Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio fixes from Michael Tsirkin:
"Several fixes, some of them for CVEs"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
vhost: scsi: add weight support
vhost: vsock: add weight support
vhost_net: fix possible infinite loop
vhost: introduce vhost_exceeds_weight()
virtio: Fix indentation of VIRTIO_MMIO
virtio: add unlikely() to WARN_ON_ONCE()

drivers/vhost/net.c

···
 	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,
···
 	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)
···
 		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);
-			break;
-		}
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 
 	vhost_tx_batch(net, nvq, sock, &msg);
 }
···
 	bool zcopy_used;
 	int sent_pkts = 0;
 
-	for (;;) {
+	do {
 		bool busyloop_intr;
 
 		/* Release DMAs done buffers first */
···
 		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);
-			break;
-		}
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 }
 
 /* Expects to be always run from workqueue - which acts as
···
 		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,
···
 			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);
-			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);
···
 		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_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);

drivers/vhost/scsi.c

···
 #define VHOST_SCSI_PREALLOC_UPAGES 2048
 #define VHOST_SCSI_PREALLOC_PROT_SGLS 2048
 
+/* Max number of requests before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * request.
+ */
+#define VHOST_SCSI_WEIGHT 256
+
 struct vhost_scsi_inflight {
 	/* Wait for the flush operation to finish */
 	struct completion comp;
···
 	struct iov_iter in_iter, prot_iter, data_iter;
 	u64 tag;
 	u32 exp_data_len, data_direction;
-	int ret, prot_bytes;
+	int ret, prot_bytes, c = 0;
 	u16 lun;
 	u8 task_attr;
 	bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI);
···
 
 	vhost_disable_notify(&vs->dev, vq);
 
-	for (;;) {
+	do {
 		ret = vhost_scsi_get_desc(vs, vq, &vc);
 		if (ret)
 			goto err;
···
 			break;
 		else if (ret == -EIO)
 			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);
 }
···
 	} v_req;
 	struct vhost_scsi_ctx vc;
 	size_t typ_size;
-	int ret;
+	int ret, c = 0;
 
 	mutex_lock(&vq->mutex);
 	/*
···
 
 	vhost_disable_notify(&vs->dev, vq);
 
-	for (;;) {
+	do {
 		ret = vhost_scsi_get_desc(vs, vq, &vc);
 		if (ret)
 			goto err;
···
 			break;
 		else if (ret == -EIO)
 			vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out);
-	}
+	} while (likely(!vhost_exceeds_weight(vq, ++c, 0)));
 out:
 	mutex_unlock(&vq->mutex);
 }
···
 		vqs[i] = &vs->vqs[i].vq;
 		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
 	}
-	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV);
+	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV,
+		       VHOST_SCSI_WEIGHT, 0);
 
 	vhost_scsi_init_inflight(vs, NULL);
 

drivers/vhost/vhost.c

···
 		vhost_vq_free_iovecs(dev->vqs[i]);
 }
 
+bool vhost_exceeds_weight(struct vhost_virtqueue *vq,
+			  int pkts, int total_len)
+{
+	struct vhost_dev *dev = vq->dev;
+
+	if ((dev->byte_weight && total_len >= dev->byte_weight) ||
+	    pkts >= dev->weight) {
+		vhost_poll_queue(&vq->poll);
+		return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(vhost_exceeds_weight);
+
 void vhost_dev_init(struct vhost_dev *dev,
-		    struct vhost_virtqueue **vqs, int nvqs, int iov_limit)
+		    struct vhost_virtqueue **vqs, int nvqs,
+		    int iov_limit, int weight, int byte_weight)
 {
 	struct vhost_virtqueue *vq;
 	int i;
···
 	dev->mm = NULL;
 	dev->worker = NULL;
 	dev->iov_limit = iov_limit;
+	dev->weight = weight;
+	dev->byte_weight = byte_weight;
 	init_llist_head(&dev->work_list);
 	init_waitqueue_head(&dev->wait);
 	INIT_LIST_HEAD(&dev->read_list);

drivers/vhost/vhost.h

···
 	struct list_head pending_list;
 	wait_queue_head_t wait;
 	int iov_limit;
+	int weight;
+	int byte_weight;
 };
 
+bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len);
 void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
-		    int nvqs, int iov_limit);
+		    int nvqs, int iov_limit, int weight, int byte_weight);
 long vhost_dev_set_owner(struct vhost_dev *dev);
 bool vhost_dev_has_owner(struct vhost_dev *dev);
 long vhost_dev_check_owner(struct vhost_dev *);

drivers/vhost/vsock.c

···
 #include "vhost.h"
 
 #define VHOST_VSOCK_DEFAULT_HOST_CID	2
+/* Max number of bytes transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others. */
+#define VHOST_VSOCK_WEIGHT 0x80000
+/* Max number of packets transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * small pkts.
+ */
+#define VHOST_VSOCK_PKT_WEIGHT 256
 
 enum {
 	VHOST_VSOCK_FEATURES = VHOST_FEATURES,
···
 			    struct vhost_virtqueue *vq)
 {
 	struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
+	int pkts = 0, total_len = 0;
 	bool added = false;
 	bool restart_tx = false;
 
···
 	/* Avoid further vmexits, we're already processing the virtqueue */
 	vhost_disable_notify(&vsock->dev, vq);
 
-	for (;;) {
+	do {
 		struct virtio_vsock_pkt *pkt;
 		struct iov_iter iov_iter;
 		unsigned out, in;
···
 		 */
 		virtio_transport_deliver_tap_pkt(pkt);
 
+		total_len += pkt->len;
 		virtio_transport_free_pkt(pkt);
-	}
+	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 	if (added)
 		vhost_signal(&vsock->dev, vq);
 
···
 	struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock,
 						 dev);
 	struct virtio_vsock_pkt *pkt;
-	int head;
+	int head, pkts = 0, total_len = 0;
 	unsigned int out, in;
 	bool added = false;
 
···
 		goto out;
 
 	vhost_disable_notify(&vsock->dev, vq);
-	for (;;) {
+	do {
 		u32 len;
 
 		if (!vhost_vsock_more_replies(vsock)) {
···
 		else
 			virtio_transport_free_pkt(pkt);
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + len);
+		len += sizeof(pkt->hdr);
+		vhost_add_used(vq, head, len);
+		total_len += len;
 		added = true;
-	}
+	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 
 no_more_replies:
 	if (added)
···
 	vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
 	vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;
 
-	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV);
+	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs),
+		       UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT,
+		       VHOST_VSOCK_WEIGHT);
 
 	file->private_data = vsock;
 	spin_lock_init(&vsock->send_pkt_list_lock);

drivers/virtio/Kconfig

···
 
 	 If unsure, say M.
 
- config VIRTIO_MMIO
+config VIRTIO_MMIO
 	tristate "Platform bus driver for memory mapped virtio devices"
 	depends on HAS_IOMEM && HAS_DMA
- 	select VIRTIO
- 	---help---
- 	 This drivers provides support for memory mapped virtio
+	select VIRTIO
+	---help---
+	 This drivers provides support for memory mapped virtio
 	 platform device driver.
 
  	 If unsure, say N.

tools/virtio/linux/kernel.h

···
 #define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 #define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 
-#define WARN_ON_ONCE(cond) ((cond) ? fprintf (stderr, "WARNING\n") : 0)
+#define WARN_ON_ONCE(cond) (unlikely(cond) ? fprintf (stderr, "WARNING\n") : 0)
 
 #define min(x, y) ({				\
 	typeof(x) _min1 = (x);			\