* [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit()
@ 2017-09-19 9:42 Jason Wang
2017-09-19 9:42 ` [PATCH net-next 2/3] virtio-net: add packet len average only when needed during XDP Jason Wang
` (2 more replies)
0 siblings, 3 replies; 8+ messages in thread
From: Jason Wang @ 2017-09-19 9:42 UTC (permalink / raw)
To: mst, jasowang, virtualization, netdev, linux-kernel; +Cc: John Fastabend
CC: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/net/virtio_net.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 511f833..a0ef4b0 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -373,7 +373,6 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi,
}
static bool virtnet_xdp_xmit(struct virtnet_info *vi,
- struct receive_queue *rq,
struct xdp_buff *xdp)
{
struct virtio_net_hdr_mrg_rxbuf *hdr;
@@ -542,7 +541,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
delta = orig_data - xdp.data;
break;
case XDP_TX:
- if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+ if (unlikely(!virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
rcu_read_unlock();
goto xdp_xmit;
@@ -677,7 +676,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
}
break;
case XDP_TX:
- if (unlikely(!virtnet_xdp_xmit(vi, rq, &xdp)))
+ if (unlikely(!virtnet_xdp_xmit(vi, &xdp)))
trace_xdp_exception(vi->dev, xdp_prog, act);
ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len);
if (unlikely(xdp_page != page))
--
2.7.4
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH net-next 2/3] virtio-net: add packet len average only when needed during XDP 2017-09-19 9:42 [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() Jason Wang @ 2017-09-19 9:42 ` Jason Wang 2017-09-20 21:28 ` David Miller 2017-09-19 9:42 ` [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT Jason Wang 2017-09-20 21:28 ` [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() David Miller 2 siblings, 1 reply; 8+ messages in thread From: Jason Wang @ 2017-09-19 9:42 UTC (permalink / raw) To: mst, jasowang, virtualization, netdev, linux-kernel; +Cc: John Fastabend There's no need to add packet len average in the case of XDP_PASS since it will be done soon after skb is created. Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jason Wang <jasowang@redhat.com> --- drivers/net/virtio_net.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a0ef4b0..db5924c 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -656,6 +656,9 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, xdp.data_end = xdp.data + (len - vi->hdr_len); act = bpf_prog_run_xdp(xdp_prog, &xdp); + if (act != XDP_PASS) + ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len); + switch (act) { case XDP_PASS: /* recalculate offset to account for any header @@ -671,14 +674,12 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, put_page(page); head_skb = page_to_skb(vi, rq, xdp_page, offset, len, PAGE_SIZE); - ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len); return head_skb; } break; case XDP_TX: if (unlikely(!virtnet_xdp_xmit(vi, &xdp))) trace_xdp_exception(vi->dev, xdp_prog, act); - ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len); if (unlikely(xdp_page != page)) goto err_xdp; rcu_read_unlock(); @@ -690,7 +691,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, case XDP_DROP: if (unlikely(xdp_page != page)) __free_pages(xdp_page, 0); - ewma_pkt_len_add(&rq->mrg_avg_pkt_len, len); goto err_xdp; } } -- 2.7.4 ^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 2/3] virtio-net: add packet len average only when needed during XDP 2017-09-19 9:42 ` [PATCH net-next 2/3] virtio-net: add packet len average only when needed during XDP Jason Wang @ 2017-09-20 21:28 ` David Miller 0 siblings, 0 replies; 8+ messages in thread From: David Miller @ 2017-09-20 21:28 UTC (permalink / raw) To: jasowang; +Cc: netdev, virtualization, john.fastabend, linux-kernel, mst From: Jason Wang <jasowang@redhat.com> Date: Tue, 19 Sep 2017 17:42:42 +0800 > There's no need to add packet len average in the case of XDP_PASS > since it will be done soon after skb is created. > > Cc: John Fastabend <john.fastabend@gmail.com> > Signed-off-by: Jason Wang <jasowang@redhat.com> Applied. ^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT 2017-09-19 9:42 [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() Jason Wang 2017-09-19 9:42 ` [PATCH net-next 2/3] virtio-net: add packet len average only when needed during XDP Jason Wang @ 2017-09-19 9:42 ` Jason Wang 2017-09-20 21:28 ` David Miller 2017-09-20 22:02 ` John Fastabend 2017-09-20 21:28 ` [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() David Miller 2 siblings, 2 replies; 8+ messages in thread From: Jason Wang @ 2017-09-19 9:42 UTC (permalink / raw) To: mst, jasowang, virtualization, netdev, linux-kernel; +Cc: John Fastabend This patch tries to add XDP_REDIRECT for virtio-net. The changes are not complex as we could use exist XDP_TX helpers for most of the work. The rest is passing the XDP_TX to NAPI handler for implementing batching. Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Jason Wang <jasowang@redhat.com> --- drivers/net/virtio_net. | 0 drivers/net/virtio_net.c | 77 ++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 62 insertions(+), 15 deletions(-) create mode 100644 drivers/net/virtio_net. diff --git a/drivers/net/virtio_net. b/drivers/net/virtio_net. new file mode 100644 index 0000000..e69de29 diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index db5924c..f6c1f13 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -29,6 +29,7 @@ #include <linux/slab.h> #include <linux/cpu.h> #include <linux/average.h> +#include <linux/filter.h> #include <net/route.h> static int napi_weight = NAPI_POLL_WEIGHT; @@ -372,8 +373,20 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, return skb; } -static bool virtnet_xdp_xmit(struct virtnet_info *vi, - struct xdp_buff *xdp) +static void virtnet_xdp_flush(struct net_device *dev) +{ + struct virtnet_info *vi = netdev_priv(dev); + struct send_queue *sq; + unsigned int qp; + + qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); + sq = &vi->sq[qp]; + + virtqueue_kick(sq->vq); +} + +static bool __virtnet_xdp_xmit(struct virtnet_info *vi, + struct xdp_buff *xdp) { struct virtio_net_hdr_mrg_rxbuf *hdr; unsigned int len; @@ -407,10 +420,19 @@ static bool virtnet_xdp_xmit(struct virtnet_info *vi, return false; } - virtqueue_kick(sq->vq); return true; } +static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) +{ + struct virtnet_info *vi = netdev_priv(dev); + bool sent = __virtnet_xdp_xmit(vi, xdp); + + if (!sent) + return -ENOSPC; + return 0; +} + static unsigned int virtnet_get_headroom(struct virtnet_info *vi) { return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0; @@ -483,7 +505,8 @@ static struct sk_buff *receive_small(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, void *ctx, - unsigned int len) + unsigned int len, + bool *xdp_xmit) { struct sk_buff *skb; struct bpf_prog *xdp_prog; @@ -493,7 +516,7 @@ static struct sk_buff *receive_small(struct net_device *dev, unsigned int buflen = SKB_DATA_ALIGN(GOOD_PACKET_LEN + headroom) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); struct page *page = virt_to_head_page(buf); - unsigned int delta = 0; + unsigned int delta = 0, err; struct page *xdp_page; len -= vi->hdr_len; @@ -541,8 +564,16 @@ static struct sk_buff *receive_small(struct net_device *dev, delta = orig_data - xdp.data; break; case XDP_TX: - if (unlikely(!virtnet_xdp_xmit(vi, &xdp))) + if (unlikely(!__virtnet_xdp_xmit(vi, &xdp))) trace_xdp_exception(vi->dev, xdp_prog, act); + else + *xdp_xmit = true; + rcu_read_unlock(); + goto xdp_xmit; + case XDP_REDIRECT: + err = xdp_do_redirect(dev, &xdp, xdp_prog); + if (!err) + *xdp_xmit = true; rcu_read_unlock(); goto xdp_xmit; default: @@ -603,7 +634,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct receive_queue *rq, void *buf, void *ctx, - unsigned int len) + unsigned int len, + bool *xdp_xmit) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); @@ -613,6 +645,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct bpf_prog *xdp_prog; unsigned int truesize; unsigned int headroom = mergeable_ctx_to_headroom(ctx); + int err; head_skb = NULL; @@ -678,12 +711,20 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } break; case XDP_TX: - if (unlikely(!virtnet_xdp_xmit(vi, &xdp))) + if (unlikely(!__virtnet_xdp_xmit(vi, &xdp))) trace_xdp_exception(vi->dev, xdp_prog, act); + else + *xdp_xmit = true; if (unlikely(xdp_page != page)) goto err_xdp; rcu_read_unlock(); goto xdp_xmit; + case XDP_REDIRECT: + err = xdp_do_redirect(dev, &xdp, xdp_prog); + if (err) + *xdp_xmit = true; + rcu_read_unlock(); + goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: @@ -788,7 +829,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, - void *buf, unsigned int len, void **ctx) + void *buf, unsigned int len, void **ctx, bool *xdp_xmit) { struct net_device *dev = vi->dev; struct sk_buff *skb; @@ -809,11 +850,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, } if (vi->mergeable_rx_bufs) - skb = receive_mergeable(dev, vi, rq, buf, ctx, len); + skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit); else if (vi->big_packets) skb = receive_big(dev, vi, rq, buf, len); else - skb = receive_small(dev, vi, rq, buf, ctx, len); + skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit); if (unlikely(!skb)) return 0; @@ -1071,7 +1112,7 @@ static void refill_work(struct work_struct *work) } } -static int virtnet_receive(struct receive_queue *rq, int budget) +static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit) { struct virtnet_info *vi = rq->vq->vdev->priv; unsigned int len, received = 0, bytes = 0; @@ -1083,13 +1124,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget) while (received < budget && (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) { - bytes += receive_buf(vi, rq, buf, len, ctx); + bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit); received++; } } else { while (received < budget && (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { - bytes += receive_buf(vi, rq, buf, len, NULL); + bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit); received++; } } @@ -1161,15 +1202,19 @@ static int virtnet_poll(struct napi_struct *napi, int budget) struct receive_queue *rq = container_of(napi, struct receive_queue, napi); unsigned int received; + bool xdp_xmit = false; virtnet_poll_cleantx(rq); - received = virtnet_receive(rq, budget); + received = virtnet_receive(rq, budget, &xdp_xmit); /* Out of packets? */ if (received < budget) virtqueue_napi_complete(napi, rq->vq, received); + if (xdp_xmit) + xdp_do_flush_map(); + return received; } @@ -2069,6 +2114,8 @@ static const struct net_device_ops virtnet_netdev = { .ndo_poll_controller = virtnet_netpoll, #endif .ndo_xdp = virtnet_xdp, + .ndo_xdp_xmit = virtnet_xdp_xmit, + .ndo_xdp_flush = virtnet_xdp_flush, .ndo_features_check = passthru_features_check, }; -- 2.7.4 ^ permalink raw reply related [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT 2017-09-19 9:42 ` [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT Jason Wang @ 2017-09-20 21:28 ` David Miller 2017-09-20 22:02 ` John Fastabend 1 sibling, 0 replies; 8+ messages in thread From: David Miller @ 2017-09-20 21:28 UTC (permalink / raw) To: jasowang; +Cc: mst, virtualization, netdev, linux-kernel, john.fastabend From: Jason Wang <jasowang@redhat.com> Date: Tue, 19 Sep 2017 17:42:43 +0800 > This patch tries to add XDP_REDIRECT for virtio-net. The changes are > not complex as we could use exist XDP_TX helpers for most of the > work. The rest is passing the XDP_TX to NAPI handler for implementing > batching. > > Cc: John Fastabend <john.fastabend@gmail.com> > Signed-off-by: Jason Wang <jasowang@redhat.com> Applied. ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT 2017-09-19 9:42 ` [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT Jason Wang 2017-09-20 21:28 ` David Miller @ 2017-09-20 22:02 ` John Fastabend 2017-09-22 4:06 ` Jason Wang 1 sibling, 1 reply; 8+ messages in thread From: John Fastabend @ 2017-09-20 22:02 UTC (permalink / raw) To: Jason Wang, mst, virtualization, netdev, linux-kernel On 09/19/2017 02:42 AM, Jason Wang wrote: > This patch tries to add XDP_REDIRECT for virtio-net. The changes are > not complex as we could use exist XDP_TX helpers for most of the > work. The rest is passing the XDP_TX to NAPI handler for implementing > batching. > > Cc: John Fastabend <john.fastabend@gmail.com> > Signed-off-by: Jason Wang <jasowang@redhat.com> > --- [...] > @@ -678,12 +711,20 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, > } > break; > case XDP_TX: > - if (unlikely(!virtnet_xdp_xmit(vi, &xdp))) > + if (unlikely(!__virtnet_xdp_xmit(vi, &xdp))) > trace_xdp_exception(vi->dev, xdp_prog, act); > + else > + *xdp_xmit = true; > if (unlikely(xdp_page != page)) > goto err_xdp; > rcu_read_unlock(); > goto xdp_xmit; > + case XDP_REDIRECT: > + err = xdp_do_redirect(dev, &xdp, xdp_prog); > + if (err) > + *xdp_xmit = true; Is this a typo? Should above be if (!err) *xdp_xmit = true; this would match the pattern in receive_small and also make more sense. > + rcu_read_unlock(); > + goto xdp_xmit; > default: > bpf_warn_invalid_xdp_action(act); > case XDP_ABORTED: > @@ -788,7 +829,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, > } > [...] Otherwise looks good to me thanks for doing this. .John ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT 2017-09-20 22:02 ` John Fastabend @ 2017-09-22 4:06 ` Jason Wang 0 siblings, 0 replies; 8+ messages in thread From: Jason Wang @ 2017-09-22 4:06 UTC (permalink / raw) To: John Fastabend, mst, virtualization, netdev, linux-kernel On 2017年09月21日 06:02, John Fastabend wrote: > On 09/19/2017 02:42 AM, Jason Wang wrote: >> This patch tries to add XDP_REDIRECT for virtio-net. The changes are >> not complex as we could use exist XDP_TX helpers for most of the >> work. The rest is passing the XDP_TX to NAPI handler for implementing >> batching. >> >> Cc: John Fastabend <john.fastabend@gmail.com> >> Signed-off-by: Jason Wang <jasowang@redhat.com> >> --- > [...] > >> @@ -678,12 +711,20 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, >> } >> break; >> case XDP_TX: >> - if (unlikely(!virtnet_xdp_xmit(vi, &xdp))) >> + if (unlikely(!__virtnet_xdp_xmit(vi, &xdp))) >> trace_xdp_exception(vi->dev, xdp_prog, act); >> + else >> + *xdp_xmit = true; >> if (unlikely(xdp_page != page)) >> goto err_xdp; >> rcu_read_unlock(); >> goto xdp_xmit; >> + case XDP_REDIRECT: >> + err = xdp_do_redirect(dev, &xdp, xdp_prog); >> + if (err) >> + *xdp_xmit = true; > Is this a typo? Should above be > > if (!err) > *xdp_xmit = true; > > this would match the pattern in receive_small and also make more sense. Right, will post a fix. > >> + rcu_read_unlock(); >> + goto xdp_xmit; >> default: >> bpf_warn_invalid_xdp_action(act); >> case XDP_ABORTED: >> @@ -788,7 +829,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, >> } >> > [...] > > Otherwise looks good to me thanks for doing this. > > .John > Thanks for the reviewing. ^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() 2017-09-19 9:42 [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() Jason Wang 2017-09-19 9:42 ` [PATCH net-next 2/3] virtio-net: add packet len average only when needed during XDP Jason Wang 2017-09-19 9:42 ` [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT Jason Wang @ 2017-09-20 21:28 ` David Miller 2 siblings, 0 replies; 8+ messages in thread From: David Miller @ 2017-09-20 21:28 UTC (permalink / raw) To: jasowang; +Cc: netdev, virtualization, john.fastabend, linux-kernel, mst From: Jason Wang <jasowang@redhat.com> Date: Tue, 19 Sep 2017 17:42:41 +0800 > CC: John Fastabend <john.fastabend@gmail.com> > Signed-off-by: Jason Wang <jasowang@redhat.com> Applied. ^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2017-09-22 4:06 UTC | newest] Thread overview: 8+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2017-09-19 9:42 [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() Jason Wang 2017-09-19 9:42 ` [PATCH net-next 2/3] virtio-net: add packet len average only when needed during XDP Jason Wang 2017-09-20 21:28 ` David Miller 2017-09-19 9:42 ` [PATCH net-next 3/3] virtio-net: support XDP_REDIRECT Jason Wang 2017-09-20 21:28 ` David Miller 2017-09-20 22:02 ` John Fastabend 2017-09-22 4:06 ` Jason Wang 2017-09-20 21:28 ` [PATCH net-next 1/3] virtio-net: remove unnecessary parameter of virtnet_xdp_xmit() David Miller
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).