aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/raw.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/raw.c')
-rw-r--r--net/ipv4/raw.c238
1 files changed, 141 insertions, 97 deletions
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index a3d5ab786e8..2c65160565e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -38,7 +38,7 @@
*/
#include <linux/types.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
#include <asm/byteorder.h>
#include <asm/current.h>
#include <asm/uaccess.h>
@@ -48,6 +48,7 @@
#include <linux/errno.h>
#include <linux/aio.h>
#include <linux/kernel.h>
+#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/sockios.h>
#include <linux/socket.h>
@@ -76,6 +77,7 @@
#include <linux/seq_file.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
+#include <linux/compat.h>
static struct raw_hashinfo raw_v4_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
@@ -109,9 +111,7 @@ EXPORT_SYMBOL_GPL(raw_unhash_sk);
static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
unsigned short num, __be32 raddr, __be32 laddr, int dif)
{
- struct hlist_node *node;
-
- sk_for_each_from(sk, node) {
+ sk_for_each_from(sk) {
struct inet_sock *inet = inet_sk(sk);
if (net_eq(sock_net(sk), net) && inet->inet_num == num &&
@@ -129,18 +129,20 @@ found:
* 0 - deliver
* 1 - block
*/
-static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb)
+static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
{
- int type;
+ struct icmphdr _hdr;
+ const struct icmphdr *hdr;
- if (!pskb_may_pull(skb, sizeof(struct icmphdr)))
+ hdr = skb_header_pointer(skb, skb_transport_offset(skb),
+ sizeof(_hdr), &_hdr);
+ if (!hdr)
return 1;
- type = icmp_hdr(skb)->type;
- if (type < 32) {
+ if (hdr->type < 32) {
__u32 data = raw_sk(sk)->filter.data;
- return ((1 << type) & data) != 0;
+ return ((1U << hdr->type) & data) != 0;
}
/* Do not block unknown ICMP types */
@@ -153,7 +155,7 @@ static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb)
* RFC 1122: SHOULD pass TOS value up to the transport layer.
* -> It does. And not only TOS, but all IP header.
*/
-static int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
+static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
{
struct sock *sk;
struct hlist_head *head;
@@ -214,6 +216,13 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
int err = 0;
int harderr = 0;
+ if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
+ ipv4_sk_update_pmtu(skb, sk, info);
+ else if (type == ICMP_REDIRECT) {
+ ipv4_sk_redirect(skb, sk);
+ return;
+ }
+
/* Report error on raw socket, if:
1. User requested ip_recverr.
2. Socket is connected (otherwise the error indication
@@ -246,7 +255,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
}
if (inet->recverr) {
- struct iphdr *iph = (struct iphdr *)skb->data;
+ const struct iphdr *iph = (const struct iphdr *)skb->data;
u8 *payload = skb->data + (iph->ihl << 2);
if (inet->hdrincl)
@@ -264,7 +273,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
{
int hash;
struct sock *raw_sk;
- struct iphdr *iph;
+ const struct iphdr *iph;
struct net *net;
hash = protocol & (RAW_HTABLE_SIZE - 1);
@@ -272,7 +281,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
read_lock(&raw_v4_hashinfo.lock);
raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
if (raw_sk != NULL) {
- iph = (struct iphdr *)skb->data;
+ iph = (const struct iphdr *)skb->data;
net = dev_net(skb->dev);
while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
@@ -280,17 +289,18 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
skb->dev->ifindex)) != NULL) {
raw_err(raw_sk, skb, info);
raw_sk = sk_next(raw_sk);
- iph = (struct iphdr *)skb->data;
+ iph = (const struct iphdr *)skb->data;
}
}
read_unlock(&raw_v4_hashinfo.lock);
}
-static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
+static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
/* Charge it to the socket. */
- if (ip_queue_rcv_skb(sk, skb) < 0) {
+ ipv4_pktinfo_prepare(sk, skb);
+ if (sock_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
@@ -313,9 +323,10 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb)
return 0;
}
-static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
- struct rtable **rtp,
- unsigned int flags)
+static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
+ void *from, size_t length,
+ struct rtable **rtp,
+ unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct net *net = sock_net(sk);
@@ -324,21 +335,24 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
unsigned int iphlen;
int err;
struct rtable *rt = *rtp;
+ int hlen, tlen;
if (length > rt->dst.dev->mtu) {
- ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport,
+ ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
rt->dst.dev->mtu);
return -EMSGSIZE;
}
if (flags&MSG_PROBE)
goto out;
+ hlen = LL_RESERVED_SPACE(rt->dst.dev);
+ tlen = rt->dst.dev->needed_tailroom;
skb = sock_alloc_send_skb(sk,
- length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15,
+ length + hlen + tlen + 15,
flags & MSG_DONTWAIT, &err);
if (skb == NULL)
goto error;
- skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev));
+ skb_reserve(skb, hlen);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
@@ -371,11 +385,11 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
if (iphlen >= sizeof(*iph)) {
if (!iph->saddr)
- iph->saddr = rt->rt_src;
+ iph->saddr = fl4->saddr;
iph->check = 0;
iph->tot_len = htons(length);
if (!iph->id)
- ip_select_ident(iph, &rt->dst, NULL);
+ ip_select_ident(skb, NULL);
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}
@@ -401,7 +415,7 @@ error:
return err;
}
-static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
+static int raw_probe_proto_opt(struct flowi4 *fl4, struct msghdr *msg)
{
struct iovec *iov;
u8 __user *type = NULL;
@@ -417,7 +431,7 @@ static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
if (!iov)
continue;
- switch (fl->proto) {
+ switch (fl4->flowi4_proto) {
case IPPROTO_ICMP:
/* check if one-byte field is readable or not. */
if (iov->iov_base && iov->iov_len < 1)
@@ -432,8 +446,8 @@ static int raw_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(fl4->fl4_icmp_type, type) ||
+ get_user(fl4->fl4_icmp_code, code))
return -EFAULT;
probed = 1;
}
@@ -454,11 +468,13 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
struct inet_sock *inet = inet_sk(sk);
struct ipcm_cookie ipc;
struct rtable *rt = NULL;
+ struct flowi4 fl4;
int free = 0;
__be32 daddr;
__be32 saddr;
u8 tos;
int err;
+ struct ip_options_data opt_copy;
err = -EMSGSIZE;
if (len > 0xFFFF)
@@ -477,16 +493,13 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
*/
if (msg->msg_namelen) {
- struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
+ DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
err = -EINVAL;
if (msg->msg_namelen < sizeof(*usin))
goto out;
if (usin->sin_family != AF_INET) {
- static int complained;
- if (!complained++)
- printk(KERN_INFO "%s forgot to set AF_INET in "
- "raw sendmsg. Fix it!\n",
- current->comm);
+ pr_info_once("%s: %s forgot to set AF_INET. Fix it!\n",
+ __func__, current->comm);
err = -EAFNOSUPPORT;
if (usin->sin_family)
goto out;
@@ -506,10 +519,12 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
ipc.tx_flags = 0;
+ ipc.ttl = 0;
+ ipc.tos = -1;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
- err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+ err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
if (err)
goto out;
if (ipc.opt)
@@ -519,8 +534,18 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
saddr = ipc.addr;
ipc.addr = daddr;
- if (!ipc.opt)
- ipc.opt = inet->opt;
+ if (!ipc.opt) {
+ struct ip_options_rcu *inet_opt;
+
+ rcu_read_lock();
+ inet_opt = rcu_dereference(inet->inet_opt);
+ if (inet_opt) {
+ memcpy(&opt_copy, inet_opt,
+ sizeof(*inet_opt) + inet_opt->opt.optlen);
+ ipc.opt = &opt_copy.opt;
+ }
+ rcu_read_unlock();
+ }
if (ipc.opt) {
err = -EINVAL;
@@ -529,13 +554,13 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
*/
if (inet->hdrincl)
goto done;
- if (ipc.opt->srr) {
+ if (ipc.opt->opt.srr) {
if (!daddr)
goto done;
- daddr = ipc.opt->faddr;
+ daddr = ipc.opt->opt.faddr;
}
}
- tos = RT_CONN_FLAGS(sk);
+ tos = get_rtconn_flags(&ipc, sk);
if (msg->msg_flags & MSG_DONTROUTE)
tos |= RTO_ONLINK;
@@ -544,28 +569,29 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
+ } else if (!ipc.oif)
+ ipc.oif = inet->uc_index;
+
+ flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
+ RT_SCOPE_UNIVERSE,
+ inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ inet_sk_flowi_flags(sk) |
+ (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+ daddr, saddr, 0, 0);
+
+ if (!inet->hdrincl) {
+ err = raw_probe_proto_opt(&fl4, msg);
+ if (err)
+ goto done;
}
- {
- struct flowi fl = { .oif = ipc.oif,
- .mark = sk->sk_mark,
- .fl4_dst = daddr,
- .fl4_src = saddr,
- .fl4_tos = tos,
- .proto = inet->hdrincl ? IPPROTO_RAW :
- sk->sk_protocol,
- };
- if (!inet->hdrincl) {
- err = raw_probe_proto_opt(&fl, msg);
- if (err)
- goto done;
- }
-
- security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 1);
- }
- if (err)
+ security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+ rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ rt = NULL;
goto done;
+ }
err = -EACCES;
if (rt->rt_flags & RTCF_BROADCAST && !sock_flag(sk, SOCK_BROADCAST))
@@ -576,19 +602,20 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
back_from_confirm:
if (inet->hdrincl)
- err = raw_send_hdrinc(sk, msg->msg_iov, len,
- &rt, msg->msg_flags);
+ err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len,
+ &rt, msg->msg_flags);
else {
if (!ipc.addr)
- ipc.addr = rt->rt_dst;
+ ipc.addr = fl4.daddr;
lock_sock(sk);
- err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0,
- &ipc, &rt, msg->msg_flags);
+ err = ip_append_data(sk, &fl4, ip_generic_getfrag,
+ msg->msg_iov, len, 0,
+ &ipc, &rt, msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else if (!(msg->msg_flags & MSG_MORE)) {
- err = ip_push_pending_frames(sk);
+ err = ip_push_pending_frames(sk, &fl4);
if (err == -ENOBUFS && !inet->recverr)
err = 0;
}
@@ -615,7 +642,7 @@ do_confirm:
static void raw_close(struct sock *sk, long timeout)
{
/*
- * Raw sockets may have direct kernel refereneces. Kill them.
+ * Raw sockets may have direct kernel references. Kill them.
*/
ip_ra_control(sk, 0, NULL);
@@ -663,17 +690,14 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
struct inet_sock *inet = inet_sk(sk);
size_t copied = 0;
int err = -EOPNOTSUPP;
- struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+ DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
struct sk_buff *skb;
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
-
if (flags & MSG_ERRQUEUE) {
- err = ip_recv_error(sk, msg, len);
+ err = ip_recv_error(sk, msg, len, addr_len);
goto out;
}
@@ -699,6 +723,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
sin->sin_port = 0;
memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ *addr_len = sizeof(*sin);
}
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
@@ -812,31 +837,48 @@ static int compat_raw_getsockopt(struct sock *sk, int level, int optname,
static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
switch (cmd) {
- case SIOCOUTQ: {
- int amount = sk_wmem_alloc_get(sk);
+ case SIOCOUTQ: {
+ int amount = sk_wmem_alloc_get(sk);
- 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->len;
- spin_unlock_bh(&sk->sk_receive_queue.lock);
- return put_user(amount, (int __user *)arg);
- }
+ 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->len;
+ spin_unlock_bh(&sk->sk_receive_queue.lock);
+ return put_user(amount, (int __user *)arg);
+ }
- default:
+ default:
+#ifdef CONFIG_IP_MROUTE
+ return ipmr_ioctl(sk, cmd, (void __user *)arg);
+#else
+ return -ENOIOCTLCMD;
+#endif
+ }
+}
+
+#ifdef CONFIG_COMPAT
+static int compat_raw_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case SIOCOUTQ:
+ case SIOCINQ:
+ return -ENOIOCTLCMD;
+ default:
#ifdef CONFIG_IP_MROUTE
- return ipmr_ioctl(sk, cmd, (void __user *)arg);
+ return ipmr_compat_ioctl(sk, cmd, compat_ptr(arg));
#else
- return -ENOIOCTLCMD;
+ return -ENOIOCTLCMD;
#endif
}
}
+#endif
struct proto raw_prot = {
.name = "RAW",
@@ -853,6 +895,7 @@ struct proto raw_prot = {
.recvmsg = raw_recvmsg,
.bind = raw_bind,
.backlog_rcv = raw_rcv_skb,
+ .release_cb = ip4_datagram_release_cb,
.hash = raw_hash_sk,
.unhash = raw_unhash_sk,
.obj_size = sizeof(struct raw_sock),
@@ -860,6 +903,7 @@ struct proto raw_prot = {
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_raw_setsockopt,
.compat_getsockopt = compat_raw_getsockopt,
+ .compat_ioctl = compat_raw_ioctl,
#endif
};
@@ -871,9 +915,7 @@ static struct sock *raw_get_first(struct seq_file *seq)
for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE;
++state->bucket) {
- struct hlist_node *node;
-
- sk_for_each(sk, node, &state->h->ht[state->bucket])
+ sk_for_each(sk, &state->h->ht[state->bucket])
if (sock_net(sk) == seq_file_net(seq))
goto found;
}
@@ -948,11 +990,13 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
srcp = inet->inet_num;
seq_printf(seq, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
+ " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n",
i, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
sk_rmem_alloc_get(sp),
- 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
+ 0, 0L, 0,
+ from_kuid_munged(seq_user_ns(seq), sock_i_uid(sp)),
+ 0, sock_i_ino(sp),
atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
}
@@ -1005,7 +1049,7 @@ static const struct file_operations raw_seq_fops = {
static __net_init int raw_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "raw", S_IRUGO, &raw_seq_fops))
+ if (!proc_create("raw", S_IRUGO, net->proc_net, &raw_seq_fops))
return -ENOMEM;
return 0;
@@ -1013,7 +1057,7 @@ static __net_init int raw_init_net(struct net *net)
static __net_exit void raw_exit_net(struct net *net)
{
- proc_net_remove(net, "raw");
+ remove_proc_entry("raw", net->proc_net);
}
static __net_initdata struct pernet_operations raw_net_ops = {
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 01:22:57 +0000