*
* Version: 0.7.0
*
+ * 070228 : Fix to allow multiple sessions with same remote MAC and same
+ * session id by including the local device ifindex in the
+ * tuple identifying a session. This also ensures packets can't
+ * be injected into a session from interfaces other than the one
+ * specified by userspace. Florian Zumbiehl <florz@florz.de>
+ * (Oh, BTW, this one is YYMMDD, in case you were wondering ...)
* 220102 : Fix module use count on failure in pppoe_create, pppox_sk -acme
* 030700 : Fixed connect logic to allow for disconnect.
* 270700 : Fixed potential SMP problems; we must protect against
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include <net/net_namespace.h>
#include <net/sock.h>
#include <asm/uaccess.h>
(memcmp(a->remote, b->remote, ETH_ALEN) == 0));
}
-static inline int cmp_addr(struct pppoe_addr *a, unsigned long sid, char *addr)
+static inline int cmp_addr(struct pppoe_addr *a, __be16 sid, char *addr)
{
return (a->sid == sid &&
(memcmp(a->remote,addr,ETH_ALEN) == 0));
}
-static int hash_item(unsigned long sid, unsigned char *addr)
+#if 8%PPPOE_HASH_BITS
+#error 8 must be a multiple of PPPOE_HASH_BITS
+#endif
+
+static int hash_item(__be16 sid, unsigned char *addr)
{
- char hash = 0;
- int i, j;
+ unsigned char hash = 0;
+ unsigned int i;
- for (i = 0; i < ETH_ALEN ; ++i) {
- for (j = 0; j < 8/PPPOE_HASH_BITS ; ++j) {
- hash ^= addr[i] >> ( j * PPPOE_HASH_BITS );
- }
+ for (i = 0 ; i < ETH_ALEN ; i++) {
+ hash ^= addr[i];
+ }
+ for (i = 0 ; i < sizeof(sid_t)*8 ; i += 8 ){
+ hash ^= (__force __u32)sid>>i;
+ }
+ for (i = 8 ; (i>>=1) >= PPPOE_HASH_BITS ; ) {
+ hash ^= hash>>i;
}
-
- for (i = 0; i < (sizeof(unsigned long)*8) / PPPOE_HASH_BITS ; ++i)
- hash ^= sid >> (i*PPPOE_HASH_BITS);
return hash & ( PPPOE_HASH_SIZE - 1 );
}
* Set/get/delete/rehash items (internal versions)
*
**********************************************************************/
-static struct pppox_sock *__get_item(unsigned long sid, unsigned char *addr)
+static struct pppox_sock *__get_item(__be16 sid, unsigned char *addr, int ifindex)
{
int hash = hash_item(sid, addr);
struct pppox_sock *ret;
ret = item_hash_table[hash];
- while (ret && !cmp_addr(&ret->pppoe_pa, sid, addr))
+ while (ret && !(cmp_addr(&ret->pppoe_pa, sid, addr) && ret->pppoe_ifindex == ifindex))
ret = ret->next;
return ret;
ret = item_hash_table[hash];
while (ret) {
- if (cmp_2_addr(&ret->pppoe_pa, &po->pppoe_pa))
+ if (cmp_2_addr(&ret->pppoe_pa, &po->pppoe_pa) && ret->pppoe_ifindex == po->pppoe_ifindex)
return -EALREADY;
ret = ret->next;
}
- if (!ret) {
- po->next = item_hash_table[hash];
- item_hash_table[hash] = po;
- }
+ po->next = item_hash_table[hash];
+ item_hash_table[hash] = po;
return 0;
}
-static struct pppox_sock *__delete_item(unsigned long sid, char *addr)
+static struct pppox_sock *__delete_item(__be16 sid, char *addr, int ifindex)
{
int hash = hash_item(sid, addr);
struct pppox_sock *ret, **src;
src = &item_hash_table[hash];
while (ret) {
- if (cmp_addr(&ret->pppoe_pa, sid, addr)) {
+ if (cmp_addr(&ret->pppoe_pa, sid, addr) && ret->pppoe_ifindex == ifindex) {
*src = ret->next;
break;
}
* Set/get/delete/rehash items
*
**********************************************************************/
-static inline struct pppox_sock *get_item(unsigned long sid,
- unsigned char *addr)
+static inline struct pppox_sock *get_item(__be16 sid,
+ unsigned char *addr, int ifindex)
{
struct pppox_sock *po;
read_lock_bh(&pppoe_hash_lock);
- po = __get_item(sid, addr);
+ po = __get_item(sid, addr, ifindex);
if (po)
sock_hold(sk_pppox(po));
read_unlock_bh(&pppoe_hash_lock);
static inline struct pppox_sock *get_item_by_addr(struct sockaddr_pppox *sp)
{
- return get_item(sp->sa_addr.pppoe.sid, sp->sa_addr.pppoe.remote);
-}
-
-static inline int set_item(struct pppox_sock *po)
-{
- int i;
-
- if (!po)
- return -EINVAL;
-
- write_lock_bh(&pppoe_hash_lock);
- i = __set_item(po);
- write_unlock_bh(&pppoe_hash_lock);
-
- return i;
+ struct net_device *dev;
+ int ifindex;
+
+ dev = dev_get_by_name(&init_net, sp->sa_addr.pppoe.dev);
+ if(!dev)
+ return NULL;
+ ifindex = dev->ifindex;
+ dev_put(dev);
+ return get_item(sp->sa_addr.pppoe.sid, sp->sa_addr.pppoe.remote, ifindex);
}
-static inline struct pppox_sock *delete_item(unsigned long sid, char *addr)
+static inline struct pppox_sock *delete_item(__be16 sid, char *addr, int ifindex)
{
struct pppox_sock *ret;
write_lock_bh(&pppoe_hash_lock);
- ret = __delete_item(sid, addr);
+ ret = __delete_item(sid, addr, ifindex);
write_unlock_bh(&pppoe_hash_lock);
return ret;
static void pppoe_flush_dev(struct net_device *dev)
{
int hash;
-
BUG_ON(dev == NULL);
- read_lock_bh(&pppoe_hash_lock);
+ write_lock_bh(&pppoe_hash_lock);
for (hash = 0; hash < PPPOE_HASH_SIZE; hash++) {
struct pppox_sock *po = item_hash_table[hash];
while (po != NULL) {
- if (po->pppoe_dev == dev) {
- struct sock *sk = sk_pppox(po);
-
- sock_hold(sk);
- po->pppoe_dev = NULL;
+ struct sock *sk = sk_pppox(po);
+ if (po->pppoe_dev != dev) {
+ po = po->next;
+ continue;
+ }
+ po->pppoe_dev = NULL;
+ dev_put(dev);
- /* We hold a reference to SK, now drop the
- * hash table lock so that we may attempt
- * to lock the socket (which can sleep).
- */
- read_unlock_bh(&pppoe_hash_lock);
- lock_sock(sk);
+ /* We always grab the socket lock, followed by the
+ * pppoe_hash_lock, in that order. Since we should
+ * hold the sock lock while doing any unbinding,
+ * we need to release the lock we're holding.
+ * Hold a reference to the sock so it doesn't disappear
+ * as we're jumping between locks.
+ */
- if (sk->sk_state &
- (PPPOX_CONNECTED | PPPOX_BOUND)) {
- pppox_unbind_sock(sk);
- dev_put(dev);
- sk->sk_state = PPPOX_ZOMBIE;
- sk->sk_state_change(sk);
- }
+ sock_hold(sk);
- release_sock(sk);
+ write_unlock_bh(&pppoe_hash_lock);
+ lock_sock(sk);
- sock_put(sk);
+ if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
+ pppox_unbind_sock(sk);
+ sk->sk_state = PPPOX_ZOMBIE;
+ sk->sk_state_change(sk);
+ }
- read_lock_bh(&pppoe_hash_lock);
+ release_sock(sk);
+ sock_put(sk);
- /* Now restart from the beginning of this
- * hash chain. We always NULL out pppoe_dev
- * so we are guaranteed to make forward
- * progress.
- */
- po = item_hash_table[hash];
- continue;
- }
- po = po->next;
+ /* Restart scan at the beginning of this hash chain.
+ * While the lock was dropped the chain contents may
+ * have changed.
+ */
+ write_lock_bh(&pppoe_hash_lock);
+ po = item_hash_table[hash];
}
}
- read_unlock_bh(&pppoe_hash_lock);
+ write_unlock_bh(&pppoe_hash_lock);
}
static int pppoe_device_event(struct notifier_block *this,
{
struct net_device *dev = (struct net_device *) ptr;
+ if (dev_net(dev) != &init_net)
+ return NOTIFY_DONE;
+
/* Only look at sockets that are using this specific device. */
switch (event) {
case NETDEV_CHANGEMTU:
static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
{
struct pppox_sock *po = pppox_sk(sk);
- struct pppox_sock *relay_po = NULL;
+ struct pppox_sock *relay_po;
if (sk->sk_state & PPPOX_BOUND) {
- struct pppoe_hdr *ph = (struct pppoe_hdr *) skb->nh.raw;
- int len = ntohs(ph->length);
- skb_pull_rcsum(skb, sizeof(struct pppoe_hdr));
- if (pskb_trim_rcsum(skb, len))
- goto abort_kfree;
-
ppp_input(&po->chan, skb);
} else if (sk->sk_state & PPPOX_RELAY) {
relay_po = get_item_by_addr(&po->pppoe_relay);
if ((sk_pppox(relay_po)->sk_state & PPPOX_CONNECTED) == 0)
goto abort_put;
- skb_pull(skb, sizeof(struct pppoe_hdr));
if (!__pppoe_xmit(sk_pppox(relay_po), skb))
goto abort_put;
} else {
{
struct pppoe_hdr *ph;
struct pppox_sock *po;
+ int len;
+
+ if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
+ goto out;
+
+ if (dev_net(dev) != &init_net)
+ goto drop;
if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
goto drop;
- if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
- goto out;
+ ph = pppoe_hdr(skb);
+ len = ntohs(ph->length);
- ph = (struct pppoe_hdr *) skb->nh.raw;
+ skb_pull_rcsum(skb, sizeof(*ph));
+ if (skb->len < len)
+ goto drop;
+
+ po = get_item(ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
+ if (!po)
+ goto drop;
+
+ if (pskb_trim_rcsum(skb, len))
+ goto drop;
+
+ return sk_receive_skb(sk_pppox(po), skb, 0);
- po = get_item((unsigned long) ph->sid, eth_hdr(skb)->h_source);
- if (po != NULL)
- return sk_receive_skb(sk_pppox(po), skb);
drop:
kfree_skb(skb);
out:
struct pppoe_hdr *ph;
struct pppox_sock *po;
- if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
+ if (dev_net(dev) != &init_net)
goto abort;
- if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
+ if (!(skb = skb_share_check(skb, GFP_ATOMIC)))
goto out;
- ph = (struct pppoe_hdr *) skb->nh.raw;
+ if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
+ goto abort;
+
+ ph = pppoe_hdr(skb);
if (ph->code != PADT_CODE)
goto abort;
- po = get_item((unsigned long) ph->sid, eth_hdr(skb)->h_source);
+ po = get_item(ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
if (po) {
struct sock *sk = sk_pppox(po);
* Initialize a new struct sock.
*
**********************************************************************/
-static int pppoe_create(struct socket *sock)
+static int pppoe_create(struct net *net, struct socket *sock)
{
int error = -ENOMEM;
struct sock *sk;
- sk = sk_alloc(PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto, 1);
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto);
if (!sk)
goto out;
{
struct sock *sk = sock->sk;
struct pppox_sock *po;
- int error = 0;
if (!sk)
return 0;
- if (sock_flag(sk, SOCK_DEAD))
+ lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD)){
+ release_sock(sk);
return -EBADF;
+ }
pppox_unbind_sock(sk);
/* Signal the death of the socket. */
sk->sk_state = PPPOX_DEAD;
+
+ /* Write lock on hash lock protects the entire "po" struct from
+ * concurrent updates via pppoe_flush_dev. The "po" struct should
+ * be considered part of the hash table contents, thus protected
+ * by the hash table lock */
+ write_lock_bh(&pppoe_hash_lock);
+
po = pppox_sk(sk);
if (po->pppoe_pa.sid) {
- delete_item(po->pppoe_pa.sid, po->pppoe_pa.remote);
+ __delete_item(po->pppoe_pa.sid,
+ po->pppoe_pa.remote, po->pppoe_ifindex);
}
- if (po->pppoe_dev)
+ if (po->pppoe_dev) {
dev_put(po->pppoe_dev);
+ po->pppoe_dev = NULL;
+ }
- po->pppoe_dev = NULL;
+ write_unlock_bh(&pppoe_hash_lock);
sock_orphan(sk);
sock->sk = NULL;
skb_queue_purge(&sk->sk_receive_queue);
+ release_sock(sk);
sock_put(sk);
- return error;
+ return 0;
}
int sockaddr_len, int flags)
{
struct sock *sk = sock->sk;
- struct net_device *dev = NULL;
+ struct net_device *dev;
struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr;
struct pppox_sock *po = pppox_sk(sk);
int error;
pppox_unbind_sock(sk);
/* Delete the old binding */
- delete_item(po->pppoe_pa.sid,po->pppoe_pa.remote);
+ delete_item(po->pppoe_pa.sid,po->pppoe_pa.remote,po->pppoe_ifindex);
if(po->pppoe_dev)
dev_put(po->pppoe_dev);
/* Don't re-bind if sid==0 */
if (sp->sa_addr.pppoe.sid != 0) {
- dev = dev_get_by_name(sp->sa_addr.pppoe.dev);
+ dev = dev_get_by_name(&init_net, sp->sa_addr.pppoe.dev);
error = -ENODEV;
if (!dev)
goto end;
po->pppoe_dev = dev;
+ po->pppoe_ifindex = dev->ifindex;
- if (!(dev->flags & IFF_UP))
+ write_lock_bh(&pppoe_hash_lock);
+ if (!(dev->flags & IFF_UP)){
+ write_unlock_bh(&pppoe_hash_lock);
goto err_put;
+ }
memcpy(&po->pppoe_pa,
&sp->sa_addr.pppoe,
sizeof(struct pppoe_addr));
- error = set_item(po);
+ error = __set_item(po);
+ write_unlock_bh(&pppoe_hash_lock);
if (error < 0)
goto err_put;
po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
dev->hard_header_len);
+ po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr);
po->chan.private = sk;
po->chan.ops = &pppoe_chan_ops;
{
struct sock *sk = sock->sk;
struct pppox_sock *po = pppox_sk(sk);
- int val = 0;
- int err = 0;
+ int val;
+ int err;
switch (cmd) {
case PPPIOCGMRU:
break;
/* PPPoE address from the user specifies an outbound
- PPPoE address to which frames are forwarded to */
+ PPPoE address which frames are forwarded to */
err = -EFAULT;
if (copy_from_user(&po->pppoe_relay,
(void __user *)arg,
err = 0;
break;
- default:;
- };
+ default:
+ err = -ENOTTY;
+ }
return err;
}
-static int pppoe_sendmsg(struct kiocb *iocb, struct socket *sock,
+static int pppoe_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len)
{
- struct sk_buff *skb = NULL;
+ struct sk_buff *skb;
struct sock *sk = sock->sk;
struct pppox_sock *po = pppox_sk(sk);
- int error = 0;
+ int error;
struct pppoe_hdr hdr;
struct pppoe_hdr *ph;
struct net_device *dev;
char *start;
+ lock_sock(sk);
if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
error = -ENOTCONN;
goto end;
hdr.code = 0;
hdr.sid = po->num;
- lock_sock(sk);
-
dev = po->pppoe_dev;
error = -EMSGSIZE;
/* Reserve space for headers. */
skb_reserve(skb, dev->hard_header_len);
- skb->nh.raw = skb->data;
+ skb_reset_network_header(skb);
skb->dev = dev;
}
error = total_len;
- dev->hard_header(skb, dev, ETH_P_PPP_SES,
- po->pppoe_pa.remote, NULL, total_len);
+ dev_hard_header(skb, dev, ETH_P_PPP_SES,
+ po->pppoe_pa.remote, NULL, total_len);
memcpy(ph, &hdr, sizeof(struct pppoe_hdr));
{
struct pppox_sock *po = pppox_sk(sk);
struct net_device *dev = po->pppoe_dev;
- struct pppoe_hdr hdr;
struct pppoe_hdr *ph;
- int headroom = skb_headroom(skb);
int data_len = skb->len;
- struct sk_buff *skb2;
if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
goto abort;
- hdr.ver = 1;
- hdr.type = 1;
- hdr.code = 0;
- hdr.sid = po->num;
- hdr.length = htons(skb->len);
-
if (!dev)
goto abort;
- /* Copy the skb if there is no space for the header. */
- if (headroom < (sizeof(struct pppoe_hdr) + dev->hard_header_len)) {
- skb2 = dev_alloc_skb(32+skb->len +
- sizeof(struct pppoe_hdr) +
- dev->hard_header_len);
-
- if (skb2 == NULL)
- goto abort;
-
- skb_reserve(skb2, dev->hard_header_len + sizeof(struct pppoe_hdr));
- memcpy(skb_put(skb2, skb->len), skb->data, skb->len);
- } else {
- /* Make a clone so as to not disturb the original skb,
- * give dev_queue_xmit something it can free.
- */
- skb2 = skb_clone(skb, GFP_ATOMIC);
- }
-
- ph = (struct pppoe_hdr *) skb_push(skb2, sizeof(struct pppoe_hdr));
- memcpy(ph, &hdr, sizeof(struct pppoe_hdr));
- skb2->protocol = __constant_htons(ETH_P_PPP_SES);
+ /* Copy the data if there is no space for the header or if it's
+ * read-only.
+ */
+ if (skb_cow_head(skb, sizeof(*ph) + dev->hard_header_len))
+ goto abort;
- skb2->nh.raw = skb2->data;
+ __skb_push(skb, sizeof(*ph));
+ skb_reset_network_header(skb);
- skb2->dev = dev;
+ ph = pppoe_hdr(skb);
+ ph->ver = 1;
+ ph->type = 1;
+ ph->code = 0;
+ ph->sid = po->num;
+ ph->length = htons(data_len);
- dev->hard_header(skb2, dev, ETH_P_PPP_SES,
- po->pppoe_pa.remote, NULL, data_len);
+ skb->protocol = __constant_htons(ETH_P_PPP_SES);
+ skb->dev = dev;
- /* We're transmitting skb2, and assuming that dev_queue_xmit
- * will free it. The generic ppp layer however, is expecting
- * that we give back 'skb' (not 'skb2') in case of failure,
- * but free it in case of success.
- */
+ dev_hard_header(skb, dev, ETH_P_PPP_SES,
+ po->pppoe_pa.remote, NULL, data_len);
- if (dev_queue_xmit(skb2) < 0)
- goto abort;
+ dev_queue_xmit(skb);
- kfree_skb(skb);
return 1;
abort:
- return 0;
+ kfree_skb(skb);
+ return 1;
}
}
-static struct ppp_channel_ops pppoe_chan_ops = {
- .start_xmit = pppoe_xmit,
+static struct ppp_channel_ops pppoe_chan_ops = {
+ .start_xmit = pppoe_xmit,
};
static int pppoe_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len, int flags)
{
struct sock *sk = sock->sk;
- struct sk_buff *skb = NULL;
+ struct sk_buff *skb;
int error = 0;
- int len;
- struct pppoe_hdr *ph = NULL;
if (sk->sk_state & PPPOX_BOUND) {
error = -EIO;
skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
flags & MSG_DONTWAIT, &error);
- if (error < 0) {
+ if (error < 0)
goto end;
- }
m->msg_namelen = 0;
if (skb) {
- error = 0;
- ph = (struct pppoe_hdr *) skb->nh.raw;
- len = ntohs(ph->length);
-
- error = memcpy_toiovec(m->msg_iov, (unsigned char *) &ph->tag[0], len);
- if (error < 0)
- goto do_skb_free;
- error = len;
+ total_len = min_t(size_t, total_len, skb->len);
+ error = skb_copy_datagram_iovec(skb, 0, m->msg_iov, total_len);
+ if (error == 0)
+ error = total_len;
}
-do_skb_free:
- if (skb)
- kfree_skb(skb);
+ kfree_skb(skb);
end:
return error;
}
{
struct pppox_sock *po;
char *dev_name;
+ DECLARE_MAC_BUF(mac);
if (v == SEQ_START_TOKEN) {
seq_puts(seq, "Id Address Device\n");
po = v;
dev_name = po->pppoe_pa.dev;
- seq_printf(seq, "%08X %02X:%02X:%02X:%02X:%02X:%02X %8s\n",
- po->pppoe_pa.sid,
- po->pppoe_pa.remote[0], po->pppoe_pa.remote[1],
- po->pppoe_pa.remote[2], po->pppoe_pa.remote[3],
- po->pppoe_pa.remote[4], po->pppoe_pa.remote[5], dev_name);
+ seq_printf(seq, "%08X %s %8s\n",
+ po->pppoe_pa.sid, print_mac(mac, po->pppoe_pa.remote), dev_name);
out:
return 0;
}
static __inline__ struct pppox_sock *pppoe_get_idx(loff_t pos)
{
- struct pppox_sock *po = NULL;
+ struct pppox_sock *po;
int i = 0;
for (; i < PPPOE_HASH_SIZE; i++) {
}
static void *pppoe_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(pppoe_hash_lock)
{
loff_t l = *pos;
goto out;
}
po = v;
- if (po->next)
+ if (po->next)
po = po->next;
else {
int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);
}
static void pppoe_seq_stop(struct seq_file *seq, void *v)
+ __releases(pppoe_hash_lock)
{
read_unlock_bh(&pppoe_hash_lock);
}
return seq_open(file, &pppoe_seq_ops);
}
-static struct file_operations pppoe_seq_fops = {
+static const struct file_operations pppoe_seq_fops = {
.owner = THIS_MODULE,
.open = pppoe_seq_open,
.read = seq_read,
{
struct proc_dir_entry *p;
- p = create_proc_entry("net/pppoe", S_IRUGO, NULL);
+ p = proc_net_fops_create(&init_net, "pppoe", S_IRUGO, &pppoe_seq_fops);
if (!p)
return -ENOMEM;
-
- p->proc_fops = &pppoe_seq_fops;
return 0;
}
#else /* CONFIG_PROC_FS */
err = pppoe_proc_init();
if (err)
goto out_unregister_pppox_proto;
-
+
dev_add_pack(&pppoes_ptype);
dev_add_pack(&pppoed_ptype);
register_netdevice_notifier(&pppoe_notifier);
dev_remove_pack(&pppoes_ptype);
dev_remove_pack(&pppoed_ptype);
unregister_netdevice_notifier(&pppoe_notifier);
- remove_proc_entry("net/pppoe", NULL);
+ remove_proc_entry("pppoe", init_net.proc_net);
proto_unregister(&pppoe_sk_proto);
}