summaryrefslogtreecommitdiff
path: root/drivers/vhost/net.c
diff options
context:
space:
mode:
authorJason Wang <jasowang@redhat.com>2018-11-15 12:43:09 +0300
committerDavid S. Miller <davem@davemloft.net>2018-11-17 23:00:42 +0300
commite4dab1e6ea64376ebd3b59281ecaaeb788116be3 (patch)
tree2f1e7d1b6ff105cec5ebcf0f1808ff7da72f9543 /drivers/vhost/net.c
parentb8b9618a4f6a6660cb1ff44dd401a4b21f2caf6c (diff)
downloadlinux-e4dab1e6ea64376ebd3b59281ecaaeb788116be3.tar.xz
vhost_net: mitigate page reference counting during page frag refill
We do a get_page() which involves a atomic operation. This patch tries to mitigate a per packet atomic operation by maintaining a reference bias which is initially USHRT_MAX. Each time a page is got, instead of calling get_page() we decrease the bias and when we find it's time to use a new page we will decrease the bias at one time through __page_cache_drain_cache(). Testpmd(virtio_user + vhost_net) + XDP_DROP on TAP shows about 1.6% improvement. Before: 4.63Mpps After: 4.71Mpps Signed-off-by: Jason Wang <jasowang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'drivers/vhost/net.c')
-rw-r--r--drivers/vhost/net.c54
1 files changed, 51 insertions, 3 deletions
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index ab11b2bee273..d919284f103b 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -141,6 +141,10 @@ struct vhost_net {
unsigned tx_zcopy_err;
/* Flush in progress. Protected by tx vq lock. */
bool tx_flush;
+ /* Private page frag */
+ struct page_frag page_frag;
+ /* Refcount bias of page frag */
+ int refcnt_bias;
};
static unsigned vhost_net_zcopy_mask __read_mostly;
@@ -637,14 +641,53 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len)
!vhost_vq_avail_empty(vq->dev, vq);
}
+#define SKB_FRAG_PAGE_ORDER get_order(32768)
+
+static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz,
+ struct page_frag *pfrag, gfp_t gfp)
+{
+ if (pfrag->page) {
+ if (pfrag->offset + sz <= pfrag->size)
+ return true;
+ __page_frag_cache_drain(pfrag->page, net->refcnt_bias);
+ }
+
+ pfrag->offset = 0;
+ net->refcnt_bias = 0;
+ if (SKB_FRAG_PAGE_ORDER) {
+ /* Avoid direct reclaim but allow kswapd to wake */
+ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) |
+ __GFP_COMP | __GFP_NOWARN |
+ __GFP_NORETRY,
+ SKB_FRAG_PAGE_ORDER);
+ if (likely(pfrag->page)) {
+ pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER;
+ goto done;
+ }
+ }
+ pfrag->page = alloc_page(gfp);
+ if (likely(pfrag->page)) {
+ pfrag->size = PAGE_SIZE;
+ goto done;
+ }
+ return false;
+
+done:
+ net->refcnt_bias = USHRT_MAX;
+ page_ref_add(pfrag->page, USHRT_MAX - 1);
+ return true;
+}
+
#define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD)
static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
struct iov_iter *from)
{
struct vhost_virtqueue *vq = &nvq->vq;
+ struct vhost_net *net = container_of(vq->dev, struct vhost_net,
+ dev);
struct socket *sock = vq->private_data;
- struct page_frag *alloc_frag = &current->task_frag;
+ struct page_frag *alloc_frag = &net->page_frag;
struct virtio_net_hdr *gso;
struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp];
struct tun_xdp_hdr *hdr;
@@ -665,7 +708,8 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
buflen += SKB_DATA_ALIGN(len + pad);
alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES);
- if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL)))
+ if (unlikely(!vhost_net_page_frag_refill(net, buflen,
+ alloc_frag, GFP_KERNEL)))
return -ENOMEM;
buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
@@ -703,7 +747,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
xdp->data_end = xdp->data + len;
hdr->buflen = buflen;
- get_page(alloc_frag->page);
+ --net->refcnt_bias;
alloc_frag->offset += buflen;
++nvq->batched_xdp;
@@ -1292,6 +1336,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
f->private_data = n;
+ n->page_frag.page = NULL;
+ n->refcnt_bias = 0;
return 0;
}
@@ -1366,6 +1412,8 @@ static int vhost_net_release(struct inode *inode, struct file *f)
kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue);
kfree(n->vqs[VHOST_NET_VQ_TX].xdp);
kfree(n->dev.vqs);
+ if (n->page_frag.page)
+ __page_frag_cache_drain(n->page_frag.page, n->refcnt_bias);
kvfree(n);
return 0;
}