[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1272057969-6526-4-git-send-email-brian.haley@hp.com>
Date: Fri, 23 Apr 2010 17:26:09 -0400
From: Brian Haley <brian.haley@...com>
To: davem@...emloft.net, yoshfuji@...ux-ipv6.org
Cc: netdev@...r.kernel.org
Subject: [PATCH 3/3] IPv6: Complete IPV6_DONTFRAG support
Finally add support to detect a local IPV6_DONTFRAG event
and return the relevant data to the user if they've enabled
IPV6_RECVPATHMTU on the socket. The next recvmsg() will
return no data, but have an IPV6_PATHMTU as ancillary data.
Signed-off-by: Brian Haley <brian.haley@...com>
---
include/linux/ipv6.h | 2 +
include/net/ipv6.h | 2 +
net/ipv6/af_inet6.c | 3 ++
net/ipv6/datagram.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++++
net/ipv6/ip6_output.c | 24 +++++++++----
net/ipv6/raw.c | 3 ++
net/ipv6/udp.c | 3 ++
7 files changed, 116 insertions(+), 8 deletions(-)
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 1976942..2ab5509 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -257,6 +257,7 @@ struct inet6_skb_parm {
};
#define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb))
+#define IP6CBMTU(skb) ((struct ip6_mtuinfo *)((skb)->cb))
static inline int inet6_iif(const struct sk_buff *skb)
{
@@ -366,6 +367,7 @@ struct ipv6_pinfo {
struct ipv6_txoptions *opt;
struct sk_buff *pktoptions;
+ struct sk_buff *rxpmtu;
struct {
struct ipv6_txoptions *opt;
u8 hop_limit;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 7ab6323..eba5cc0 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -578,9 +578,11 @@ extern int ip6_datagram_connect(struct sock *sk,
struct sockaddr *addr, int addr_len);
extern int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len);
+extern int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len);
extern void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port,
u32 info, u8 *payload);
extern void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info);
+extern void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu);
extern int inet6_release(struct socket *sock);
extern int inet6_bind(struct socket *sock, struct sockaddr *uaddr,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3192aa0..d2df314 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -417,6 +417,9 @@ void inet6_destroy_sock(struct sock *sk)
if ((skb = xchg(&np->pktoptions, NULL)) != NULL)
kfree_skb(skb);
+ if ((skb = xchg(&np->rxpmtu, NULL)) != NULL)
+ kfree_skb(skb);
+
/* Free flowlabels */
fl6_free_socklist(sk);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index f5076d3..5959230 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -278,6 +278,45 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
kfree_skb(skb);
}
+void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6hdr *iph;
+ struct sk_buff *skb;
+ struct ip6_mtuinfo *mtu_info;
+
+ if (!np->rxopt.bits.rxpmtu)
+ return;
+
+ skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ skb_put(skb, sizeof(struct ipv6hdr));
+ skb_reset_network_header(skb);
+ iph = ipv6_hdr(skb);
+ ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);
+
+ mtu_info = IP6CBMTU(skb);
+ if (!mtu_info) {
+ kfree_skb(skb);
+ return;
+ }
+
+ mtu_info->ip6m_mtu = mtu;
+ mtu_info->ip6m_addr.sin6_family = AF_INET6;
+ mtu_info->ip6m_addr.sin6_port = 0;
+ mtu_info->ip6m_addr.sin6_flowinfo = 0;
+ mtu_info->ip6m_addr.sin6_scope_id = fl->oif;
+ ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
+
+ __skb_pull(skb, skb_tail_pointer(skb) - skb->data);
+ skb_reset_transport_header(skb);
+
+ skb = xchg(&np->rxpmtu, skb);
+ kfree_skb(skb);
+}
+
/*
* Handle MSG_ERRQUEUE
*/
@@ -381,6 +420,54 @@ out:
return err;
}
+/*
+ * Handle IPV6_RECVPATHMTU
+ */
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct sk_buff *skb;
+ struct sockaddr_in6 *sin;
+ struct ip6_mtuinfo mtu_info;
+ int err;
+ int copied;
+
+ err = -EAGAIN;
+ skb = xchg(&np->rxpmtu, NULL);
+ if (skb == NULL)
+ goto out;
+
+ copied = skb->len;
+ if (copied > len) {
+ msg->msg_flags |= MSG_TRUNC;
+ copied = len;
+ }
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ if (err)
+ goto out_free_skb;
+
+ sock_recv_timestamp(msg, sk, skb);
+
+ memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
+
+ sin = (struct sockaddr_in6 *)msg->msg_name;
+ if (sin) {
+ sin->sin6_family = AF_INET6;
+ sin->sin6_flowinfo = 0;
+ sin->sin6_port = 0;
+ sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
+ ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr);
+ }
+
+ put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
+
+ err = copied;
+
+out_free_skb:
+ kfree_skb(skb);
+out:
+ return err;
+}
int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 54d43dd..61e2bef 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1219,15 +1219,23 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
*/
inet->cork.length += length;
- if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
- (rt->u.dst.dev->features & NETIF_F_UFO)) {
+ if (length > mtu) {
+ int proto = sk->sk_protocol;
+ if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
+ ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen);
+ return -EMSGSIZE;
+ }
- err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len,
- fragheaderlen, transhdrlen, mtu,
- flags);
- if (err)
- goto error;
- return 0;
+ if (proto == IPPROTO_UDP &&
+ (rt->u.dst.dev->features & NETIF_F_UFO)) {
+
+ err = ip6_ufo_append_data(sk, getfrag, from, length,
+ hh_len, fragheaderlen,
+ transhdrlen, mtu, flags);
+ if (err)
+ goto error;
+ return 0;
+ }
}
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 44a84ea..8562738 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -461,6 +461,9 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len);
+ if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ return ipv6_recv_rxpmtu(sk, msg, len);
+
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
goto out;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 39e3665..2850e35 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -335,6 +335,9 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len);
+ if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ return ipv6_recv_rxpmtu(sk, msg, len);
+
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
&peeked, &err);
--
1.5.4.3
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists