Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Arseny Krasnov <arseny.krasnov@kaspersky.com>
To:     Stefan Hajnoczi <stefanha@redhat.com>,
        Stefano Garzarella <sgarzare@redhat.com>,
        "Michael S. Tsirkin" <mst@redhat.com>,
        Jason Wang <jasowang@redhat.com>,
        "David S. Miller" <davem@davemloft.net>,
        Jakub Kicinski <kuba@kernel.org>,
        Jorgen Hansen <jhansen@vmware.com>,
        Andra Paraschiv <andraprs@amazon.com>,
        Colin Ian King <colin.king@canonical.com>,
        Norbert Slusarek <nslusarek@gmx.net>,
        Jeff Vander Stoep <jeffv@google.com>,
        Alexander Popov <alex.popov@linux.com>
CC:     <kvm@vger.kernel.org>, <virtualization@lists.linux-foundation.org>,
        <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <stsp2@yandex.ru>, <arseny.krasnov@kaspersky.com>,
        <oxffffaa@gmail.com>
Subject: [RFC PATCH v8 11/19] virtio/vsock: dequeue callback for SOCK_SEQPACKET
Date:   Tue, 13 Apr 2021 15:44:40 +0300
Message-ID: <20210413124443.3403382-1-arseny.krasnov@kaspersky.com>
In-Reply-To: <20210413123954.3396314-1-arseny.krasnov@kaspersky.com>
References: <20210413123954.3396314-1-arseny.krasnov@kaspersky.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-KSE-AttachmentFiltering-Interceptor-Info: no applicable attachment filtering
 rules found
X-KSE-Antivirus-Interceptor-Info: scan successful
X-KSE-Antivirus-Info: Clean, bases: 13.04.2021 10:53:00
X-KSE-BulkMessagesFiltering-Scan-Result: InTheLimit
X-KSE-AttachmentFiltering-Interceptor-Info: no applicable attachment filtering
 rules found
X-KSE-BulkMessagesFiltering-Scan-Result: InTheLimit
X-KLMS-Rule-ID: 52
X-KLMS-Message-Action: clean
X-KLMS-AntiSpam-Status: not scanned, disabled by settings
X-KLMS-AntiSpam-Interceptor-Info: not scanned
X-KLMS-AntiPhishing: Clean, bases: 2021/04/13 07:05:00
X-KLMS-AntiVirus: Kaspersky Security for Linux Mail Server, version 8.0.3.30, bases: 2021/04/13 03:14:00 #16587160
X-KLMS-AntiVirus-Status: Clean, skipped
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

This adds transport callback and it's logic for SEQPACKET dequeue.
Callback fetches RW packets from rx queue of socket until whole record
is copied(if user's buffer is full, user is not woken up). This is done
to not stall sender, because if we wake up user and it leaves syscall,
nobody will send credit update for rest of record, and sender will wait
for next enter of read syscall at receiver's side. So if user buffer is
full, we just send credit update and drop data.

Signed-off-by: Arseny Krasnov <arseny.krasnov@kaspersky.com>
---
v7 -> v8:
 - Things like SEQ_BEGIN, SEQ_END, 'msg_len' and 'msg_id' now removed.
   This callback fetches and copies RW packets to user's buffer, until
   last packet of message found(this packet is marked in 'flags' field
   of header).

 include/linux/virtio_vsock.h            |  5 ++
 net/vmw_vsock/virtio_transport_common.c | 73 +++++++++++++++++++++++++
 2 files changed, 78 insertions(+)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index dc636b727179..02acf6e9ae04 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -80,6 +80,11 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,
 			       size_t len, int flags);
 
+ssize_t
+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   int flags,
+				   bool *msg_ready);
 s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
 s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 833104b71a1c..8492b8bd5df5 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -393,6 +393,67 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	return err;
 }
 
+static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
+						 struct msghdr *msg,
+						 int flags,
+						 bool *msg_ready)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	struct virtio_vsock_pkt *pkt;
+	int err = 0;
+	size_t user_buf_len = msg->msg_iter.count;
+
+	*msg_ready = false;
+	spin_lock_bh(&vvs->rx_lock);
+
+	while (!*msg_ready && !list_empty(&vvs->rx_queue) && err >= 0) {
+		pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list);
+
+		if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RW) {
+			size_t bytes_to_copy;
+			size_t pkt_len;
+
+			pkt_len = (size_t)le32_to_cpu(pkt->hdr.len);
+			bytes_to_copy = min(user_buf_len, pkt_len);
+
+			/* sk_lock is held by caller so no one else can dequeue.
+			 * Unlock rx_lock since memcpy_to_msg() may sleep.
+			 */
+			spin_unlock_bh(&vvs->rx_lock);
+
+			if (memcpy_to_msg(msg, pkt->buf, bytes_to_copy)) {
+				err = -EINVAL;
+				break;
+			}
+
+			spin_lock_bh(&vvs->rx_lock);
+
+			/* If user sets 'MSG_TRUNC' we return real length
+			 * of message.
+			 */
+			if (flags & MSG_TRUNC)
+				err += pkt_len;
+			else
+				err += bytes_to_copy;
+
+			user_buf_len -= bytes_to_copy;
+
+			if (pkt->hdr.flags & VIRTIO_VSOCK_SEQ_EOR)
+				*msg_ready = true;
+		}
+
+		virtio_transport_dec_rx_pkt(vvs, pkt);
+		list_del(&pkt->list);
+		virtio_transport_free_pkt(pkt);
+	}
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	virtio_transport_send_credit_update(vsk);
+
+	return err;
+}
+
 ssize_t
 virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 				struct msghdr *msg,
@@ -405,6 +466,18 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 }
 EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue);
 
+ssize_t
+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   int flags, bool *msg_ready)
+{
+	if (flags & MSG_PEEK)
+		return -EOPNOTSUPP;
+
+	return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags, msg_ready);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue);
+
 int
 virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,
-- 
2.25.1