search for: skb_peek

No need to check the support of mergeable buffer inside the recevie loop as the whole handle_rx()_xx is in the read critical region. So this patch move it ahead of the receiving loop. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/net.c | 5 +++-- 1 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index

No need to check the support of mergeable buffer inside the recevie loop as the whole handle_rx()_xx is in the read critical region. So this patch move it ahead of the receiving loop. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/net.c | 5 +++-- 1 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index

Hi, I ran into an issue where netback driver is crashing with BUG_ON(npo.meta_prod > ARRAY_SIZE(netbk->meta)). It is happening in Intel 10Gbps network when larger mtu values are used. The problem seems to be the way the slots are counted. After applying this patch things ran fine in my environment. I request to validate my changes. Thanks Siva

hi i tried the example given on the examples page to duplicate selected traffic like tc qdisc add dev eth0 root handle 1: prio tc qdisc add dev eth0 parent 1:3 handle 3: netem duplicate 40% tc filter add dev eth0 protocol ip parent 1:0 prio 3 u32 match ip dst 11.0.2.2 flowid 1:3 when i ping from 11.0.2.2 to this interface my machine hangs. the same thing works for drop or delay. i would

...+ tun = __tun_get(tfile); > + if (!tun) > + return 0; > + > + if (tun->flags & IFF_TX_ARRAY) { > + ret = skb_array_peek_len(&tfile->tx_array); > + } else { > + struct sk_buff *head; > + > + spin_lock_bh(&sk->sk_receive_queue.lock); > + head = skb_peek(&sk->sk_receive_queue); > + if (likely(head)) { > + ret = head->len; > + if (skb_vlan_tag_present(head)) > + ret += VLAN_HLEN; > + } > + spin_unlock_bh(&sk->sk_receive_queue.lock); > + } > + > + tun_put(tun); > + return ret; > +} > + &g...

...udp.h> +#include <linux/netdevice.h> + #include <net/sock.h> #include "vhost.h" @@ -186,6 +190,44 @@ static void handle_tx(struct vhost_net *net) unuse_mm(net->dev.mm); } +static int peek_head(struct sock *sk) +{ + struct sk_buff *skb; + + lock_sock(sk); + skb = skb_peek(&sk->sk_receive_queue); + if (unlikely(!skb)) { + release_sock(sk); + return 0; + } + /* Userspace virtio server has the following hack so + * guests rely on it, and we have to replicate it, too: */ + /* Use port number to detect incoming IPv4 DHCP response packets, + * and fill in the c...

...udp.h> +#include <linux/netdevice.h> + #include <net/sock.h> #include "vhost.h" @@ -186,6 +190,44 @@ static void handle_tx(struct vhost_net *net) unuse_mm(net->dev.mm); } +static int peek_head(struct sock *sk) +{ + struct sk_buff *skb; + + lock_sock(sk); + skb = skb_peek(&sk->sk_receive_queue); + if (unlikely(!skb)) { + release_sock(sk); + return 0; + } + /* Userspace virtio server has the following hack so + * guests rely on it, and we have to replicate it, too: */ + /* Use port number to detect incoming IPv4 DHCP response packets, + * and fill in the c...

...>sk; + struct tun_struct *tun; + int ret = 0; + + tun = __tun_get(tfile); + if (!tun) + return 0; + + if (tun->flags & IFF_TX_ARRAY) { + ret = skb_array_peek_len(&tfile->tx_array); + } else { + struct sk_buff *head; + + spin_lock_bh(&sk->sk_receive_queue.lock); + head = skb_peek(&sk->sk_receive_queue); + if (likely(head)) { + ret = head->len; + if (skb_vlan_tag_present(head)) + ret += VLAN_HLEN; + } + spin_unlock_bh(&sk->sk_receive_queue.lock); + } + + tun_put(tun); + return ret; +} + /* Ops structure to mimic raw sockets with tun */ static con...

...>sk; + struct tun_struct *tun; + int ret = 0; + + tun = __tun_get(tfile); + if (!tun) + return 0; + + if (tun->flags & IFF_TX_ARRAY) { + ret = skb_array_peek_len(&tfile->tx_array); + } else { + struct sk_buff *head; + + spin_lock_bh(&sk->sk_receive_queue.lock); + head = skb_peek(&sk->sk_receive_queue); + if (likely(head)) { + ret = head->len; + if (skb_vlan_tag_present(head)) + ret += VLAN_HLEN; + } + spin_unlock_bh(&sk->sk_receive_queue.lock); + } + + tun_put(tun); + return ret; +} + /* Ops structure to mimic raw sockets with tun */ static con...

...the user's buffer, I think we should queue it again. In fact, before commit 71dc9ec9ac7d ("virtio/vsock: replace virtio_vsock_pkt with sk_buff"), we used to remove the packet from the rx_queue, only if memcpy_to_msg() was successful. Maybe it is better to do as we did before and use skb_peek() at the beginning of the loop and __skb_unlink() when skb->len == 0. Thanks, Stefano > goto out; >+ } > > spin_lock_bh(&vvs->rx_lock); > >-- >2.25.1 >

...9;t need to change skbuff state to update > 'rx_bytes' and 'fwd_cnt' correctly. >2) For SOCK_STREAM, when copying data to user fails, current skbuff is > not dropped. Next read attempt will use same skbuff and last offset. > Instead of 'skb_dequeue()', 'skb_peek()' + '__skb_unlink()' are used. > This behaviour was implemented before skbuff support. >3) For SOCK_SEQPACKET it removes unneeded 'skb_pull()' call, because for > this type of socket each skbuff is used only once: after removing it > from socket's queue, i...

...nclude <linux/netdevice.h> + #include <net/sock.h> #include "vhost.h" @@ -191,6 +195,42 @@ static void handle_tx(struct vhost_net *net) unuse_mm(net->dev.mm); } +static int peek_head(struct sock *sk) +{ + struct sk_buff *head; + int ret; + + lock_sock(sk); + head = skb_peek(&sk->sk_receive_queue); + if (likely(head)) { + ret = 1; + /* Userspace virtio server has the following hack so + * guests rely on it, and we have to replicate it, too: */ + /* On linux guests, some apps that use recvmsg with AF_PACKET + * sockets, don't know how to handle CHECKSU...

...nclude <linux/netdevice.h> + #include <net/sock.h> #include "vhost.h" @@ -191,6 +195,42 @@ static void handle_tx(struct vhost_net *net) unuse_mm(net->dev.mm); } +static int peek_head(struct sock *sk) +{ + struct sk_buff *head; + int ret; + + lock_sock(sk); + head = skb_peek(&sk->sk_receive_queue); + if (likely(head)) { + ret = 1; + /* Userspace virtio server has the following hack so + * guests rely on it, and we have to replicate it, too: */ + /* On linux guests, some apps that use recvmsg with AF_PACKET + * sockets, don't know how to handle CHECKSU...

...o update >>> ? 'rx_bytes' and 'fwd_cnt' correctly. >>> 2) For SOCK_STREAM, when copying data to user fails, current skbuff is >>> ? not dropped. Next read attempt will use same skbuff and last offset. >>> ? Instead of 'skb_dequeue()', 'skb_peek()' + '__skb_unlink()' are used. >>> ? This behaviour was implemented before skbuff support. >>> 3) For SOCK_SEQPACKET it removes unneeded 'skb_pull()' call, because for >>> ? this type of socket each skbuff is used only once: after removing it >>...

...len += len; if (unlikely(total_len >= VHOST_NET_WEIGHT)) { vhost_poll_queue(&vq->poll); @@ -182,12 +181,22 @@ unuse_mm(net->dev.mm); } +static int skb_head_len(struct sk_buff_head *skq) +{ + struct sk_buff *head; + + head = skb_peek(skq); + if (head) + return head->len; + return 0; +} + /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_rx(struct vhost_net *net) { struct vhost_virtqueue *vq = &net->d...

...len += len; if (unlikely(total_len >= VHOST_NET_WEIGHT)) { vhost_poll_queue(&vq->poll); @@ -182,12 +181,22 @@ unuse_mm(net->dev.mm); } +static int skb_head_len(struct sk_buff_head *skq) +{ + struct sk_buff *head; + + head = skb_peek(skq); + if (head) + return head->len; + return 0; +} + /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_rx(struct vhost_net *net) { struct vhost_virtqueue *vq = &net->d...

...tatic int peek_head_len(struct sock *sk) { + struct socket *sock = sk->sk_socket; struct sk_buff *head; int len = 0; unsigned long flags; + if (sock->ops->peek_len) + return sock->ops->peek_len(sock); + spin_lock_irqsave(&sk->sk_receive_queue.lock, flags); head = skb_peek(&sk->sk_receive_queue); if (likely(head)) { @@ -497,6 +501,16 @@ static int peek_head_len(struct sock *sk) return len; } +static int sk_has_rx_data(struct sock *sk) +{ + struct socket *sock = sk->sk_socket; + + if (sock->ops->peek_len) + return sock->ops->peek_len(sock...

...signal(&net->dev, vq, head, + 0); + } break; } if (err != len) @@ -186,12 +192,25 @@ static void handle_tx(struct vhost_net * unuse_mm(net->dev.mm); } +static int vhost_head_len(struct sock *sk) +{ + struct sk_buff *head; + int len = 0; + + lock_sock(sk); + head = skb_peek(&sk->sk_receive_queue); + if (head) + len = head->len; + release_sock(sk); + return len; +} + /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_rx(struct vhost_net *net) { struct vhost_virtqueue *vq =...

...signal(&net->dev, vq, head, + 0); + } break; } if (err != len) @@ -186,12 +192,25 @@ static void handle_tx(struct vhost_net * unuse_mm(net->dev.mm); } +static int vhost_head_len(struct sock *sk) +{ + struct sk_buff *head; + int len = 0; + + lock_sock(sk); + head = skb_peek(&sk->sk_receive_queue); + if (head) + len = head->len; + release_sock(sk); + return len; +} + /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_rx(struct vhost_net *net) { struct vhost_virtqueue *vq =...

...rd_desc(vq, 1); tx_poll_start(net, sock); break; } @@ -186,12 +186,25 @@ static void handle_tx(struct vhost_net * unuse_mm(net->dev.mm); } +static int vhost_head_len(struct vhost_virtqueue *vq, struct sock *sk) +{ + struct sk_buff *head; + int len = 0; + + lock_sock(sk); + head = skb_peek(&sk->sk_receive_queue); + if (head) + len = head->len + vq->sock_hlen; + release_sock(sk); + return len; +} + /* Expects to be always run from workqueue - which acts as * read-size critical section for our kind of RCU. */ static void handle_rx(struct vhost_net *net) { struct vh...