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>,
        Arseny Krasnov <arseny.krasnov@kaspersky.com>,
        Andra Paraschiv <andraprs@amazon.com>,
        Colin Ian King <colin.king@canonical.com>,
        Jeff Vander Stoep <jeffv@google.com>
CC:     <kvm@vger.kernel.org>, <virtualization@lists.linux-foundation.org>,
        <netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <stsp2@yandex.ru>, <oxffffaa@gmail.com>
Subject: [RFC PATCH v3 07/13] virtio/vsock: dequeue callback for SOCK_SEQPACKET
Date:   Mon, 25 Jan 2021 14:13:59 +0300
Message-ID: <20210125111402.598929-1-arseny.krasnov@kaspersky.com>
In-Reply-To: <20210125110903.597155-1-arseny.krasnov@kaspersky.com>
References: <20210125110903.597155-1-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: 1/25/2021 10:11:00 AM
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: 2021/01/25 10:04:00
X-KLMS-AntiVirus: Kaspersky Security for Linux Mail Server, version 8.0.3.30, bases: 2021/01/25 05:31:00 #16022694
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. If during copy SEQ_BEGIN
was found(and not all data was copied), copying is restarted by reset
user's iov iterator(previous unfinished data is dropped).

Signed-off-by: Arseny Krasnov <arseny.krasnov@kaspersky.com>
---
 include/linux/virtio_vsock.h            |   4 +
 include/uapi/linux/virtio_vsock.h       |   9 ++
 net/vmw_vsock/virtio_transport_common.c | 128 ++++++++++++++++++++++++
 3 files changed, 141 insertions(+)

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index dc636b727179..7f0ef5204e33 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -36,6 +36,10 @@ struct virtio_vsock_sock {
 	u32 rx_bytes;
 	u32 buf_alloc;
 	struct list_head rx_queue;
+
+	/* For SOCK_SEQPACKET */
+	u32 user_read_seq_len;
+	u32 user_read_copied;
 };
 
 struct virtio_vsock_pkt {
diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h
index 1d57ed3d84d2..058908bc19fc 100644
--- a/include/uapi/linux/virtio_vsock.h
+++ b/include/uapi/linux/virtio_vsock.h
@@ -65,6 +65,7 @@ struct virtio_vsock_hdr {
 
 enum virtio_vsock_type {
 	VIRTIO_VSOCK_TYPE_STREAM = 1,
+	VIRTIO_VSOCK_TYPE_SEQPACKET = 2,
 };
 
 enum virtio_vsock_op {
@@ -83,6 +84,9 @@ enum virtio_vsock_op {
 	VIRTIO_VSOCK_OP_CREDIT_UPDATE = 6,
 	/* Request the peer to send the credit info to us */
 	VIRTIO_VSOCK_OP_CREDIT_REQUEST = 7,
+
+	/* Record begin for SOCK_SEQPACKET */
+	VIRTIO_VSOCK_OP_SEQ_BEGIN = 8,
 };
 
 /* VIRTIO_VSOCK_OP_SHUTDOWN flags values */
@@ -91,4 +95,9 @@ enum virtio_vsock_shutdown {
 	VIRTIO_VSOCK_SHUTDOWN_SEND = 2,
 };
 
+/* VIRTIO_VSOCK_OP_RW flags values for SOCK_SEQPACKET type */
+enum virtio_vsock_rw_seqpacket {
+	VIRTIO_VSOCK_RW_EOR = 1,
+};
+
 #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 5956939eebb7..e66ec39445ff 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -397,6 +397,132 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
 	return err;
 }
 
+static inline void virtio_transport_del_n_free_pkt(struct virtio_vsock_pkt *pkt)
+{
+	list_del(&pkt->list);
+	virtio_transport_free_pkt(pkt);
+}
+
+static size_t virtio_transport_drop_until_seq_begin(struct virtio_vsock_sock *vvs)
+{
+	struct virtio_vsock_pkt *pkt, *n;
+	size_t bytes_dropped = 0;
+
+	list_for_each_entry_safe(pkt, n, &vvs->rx_queue, list) {
+		if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_SEQ_BEGIN)
+			break;
+
+		bytes_dropped += le32_to_cpu(pkt->hdr.len);
+		virtio_transport_dec_rx_pkt(vvs, pkt);
+		virtio_transport_del_n_free_pkt(pkt);
+	}
+
+	return bytes_dropped;
+}
+
+static ssize_t virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
+						     struct msghdr *msg,
+						     size_t user_buf_len)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	struct virtio_vsock_pkt *pkt;
+	size_t bytes_handled = 0;
+	int err = 0;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	if (user_buf_len == 0) {
+		/* User's buffer is full, we processing rest of
+		 * record and drop it. If 'SEQ_BEGIN' is found
+		 * while iterating, user will be woken up,
+		 * because record is already copied, and we
+		 * don't care about absent of some tail RW packets
+		 * of it. Return number of bytes(rest of record),
+		 * but ignore credit update for such absent bytes.
+		 */
+		bytes_handled = virtio_transport_drop_until_seq_begin(vvs);
+		vvs->user_read_copied += bytes_handled;
+
+		if (!list_empty(&vvs->rx_queue) &&
+		    vvs->user_read_copied < vvs->user_read_seq_len) {
+			/* 'SEQ_BEGIN' found, but record isn't complete.
+			 * Set number of copied bytes to fit record size
+			 * and force counters to finish receiving.
+			 */
+			bytes_handled += (vvs->user_read_seq_len - vvs->user_read_copied);
+			vvs->user_read_copied = vvs->user_read_seq_len;
+		}
+	}
+
+	/* Now start copying. */
+	while (vvs->user_read_copied < vvs->user_read_seq_len &&
+	       vvs->rx_bytes &&
+	       user_buf_len &&
+	       !err) {
+		pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list);
+
+		switch (le16_to_cpu(pkt->hdr.op)) {
+		case VIRTIO_VSOCK_OP_SEQ_BEGIN: {
+			/* Unexpected 'SEQ_BEGIN' during record copy:
+			 * Leave receive loop, 'EAGAIN' will restart it from
+			 * outer receive loop, packet is still in queue and
+			 * counters are cleared. So in next loop enter,
+			 * 'SEQ_BEGIN' will be dequeued first. User's iov
+			 * iterator will be reset in outer loop. Also
+			 * send credit update, because some bytes could be
+			 * copied. User will never see unfinished record.
+			 */
+			err = -EAGAIN;
+			break;
+		}
+		case 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)) {
+				spin_lock_bh(&vvs->rx_lock);
+				err = -EINVAL;
+				break;
+			}
+
+			spin_lock_bh(&vvs->rx_lock);
+			user_buf_len -= bytes_to_copy;
+			bytes_handled += pkt->len;
+			vvs->user_read_copied += bytes_to_copy;
+
+			if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_RW_EOR)
+				msg->msg_flags |= MSG_EOR;
+			break;
+		}
+		default:
+			;
+		}
+
+		/* For unexpected 'SEQ_BEGIN', keep such packet in queue,
+		 * but drop any other type of packet.
+		 */
+		if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_SEQ_BEGIN) {
+			virtio_transport_dec_rx_pkt(vvs, pkt);
+			virtio_transport_del_n_free_pkt(pkt);
+		}
+	}
+
+	spin_unlock_bh(&vvs->rx_lock);
+
+	virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_SEQPACKET,
+					    NULL);
+
+	return err ?: bytes_handled;
+}
+
 ssize_t
 virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 				struct msghdr *msg,
@@ -481,6 +607,8 @@ int virtio_transport_do_socket_init(struct vsock_sock *vsk,
 	spin_lock_init(&vvs->rx_lock);
 	spin_lock_init(&vvs->tx_lock);
 	INIT_LIST_HEAD(&vvs->rx_queue);
+	vvs->user_read_copied = 0;
+	vvs->user_read_seq_len = 0;
 
 	return 0;
 }
-- 
2.25.1