summaryrefslogtreecommitdiff
path: root/net/ipv6/raw.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/raw.c')
-rw-r--r--net/ipv6/raw.c678
1 files changed, 326 insertions, 352 deletions
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index c45f7a5c36e9..b4cd05dba9b6 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* RAW sockets for IPv6
* Linux INET6 implementation
@@ -11,11 +12,6 @@
* Hideaki YOSHIFUJI : sin6_scope_id support
* YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance)
* Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#include <linux/errno.h>
@@ -32,7 +28,7 @@
#include <linux/netfilter_ipv6.h>
#include <linux/skbuff.h>
#include <linux/compat.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <net/net_namespace.h>
@@ -63,44 +59,32 @@
#include <linux/seq_file.h>
#include <linux/export.h>
-static struct raw_hashinfo raw_v6_hashinfo = {
- .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock),
-};
-
-static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
- unsigned short num, const struct in6_addr *loc_addr,
- const struct in6_addr *rmt_addr, int dif)
-{
- bool is_multicast = ipv6_addr_is_multicast(loc_addr);
-
- sk_for_each_from(sk)
- if (inet_sk(sk)->inet_num == num) {
- struct ipv6_pinfo *np = inet6_sk(sk);
+#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */
- if (!net_eq(sock_net(sk), net))
- continue;
+struct raw_hashinfo raw_v6_hashinfo;
+EXPORT_SYMBOL_GPL(raw_v6_hashinfo);
- if (!ipv6_addr_any(&np->daddr) &&
- !ipv6_addr_equal(&np->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))
- goto found;
- if (is_multicast &&
- inet6_mc_check(sk, loc_addr, rmt_addr))
- goto found;
- continue;
- }
- goto found;
- }
- sk = NULL;
-found:
- return sk;
+bool raw_v6_match(struct net *net, const struct sock *sk, unsigned short num,
+ const struct in6_addr *loc_addr,
+ const struct in6_addr *rmt_addr, int dif, int sdif)
+{
+ if (inet_sk(sk)->inet_num != num ||
+ !net_eq(sock_net(sk), net) ||
+ (!ipv6_addr_any(&sk->sk_v6_daddr) &&
+ !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
+ !raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif))
+ return false;
+
+ if (ipv6_addr_any(&sk->sk_v6_rcv_saddr) ||
+ ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr) ||
+ (ipv6_addr_is_multicast(loc_addr) &&
+ inet6_mc_check(sk, loc_addr, rmt_addr)))
+ return true;
+
+ return false;
}
+EXPORT_SYMBOL_GPL(raw_v6_match);
/*
* 0 - deliver
@@ -108,11 +92,14 @@ found:
*/
static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb)
{
- struct icmp6hdr *_hdr;
+ struct icmp6hdr _hdr;
const struct icmp6hdr *hdr;
+ /* 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),
- sizeof(_hdr), &_hdr);
+ ICMPV6_HDRLEN, &_hdr);
if (hdr) {
const __u32 *data = &raw6_sk(sk)->filter.data[0];
unsigned int type = hdr->icmp6_type;
@@ -153,29 +140,32 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister);
*/
static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
{
+ struct net *net = dev_net(skb->dev);
const struct in6_addr *saddr;
const struct in6_addr *daddr;
+ struct hlist_head *hlist;
struct sock *sk;
bool delivered = false;
__u8 hash;
- struct net *net;
saddr = &ipv6_hdr(skb)->saddr;
daddr = saddr + 1;
- hash = nexthdr & (RAW_HTABLE_SIZE - 1);
-
- read_lock(&raw_v6_hashinfo.lock);
- sk = sk_head(&raw_v6_hashinfo.ht[hash]);
-
- if (sk == NULL)
- goto out;
+ hash = raw_hashfunc(net, nexthdr);
+ hlist = &raw_v6_hashinfo.ht[hash];
+ rcu_read_lock();
+ sk_for_each_rcu(sk, hlist) {
+ int filtered;
- net = dev_net(skb->dev);
- sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif);
+ if (!raw_v6_match(net, sk, nexthdr, daddr, saddr,
+ inet6_iif(skb), inet6_sdif(skb)))
+ continue;
- while (sk) {
- int filtered;
+ if (atomic_read(&sk->sk_rmem_alloc) >=
+ READ_ONCE(sk->sk_rcvbuf)) {
+ sk_drops_inc(sk);
+ continue;
+ }
delivered = true;
switch (nexthdr) {
@@ -210,32 +200,22 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
/* Not releasing hash table! */
- if (clone) {
- nf_reset(clone);
+ if (clone)
rawv6_rcv(sk, clone);
- }
}
- sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr,
- IP6CB(skb)->iif);
}
-out:
- read_unlock(&raw_v6_hashinfo.lock);
+ rcu_read_unlock();
return delivered;
}
bool raw6_local_deliver(struct sk_buff *skb, int nexthdr)
{
- struct sock *raw_sk;
-
- raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]);
- if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
- raw_sk = NULL;
-
- return raw_sk != NULL;
+ return ipv6_raw_deliver(skb, nexthdr);
}
/* This cleans up af_inet6 a bit. -DaveM */
-static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int rawv6_bind(struct sock *sk, struct sockaddr_unsized *uaddr,
+ int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -246,6 +226,10 @@ 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 */
@@ -275,7 +259,9 @@ 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_unlock;
+ }
+ if (sk->sk_bound_dev_if) {
err = -ENODEV;
dev = dev_get_by_index_rcu(sock_net(sk),
sk->sk_bound_dev_if);
@@ -287,7 +273,8 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
* unspecified and mapped address have a v4 equivalent.
*/
v4addr = LOOPBACK4_IPV6;
- if (!(addr_type & IPV6_ADDR_MULTICAST)) {
+ if (!(addr_type & IPV6_ADDR_MULTICAST) &&
+ !ipv6_can_nonlocal_bind(sock_net(sk), inet)) {
err = -EADDRNOTAVAIL;
if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr,
dev, 0)) {
@@ -297,7 +284,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
}
inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
- np->rcv_saddr = addr->sin6_addr;
+ sk->sk_v6_rcv_saddr = addr->sin6_addr;
if (!(addr_type & IPV6_ADDR_MULTICAST))
np->saddr = addr->sin6_addr;
err = 0;
@@ -309,10 +296,9 @@ out:
}
static void rawv6_err(struct sock *sk, struct sk_buff *skb,
- struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, __be32 info)
+ u8 type, u8 code, int offset, __be32 info)
{
- struct inet_sock *inet = inet_sk(sk);
+ bool recverr = inet6_test_bit(RECVERR6, sk);
struct ipv6_pinfo *np = inet6_sk(sk);
int err;
int harderr;
@@ -322,71 +308,69 @@ static void rawv6_err(struct sock *sk, struct sk_buff *skb,
2. Socket is connected (otherwise the error indication
is useless without recverr and error is hard.
*/
- if (!np->recverr && sk->sk_state != TCP_ESTABLISHED)
+ if (!recverr && sk->sk_state != TCP_ESTABLISHED)
return;
harderr = icmpv6_err_convert(type, code, &err);
if (type == ICMPV6_PKT_TOOBIG) {
ip6_sk_update_pmtu(skb, sk, info);
- harderr = (np->pmtudisc == IPV6_PMTUDISC_DO);
+ harderr = (READ_ONCE(np->pmtudisc) == IPV6_PMTUDISC_DO);
}
- if (type == NDISC_REDIRECT)
+ if (type == NDISC_REDIRECT) {
ip6_sk_redirect(skb, sk);
- if (np->recverr) {
+ return;
+ }
+ if (recverr) {
u8 *payload = skb->data;
- if (!inet->hdrincl)
+ if (!inet_test_bit(HDRINCL, sk))
payload += offset;
ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload);
}
- if (np->recverr || harderr) {
+ if (recverr || harderr) {
sk->sk_err = err;
- sk->sk_error_report(sk);
+ sk_error_report(sk);
}
}
void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
u8 type, u8 code, int inner_offset, __be32 info)
{
+ struct net *net = dev_net(skb->dev);
+ struct hlist_head *hlist;
struct sock *sk;
int hash;
- const struct in6_addr *saddr, *daddr;
- struct net *net;
-
- hash = nexthdr & (RAW_HTABLE_SIZE - 1);
- read_lock(&raw_v6_hashinfo.lock);
- sk = sk_head(&raw_v6_hashinfo.ht[hash]);
- if (sk != NULL) {
+ hash = raw_hashfunc(net, nexthdr);
+ hlist = &raw_v6_hashinfo.ht[hash];
+ rcu_read_lock();
+ sk_for_each_rcu(sk, hlist) {
/* 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))) {
- rawv6_err(sk, skb, NULL, type, code,
- inner_offset, info);
- sk = sk_next(sk);
- }
+
+ if (!raw_v6_match(net, sk, nexthdr, &ip6h->saddr, &ip6h->daddr,
+ inet6_iif(skb), inet6_iif(skb)))
+ continue;
+ rawv6_err(sk, skb, type, code, inner_offset, info);
}
- read_unlock(&raw_v6_hashinfo.lock);
+ rcu_read_unlock();
}
static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
+ enum skb_drop_reason reason;
+
if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) &&
skb_checksum_complete(skb)) {
- atomic_inc(&sk->sk_drops);
- kfree_skb(skb);
+ sk_drops_inc(sk);
+ sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM);
return NET_RX_DROP;
}
/* Charge it to the socket. */
skb_dst_drop(skb);
- if (sock_queue_rcv_skb(sk, skb) < 0) {
- kfree_skb(skb);
+ if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) {
+ sk_skb_reason_drop(sk, skb, reason);
return NET_RX_DROP;
}
@@ -406,10 +390,11 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
struct raw6_sock *rp = raw6_sk(sk);
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
- atomic_inc(&sk->sk_drops);
- kfree_skb(skb);
+ sk_drops_inc(sk);
+ sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_XFRM_POLICY);
return NET_RX_DROP;
}
+ nf_reset_ct(skb);
if (!rp->checksum)
skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -428,10 +413,10 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
skb->len,
inet->inet_num, 0));
- if (inet->hdrincl) {
+ if (inet_test_bit(HDRINCL, sk)) {
if (skb_checksum_complete(skb)) {
- atomic_inc(&sk->sk_drops);
- kfree_skb(skb);
+ sk_drops_inc(sk);
+ sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_SKB_CSUM);
return NET_RX_DROP;
}
}
@@ -446,12 +431,11 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
* we return it, otherwise we block.
*/
-static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
- struct msghdr *msg, size_t len,
- int noblock, int flags, int *addr_len)
+static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ 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;
@@ -459,16 +443,13 @@ 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);
+ if (np->rxopt.bits.rxpmtu && READ_ONCE(np->rxpmtu))
+ return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
- skb = skb_recv_datagram(sk, flags, noblock, &err);
+ skb = skb_recv_datagram(sk, flags, &err);
if (!skb)
goto out;
@@ -479,13 +460,13 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
}
if (skb_csum_unnecessary(skb)) {
- err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ err = skb_copy_datagram_msg(skb, 0, msg, copied);
} else if (msg->msg_flags&MSG_TRUNC) {
if (__skb_checksum_complete(skb))
goto csum_copy_err;
- err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ err = skb_copy_datagram_msg(skb, 0, msg, copied);
} else {
- err = skb_copy_and_csum_datagram_iovec(skb, 0, msg->msg_iov);
+ err = skb_copy_and_csum_datagram_msg(skb, 0, msg);
if (err == -EINVAL)
goto csum_copy_err;
}
@@ -499,10 +480,11 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
sin6->sin6_addr = ipv6_hdr(skb)->saddr;
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
- IP6CB(skb)->iif);
+ inet6_iif(skb));
+ *addr_len = sizeof(*sin6);
}
- sock_recv_ts_and_drops(msg, sk, skb);
+ sock_recv_cmsgs(msg, sk, skb);
if (np->rxopt.all)
ip6_datagram_recv_ctl(sk, msg, skb);
@@ -529,6 +511,7 @@ csum_copy_err:
static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
struct raw6_sock *rp)
{
+ struct ipv6_txoptions *opt;
struct sk_buff *skb;
int err = 0;
int offset;
@@ -540,11 +523,15 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
if (!rp->checksum)
goto send;
- if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
+ skb = skb_peek(&sk->sk_write_queue);
+ if (!skb)
goto out;
offset = rp->offset;
total_len = inet_sk(sk)->cork.base.length;
+ opt = inet6_sk(sk)->cork.opt;
+ total_len -= opt ? opt->opt_flen : 0;
+
if (offset >= total_len - 1) {
err = -EINVAL;
ip6_flush_pending_frames(sk);
@@ -580,8 +567,11 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
}
offset += skb_transport_offset(skb);
- if (skb_copy_bits(skb, offset, &csum, 2))
- BUG();
+ err = skb_copy_bits(skb, offset, &csum, 2);
+ if (err < 0) {
+ ip6_flush_pending_frames(sk);
+ goto out;
+ }
/* in case cksum was not initialized */
if (unlikely(csum))
@@ -593,8 +583,7 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP)
csum = CSUM_MANGLED_0;
- if (skb_store_bits(skb, offset, &csum, 2))
- BUG();
+ BUG_ON(skb_store_bits(skb, offset, &csum, 2));
send:
err = ip6_push_pending_frames(sk);
@@ -602,15 +591,15 @@ out:
return err;
}
-static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
+static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
struct flowi6 *fl6, struct dst_entry **dstp,
- unsigned int flags)
+ unsigned int flags, const struct sockcm_cookie *sockc)
{
- struct ipv6_pinfo *np = inet6_sk(sk);
+ struct net *net = sock_net(sk);
struct ipv6hdr *iph;
struct sk_buff *skb;
int err;
- struct rt6_info *rt = (struct rt6_info *)*dstp;
+ struct rt6_info *rt = dst_rt6_info(*dstp);
int hlen = LL_RESERVED_SPACE(rt->dst.dev);
int tlen = rt->dst.dev->needed_tailroom;
@@ -618,20 +607,22 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
return -EMSGSIZE;
}
+ if (length < sizeof(struct ipv6hdr))
+ return -EINVAL;
if (flags&MSG_PROBE)
goto out;
skb = sock_alloc_send_skb(sk,
length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
- if (skb == NULL)
+ if (!skb)
goto error;
skb_reserve(skb, hlen);
- skb->priority = sk->sk_priority;
- skb->mark = sk->sk_mark;
- skb_dst_set(skb, &rt->dst);
- *dstp = NULL;
+ skb->protocol = htons(ETH_P_IPV6);
+ skb->priority = sockc->priority;
+ skb->mark = sockc->mark;
+ skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
skb_put(skb, length);
skb_reset_network_header(skb);
@@ -639,97 +630,119 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
skb->ip_summed = CHECKSUM_NONE;
+ skb_setup_tx_timestamp(skb, sockc);
+
+ if (flags & MSG_CONFIRM)
+ skb_set_dst_pending_confirm(skb, 1);
+
skb->transport_header = skb->network_header;
- err = memcpy_fromiovecend((void *)iph, from, 0, length);
- if (err)
- goto error_fault;
+ err = memcpy_from_msg(iph, msg, length);
+ if (err) {
+ err = -EFAULT;
+ kfree_skb(skb);
+ goto error;
+ }
- 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);
+ skb_dst_set(skb, &rt->dst);
+ *dstp = NULL;
+
+ /* if egress device is enslaved to an L3 master device pass the
+ * skb to its handler for processing
+ */
+ skb = l3mdev_ip6_out(sk, skb);
+ if (unlikely(!skb))
+ return 0;
+
+ /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev
+ * in the error path. Since skb has been freed, the dst could
+ * have been queued for deletion.
+ */
+ rcu_read_lock();
+ IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
+ err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
+ NULL, rt->dst.dev, dst_output);
if (err > 0)
err = net_xmit_errno(err);
- if (err)
- goto error;
+ if (err) {
+ IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
+ rcu_read_unlock();
+ goto error_check;
+ }
+ rcu_read_unlock();
out:
return 0;
-error_fault:
- err = -EFAULT;
- kfree_skb(skb);
error:
- IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
- if (err == -ENOBUFS && !np->recverr)
+ IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
+error_check:
+ if (err == -ENOBUFS && !inet6_test_bit(RECVERR6, sk))
err = 0;
return err;
}
-static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg)
+struct raw6_frag_vec {
+ struct msghdr *msg;
+ int hlen;
+ char c[4];
+};
+
+static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6)
{
- struct iovec *iov;
- u8 __user *type = NULL;
- u8 __user *code = NULL;
- u8 len = 0;
- int probed = 0;
- int i;
-
- if (!msg->msg_iov)
- return 0;
+ int err = 0;
+ switch (fl6->flowi6_proto) {
+ case IPPROTO_ICMPV6:
+ rfv->hlen = 2;
+ err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen);
+ if (!err) {
+ fl6->fl6_icmp_type = rfv->c[0];
+ fl6->fl6_icmp_code = rfv->c[1];
+ }
+ break;
+ case IPPROTO_MH:
+ rfv->hlen = 4;
+ err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen);
+ if (!err)
+ fl6->fl6_mh_type = rfv->c[2];
+ }
+ return err;
+}
- for (i = 0; i < msg->msg_iovlen; i++) {
- iov = &msg->msg_iov[i];
- if (!iov)
- continue;
+static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
+ struct sk_buff *skb)
+{
+ struct raw6_frag_vec *rfv = from;
- switch (fl6->flowi6_proto) {
- case IPPROTO_ICMPV6:
- /* check if one-byte field is readable or not. */
- if (iov->iov_base && iov->iov_len < 1)
- break;
-
- if (!type) {
- type = iov->iov_base;
- /* check if code field is readable or not. */
- if (iov->iov_len > 1)
- code = type + 1;
- } else if (!code)
- code = iov->iov_base;
-
- if (type && code) {
- if (get_user(fl6->fl6_icmp_type, type) ||
- get_user(fl6->fl6_icmp_code, code))
- return -EFAULT;
- probed = 1;
- }
- break;
- case IPPROTO_MH:
- if (iov->iov_base && iov->iov_len < 1)
- break;
- /* check if type field is readable or not. */
- if (iov->iov_len > 2 - len) {
- u8 __user *p = iov->iov_base;
- if (get_user(fl6->fl6_mh_type, &p[2 - len]))
- return -EFAULT;
- probed = 1;
- } else
- len += iov->iov_len;
+ if (offset < rfv->hlen) {
+ int copy = min(rfv->hlen - offset, len);
- break;
- default:
- probed = 1;
- break;
- }
- if (probed)
- break;
+ if (skb->ip_summed == CHECKSUM_PARTIAL)
+ memcpy(to, rfv->c + offset, copy);
+ else
+ skb->csum = csum_block_add(
+ skb->csum,
+ csum_partial_copy_nocheck(rfv->c + offset,
+ to, copy),
+ odd);
+
+ odd = 0;
+ offset += copy;
+ to += copy;
+ len -= copy;
+
+ if (!len)
+ return 0;
}
- return 0;
+
+ offset -= rfv->hlen;
+
+ return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb);
}
-static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
- struct msghdr *msg, size_t len)
+static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
+ struct ipv6_txoptions *opt_to_free = NULL;
struct ipv6_txoptions opt_space;
- struct sockaddr_in6 * sin6 = (struct sockaddr_in6 *) msg->msg_name;
+ 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);
@@ -737,11 +750,11 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
struct ipv6_txoptions *opt = NULL;
struct ip6_flowlabel *flowlabel = NULL;
struct dst_entry *dst = NULL;
+ struct raw6_frag_vec rfv;
struct flowi6 fl6;
+ struct ipcm6_cookie ipc6;
int addr_len = msg->msg_namelen;
- int hlimit = -1;
- int tclass = -1;
- int dontfrag = -1;
+ int hdrincl;
u16 proto;
int err;
@@ -755,12 +768,17 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
+ hdrincl = inet_test_bit(HDRINCL, sk);
+
+ ipcm6_init_sk(&ipc6, sk);
+
/*
* Get and verify the address.
*/
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_mark = sk->sk_mark;
+ fl6.flowi6_mark = ipc6.sockc.mark;
+ fl6.flowi6_uid = sk_uid(sk);
if (sin6) {
if (addr_len < SIN6_LEN_RFC2133)
@@ -774,20 +792,20 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (!proto)
proto = inet->inet_num;
- else if (proto != inet->inet_num)
+ else if (proto != inet->inet_num &&
+ inet->inet_num != IPPROTO_RAW)
return -EINVAL;
if (proto > 255)
return -EINVAL;
daddr = &sin6->sin6_addr;
- if (np->sndflow) {
+ if (inet6_test_bit(SNDFLOW, sk)) {
fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (flowlabel == NULL)
+ if (IS_ERR(flowlabel))
return -EINVAL;
- daddr = &flowlabel->dst;
}
}
@@ -796,8 +814,8 @@ 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 &&
@@ -808,7 +826,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
return -EDESTADDRREQ;
proto = inet->inet_num;
- daddr = &np->daddr;
+ daddr = &sk->sk_v6_daddr;
fl6.flowlabel = np->flow_label;
}
@@ -819,31 +837,39 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
opt = &opt_space;
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(struct ipv6_txoptions);
+ ipc6.opt = opt;
- err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, opt,
- &hlimit, &tclass, &dontfrag);
+ err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
}
if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
- if (flowlabel == NULL)
+ if (IS_ERR(flowlabel))
return -EINVAL;
}
if (!(opt->opt_nflen|opt->opt_flen))
opt = NULL;
}
- if (opt == NULL)
- opt = np->opt;
+ if (!opt) {
+ opt = txopt_get(np);
+ opt_to_free = opt;
+ }
if (flowlabel)
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
fl6.flowi6_proto = proto;
- err = rawv6_probe_proto_opt(&fl6, msg);
- if (err)
- goto out;
+ fl6.flowi6_mark = ipc6.sockc.mark;
+
+ if (!hdrincl) {
+ rfv.msg = msg;
+ rfv.hlen = 0;
+ err = rawv6_probe_proto_opt(&rfv, &fl6);
+ if (err)
+ goto out;
+ }
if (!ipv6_addr_any(daddr))
fl6.daddr = *daddr;
@@ -855,42 +881,37 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
final_p = fl6_update_dst(&fl6, opt, &final);
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
- fl6.flowi6_oif = np->mcast_oif;
+ fl6.flowi6_oif = READ_ONCE(np->mcast_oif);
else if (!fl6.flowi6_oif)
- fl6.flowi6_oif = np->ucast_oif;
- security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+ fl6.flowi6_oif = READ_ONCE(np->ucast_oif);
+ security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
- dst = ip6_dst_lookup_flow(sk, &fl6, final_p, true);
+ if (hdrincl)
+ fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
+
+ fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
+
+ dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto out;
}
- if (hlimit < 0) {
- if (ipv6_addr_is_multicast(&fl6.daddr))
- hlimit = np->mcast_hops;
- else
- hlimit = np->hop_limit;
- if (hlimit < 0)
- hlimit = ip6_dst_hoplimit(dst);
- }
-
- if (tclass < 0)
- tclass = np->tclass;
-
- if (dontfrag < 0)
- dontfrag = np->dontfrag;
+ if (ipc6.hlimit < 0)
+ ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
- if (inet->hdrincl)
- err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags);
+ if (hdrincl)
+ err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
+ msg->msg_flags, &ipc6.sockc);
else {
+ ipc6.opt = opt;
lock_sock(sk);
- err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
- len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info*)dst,
- msg->msg_flags, dontfrag);
+ err = ip6_append_data(sk, raw6_getfrag, &rfv,
+ len, 0, &ipc6, &fl6, dst_rt6_info(dst),
+ msg->msg_flags);
if (err)
ip6_flush_pending_frames(sk);
@@ -902,23 +923,25 @@ done:
dst_release(dst);
out:
fl6_sock_release(flowlabel);
- return err<0?err:len;
+ txopt_put(opt_to_free);
+ return err < 0 ? err : len;
do_confirm:
- dst_confirm(dst);
+ if (msg->msg_flags & MSG_PROBE)
+ dst_confirm_neigh(dst, &fl6.daddr);
if (!(msg->msg_flags & MSG_PROBE) || len)
goto back_from_confirm;
err = 0;
goto done;
}
-static int rawv6_seticmpfilter(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+static int rawv6_seticmpfilter(struct sock *sk, int optname,
+ sockptr_t optval, int optlen)
{
switch (optname) {
case ICMPV6_FILTER:
if (optlen > sizeof(struct icmp6_filter))
optlen = sizeof(struct icmp6_filter);
- if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen))
+ if (copy_from_sockptr(&raw6_sk(sk)->filter, optval, optlen))
return -EFAULT;
return 0;
default:
@@ -928,7 +951,7 @@ static int rawv6_seticmpfilter(struct sock *sk, int level, int optname,
return 0;
}
-static int rawv6_geticmpfilter(struct sock *sk, int level, int optname,
+static int rawv6_geticmpfilter(struct sock *sk, int optname,
char __user *optval, int __user *optlen)
{
int len;
@@ -955,15 +978,23 @@ 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, unsigned int optlen)
+ sockptr_t optval, unsigned int optlen)
{
struct raw6_sock *rp = raw6_sk(sk);
int val;
- if (get_user(val, (int __user *)optval))
+ if (optlen < sizeof(val))
+ return -EINVAL;
+
+ if (copy_from_sockptr(&val, optval, sizeof(val)))
return -EFAULT;
switch (optname) {
+ case IPV6_HDRINCL:
+ if (sk->sk_type != SOCK_RAW)
+ return -EINVAL;
+ inet_assign_bit(HDRINCL, sk, val);
+ return 0;
case IPV6_CHECKSUM:
if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 &&
level == IPPROTO_IPV6) {
@@ -997,7 +1028,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
}
static int rawv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
+ sockptr_t optval, unsigned int optlen)
{
switch (level) {
case SOL_RAW:
@@ -1006,10 +1037,12 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname,
case SOL_ICMPV6:
if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
return -EOPNOTSUPP;
- return rawv6_seticmpfilter(sk, level, optname, optval, optlen);
+ return rawv6_seticmpfilter(sk, optname, optval, optlen);
case SOL_IPV6:
- if (optname == IPV6_CHECKSUM)
+ if (optname == IPV6_CHECKSUM ||
+ optname == IPV6_HDRINCL)
break;
+ fallthrough;
default:
return ipv6_setsockopt(sk, level, optname, optval, optlen);
}
@@ -1017,38 +1050,19 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname,
return do_rawv6_setsockopt(sk, level, optname, optval, optlen);
}
-#ifdef CONFIG_COMPAT
-static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- switch (level) {
- case SOL_RAW:
- break;
- 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 compat_ipv6_setsockopt(sk, level, optname,
- optval, optlen);
- }
- return do_rawv6_setsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct raw6_sock *rp = raw6_sk(sk);
int val, len;
- if (get_user(len,optlen))
+ if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
+ case IPV6_HDRINCL:
+ val = inet_test_bit(HDRINCL, sk);
+ break;
case IPV6_CHECKSUM:
/*
* We allow getsockopt() for IPPROTO_IPV6-level
@@ -1069,7 +1083,7 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname,
if (put_user(len, optlen))
return -EFAULT;
- if (copy_to_user(optval,&val,len))
+ if (copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
@@ -1084,10 +1098,12 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname,
case SOL_ICMPV6:
if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
return -EOPNOTSUPP;
- return rawv6_geticmpfilter(sk, level, optname, optval, optlen);
+ return rawv6_geticmpfilter(sk, optname, optval, optlen);
case SOL_IPV6:
- if (optname == IPV6_CHECKSUM)
+ if (optname == IPV6_CHECKSUM ||
+ optname == IPV6_HDRINCL)
break;
+ fallthrough;
default:
return ipv6_getsockopt(sk, level, optname, optval, optlen);
}
@@ -1095,52 +1111,29 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname,
return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
}
-#ifdef CONFIG_COMPAT
-static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- switch (level) {
- case SOL_RAW:
- break;
- 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 compat_ipv6_getsockopt(sk, level, optname,
- optval, optlen);
- }
- return do_rawv6_getsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
-static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg)
+static int rawv6_ioctl(struct sock *sk, int cmd, int *karg)
{
switch (cmd) {
case SIOCOUTQ: {
- int amount = sk_wmem_alloc_get(sk);
-
- return put_user(amount, (int __user *)arg);
+ *karg = sk_wmem_alloc_get(sk);
+ return 0;
}
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);
+ if (skb)
+ *karg = skb->len;
+ else
+ *karg = 0;
spin_unlock_bh(&sk->sk_receive_queue.lock);
- return put_user(amount, (int __user *)arg);
+ return 0;
}
default:
#ifdef CONFIG_IPV6_MROUTE
- return ip6mr_ioctl(sk, cmd, (void __user *)arg);
+ return ip6mr_ioctl(sk, cmd, karg);
#else
return -ENOIOCTLCMD;
#endif
@@ -1177,14 +1170,13 @@ 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);
+ sk->sk_drop_counters = &rp->drop_counters;
switch (inet_sk(sk)->inet_num) {
case IPPROTO_ICMPV6:
rp->checksum = 1;
@@ -1205,8 +1197,8 @@ struct proto rawv6_prot = {
.owner = THIS_MODULE,
.close = rawv6_close,
.destroy = raw6_destroy,
- .connect = ip6_datagram_connect,
- .disconnect = udp_disconnect,
+ .connect = ip6_datagram_connect_v6_only,
+ .disconnect = __udp_disconnect,
.ioctl = rawv6_ioctl,
.init = rawv6_init_sk,
.setsockopt = rawv6_setsockopt,
@@ -1218,12 +1210,14 @@ struct proto rawv6_prot = {
.hash = raw_hash_sk,
.unhash = raw_unhash_sk,
.obj_size = sizeof(struct raw6_sock),
+ .ipv6_pinfo_offset = offsetof(struct raw6_sock, inet6),
+ .useroffset = offsetof(struct raw6_sock, filter),
+ .usersize = sizeof_field(struct raw6_sock, filter),
.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
+ .diag_destroy = raw_abort,
};
#ifdef CONFIG_PROC_FS
@@ -1247,22 +1241,10 @@ static const struct seq_operations raw6_seq_ops = {
.show = raw6_seq_show,
};
-static int raw6_seq_open(struct inode *inode, struct file *file)
-{
- return raw_seq_open(inode, file, &raw_v6_hashinfo, &raw6_seq_ops);
-}
-
-static const struct file_operations raw6_seq_fops = {
- .owner = THIS_MODULE,
- .open = raw6_seq_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
static int __net_init raw6_init_net(struct net *net)
{
- if (!proc_create("raw6", S_IRUGO, net->proc_net, &raw6_seq_fops))
+ if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops,
+ sizeof(struct raw_iter_state), &raw_v6_hashinfo))
return -ENOMEM;
return 0;
@@ -1290,7 +1272,7 @@ void raw6_proc_exit(void)
#endif /* CONFIG_PROC_FS */
/* Same as inet6_dgram_ops, sans udp_poll. */
-static const struct proto_ops inet6_sockraw_ops = {
+const struct proto_ops inet6_sockraw_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
.release = inet6_release,
@@ -1301,6 +1283,7 @@ static const struct proto_ops inet6_sockraw_ops = {
.getname = inet6_getname,
.poll = datagram_poll, /* ok */
.ioctl = inet6_ioctl, /* must change */
+ .gettstamp = sock_gettstamp,
.listen = sock_no_listen, /* ok */
.shutdown = inet_shutdown, /* ok */
.setsockopt = sock_common_setsockopt, /* ok */
@@ -1308,10 +1291,8 @@ static const struct proto_ops inet6_sockraw_ops = {
.sendmsg = inet_sendmsg, /* ok */
.recvmsg = sock_common_recvmsg, /* ok */
.mmap = sock_no_mmap,
- .sendpage = sock_no_sendpage,
#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_sock_common_setsockopt,
- .compat_getsockopt = compat_sock_common_getsockopt,
+ .compat_ioctl = inet6_compat_ioctl,
#endif
};
@@ -1320,19 +1301,12 @@ static struct inet_protosw rawv6_protosw = {
.protocol = IPPROTO_IP, /* wild card */
.prot = &rawv6_prot,
.ops = &inet6_sockraw_ops,
- .no_check = UDP_CSUM_DEFAULT,
.flags = INET_PROTOSW_REUSE,
};
int __init rawv6_init(void)
{
- int ret;
-
- ret = inet6_register_protosw(&rawv6_protosw);
- if (ret)
- goto out;
-out:
- return ret;
+ return inet6_register_protosw(&rawv6_protosw);
}
void rawv6_exit(void)
generated by cgit (git 2.34.1) at 2025-12-21 21:11:34 +0000