From patchwork Fri Oct 7 10:01:49 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Stefan Hajnoczi X-Patchwork-Id: 9365939 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 566FD6077E for ; Fri, 7 Oct 2016 10:06:44 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 4574D2949C for ; Fri, 7 Oct 2016 10:06:44 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 386182949E; Fri, 7 Oct 2016 10:06:44 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 907DE2949C for ; Fri, 7 Oct 2016 10:06:43 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752759AbcJGKGm (ORCPT ); Fri, 7 Oct 2016 06:06:42 -0400 Received: from mx1.redhat.com ([209.132.183.28]:41980 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752385AbcJGKGm (ORCPT ); Fri, 7 Oct 2016 06:06:42 -0400 Received: from int-mx13.intmail.prod.int.phx2.redhat.com (int-mx13.intmail.prod.int.phx2.redhat.com [10.5.11.26]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id E708B326933; Fri, 7 Oct 2016 10:06:41 +0000 (UTC) Received: from localhost (ovpn-112-51.ams2.redhat.com [10.36.112.51]) by int-mx13.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id u97A6eoQ031371; Fri, 7 Oct 2016 06:06:41 -0400 From: Stefan Hajnoczi To: linux-nfs@vger.kernel.org Cc: Anna Schumaker , "J. Bruce Fields" , Trond Myklebust , Stefan Hajnoczi Subject: [PATCH v2 05/10] VSOCK: add tcp_read_sock()-like vsock_read_sock() function Date: Fri, 7 Oct 2016 11:01:49 +0100 Message-Id: <1475834514-4058-6-git-send-email-stefanha@redhat.com> In-Reply-To: <1475834514-4058-1-git-send-email-stefanha@redhat.com> References: <1475834514-4058-1-git-send-email-stefanha@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.26 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.29]); Fri, 07 Oct 2016 10:06:41 +0000 (UTC) Sender: linux-nfs-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-nfs@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP The tcp_read_sock() interface dequeues skbs and gives them to the caller's callback function for processing. This interface can avoid data copies since the caller accesses the skb instead of using its own receive buffer. This patch implements vsock_read_sock() for AF_VSOCK SOCK_STREAM sockets. The implementation is only for virtio-vsock at this time, not for the VMware VMCI transport. It is not zero-copy yet because the virtio-vsock receive queue does not consist of skbs. The tcp_read_sock()-like interface is needed for AF_VSOCK sunrpc support. Signed-off-by: Stefan Hajnoczi --- drivers/vhost/vsock.c | 1 + include/linux/virtio_vsock.h | 4 ++ include/net/af_vsock.h | 5 +++ net/vmw_vsock/af_vsock.c | 16 ++++++++ net/vmw_vsock/virtio_transport.c | 1 + net/vmw_vsock/virtio_transport_common.c | 66 +++++++++++++++++++++++++++++++++ net/vmw_vsock/vmci_transport.c | 8 ++++ 7 files changed, 101 insertions(+) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index e3b30ea..bfa8f3b 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -677,6 +677,7 @@ static struct virtio_transport vhost_transport = { .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .stream_read_sock = virtio_transport_stream_read_sock, .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 9638bfe..3d5710d 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -5,6 +5,7 @@ #include #include #include +#include /* for sk_read_actor_t */ #define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 #define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) @@ -123,6 +124,9 @@ int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); bool virtio_transport_stream_is_active(struct vsock_sock *vsk); bool virtio_transport_stream_allow(u32 cid, u32 port); +int virtio_transport_stream_read_sock(struct vsock_sock *vsk, + read_descriptor_t *desc, + sk_read_actor_t recv_actor); int virtio_transport_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr); bool virtio_transport_dgram_allow(u32 cid, u32 port); diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index f275896..f46a26c 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -19,6 +19,7 @@ #include #include #include +#include /* for sk_read_actor_t */ #include "vsock_addr.h" @@ -73,6 +74,8 @@ struct vsock_sock { void *trans; }; +int vsock_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor); s64 vsock_stream_has_data(struct vsock_sock *vsk); s64 vsock_stream_has_space(struct vsock_sock *vsk); void vsock_pending_work(struct work_struct *work); @@ -122,6 +125,8 @@ struct vsock_transport { u64 (*stream_rcvhiwat)(struct vsock_sock *); bool (*stream_is_active)(struct vsock_sock *); bool (*stream_allow)(u32 cid, u32 port); + int (*stream_read_sock)(struct vsock_sock *, read_descriptor_t *desc, + sk_read_actor_t recv_actor); /* Notification. */ int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 8a398b3..e35fbb4 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -705,6 +705,22 @@ static void vsock_sk_destruct(struct sock *sk) put_cred(vsk->owner); } +/* See documentation for tcp_read_sock() */ +int vsock_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + struct vsock_sock *vsp = vsock_sk(sk); + + if (sk->sk_type != SOCK_STREAM) + return -EOPNOTSUPP; + + if (sk->sk_state != SS_CONNECTED && sk->sk_state != SS_DISCONNECTING) + return -ENOTCONN; + + return transport->stream_read_sock(vsp, desc, recv_actor); +} +EXPORT_SYMBOL(vsock_read_sock); + static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int err; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 936d7ee..4f1efc8 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -432,6 +432,7 @@ static struct virtio_transport virtio_transport = { .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .stream_read_sock = virtio_transport_stream_read_sock, .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a53b3a1..3bfd845 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -250,6 +250,72 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk, EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); int +virtio_transport_stream_read_sock(struct vsock_sock *vsk, + read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + struct virtio_vsock_sock *vvs; + int ret = 0; + + vvs = vsk->trans; + + spin_lock_bh(&vvs->rx_lock); + while (!list_empty(&vvs->rx_queue)) { + struct virtio_vsock_pkt *pkt; + struct sk_buff *skb; + size_t len; + int used; + + pkt = list_first_entry(&vvs->rx_queue, + struct virtio_vsock_pkt, list); + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock so recv_actor() can sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + len = pkt->len - pkt->off; + skb = alloc_skb(len, GFP_KERNEL); + if (!skb) { + ret = -ENOMEM; + goto out_nolock; + } + + memcpy(skb_put(skb, len), + pkt->buf + pkt->off, + len); + + used = recv_actor(desc, skb, 0, len); + + kfree_skb(skb); + + spin_lock_bh(&vvs->rx_lock); + + if (used > 0) { + ret += used; + pkt->off += used; + if (pkt->off == pkt->len) { + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + } + + if (used <= 0 || !desc->count) + break; + } + spin_unlock_bh(&vvs->rx_lock); + +out_nolock: + if (ret > 0) + virtio_transport_send_credit_update(vsk, + VIRTIO_VSOCK_TYPE_STREAM, NULL); + + return ret; +} +EXPORT_SYMBOL_GPL(virtio_transport_stream_read_sock); + +int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 4be4fbb..d6204d9 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -654,6 +654,13 @@ static bool vmci_transport_stream_allow(u32 cid, u32 port) return true; } +static int vmci_transport_stream_read_sock(struct vsock_sock *vsk, + read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + return -EOPNOTSUPP; /* not yet implemented */ +} + /* This is invoked as part of a tasklet that's scheduled when the VMCI * interrupt fires. This is run in bottom-half context but it defers most of * its work to the packet handling work queue. @@ -2069,6 +2076,7 @@ static const struct vsock_transport vmci_transport = { .stream_rcvhiwat = vmci_transport_stream_rcvhiwat, .stream_is_active = vmci_transport_stream_is_active, .stream_allow = vmci_transport_stream_allow, + .stream_read_sock = vmci_transport_stream_read_sock, .notify_poll_in = vmci_transport_notify_poll_in, .notify_poll_out = vmci_transport_notify_poll_out, .notify_recv_init = vmci_transport_notify_recv_init,