summaryrefslogtreecommitdiff
path: root/drivers/vhost/net.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vhost/net.c')
-rw-r--r--drivers/vhost/net.c56
1 files changed, 36 insertions, 20 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 986058a57917..e7cf7d21cfb5 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -32,6 +32,7 @@
#include <linux/skbuff.h>
#include <net/sock.h>
+#include <net/xdp.h>
#include "vhost.h"
@@ -45,8 +46,10 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
#define VHOST_NET_WEIGHT 0x80000
/* Max number of packets transferred before requeueing the job.
- * Using this limit prevents one virtqueue from starving rx. */
-#define VHOST_NET_PKT_WEIGHT(vq) ((vq)->num * 2)
+ * Using this limit prevents one virtqueue from starving others with small
+ * pkts.
+ */
+#define VHOST_NET_PKT_WEIGHT 256
/* MAX number of TX used buffers for outstanding zerocopy */
#define VHOST_MAX_PEND 128
@@ -105,7 +108,9 @@ struct vhost_net_virtqueue {
/* vhost zerocopy support fields below: */
/* last used idx for outstanding DMA zerocopy buffers */
int upend_idx;
- /* first used idx for DMA done zerocopy buffers */
+ /* For TX, first used idx for DMA done zerocopy buffers
+ * For RX, number of batched heads
+ */
int done_idx;
/* an array of userspace buffers info */
struct ubuf_info *ubuf_info;
@@ -181,10 +186,10 @@ static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq)
static int vhost_net_buf_peek_len(void *ptr)
{
- if (tun_is_xdp_buff(ptr)) {
- struct xdp_buff *xdp = tun_ptr_to_xdp(ptr);
+ if (tun_is_xdp_frame(ptr)) {
+ struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr);
- return xdp->data_end - xdp->data;
+ return xdpf->len;
}
return __skb_array_len_with_tag(ptr);
@@ -586,7 +591,7 @@ static void handle_tx(struct vhost_net *net)
vhost_zerocopy_signal_used(net, vq);
vhost_net_tx_packet(net);
if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
- unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT(vq))) {
+ unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) {
vhost_poll_queue(&vq->poll);
break;
}
@@ -626,6 +631,18 @@ static int sk_has_rx_data(struct sock *sk)
return skb_queue_empty(&sk->sk_receive_queue);
}
+static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
+{
+ struct vhost_virtqueue *vq = &nvq->vq;
+ struct vhost_dev *dev = vq->dev;
+
+ if (!nvq->done_idx)
+ return;
+
+ vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+ nvq->done_idx = 0;
+}
+
static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
{
struct vhost_net_virtqueue *rvq = &net->vqs[VHOST_NET_VQ_RX];
@@ -635,6 +652,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
int len = peek_head_len(rvq, sk);
if (!len && vq->busyloop_timeout) {
+ /* Flush batched heads first */
+ vhost_rx_signal_used(rvq);
/* Both tx vq and rx socket were polled here */
mutex_lock_nested(&vq->mutex, 1);
vhost_disable_notify(&net->dev, vq);
@@ -762,12 +781,13 @@ static void handle_rx(struct vhost_net *net)
};
size_t total_len = 0;
int err, mergeable;
- s16 headcount, nheads = 0;
+ s16 headcount;
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
struct socket *sock;
struct iov_iter fixup;
__virtio16 num_buffers;
+ int recv_pkts = 0;
mutex_lock_nested(&vq->mutex, 0);
sock = vq->private_data;
@@ -790,8 +810,8 @@ static void handle_rx(struct vhost_net *net)
while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
sock_len += sock_hlen;
vhost_len = sock_len + vhost_hlen;
- headcount = get_rx_bufs(vq, vq->heads + nheads, vhost_len,
- &in, vq_log, &log,
+ headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
+ vhost_len, &in, vq_log, &log,
likely(mergeable) ? UIO_MAXIOV : 1);
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
@@ -862,25 +882,21 @@ static void handle_rx(struct vhost_net *net)
vhost_discard_vq_desc(vq, headcount);
goto out;
}
- nheads += headcount;
- if (nheads > VHOST_RX_BATCH) {
- vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
- nheads);
- nheads = 0;
- }
+ nvq->done_idx += headcount;
+ if (nvq->done_idx > VHOST_RX_BATCH)
+ vhost_rx_signal_used(nvq);
if (unlikely(vq_log))
vhost_log_write(vq, vq_log, log, vhost_len);
total_len += vhost_len;
- if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
+ if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
+ unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) {
vhost_poll_queue(&vq->poll);
goto out;
}
}
vhost_net_enable_vq(net, vq);
out:
- if (nheads)
- vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
- nheads);
+ vhost_rx_signal_used(nvq);
mutex_unlock(&vq->mutex);
}