From e82b9b0727ff6d665fff2d326162b460dded554d Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 17 May 2019 00:29:49 -0400 Subject: vhost: introduce vhost_exceeds_weight() We used to have vhost_exceeds_weight() for vhost-net to: - prevent vhost kthread from hogging the cpu - balance the time spent between TX and RX This function could be useful for vsock and scsi as well. So move it to vhost.c. Device must specify a weight which counts the number of requests, or it can also specific a byte_weight which counts the number of bytes that has been processed. Signed-off-by: Jason Wang Reviewed-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- drivers/vhost/net.c | 22 ++++++---------------- 1 file changed, 6 insertions(+), 16 deletions(-) (limited to 'drivers/vhost/net.c') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index df51a35cf537..061a06dc12a3 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -604,12 +604,6 @@ static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter, return iov_iter_count(iter); } -static bool vhost_exceeds_weight(int pkts, int total_len) -{ - return total_len >= VHOST_NET_WEIGHT || - pkts >= VHOST_NET_PKT_WEIGHT; -} - static int get_tx_bufs(struct vhost_net *net, struct vhost_net_virtqueue *nvq, struct msghdr *msg, @@ -845,10 +839,8 @@ done: vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->done_idx].len = 0; ++nvq->done_idx; - if (vhost_exceeds_weight(++sent_pkts, total_len)) { - vhost_poll_queue(&vq->poll); + if (vhost_exceeds_weight(vq, ++sent_pkts, total_len)) break; - } } vhost_tx_batch(net, nvq, sock, &msg); @@ -951,10 +943,9 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) else vhost_zerocopy_signal_used(net, vq); vhost_net_tx_packet(net); - if (unlikely(vhost_exceeds_weight(++sent_pkts, total_len))) { - vhost_poll_queue(&vq->poll); + if (unlikely(vhost_exceeds_weight(vq, ++sent_pkts, + total_len))) break; - } } } @@ -1239,10 +1230,8 @@ static void handle_rx(struct vhost_net *net) vhost_log_write(vq, vq_log, log, vhost_len, vq->iov, in); total_len += vhost_len; - if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) { - vhost_poll_queue(&vq->poll); + if (unlikely(vhost_exceeds_weight(vq, ++recv_pkts, total_len))) goto out; - } } if (unlikely(busyloop_intr)) vhost_poll_queue(&vq->poll); @@ -1338,7 +1327,8 @@ static int vhost_net_open(struct inode *inode, struct file *f) vhost_net_buf_init(&n->vqs[i].rxq); } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, - UIO_MAXIOV + VHOST_NET_BATCH); + UIO_MAXIOV + VHOST_NET_BATCH, + VHOST_NET_WEIGHT, VHOST_NET_PKT_WEIGHT); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); -- cgit From e2412c07f8f3040593dfb88207865a3cd58680c0 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 17 May 2019 00:29:50 -0400 Subject: vhost_net: fix possible infinite loop When the rx buffer is too small for a packet, we will discard the vq descriptor and retry it for the next packet: while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk, &busyloop_intr))) { ... /* On overrun, truncate and discard */ if (unlikely(headcount > UIO_MAXIOV)) { iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1); err = sock->ops->recvmsg(sock, &msg, 1, MSG_DONTWAIT | MSG_TRUNC); pr_debug("Discarded rx packet: len %zd\n", sock_len); continue; } ... } This makes it possible to trigger a infinite while..continue loop through the co-opreation of two VMs like: 1) Malicious VM1 allocate 1 byte rx buffer and try to slow down the vhost process as much as possible e.g using indirect descriptors or other. 2) Malicious VM2 generate packets to VM1 as fast as possible Fixing this by checking against weight at the end of RX and TX loop. This also eliminate other similar cases when: - userspace is consuming the packets in the meanwhile - theoretical TOCTOU attack if guest moving avail index back and forth to hit the continue after vhost find guest just add new buffers This addresses CVE-2019-3900. Fixes: d8316f3991d20 ("vhost: fix total length when packets are too short") Fixes: 3a4d5c94e9593 ("vhost_net: a kernel-level virtio server") Signed-off-by: Jason Wang Reviewed-by: Stefan Hajnoczi Signed-off-by: Michael S. Tsirkin --- drivers/vhost/net.c | 29 +++++++++++++---------------- 1 file changed, 13 insertions(+), 16 deletions(-) (limited to 'drivers/vhost/net.c') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 061a06dc12a3..2d9df786a9d3 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -773,7 +773,7 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) int sent_pkts = 0; bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX); - for (;;) { + do { bool busyloop_intr = false; if (nvq->done_idx == VHOST_NET_BATCH) @@ -839,9 +839,7 @@ done: vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); vq->heads[nvq->done_idx].len = 0; ++nvq->done_idx; - if (vhost_exceeds_weight(vq, ++sent_pkts, total_len)) - break; - } + } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); vhost_tx_batch(net, nvq, sock, &msg); } @@ -866,7 +864,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) bool zcopy_used; int sent_pkts = 0; - for (;;) { + do { bool busyloop_intr; /* Release DMAs done buffers first */ @@ -943,10 +941,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) else vhost_zerocopy_signal_used(net, vq); vhost_net_tx_packet(net); - if (unlikely(vhost_exceeds_weight(vq, ++sent_pkts, - total_len))) - break; - } + } while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len))); } /* Expects to be always run from workqueue - which acts as @@ -1144,8 +1139,11 @@ static void handle_rx(struct vhost_net *net) vq->log : NULL; mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF); - while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk, - &busyloop_intr))) { + do { + sock_len = vhost_net_rx_peek_head_len(net, sock->sk, + &busyloop_intr); + if (!sock_len) + break; sock_len += sock_hlen; vhost_len = sock_len + vhost_hlen; headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx, @@ -1230,12 +1228,11 @@ static void handle_rx(struct vhost_net *net) vhost_log_write(vq, vq_log, log, vhost_len, vq->iov, in); total_len += vhost_len; - if (unlikely(vhost_exceeds_weight(vq, ++recv_pkts, total_len))) - goto out; - } + } while (likely(!vhost_exceeds_weight(vq, ++recv_pkts, total_len))); + if (unlikely(busyloop_intr)) vhost_poll_queue(&vq->poll); - else + else if (!sock_len) vhost_net_enable_vq(net, vq); out: vhost_net_signal_used(nvq); @@ -1328,7 +1325,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, UIO_MAXIOV + VHOST_NET_BATCH, - VHOST_NET_WEIGHT, VHOST_NET_PKT_WEIGHT); + VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); -- cgit