vhost: introduce vhost_exceeds_weight()

BugLink: https://bugs.launchpad.net/bugs/1838824
commit e82b9b0727ff6d665fff2d326162b460dded554d upstream.

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>
Signed-off-by: Balbir Singh <sblbir@amzn.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Khalid Elmously <khalid.elmously@canonical.com>

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 24314135636d9545a182822e74e846a7b5e3d0e4..7c0fcda639959ec11046f8f8c09881055794d881 100644 (file)
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -450,12 +450,6 @@ 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)
@@ -588,10 +582,9 @@ 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);
@@ -872,10 +865,8 @@ 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;
-               }
        }
        vhost_net_enable_vq(net, vq);
 out:
@@ -954,7 +945,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
                n->vqs[i].sock_hlen = 0;
                vhost_net_buf_init(&n->vqs[i].rxq);
        }
-       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);

diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index b4a971c6accd548843c7c32eda393f767ee67f96..38b394c7ce4253a575439f20da7d37f7ba2828a7 100644 (file)
--- a/drivers/vhost/scsi.c
+++ b/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;
@@ -1399,7 +1405,7 @@ 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);
 

diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 6f86dd6cc4b33479f43ae5c156d88cf083e9ecdf..f988d7ac8da7ecff6cfc6b892108d3d9a41785d1 100644 (file)
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -412,8 +412,24 @@ 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;
@@ -427,6 +443,8 @@ void vhost_dev_init(struct vhost_dev *dev,
        dev->iotlb = NULL;
        dev->mm = NULL;
        dev->worker = NULL;
+       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);

diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 75d21d4a83541c534998d1d1aa8b7650eca4415f..950c5c4e4ee3d97cd91ee5454bd36c5e1510d28b 100644 (file)
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -173,9 +173,13 @@ struct vhost_dev {
        struct list_head read_list;
        struct list_head pending_list;
        wait_queue_head_t wait;
+       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 *);

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index d0cf3d5aa5701609bb421c539ca121e49811a050..d676639836560067125a19d3ce769901d98180f4 100644 (file)
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -21,6 +21,14 @@
 #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,
@@ -531,7 +539,8 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
        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));
+       vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs),
+                      VHOST_VSOCK_PKT_WEIGHT, VHOST_VSOCK_WEIGHT);
 
        file->private_data = vsock;
        spin_lock_init(&vsock->send_pkt_list_lock);