aboutsummaryrefslogtreecommitdiff
path: root/net/ipv6/raw.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/raw.c')
-rw-r--r--net/ipv6/raw.c663
1 files changed, 325 insertions, 338 deletions
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 8897ccf8086..b2dc60b0c76 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -7,8 +7,6 @@
*
* Adapted from linux/net/ipv4/raw.c
*
- * $Id: raw.c,v 1.51 2002/02/01 22:01:04 davem Exp $
- *
* Fixes:
* Hideaki YOSHIFUJI : sin6_scope_id support
* YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance)
@@ -23,6 +21,7 @@
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
+#include <linux/slab.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
@@ -32,6 +31,7 @@
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <linux/skbuff.h>
+#include <linux/compat.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
@@ -50,9 +50,10 @@
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/tcp_states.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
+#include <linux/mroute6.h>
#include <net/raw.h>
#include <net/rawv6.h>
@@ -60,45 +61,35 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <linux/export.h>
+
+#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */
static struct raw_hashinfo raw_v6_hashinfo = {
- .lock = __RW_LOCK_UNLOCKED(),
+ .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock),
};
-static void raw_v6_hash(struct sock *sk)
-{
- raw_hash_sk(sk, &raw_v6_hashinfo);
-}
-
-static void raw_v6_unhash(struct sock *sk)
-{
- raw_unhash_sk(sk, &raw_v6_hashinfo);
-}
-
-
static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
- unsigned short num, struct in6_addr *loc_addr,
- struct in6_addr *rmt_addr, int dif)
+ unsigned short num, const struct in6_addr *loc_addr,
+ const struct in6_addr *rmt_addr, int dif)
{
- struct hlist_node *node;
- int is_multicast = ipv6_addr_is_multicast(loc_addr);
+ bool is_multicast = ipv6_addr_is_multicast(loc_addr);
- sk_for_each_from(sk, node)
- if (inet_sk(sk)->num == num) {
- struct ipv6_pinfo *np = inet6_sk(sk);
+ sk_for_each_from(sk)
+ if (inet_sk(sk)->inet_num == num) {
- if (sk->sk_net != net)
+ if (!net_eq(sock_net(sk), net))
continue;
- if (!ipv6_addr_any(&np->daddr) &&
- !ipv6_addr_equal(&np->daddr, rmt_addr))
+ if (!ipv6_addr_any(&sk->sk_v6_daddr) &&
+ !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
continue;
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
continue;
- if (!ipv6_addr_any(&np->rcv_saddr)) {
- if (ipv6_addr_equal(&np->rcv_saddr, loc_addr))
+ if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+ if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))
goto found;
if (is_multicast &&
inet6_mc_check(sk, loc_addr, rmt_addr))
@@ -116,38 +107,40 @@ found:
* 0 - deliver
* 1 - block
*/
-static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb)
+static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb)
{
- struct icmp6hdr *icmph;
- struct raw6_sock *rp = raw6_sk(sk);
+ struct icmp6hdr _hdr;
+ const struct icmp6hdr *hdr;
- if (pskb_may_pull(skb, sizeof(struct icmp6hdr))) {
- __u32 *data = &rp->filter.data[0];
- int bit_nr;
-
- icmph = (struct icmp6hdr *) skb->data;
- bit_nr = icmph->icmp6_type;
+ /* We require only the four bytes of the ICMPv6 header, not any
+ * additional bytes of message body in "struct icmp6hdr".
+ */
+ hdr = skb_header_pointer(skb, skb_transport_offset(skb),
+ ICMPV6_HDRLEN, &_hdr);
+ if (hdr) {
+ const __u32 *data = &raw6_sk(sk)->filter.data[0];
+ unsigned int type = hdr->icmp6_type;
- return (data[bit_nr >> 5] & (1 << (bit_nr & 31))) != 0;
+ return (data[type >> 5] & (1U << (type & 31))) != 0;
}
- return 0;
+ return 1;
}
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
-static int (*mh_filter)(struct sock *sock, struct sk_buff *skb);
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb);
+
+static mh_filter_t __rcu *mh_filter __read_mostly;
-int rawv6_mh_filter_register(int (*filter)(struct sock *sock,
- struct sk_buff *skb))
+int rawv6_mh_filter_register(mh_filter_t filter)
{
rcu_assign_pointer(mh_filter, filter);
return 0;
}
EXPORT_SYMBOL(rawv6_mh_filter_register);
-int rawv6_mh_filter_unregister(int (*filter)(struct sock *sock,
- struct sk_buff *skb))
+int rawv6_mh_filter_unregister(mh_filter_t filter)
{
- rcu_assign_pointer(mh_filter, NULL);
+ RCU_INIT_POINTER(mh_filter, NULL);
synchronize_rcu();
return 0;
}
@@ -162,44 +155,39 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister);
*
* Caller owns SKB so we must make clones.
*/
-static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
+static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
{
- struct in6_addr *saddr;
- struct in6_addr *daddr;
+ const struct in6_addr *saddr;
+ const struct in6_addr *daddr;
struct sock *sk;
- int delivered = 0;
+ bool delivered = false;
__u8 hash;
struct net *net;
saddr = &ipv6_hdr(skb)->saddr;
daddr = saddr + 1;
- hash = nexthdr & (MAX_INET_PROTOS - 1);
+ hash = nexthdr & (RAW_HTABLE_SIZE - 1);
read_lock(&raw_v6_hashinfo.lock);
sk = sk_head(&raw_v6_hashinfo.ht[hash]);
- /*
- * The first socket found will be delivered after
- * delivery to transport protocols.
- */
-
if (sk == NULL)
goto out;
- net = skb->dev->nd_net;
+ net = dev_net(skb->dev);
sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif);
while (sk) {
int filtered;
- delivered = 1;
+ delivered = true;
switch (nexthdr) {
case IPPROTO_ICMPV6:
filtered = icmpv6_filter(sk, skb);
break;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_MH:
{
/* XXX: To validate MH only once for each packet,
@@ -208,10 +196,10 @@ static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
* policy is placed in rawv6_rcv() because it is
* required for each socket.
*/
- int (*filter)(struct sock *sock, struct sk_buff *skb);
+ mh_filter_t *filter;
filter = rcu_dereference(mh_filter);
- filtered = filter ? filter(sk, skb) : 0;
+ filtered = filter ? (*filter)(sk, skb) : 0;
break;
}
#endif
@@ -239,11 +227,11 @@ out:
return delivered;
}
-int raw6_local_deliver(struct sk_buff *skb, int nexthdr)
+bool raw6_local_deliver(struct sk_buff *skb, int nexthdr)
{
struct sock *raw_sk;
- raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (MAX_INET_PROTOS - 1)]);
+ raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]);
if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
raw_sk = NULL;
@@ -262,11 +250,15 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
+
+ if (addr->sin6_family != AF_INET6)
+ return -EINVAL;
+
addr_type = ipv6_addr_type(&addr->sin6_addr);
/* Raw sockets are IPv6 only */
if (addr_type == IPV6_ADDR_MAPPED)
- return(-EADDRNOTAVAIL);
+ return -EADDRNOTAVAIL;
lock_sock(sk);
@@ -274,11 +266,12 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (sk->sk_state != TCP_CLOSE)
goto out;
+ rcu_read_lock();
/* Check if the address belongs to the host. */
if (addr_type != IPV6_ADDR_ANY) {
struct net_device *dev = NULL;
- if (addr_type & IPV6_ADDR_LINKLOCAL) {
+ if (__ipv6_addr_needs_scope_id(addr_type)) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
addr->sin6_scope_id) {
/* Override any existing binding, if another
@@ -289,13 +282,13 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
/* Binding to link-local address requires an interface */
if (!sk->sk_bound_dev_if)
- goto out;
+ goto out_unlock;
- dev = dev_get_by_index(sk->sk_net, sk->sk_bound_dev_if);
- if (!dev) {
- err = -ENODEV;
- goto out;
- }
+ err = -ENODEV;
+ dev = dev_get_by_index_rcu(sock_net(sk),
+ sk->sk_bound_dev_if);
+ if (!dev)
+ goto out_unlock;
}
/* ipv4 addr of the socket is invalid. Only the
@@ -304,22 +297,20 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
v4addr = LOOPBACK4_IPV6;
if (!(addr_type & IPV6_ADDR_MULTICAST)) {
err = -EADDRNOTAVAIL;
- if (!ipv6_chk_addr(sk->sk_net, &addr->sin6_addr,
+ if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr,
dev, 0)) {
- if (dev)
- dev_put(dev);
- goto out;
+ goto out_unlock;
}
}
- if (dev)
- dev_put(dev);
}
- inet->rcv_saddr = inet->saddr = v4addr;
- ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr);
+ inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
+ sk->sk_v6_rcv_saddr = addr->sin6_addr;
if (!(addr_type & IPV6_ADDR_MULTICAST))
- ipv6_addr_copy(&np->saddr, &addr->sin6_addr);
+ np->saddr = addr->sin6_addr;
err = 0;
+out_unlock:
+ rcu_read_unlock();
out:
release_sock(sk);
return err;
@@ -327,7 +318,7 @@ out:
static void rawv6_err(struct sock *sk, struct sk_buff *skb,
struct inet6_skb_parm *opt,
- int type, int code, int offset, __be32 info)
+ u8 type, u8 code, int offset, __be32 info)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -343,9 +334,14 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
return;
harderr = icmpv6_err_convert(type, code, &err);
- if (type == ICMPV6_PKT_TOOBIG)
+ if (type == ICMPV6_PKT_TOOBIG) {
+ ip6_sk_update_pmtu(skb, sk, info);
harderr = (np->pmtudisc == IPV6_PMTUDISC_DO);
-
+ }
+ if (type == NDISC_REDIRECT) {
+ ip6_sk_redirect(skb, sk);
+ return;
+ }
if (np->recverr) {
u8 *payload = skb->data;
if (!inet->hdrincl)
@@ -360,11 +356,11 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
}
void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
- int type, int code, int inner_offset, __be32 info)
+ u8 type, u8 code, int inner_offset, __be32 info)
{
struct sock *sk;
int hash;
- struct in6_addr *saddr, *daddr;
+ const struct in6_addr *saddr, *daddr;
struct net *net;
hash = nexthdr & (RAW_HTABLE_SIZE - 1);
@@ -372,9 +368,11 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
read_lock(&raw_v6_hashinfo.lock);
sk = sk_head(&raw_v6_hashinfo.ht[hash]);
if (sk != NULL) {
- saddr = &ipv6_hdr(skb)->saddr;
- daddr = &ipv6_hdr(skb)->daddr;
- net = skb->dev->nd_net;
+ /* Note: ipv6_hdr(skb) != skb->data */
+ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data;
+ saddr = &ip6h->saddr;
+ daddr = &ip6h->daddr;
+ net = dev_net(skb->dev);
while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr,
IP6CB(skb)->iif))) {
@@ -386,20 +384,20 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
read_unlock(&raw_v6_hashinfo.lock);
}
-static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb)
+static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
- if ((raw6_sk(sk)->checksum || sk->sk_filter) &&
+ if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) &&
skb_checksum_complete(skb)) {
atomic_inc(&sk->sk_drops);
kfree_skb(skb);
- return 0;
+ return NET_RX_DROP;
}
/* Charge it to the socket. */
- if (sock_queue_rcv_skb(sk,skb)<0) {
- atomic_inc(&sk->sk_drops);
+ skb_dst_drop(skb);
+ if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
- return 0;
+ return NET_RX_DROP;
}
return 0;
@@ -431,20 +429,20 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
skb_network_header_len(skb));
if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr,
- skb->len, inet->num, skb->csum))
+ skb->len, inet->inet_num, skb->csum))
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
if (!skb_csum_unnecessary(skb))
skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr,
skb->len,
- inet->num, 0));
+ inet->inet_num, 0));
if (inet->hdrincl) {
if (skb_checksum_complete(skb)) {
atomic_inc(&sk->sk_drops);
kfree_skb(skb);
- return 0;
+ return NET_RX_DROP;
}
}
@@ -463,7 +461,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
int noblock, int flags, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
- struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)msg->msg_name;
+ DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
struct sk_buff *skb;
size_t copied;
int err;
@@ -471,11 +469,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_OOB)
return -EOPNOTSUPP;
- if (addr_len)
- *addr_len=sizeof(*sin6);
-
if (flags & MSG_ERRQUEUE)
- return ipv6_recv_error(sk, msg, len);
+ return ipv6_recv_error(sk, msg, len, addr_len);
+
+ if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -505,17 +503,17 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (sin6) {
sin6->sin6_family = AF_INET6;
sin6->sin6_port = 0;
- ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr);
+ sin6->sin6_addr = ipv6_hdr(skb)->saddr;
sin6->sin6_flowinfo = 0;
- sin6->sin6_scope_id = 0;
- if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
- sin6->sin6_scope_id = IP6CB(skb)->iif;
+ sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
+ IP6CB(skb)->iif);
+ *addr_len = sizeof(*sin6);
}
- sock_recv_timestamp(msg, sk, skb);
+ sock_recv_ts_and_drops(msg, sk, skb);
if (np->rxopt.all)
- datagram_recv_ctl(sk, msg, skb);
+ ip6_datagram_recv_ctl(sk, msg, skb);
err = copied;
if (flags & MSG_TRUNC)
@@ -533,11 +531,10 @@ csum_copy_err:
as some normal condition.
*/
err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH;
- atomic_inc(&sk->sk_drops);
goto out;
}
-static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl,
+static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
struct raw6_sock *rp)
{
struct sk_buff *skb;
@@ -555,8 +552,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl,
goto out;
offset = rp->offset;
- total_len = inet_sk(sk)->cork.length - (skb_network_header(skb) -
- skb->data);
+ total_len = inet_sk(sk)->cork.base.length;
if (offset >= total_len - 1) {
err = -EINVAL;
ip6_flush_pending_frames(sk);
@@ -599,11 +595,10 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl,
if (unlikely(csum))
tmp_csum = csum_sub(tmp_csum, csum_unfold(csum));
- csum = csum_ipv6_magic(&fl->fl6_src,
- &fl->fl6_dst,
- total_len, fl->proto, tmp_csum);
+ csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
+ total_len, fl6->flowi6_proto, tmp_csum);
- if (csum == 0 && fl->proto == IPPROTO_UDP)
+ if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP)
csum = CSUM_MANGLED_0;
if (skb_store_bits(skb, offset, &csum, 2))
@@ -616,33 +611,36 @@ out:
}
static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
- struct flowi *fl, struct rt6_info *rt,
+ struct flowi6 *fl6, struct dst_entry **dstp,
unsigned int flags)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6hdr *iph;
struct sk_buff *skb;
- unsigned int hh_len;
int err;
+ struct rt6_info *rt = (struct rt6_info *)*dstp;
+ int hlen = LL_RESERVED_SPACE(rt->dst.dev);
+ int tlen = rt->dst.dev->needed_tailroom;
- if (length > rt->u.dst.dev->mtu) {
- ipv6_local_error(sk, EMSGSIZE, fl, rt->u.dst.dev->mtu);
+ if (length > rt->dst.dev->mtu) {
+ ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
- hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
-
- skb = sock_alloc_send_skb(sk, length+hh_len+15,
- flags&MSG_DONTWAIT, &err);
+ skb = sock_alloc_send_skb(sk,
+ length + hlen + tlen + 15,
+ flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
- skb_reserve(skb, hh_len);
+ skb_reserve(skb, hlen);
+ skb->protocol = htons(ETH_P_IPV6);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
- skb->dst = dst_clone(&rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
+ *dstp = NULL;
skb_put(skb, length);
skb_reset_network_header(skb);
@@ -655,11 +653,11 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
if (err)
goto error_fault;
- IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
- err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
- dst_output);
+ IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
+ err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
+ rt->dst.dev, dst_output);
if (err > 0)
- err = np->recverr ? net_xmit_errno(err) : 0;
+ err = net_xmit_errno(err);
if (err)
goto error;
out:
@@ -669,11 +667,13 @@ error_fault:
err = -EFAULT;
kfree_skb(skb);
error:
- IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
+ IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
+ if (err == -ENOBUFS && !np->recverr)
+ err = 0;
return err;
}
-static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
+static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
{
struct iovec *iov;
u8 __user *type = NULL;
@@ -690,7 +690,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
if (!iov)
continue;
- switch (fl->proto) {
+ switch (fl6->flowi6_proto) {
case IPPROTO_ICMPV6:
/* check if one-byte field is readable or not. */
if (iov->iov_base && iov->iov_len < 1)
@@ -705,8 +705,8 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
code = iov->iov_base;
if (type && code) {
- if (get_user(fl->fl_icmp_type, type) ||
- get_user(fl->fl_icmp_code, code))
+ if (get_user(fl6->fl6_icmp_type, type) ||
+ get_user(fl6->fl6_icmp_code, code))
return -EFAULT;
probed = 1;
}
@@ -717,7 +717,7 @@ static int rawv6_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
/* check if type field is readable or not. */
if (iov->iov_len > 2 - len) {
u8 __user *p = iov->iov_base;
- if (get_user(fl->fl_mh_type, &p[2 - len]))
+ if (get_user(fl6->fl6_mh_type, &p[2 - len]))
return -EFAULT;
probed = 1;
} else
@@ -738,18 +738,19 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len)
{
struct ipv6_txoptions opt_space;
- struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name;
- struct in6_addr *daddr, *final_p = NULL, final;
+ DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
+ struct in6_addr *daddr, *final_p, final;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct raw6_sock *rp = raw6_sk(sk);
struct ipv6_txoptions *opt = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct dst_entry *dst = NULL;
- struct flowi fl;
+ struct flowi6 fl6;
int addr_len = msg->msg_namelen;
int hlimit = -1;
int tclass = -1;
+ int dontfrag = -1;
u16 proto;
int err;
@@ -766,36 +767,35 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
/*
* Get and verify the address.
*/
- memset(&fl, 0, sizeof(fl));
+ memset(&fl6, 0, sizeof(fl6));
- fl.mark = sk->sk_mark;
+ fl6.flowi6_mark = sk->sk_mark;
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (sin6->sin6_family && sin6->sin6_family != AF_INET6)
- return(-EAFNOSUPPORT);
+ return -EAFNOSUPPORT;
/* port is the proto value [0..255] carried in nexthdr */
proto = ntohs(sin6->sin6_port);
if (!proto)
- proto = inet->num;
- else if (proto != inet->num)
- return(-EINVAL);
+ proto = inet->inet_num;
+ else if (proto != inet->inet_num)
+ return -EINVAL;
if (proto > 255)
- return(-EINVAL);
+ return -EINVAL;
daddr = &sin6->sin6_addr;
if (np->sndflow) {
- fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
- if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
- flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+ fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
+ if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
+ flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
- daddr = &flowlabel->dst;
}
}
@@ -804,46 +804,38 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
* sk->sk_dst_cache.
*/
if (sk->sk_state == TCP_ESTABLISHED &&
- ipv6_addr_equal(daddr, &np->daddr))
- daddr = &np->daddr;
+ ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
+ daddr = &sk->sk_v6_daddr;
if (addr_len >= sizeof(struct sockaddr_in6) &&
sin6->sin6_scope_id &&
- ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
- fl.oif = sin6->sin6_scope_id;
+ __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr)))
+ fl6.flowi6_oif = sin6->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
- proto = inet->num;
- daddr = &np->daddr;
- fl.fl6_flowlabel = np->flow_label;
- }
-
- if (ipv6_addr_any(daddr)) {
- /*
- * unspecified destination address
- * treated as error... is this correct ?
- */
- fl6_sock_release(flowlabel);
- return(-EINVAL);
+ proto = inet->inet_num;
+ daddr = &sk->sk_v6_daddr;
+ fl6.flowlabel = np->flow_label;
}
- if (fl.oif == 0)
- fl.oif = sk->sk_bound_dev_if;
+ if (fl6.flowi6_oif == 0)
+ fl6.flowi6_oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
opt = &opt_space;
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(struct ipv6_txoptions);
- err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
+ err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
+ &hlimit, &tclass, &dontfrag);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
}
- if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
- flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
+ if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
+ flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
if (flowlabel == NULL)
return -EINVAL;
}
@@ -856,73 +848,56 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
- fl.proto = proto;
- err = rawv6_probe_proto_opt(&fl, msg);
+ fl6.flowi6_proto = proto;
+ err = rawv6_probe_proto_opt(&fl6, msg);
if (err)
goto out;
- ipv6_addr_copy(&fl.fl6_dst, daddr);
- if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
- ipv6_addr_copy(&fl.fl6_src, &np->saddr);
+ if (!ipv6_addr_any(daddr))
+ fl6.daddr = *daddr;
+ else
+ fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
+ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
+ fl6.saddr = np->saddr;
- /* merge ip6_build_xmit from ip6_output */
- if (opt && opt->srcrt) {
- struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
- ipv6_addr_copy(&final, &fl.fl6_dst);
- ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
- final_p = &final;
- }
+ final_p = fl6_update_dst(&fl6, opt, &final);
- if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
- fl.oif = np->mcast_oif;
- security_sk_classify_flow(sk, &fl);
+ if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
+ fl6.flowi6_oif = np->mcast_oif;
+ else if (!fl6.flowi6_oif)
+ fl6.flowi6_oif = np->ucast_oif;
+ security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- err = ip6_dst_lookup(sk, &dst, &fl);
- if (err)
+ dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+ if (IS_ERR(dst)) {
+ err = PTR_ERR(dst);
goto out;
- if (final_p)
- ipv6_addr_copy(&fl.fl6_dst, final_p);
-
- if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) {
- if (err == -EREMOTE)
- err = ip6_dst_blackhole(sk, &dst, &fl);
- if (err < 0)
- goto out;
}
+ if (hlimit < 0)
+ hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
- if (hlimit < 0) {
- if (ipv6_addr_is_multicast(&fl.fl6_dst))
- hlimit = np->mcast_hops;
- else
- hlimit = np->hop_limit;
- if (hlimit < 0)
- hlimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hlimit < 0)
- hlimit = ipv6_get_hoplimit(dst->dev);
- }
-
- if (tclass < 0) {
+ if (tclass < 0)
tclass = np->tclass;
- if (tclass < 0)
- tclass = 0;
- }
+
+ if (dontfrag < 0)
+ dontfrag = np->dontfrag;
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
- if (inet->hdrincl) {
- err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl, (struct rt6_info*)dst, msg->msg_flags);
- } else {
+ if (inet->hdrincl)
+ err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags);
+ else {
lock_sock(sk);
err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
- len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst,
- msg->msg_flags);
+ len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst,
+ msg->msg_flags, dontfrag);
if (err)
ip6_flush_pending_frames(sk);
else if (!(msg->msg_flags & MSG_MORE))
- err = rawv6_push_pending_frames(sk, &fl, rp);
+ err = rawv6_push_pending_frames(sk, &fl6, rp);
release_sock(sk);
}
done:
@@ -982,7 +957,7 @@ static int rawv6_geticmpfilter(struct sock *sk, int level, int optname,
static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
struct raw6_sock *rp = raw6_sk(sk);
int val;
@@ -991,44 +966,54 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
return -EFAULT;
switch (optname) {
- case IPV6_CHECKSUM:
- /* You may get strange result with a positive odd offset;
- RFC2292bis agrees with me. */
- if (val > 0 && (val&1))
- return(-EINVAL);
- if (val < 0) {
- rp->checksum = 0;
- } else {
- rp->checksum = 1;
- rp->offset = val;
- }
+ case IPV6_CHECKSUM:
+ if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 &&
+ level == IPPROTO_IPV6) {
+ /*
+ * RFC3542 tells that IPV6_CHECKSUM socket
+ * option in the IPPROTO_IPV6 level is not
+ * allowed on ICMPv6 sockets.
+ * If you want to set it, use IPPROTO_RAW
+ * level IPV6_CHECKSUM socket option
+ * (Linux extension).
+ */
+ return -EINVAL;
+ }
- return 0;
- break;
+ /* You may get strange result with a positive odd offset;
+ RFC2292bis agrees with me. */
+ if (val > 0 && (val&1))
+ return -EINVAL;
+ if (val < 0) {
+ rp->checksum = 0;
+ } else {
+ rp->checksum = 1;
+ rp->offset = val;
+ }
- default:
- return(-ENOPROTOOPT);
+ return 0;
+
+ default:
+ return -ENOPROTOOPT;
}
}
static int rawv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
- switch(level) {
- case SOL_RAW:
- break;
+ switch (level) {
+ case SOL_RAW:
+ break;
- case SOL_ICMPV6:
- if (inet_sk(sk)->num != IPPROTO_ICMPV6)
- return -EOPNOTSUPP;
- return rawv6_seticmpfilter(sk, level, optname, optval,
- optlen);
- case SOL_IPV6:
- if (optname == IPV6_CHECKSUM)
- break;
- default:
- return ipv6_setsockopt(sk, level, optname, optval,
- optlen);
+ case SOL_ICMPV6:
+ if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
+ return -EOPNOTSUPP;
+ return rawv6_seticmpfilter(sk, level, optname, optval, optlen);
+ case SOL_IPV6:
+ if (optname == IPV6_CHECKSUM)
+ break;
+ default:
+ return ipv6_setsockopt(sk, level, optname, optval, optlen);
}
return do_rawv6_setsockopt(sk, level, optname, optval, optlen);
@@ -1036,13 +1021,13 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname,
#ifdef CONFIG_COMPAT
static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
switch (level) {
case SOL_RAW:
break;
case SOL_ICMPV6:
- if (inet_sk(sk)->num != IPPROTO_ICMPV6)
+ if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
return -EOPNOTSUPP;
return rawv6_seticmpfilter(sk, level, optname, optval, optlen);
case SOL_IPV6:
@@ -1067,6 +1052,11 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
switch (optname) {
case IPV6_CHECKSUM:
+ /*
+ * We allow getsockopt() for IPPROTO_IPV6-level
+ * IPV6_CHECKSUM socket option on ICMPv6 sockets
+ * since RFC3542 is silent about it.
+ */
if (rp->checksum == 0)
val = -1;
else
@@ -1089,21 +1079,19 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
static int rawv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
- switch(level) {
- case SOL_RAW:
- break;
+ switch (level) {
+ case SOL_RAW:
+ break;
- case SOL_ICMPV6:
- if (inet_sk(sk)->num != IPPROTO_ICMPV6)
- return -EOPNOTSUPP;
- return rawv6_geticmpfilter(sk, level, optname, optval,
- optlen);
- case SOL_IPV6:
- if (optname == IPV6_CHECKSUM)
- break;
- default:
- return ipv6_getsockopt(sk, level, optname, optval,
- optlen);
+ case SOL_ICMPV6:
+ if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
+ return -EOPNOTSUPP;
+ return rawv6_geticmpfilter(sk, level, optname, optval, optlen);
+ case SOL_IPV6:
+ if (optname == IPV6_CHECKSUM)
+ break;
+ default:
+ return ipv6_getsockopt(sk, level, optname, optval, optlen);
}
return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
@@ -1117,7 +1105,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname,
case SOL_RAW:
break;
case SOL_ICMPV6:
- if (inet_sk(sk)->num != IPPROTO_ICMPV6)
+ if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
return -EOPNOTSUPP;
return rawv6_geticmpfilter(sk, level, optname, optval, optlen);
case SOL_IPV6:
@@ -1133,43 +1121,73 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname,
static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
- switch(cmd) {
- case SIOCOUTQ:
- {
- int amount = atomic_read(&sk->sk_wmem_alloc);
- return put_user(amount, (int __user *)arg);
- }
- case SIOCINQ:
- {
- struct sk_buff *skb;
- int amount = 0;
-
- spin_lock_bh(&sk->sk_receive_queue.lock);
- skb = skb_peek(&sk->sk_receive_queue);
- if (skb != NULL)
- amount = skb->tail - skb->transport_header;
- spin_unlock_bh(&sk->sk_receive_queue.lock);
- return put_user(amount, (int __user *)arg);
- }
+ switch (cmd) {
+ case SIOCOUTQ: {
+ int amount = sk_wmem_alloc_get(sk);
- default:
- return -ENOIOCTLCMD;
+ return put_user(amount, (int __user *)arg);
+ }
+ case SIOCINQ: {
+ struct sk_buff *skb;
+ int amount = 0;
+
+ spin_lock_bh(&sk->sk_receive_queue.lock);
+ skb = skb_peek(&sk->sk_receive_queue);
+ if (skb != NULL)
+ amount = skb_tail_pointer(skb) -
+ skb_transport_header(skb);
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ return put_user(amount, (int __user *)arg);
+ }
+
+ default:
+#ifdef CONFIG_IPV6_MROUTE
+ return ip6mr_ioctl(sk, cmd, (void __user *)arg);
+#else
+ return -ENOIOCTLCMD;
+#endif
}
}
-static void rawv6_close(struct sock *sk, long timeout)
+#ifdef CONFIG_COMPAT
+static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg)
{
- if (inet_sk(sk)->num == IPPROTO_RAW)
- ip6_ra_control(sk, -1, NULL);
+ switch (cmd) {
+ case SIOCOUTQ:
+ case SIOCINQ:
+ return -ENOIOCTLCMD;
+ default:
+#ifdef CONFIG_IPV6_MROUTE
+ return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg));
+#else
+ return -ENOIOCTLCMD;
+#endif
+ }
+}
+#endif
+static void rawv6_close(struct sock *sk, long timeout)
+{
+ if (inet_sk(sk)->inet_num == IPPROTO_RAW)
+ ip6_ra_control(sk, -1);
+ ip6mr_sk_done(sk);
sk_common_release(sk);
}
+static void raw6_destroy(struct sock *sk)
+{
+ lock_sock(sk);
+ ip6_flush_pending_frames(sk);
+ release_sock(sk);
+
+ inet6_destroy_sock(sk);
+}
+
static int rawv6_init_sk(struct sock *sk)
{
struct raw6_sock *rp = raw6_sk(sk);
- switch (inet_sk(sk)->num) {
+ switch (inet_sk(sk)->inet_num) {
case IPPROTO_ICMPV6:
rp->checksum = 1;
rp->offset = 2;
@@ -1181,75 +1199,46 @@ static int rawv6_init_sk(struct sock *sk)
default:
break;
}
- return(0);
+ return 0;
}
-DEFINE_PROTO_INUSE(rawv6)
-
struct proto rawv6_prot = {
.name = "RAWv6",
.owner = THIS_MODULE,
.close = rawv6_close,
- .connect = ip6_datagram_connect,
+ .destroy = raw6_destroy,
+ .connect = ip6_datagram_connect_v6_only,
.disconnect = udp_disconnect,
.ioctl = rawv6_ioctl,
.init = rawv6_init_sk,
- .destroy = inet6_destroy_sock,
.setsockopt = rawv6_setsockopt,
.getsockopt = rawv6_getsockopt,
.sendmsg = rawv6_sendmsg,
.recvmsg = rawv6_recvmsg,
.bind = rawv6_bind,
.backlog_rcv = rawv6_rcv_skb,
- .hash = raw_v6_hash,
- .unhash = raw_v6_unhash,
+ .hash = raw_hash_sk,
+ .unhash = raw_unhash_sk,
.obj_size = sizeof(struct raw6_sock),
+ .h.raw_hash = &raw_v6_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_rawv6_setsockopt,
.compat_getsockopt = compat_rawv6_getsockopt,
+ .compat_ioctl = compat_rawv6_ioctl,
#endif
- REF_PROTO_INUSE(rawv6)
};
#ifdef CONFIG_PROC_FS
-static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
-{
- struct ipv6_pinfo *np = inet6_sk(sp);
- struct in6_addr *dest, *src;
- __u16 destp, srcp;
-
- dest = &np->daddr;
- src = &np->rcv_saddr;
- destp = 0;
- srcp = inet_sk(sp)->num;
- seq_printf(seq,
- "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
- "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
- i,
- src->s6_addr32[0], src->s6_addr32[1],
- src->s6_addr32[2], src->s6_addr32[3], srcp,
- dest->s6_addr32[0], dest->s6_addr32[1],
- dest->s6_addr32[2], dest->s6_addr32[3], destp,
- sp->sk_state,
- atomic_read(&sp->sk_wmem_alloc),
- atomic_read(&sp->sk_rmem_alloc),
- 0, 0L, 0,
- sock_i_uid(sp), 0,
- sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
-}
-
static int raw6_seq_show(struct seq_file *seq, void *v)
{
- if (v == SEQ_START_TOKEN)
- seq_printf(seq,
- " sl "
- "local_address "
- "remote_address "
- "st tx_queue rx_queue tr tm->when retrnsmt"
- " uid timeout inode drops\n");
- else
- raw6_sock_seq_show(seq, v, raw_seq_private(seq)->bucket);
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
+ } else {
+ struct sock *sp = v;
+ __u16 srcp = inet_sk(sp)->inet_num;
+ ip6_dgram_sock_seq_show(seq, v, srcp, 0,
+ raw_seq_private(seq)->bucket);
+ }
return 0;
}
@@ -1273,17 +1262,17 @@ static const struct file_operations raw6_seq_fops = {
.release = seq_release_net,
};
-static int raw6_init_net(struct net *net)
+static int __net_init raw6_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "raw6", S_IRUGO, &raw6_seq_fops))
+ if (!proc_create("raw6", S_IRUGO, net->proc_net, &raw6_seq_fops))
return -ENOMEM;
return 0;
}
-static void raw6_exit_net(struct net *net)
+static void __net_exit raw6_exit_net(struct net *net)
{
- proc_net_remove(net, "raw6");
+ remove_proc_entry("raw6", net->proc_net);
}
static struct pernet_operations raw6_net_ops = {
@@ -1333,8 +1322,6 @@ static struct inet_protosw rawv6_protosw = {
.protocol = IPPROTO_IP, /* wild card */
.prot = &rawv6_prot,
.ops = &inet6_sockraw_ops,
- .capability = CAP_NET_RAW,
- .no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_REUSE,
};
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 01:56:56 +0000