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 <jasowang@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

CVE-2019-3900

(backported from commit e82b9b07)
[tyhicks: Backport to Xenial:
 - Adjust handle_tx() instead of handle_tx_{copy,zerocopy}() due to
   missing commit 0d20bdf3 ("vhost_net: split out datacopy logic")
 - Considerable context adjustments throughout the patch due to a lack
   of missing the iov_limit member of the vhost_dev struct which was
   added later in commit b46a0bf7 ("vhost: fix OOB in get_rx_bufs()")
 - Context adjustment in call to vhost_log_write() in hunk #3 of net.c due to
   missing and unneeded commit cc5e7107 ("vhost: log dirty page correctly")
 - Context adjustment in hunk #3 of net.c due to using break instead of goto
   out
 - Context adjustment in hunk #4 of net.c due to missing and unneeded commit
   c67df11f ("vhost_net: try batch dequing from skb array")
 - Don't patch vsock.c since Xenial doesn't have vhost vsock support
 - Adjust context in vhost_dev_init() to account for different local variables
 - Adjust context in struct vhost_dev to account for different struct members]
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Acked-by: Stefan Bader <stefan.bader@canonical.com>
Acked-by: Connor Kuehl <connor.kuehl@canonical.com>
Signed-off-by: Khalid Elmously <khalid.elmously@canonical.com>

drivers/vhost/net.c

@@ -302,12 +302,6 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net)
 	       min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2);
 }
 
-static bool vhost_exceeds_weight(int pkts, int total_len)
-{
-	return total_len >= VHOST_NET_WEIGHT ||
-	       pkts >= VHOST_NET_PKT_WEIGHT;
-}
-
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -431,10 +425,9 @@ static void handle_tx(struct vhost_net *net)
 		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;
-		}
 	}
 out:
 	mutex_unlock(&vq->mutex);
@@ -655,10 +648,8 @@ static void handle_rx(struct vhost_net *net)
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		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)))
 			break;
-		}
 	}
 out:
 	mutex_unlock(&vq->mutex);
@@ -728,7 +719,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		n->vqs[i].vhost_hlen = 0;
 		n->vqs[i].sock_hlen = 0;
 	}
-	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
+	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
+		       VHOST_NET_WEIGHT, VHOST_NET_PKT_WEIGHT);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);

drivers/vhost/scsi.c

@@ -58,6 +58,12 @@
 #define VHOST_SCSI_PREALLOC_UPAGES 2048
 #define VHOST_SCSI_PREALLOC_PROT_SGLS 512
 
+/* 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;
@@ -1443,7 +1449,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 		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);
+	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, VHOST_SCSI_WEIGHT, 0);
 
 	vhost_scsi_init_inflight(vs, NULL);
 

drivers/vhost/vhost.c

@@ -370,8 +370,24 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev)
 		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)
+		    struct vhost_virtqueue **vqs, int nvqs,
+		    int weight, int byte_weight)
 {
 	struct vhost_virtqueue *vq;
 	int i;
@@ -386,6 +402,8 @@ void vhost_dev_init(struct vhost_dev *dev,
 	spin_lock_init(&dev->work_lock);
 	INIT_LIST_HEAD(&dev->work_list);
 	dev->worker = NULL;
+	dev->weight = weight;
+	dev->byte_weight = byte_weight;
 
 	for (i = 0; i < dev->nvqs; ++i) {
 		vq = dev->vqs[i];

drivers/vhost/vhost.h

@@ -127,9 +127,13 @@ struct vhost_dev {
 	spinlock_t work_lock;
 	struct list_head work_list;
 	struct task_struct *worker;
+	int weight;
+	int byte_weight;
 };
 
-void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs);
+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 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 *);