XUYDShliZr3CU= 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-81-9pD9xVmuP_29szuAiGMrqw-1; Mon, 21 Oct 2019 05:47:12 -0400 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id EDEC6800D41; Mon, 21 Oct 2019 09:47:10 +0000 (UTC) Received: from [10.36.112.26] (ovpn-112-26.ams2.redhat.com [10.36.112.26]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 08B28108116C; Mon, 21 Oct 2019 09:47:08 +0000 (UTC) To: Marvin Liu , tiwei.bie@intel.com, zhihong.wang@intel.com, stephen@networkplumber.org, gavin.hu@arm.com Cc: dev@dpdk.org References: <20191015160739.51940-1-yong.liu@intel.com> <20191021154016.16274-1-yong.liu@intel.com> <20191021154016.16274-7-yong.liu@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: <60b6ef0f-0433-29ff-46a1-3c0bcb73851f@redhat.com> Date: Mon, 21 Oct 2019 11:47:07 +0200 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: <20191021154016.16274-7-yong.liu@intel.com> Content-Language: en-US X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 X-MC-Unique: 9pD9xVmuP_29szuAiGMrqw-1 X-Mimecast-Spam-Score: 0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Subject: Re: [dpdk-dev] [PATCH v7 06/13] vhost: add packed ring batch dequeue 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 10/21/19 5:40 PM, Marvin Liu wrote: > Add batch dequeue function like enqueue function for packed ring, batch > dequeue function will not support chained descritpors, single packet > dequeue function will handle it. >=20 > Signed-off-by: Marvin Liu >=20 > diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h > index a2b9221e0..67724c342 100644 > --- a/lib/librte_vhost/vhost.h > +++ b/lib/librte_vhost/vhost.h > @@ -39,6 +39,9 @@ > =20 > #define VHOST_LOG_CACHE_NR 32 > =20 > +#define PACKED_DESC_SINGLE_DEQUEUE_FLAG (VRING_DESC_F_NEXT | \ > +=09=09=09=09=09 VRING_DESC_F_INDIRECT) > + > #define PACKED_BATCH_SIZE (RTE_CACHE_LINE_SIZE / \ > =09=09=09 sizeof(struct vring_packed_desc)) > #define PACKED_BATCH_MASK (PACKED_BATCH_SIZE - 1) > diff --git a/lib/librte_vhost/virtio_net.c b/lib/librte_vhost/virtio_net.= c > index 317be1aed..f13fcafbb 100644 > --- a/lib/librte_vhost/virtio_net.c > +++ b/lib/librte_vhost/virtio_net.c > @@ -1635,6 +1635,114 @@ virtio_dev_tx_split(struct virtio_net *dev, struc= t vhost_virtqueue *vq, > =09return i; > } > =20 > +static __rte_always_inline int > +vhost_reserve_avail_batch_packed(struct virtio_net *dev, > +=09=09=09=09 struct vhost_virtqueue *vq, > +=09=09=09=09 struct rte_mempool *mbuf_pool, > +=09=09=09=09 struct rte_mbuf **pkts, > +=09=09=09=09 uint16_t avail_idx, > +=09=09=09=09 uintptr_t *desc_addrs, > +=09=09=09=09 uint16_t *ids) > +{ > +=09bool wrap =3D vq->avail_wrap_counter; > +=09struct vring_packed_desc *descs =3D vq->desc_packed; > +=09struct virtio_net_hdr *hdr; > +=09uint64_t lens[PACKED_BATCH_SIZE]; > +=09uint64_t buf_lens[PACKED_BATCH_SIZE]; > +=09uint32_t buf_offset =3D dev->vhost_hlen; > +=09uint16_t flags, i; > + > +=09if (unlikely(avail_idx & PACKED_BATCH_MASK)) > +=09=09return -1; > +=09if (unlikely((avail_idx + PACKED_BATCH_SIZE) > vq->size)) > +=09=09return -1; > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) { > +=09=09flags =3D descs[avail_idx + i].flags; > +=09=09if (unlikely((wrap !=3D !!(flags & VRING_DESC_F_AVAIL)) || > +=09=09=09 (wrap =3D=3D !!(flags & VRING_DESC_F_USED)) || > +=09=09=09 (flags & PACKED_DESC_SINGLE_DEQUEUE_FLAG))) > +=09=09=09return -1; > +=09} > + > +=09rte_smp_rmb(); > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) > +=09=09lens[i] =3D descs[avail_idx + i].len; > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) { > +=09=09desc_addrs[i] =3D vhost_iova_to_vva(dev, vq, > +=09=09=09=09=09=09 descs[avail_idx + i].addr, > +=09=09=09=09=09=09 &lens[i], VHOST_ACCESS_RW); > +=09} > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) { > +=09=09if (unlikely((lens[i] !=3D descs[avail_idx + i].len))) > +=09=09=09return -1; > +=09} > + > +=09if (rte_pktmbuf_alloc_bulk(mbuf_pool, pkts, PACKED_BATCH_SIZE)) Same here, you may want to create a variant of Flavio's virtio_dev_pktmbuf_alloc for bulk allocations. > +=09=09return -1; > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) > +=09=09buf_lens[i] =3D pkts[i]->buf_len - pkts[i]->data_off; > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) { > +=09=09if (unlikely(buf_lens[i] < (lens[i] - buf_offset))) > +=09=09=09goto free_buf; > +=09} > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) { > +=09=09pkts[i]->pkt_len =3D descs[avail_idx + i].len - buf_offset; > +=09=09pkts[i]->data_len =3D pkts[i]->pkt_len; > +=09=09ids[i] =3D descs[avail_idx + i].id; > +=09} > + > +=09if (virtio_net_with_host_offload(dev)) { > +=09=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) { > +=09=09=09hdr =3D (struct virtio_net_hdr *)(desc_addrs[i]); > +=09=09=09vhost_dequeue_offload(hdr, pkts[i]); > +=09=09} > +=09} > + > +=09return 0; > + > +free_buf: > +=09for (i =3D 0; i < PACKED_BATCH_SIZE; i++) > +=09=09rte_pktmbuf_free(pkts[i]); > + > +=09return -1; > +} > + > +static __rte_unused int > +virtio_dev_tx_batch_packed(struct virtio_net *dev, > +=09=09=09 struct vhost_virtqueue *vq, > +=09=09=09 struct rte_mempool *mbuf_pool, > +=09=09=09 struct rte_mbuf **pkts) > +{ > +=09uint16_t avail_idx =3D vq->last_avail_idx; > +=09uint32_t buf_offset =3D dev->vhost_hlen; > +=09uintptr_t desc_addrs[PACKED_BATCH_SIZE]; > +=09uint16_t ids[PACKED_BATCH_SIZE]; > +=09uint16_t i; > + > +=09if (vhost_reserve_avail_batch_packed(dev, vq, mbuf_pool, pkts, > +=09=09=09=09=09 avail_idx, desc_addrs, ids)) > +=09=09return -1; > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) > +=09=09rte_prefetch0((void *)(uintptr_t)desc_addrs[i]); > + > +=09vhost_for_each_try_unroll(i, 0, PACKED_BATCH_SIZE) > +=09=09rte_memcpy(rte_pktmbuf_mtod_offset(pkts[i], void *, 0), > +=09=09=09 (void *)(uintptr_t)(desc_addrs[i] + buf_offset), > +=09=09=09 pkts[i]->pkt_len); > + > +=09vq_inc_last_avail_packed(vq, PACKED_BATCH_SIZE); > + > +=09return 0; > +} > + > static __rte_always_inline int > vhost_dequeue_single_packed(struct virtio_net *dev, > =09=09=09 struct vhost_virtqueue *vq, >=20