* [PATCH v3 01/12] l2tp: Relocate pppol2tp driver to new net/l2tp directory
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
@ 2010-03-30 16:17 ` James Chapman
2010-03-30 16:17 ` [PATCH v3 02/12] l2tp: Split pppol2tp patch into separate l2tp and ppp parts James Chapman
` (10 subsequent siblings)
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:17 UTC (permalink / raw)
To: netdev
This patch moves the existing pppol2tp driver from drivers/net into a
new net/l2tp directory, which is where the upcoming L2TPv3 code will
live. The existing CONFIG_PPPOL2TP config option is left in its
current place to avoid "make oldconfig" issues when an existing
pppol2tp user takes this change. (This is the same approach used for
the pppoatm driver, which moved to net/atm.)
There are no code changes. The existing drivers/net/pppol2tp.c is
simply moved to net/l2tp.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
Am I being paranoid about not moving CONFIG_PPPOL2TP from
drivers/net/Kconfig to net/l2tp/Kconfig?
---
drivers/net/Makefile | 2
drivers/net/pppol2tp.c | 2680 ------------------------------------------------
net/Makefile | 1
net/l2tp/Makefile | 5
net/l2tp/pppol2tp.c | 2680 ++++++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 2687 insertions(+), 2681 deletions(-)
delete mode 100644 drivers/net/pppol2tp.c
create mode 100644 net/l2tp/Makefile
create mode 100644 net/l2tp/pppol2tp.c
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 4788862..ac83fb4 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -160,7 +160,7 @@ obj-$(CONFIG_PPP_DEFLATE) += ppp_deflate.o
obj-$(CONFIG_PPP_BSDCOMP) += bsd_comp.o
obj-$(CONFIG_PPP_MPPE) += ppp_mppe.o
obj-$(CONFIG_PPPOE) += pppox.o pppoe.o
-obj-$(CONFIG_PPPOL2TP) += pppox.o pppol2tp.o
+obj-$(CONFIG_PPPOL2TP) += pppox.o
obj-$(CONFIG_SLIP) += slip.o
obj-$(CONFIG_SLHC) += slhc.o
diff --git a/drivers/net/pppol2tp.c b/drivers/net/pppol2tp.c
deleted file mode 100644
index 449a982..0000000
--- a/drivers/net/pppol2tp.c
+++ /dev/null
@@ -1,2680 +0,0 @@
-/*****************************************************************************
- * Linux PPP over L2TP (PPPoX/PPPoL2TP) Sockets
- *
- * PPPoX --- Generic PPP encapsulation socket family
- * PPPoL2TP --- PPP over L2TP (RFC 2661)
- *
- * Version: 1.0.0
- *
- * Authors: Martijn van Oosterhout <kleptog@svana.org>
- * James Chapman (jchapman@katalix.com)
- * Contributors:
- * Michal Ostrowski <mostrows@speakeasy.net>
- * Arnaldo Carvalho de Melo <acme@xconectiva.com.br>
- * David S. Miller (davem@redhat.com)
- *
- * License:
- * 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.
- *
- */
-
-/* This driver handles only L2TP data frames; control frames are handled by a
- * userspace application.
- *
- * To send data in an L2TP session, userspace opens a PPPoL2TP socket and
- * attaches it to a bound UDP socket with local tunnel_id / session_id and
- * peer tunnel_id / session_id set. Data can then be sent or received using
- * regular socket sendmsg() / recvmsg() calls. Kernel parameters of the socket
- * can be read or modified using ioctl() or [gs]etsockopt() calls.
- *
- * When a PPPoL2TP socket is connected with local and peer session_id values
- * zero, the socket is treated as a special tunnel management socket.
- *
- * Here's example userspace code to create a socket for sending/receiving data
- * over an L2TP session:-
- *
- * struct sockaddr_pppol2tp sax;
- * int fd;
- * int session_fd;
- *
- * fd = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP);
- *
- * sax.sa_family = AF_PPPOX;
- * sax.sa_protocol = PX_PROTO_OL2TP;
- * sax.pppol2tp.fd = tunnel_fd; // bound UDP socket
- * sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr;
- * sax.pppol2tp.addr.sin_port = addr->sin_port;
- * sax.pppol2tp.addr.sin_family = AF_INET;
- * sax.pppol2tp.s_tunnel = tunnel_id;
- * sax.pppol2tp.s_session = session_id;
- * sax.pppol2tp.d_tunnel = peer_tunnel_id;
- * sax.pppol2tp.d_session = peer_session_id;
- *
- * session_fd = connect(fd, (struct sockaddr *)&sax, sizeof(sax));
- *
- * A pppd plugin that allows PPP traffic to be carried over L2TP using
- * this driver is available from the OpenL2TP project at
- * http://openl2tp.sourceforge.net.
- */
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/list.h>
-#include <asm/uaccess.h>
-
-#include <linux/kernel.h>
-#include <linux/spinlock.h>
-#include <linux/kthread.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/errno.h>
-#include <linux/jiffies.h>
-
-#include <linux/netdevice.h>
-#include <linux/net.h>
-#include <linux/inetdevice.h>
-#include <linux/skbuff.h>
-#include <linux/init.h>
-#include <linux/ip.h>
-#include <linux/udp.h>
-#include <linux/if_pppox.h>
-#include <linux/if_pppol2tp.h>
-#include <net/sock.h>
-#include <linux/ppp_channel.h>
-#include <linux/ppp_defs.h>
-#include <linux/if_ppp.h>
-#include <linux/file.h>
-#include <linux/hash.h>
-#include <linux/sort.h>
-#include <linux/proc_fs.h>
-#include <linux/nsproxy.h>
-#include <net/net_namespace.h>
-#include <net/netns/generic.h>
-#include <net/dst.h>
-#include <net/ip.h>
-#include <net/udp.h>
-#include <net/xfrm.h>
-
-#include <asm/byteorder.h>
-#include <asm/atomic.h>
-
-
-#define PPPOL2TP_DRV_VERSION "V1.0"
-
-/* L2TP header constants */
-#define L2TP_HDRFLAG_T 0x8000
-#define L2TP_HDRFLAG_L 0x4000
-#define L2TP_HDRFLAG_S 0x0800
-#define L2TP_HDRFLAG_O 0x0200
-#define L2TP_HDRFLAG_P 0x0100
-
-#define L2TP_HDR_VER_MASK 0x000F
-#define L2TP_HDR_VER 0x0002
-
-/* Space for UDP, L2TP and PPP headers */
-#define PPPOL2TP_HEADER_OVERHEAD 40
-
-/* Just some random numbers */
-#define L2TP_TUNNEL_MAGIC 0x42114DDA
-#define L2TP_SESSION_MAGIC 0x0C04EB7D
-
-#define PPPOL2TP_HASH_BITS 4
-#define PPPOL2TP_HASH_SIZE (1 << PPPOL2TP_HASH_BITS)
-
-/* Default trace flags */
-#define PPPOL2TP_DEFAULT_DEBUG_FLAGS 0
-
-#define PRINTK(_mask, _type, _lvl, _fmt, args...) \
- do { \
- if ((_mask) & (_type)) \
- printk(_lvl "PPPOL2TP: " _fmt, ##args); \
- } while(0)
-
-/* Number of bytes to build transmit L2TP headers.
- * Unfortunately the size is different depending on whether sequence numbers
- * are enabled.
- */
-#define PPPOL2TP_L2TP_HDR_SIZE_SEQ 10
-#define PPPOL2TP_L2TP_HDR_SIZE_NOSEQ 6
-
-struct pppol2tp_tunnel;
-
-/* Describes a session. It is the sk_user_data field in the PPPoL2TP
- * socket. Contains information to determine incoming packets and transmit
- * outgoing ones.
- */
-struct pppol2tp_session
-{
- int magic; /* should be
- * L2TP_SESSION_MAGIC */
- int owner; /* pid that opened the socket */
-
- struct sock *sock; /* Pointer to the session
- * PPPoX socket */
- struct sock *tunnel_sock; /* Pointer to the tunnel UDP
- * socket */
-
- struct pppol2tp_addr tunnel_addr; /* Description of tunnel */
-
- struct pppol2tp_tunnel *tunnel; /* back pointer to tunnel
- * context */
-
- char name[20]; /* "sess xxxxx/yyyyy", where
- * x=tunnel_id, y=session_id */
- int mtu;
- int mru;
- int flags; /* accessed by PPPIOCGFLAGS.
- * Unused. */
- unsigned recv_seq:1; /* expect receive packets with
- * sequence numbers? */
- unsigned send_seq:1; /* send packets with sequence
- * numbers? */
- unsigned lns_mode:1; /* behave as LNS? LAC enables
- * sequence numbers under
- * control of LNS. */
- int debug; /* bitmask of debug message
- * categories */
- int reorder_timeout; /* configured reorder timeout
- * (in jiffies) */
- u16 nr; /* session NR state (receive) */
- u16 ns; /* session NR state (send) */
- struct sk_buff_head reorder_q; /* receive reorder queue */
- struct pppol2tp_ioc_stats stats;
- struct hlist_node hlist; /* Hash list node */
-};
-
-/* The sk_user_data field of the tunnel's UDP socket. It contains info to track
- * all the associated sessions so incoming packets can be sorted out
- */
-struct pppol2tp_tunnel
-{
- int magic; /* Should be L2TP_TUNNEL_MAGIC */
- rwlock_t hlist_lock; /* protect session_hlist */
- struct hlist_head session_hlist[PPPOL2TP_HASH_SIZE];
- /* hashed list of sessions,
- * hashed by id */
- int debug; /* bitmask of debug message
- * categories */
- char name[12]; /* "tunl xxxxx" */
- struct pppol2tp_ioc_stats stats;
-
- void (*old_sk_destruct)(struct sock *);
-
- struct sock *sock; /* Parent socket */
- struct list_head list; /* Keep a list of all open
- * prepared sockets */
- struct net *pppol2tp_net; /* the net we belong to */
-
- atomic_t ref_count;
-};
-
-/* Private data stored for received packets in the skb.
- */
-struct pppol2tp_skb_cb {
- u16 ns;
- u16 nr;
- u16 has_seq;
- u16 length;
- unsigned long expires;
-};
-
-#define PPPOL2TP_SKB_CB(skb) ((struct pppol2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)])
-
-static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb);
-static void pppol2tp_tunnel_free(struct pppol2tp_tunnel *tunnel);
-
-static atomic_t pppol2tp_tunnel_count;
-static atomic_t pppol2tp_session_count;
-static struct ppp_channel_ops pppol2tp_chan_ops = { pppol2tp_xmit , NULL };
-static const struct proto_ops pppol2tp_ops;
-
-/* per-net private data for this module */
-static int pppol2tp_net_id __read_mostly;
-struct pppol2tp_net {
- struct list_head pppol2tp_tunnel_list;
- rwlock_t pppol2tp_tunnel_list_lock;
-};
-
-static inline struct pppol2tp_net *pppol2tp_pernet(struct net *net)
-{
- BUG_ON(!net);
-
- return net_generic(net, pppol2tp_net_id);
-}
-
-/* Helpers to obtain tunnel/session contexts from sockets.
- */
-static inline struct pppol2tp_session *pppol2tp_sock_to_session(struct sock *sk)
-{
- struct pppol2tp_session *session;
-
- if (sk == NULL)
- return NULL;
-
- sock_hold(sk);
- session = (struct pppol2tp_session *)(sk->sk_user_data);
- if (session == NULL) {
- sock_put(sk);
- goto out;
- }
-
- BUG_ON(session->magic != L2TP_SESSION_MAGIC);
-out:
- return session;
-}
-
-static inline struct pppol2tp_tunnel *pppol2tp_sock_to_tunnel(struct sock *sk)
-{
- struct pppol2tp_tunnel *tunnel;
-
- if (sk == NULL)
- return NULL;
-
- sock_hold(sk);
- tunnel = (struct pppol2tp_tunnel *)(sk->sk_user_data);
- if (tunnel == NULL) {
- sock_put(sk);
- goto out;
- }
-
- BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-out:
- return tunnel;
-}
-
-/* Tunnel reference counts. Incremented per session that is added to
- * the tunnel.
- */
-static inline void pppol2tp_tunnel_inc_refcount(struct pppol2tp_tunnel *tunnel)
-{
- atomic_inc(&tunnel->ref_count);
-}
-
-static inline void pppol2tp_tunnel_dec_refcount(struct pppol2tp_tunnel *tunnel)
-{
- if (atomic_dec_and_test(&tunnel->ref_count))
- pppol2tp_tunnel_free(tunnel);
-}
-
-/* Session hash list.
- * The session_id SHOULD be random according to RFC2661, but several
- * L2TP implementations (Cisco and Microsoft) use incrementing
- * session_ids. So we do a real hash on the session_id, rather than a
- * simple bitmask.
- */
-static inline struct hlist_head *
-pppol2tp_session_id_hash(struct pppol2tp_tunnel *tunnel, u16 session_id)
-{
- unsigned long hash_val = (unsigned long) session_id;
- return &tunnel->session_hlist[hash_long(hash_val, PPPOL2TP_HASH_BITS)];
-}
-
-/* Lookup a session by id
- */
-static struct pppol2tp_session *
-pppol2tp_session_find(struct pppol2tp_tunnel *tunnel, u16 session_id)
-{
- struct hlist_head *session_list =
- pppol2tp_session_id_hash(tunnel, session_id);
- struct pppol2tp_session *session;
- struct hlist_node *walk;
-
- read_lock_bh(&tunnel->hlist_lock);
- hlist_for_each_entry(session, walk, session_list, hlist) {
- if (session->tunnel_addr.s_session == session_id) {
- read_unlock_bh(&tunnel->hlist_lock);
- return session;
- }
- }
- read_unlock_bh(&tunnel->hlist_lock);
-
- return NULL;
-}
-
-/* Lookup a tunnel by id
- */
-static struct pppol2tp_tunnel *pppol2tp_tunnel_find(struct net *net, u16 tunnel_id)
-{
- struct pppol2tp_tunnel *tunnel;
- struct pppol2tp_net *pn = pppol2tp_pernet(net);
-
- read_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- list_for_each_entry(tunnel, &pn->pppol2tp_tunnel_list, list) {
- if (tunnel->stats.tunnel_id == tunnel_id) {
- read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
- return tunnel;
- }
- }
- read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
-
- return NULL;
-}
-
-/*****************************************************************************
- * Receive data handling
- *****************************************************************************/
-
-/* Queue a skb in order. We come here only if the skb has an L2TP sequence
- * number.
- */
-static void pppol2tp_recv_queue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
-{
- struct sk_buff *skbp;
- struct sk_buff *tmp;
- u16 ns = PPPOL2TP_SKB_CB(skb)->ns;
-
- spin_lock_bh(&session->reorder_q.lock);
- skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
- if (PPPOL2TP_SKB_CB(skbp)->ns > ns) {
- __skb_queue_before(&session->reorder_q, skbp, skb);
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n",
- session->name, ns, PPPOL2TP_SKB_CB(skbp)->ns,
- skb_queue_len(&session->reorder_q));
- session->stats.rx_oos_packets++;
- goto out;
- }
- }
-
- __skb_queue_tail(&session->reorder_q, skb);
-
-out:
- spin_unlock_bh(&session->reorder_q.lock);
-}
-
-/* Dequeue a single skb.
- */
-static void pppol2tp_recv_dequeue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
-{
- struct pppol2tp_tunnel *tunnel = session->tunnel;
- int length = PPPOL2TP_SKB_CB(skb)->length;
- struct sock *session_sock = NULL;
-
- /* We're about to requeue the skb, so return resources
- * to its current owner (a socket receive buffer).
- */
- skb_orphan(skb);
-
- tunnel->stats.rx_packets++;
- tunnel->stats.rx_bytes += length;
- session->stats.rx_packets++;
- session->stats.rx_bytes += length;
-
- if (PPPOL2TP_SKB_CB(skb)->has_seq) {
- /* Bump our Nr */
- session->nr++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: updated nr to %hu\n", session->name, session->nr);
- }
-
- /* If the socket is bound, send it in to PPP's input queue. Otherwise
- * queue it on the session socket.
- */
- session_sock = session->sock;
- if (session_sock->sk_state & PPPOX_BOUND) {
- struct pppox_sock *po;
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: recv %d byte data frame, passing to ppp\n",
- session->name, length);
-
- /* We need to forget all info related to the L2TP packet
- * gathered in the skb as we are going to reuse the same
- * skb for the inner packet.
- * Namely we need to:
- * - reset xfrm (IPSec) information as it applies to
- * the outer L2TP packet and not to the inner one
- * - release the dst to force a route lookup on the inner
- * IP packet since skb->dst currently points to the dst
- * of the UDP tunnel
- * - reset netfilter information as it doesn't apply
- * to the inner packet either
- */
- secpath_reset(skb);
- skb_dst_drop(skb);
- nf_reset(skb);
-
- po = pppox_sk(session_sock);
- ppp_input(&po->chan, skb);
- } else {
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
- "%s: socket not bound\n", session->name);
-
- /* Not bound. Nothing we can do, so discard. */
- session->stats.rx_errors++;
- kfree_skb(skb);
- }
-
- sock_put(session->sock);
-}
-
-/* Dequeue skbs from the session's reorder_q, subject to packet order.
- * Skbs that have been in the queue for too long are simply discarded.
- */
-static void pppol2tp_recv_dequeue(struct pppol2tp_session *session)
-{
- struct sk_buff *skb;
- struct sk_buff *tmp;
-
- /* If the pkt at the head of the queue has the nr that we
- * expect to send up next, dequeue it and any other
- * in-sequence packets behind it.
- */
- spin_lock_bh(&session->reorder_q.lock);
- skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
- if (time_after(jiffies, PPPOL2TP_SKB_CB(skb)->expires)) {
- session->stats.rx_seq_discards++;
- session->stats.rx_errors++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: oos pkt %hu len %d discarded (too old), "
- "waiting for %hu, reorder_q_len=%d\n",
- session->name, PPPOL2TP_SKB_CB(skb)->ns,
- PPPOL2TP_SKB_CB(skb)->length, session->nr,
- skb_queue_len(&session->reorder_q));
- __skb_unlink(skb, &session->reorder_q);
- kfree_skb(skb);
- sock_put(session->sock);
- continue;
- }
-
- if (PPPOL2TP_SKB_CB(skb)->has_seq) {
- if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: holding oos pkt %hu len %d, "
- "waiting for %hu, reorder_q_len=%d\n",
- session->name, PPPOL2TP_SKB_CB(skb)->ns,
- PPPOL2TP_SKB_CB(skb)->length, session->nr,
- skb_queue_len(&session->reorder_q));
- goto out;
- }
- }
- __skb_unlink(skb, &session->reorder_q);
-
- /* Process the skb. We release the queue lock while we
- * do so to let other contexts process the queue.
- */
- spin_unlock_bh(&session->reorder_q.lock);
- pppol2tp_recv_dequeue_skb(session, skb);
- spin_lock_bh(&session->reorder_q.lock);
- }
-
-out:
- spin_unlock_bh(&session->reorder_q.lock);
-}
-
-static inline int pppol2tp_verify_udp_checksum(struct sock *sk,
- struct sk_buff *skb)
-{
- struct udphdr *uh = udp_hdr(skb);
- u16 ulen = ntohs(uh->len);
- struct inet_sock *inet;
- __wsum psum;
-
- if (sk->sk_no_check || skb_csum_unnecessary(skb) || !uh->check)
- return 0;
-
- inet = inet_sk(sk);
- psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr, ulen,
- IPPROTO_UDP, 0);
-
- if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
- !csum_fold(csum_add(psum, skb->csum)))
- return 0;
-
- skb->csum = psum;
-
- return __skb_checksum_complete(skb);
-}
-
-/* Internal receive frame. Do the real work of receiving an L2TP data frame
- * here. The skb is not on a list when we get here.
- * Returns 0 if the packet was a data packet and was successfully passed on.
- * Returns 1 if the packet was not a good data packet and could not be
- * forwarded. All such packets are passed up to userspace to deal with.
- */
-static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb)
-{
- struct pppol2tp_session *session = NULL;
- struct pppol2tp_tunnel *tunnel;
- unsigned char *ptr, *optr;
- u16 hdrflags;
- u16 tunnel_id, session_id;
- int length;
- int offset;
-
- tunnel = pppol2tp_sock_to_tunnel(sock);
- if (tunnel == NULL)
- goto no_tunnel;
-
- if (tunnel->sock && pppol2tp_verify_udp_checksum(tunnel->sock, skb))
- goto discard_bad_csum;
-
- /* UDP always verifies the packet length. */
- __skb_pull(skb, sizeof(struct udphdr));
-
- /* Short packet? */
- if (!pskb_may_pull(skb, 12)) {
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
- "%s: recv short packet (len=%d)\n", tunnel->name, skb->len);
- goto error;
- }
-
- /* Point to L2TP header */
- optr = ptr = skb->data;
-
- /* Get L2TP header flags */
- hdrflags = ntohs(*(__be16*)ptr);
-
- /* Trace packet contents, if enabled */
- if (tunnel->debug & PPPOL2TP_MSG_DATA) {
- length = min(16u, skb->len);
- if (!pskb_may_pull(skb, length))
- goto error;
-
- printk(KERN_DEBUG "%s: recv: ", tunnel->name);
-
- offset = 0;
- do {
- printk(" %02X", ptr[offset]);
- } while (++offset < length);
-
- printk("\n");
- }
-
- /* Get length of L2TP packet */
- length = skb->len;
-
- /* If type is control packet, it is handled by userspace. */
- if (hdrflags & L2TP_HDRFLAG_T) {
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: recv control packet, len=%d\n", tunnel->name, length);
- goto error;
- }
-
- /* Skip flags */
- ptr += 2;
-
- /* If length is present, skip it */
- if (hdrflags & L2TP_HDRFLAG_L)
- ptr += 2;
-
- /* Extract tunnel and session ID */
- tunnel_id = ntohs(*(__be16 *) ptr);
- ptr += 2;
- session_id = ntohs(*(__be16 *) ptr);
- ptr += 2;
-
- /* Find the session context */
- session = pppol2tp_session_find(tunnel, session_id);
- if (!session) {
- /* Not found? Pass to userspace to deal with */
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
- "%s: no socket found (%hu/%hu). Passing up.\n",
- tunnel->name, tunnel_id, session_id);
- goto error;
- }
- sock_hold(session->sock);
-
- /* The ref count on the socket was increased by the above call since
- * we now hold a pointer to the session. Take care to do sock_put()
- * when exiting this function from now on...
- */
-
- /* Handle the optional sequence numbers. If we are the LAC,
- * enable/disable sequence numbers under the control of the LNS. If
- * no sequence numbers present but we were expecting them, discard
- * frame.
- */
- if (hdrflags & L2TP_HDRFLAG_S) {
- u16 ns, nr;
- ns = ntohs(*(__be16 *) ptr);
- ptr += 2;
- nr = ntohs(*(__be16 *) ptr);
- ptr += 2;
-
- /* Received a packet with sequence numbers. If we're the LNS,
- * check if we sre sending sequence numbers and if not,
- * configure it so.
- */
- if ((!session->lns_mode) && (!session->send_seq)) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
- "%s: requested to enable seq numbers by LNS\n",
- session->name);
- session->send_seq = -1;
- }
-
- /* Store L2TP info in the skb */
- PPPOL2TP_SKB_CB(skb)->ns = ns;
- PPPOL2TP_SKB_CB(skb)->nr = nr;
- PPPOL2TP_SKB_CB(skb)->has_seq = 1;
-
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: recv data ns=%hu, nr=%hu, session nr=%hu\n",
- session->name, ns, nr, session->nr);
- } else {
- /* No sequence numbers.
- * If user has configured mandatory sequence numbers, discard.
- */
- if (session->recv_seq) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
- "%s: recv data has no seq numbers when required. "
- "Discarding\n", session->name);
- session->stats.rx_seq_discards++;
- goto discard;
- }
-
- /* If we're the LAC and we're sending sequence numbers, the
- * LNS has requested that we no longer send sequence numbers.
- * If we're the LNS and we're sending sequence numbers, the
- * LAC is broken. Discard the frame.
- */
- if ((!session->lns_mode) && (session->send_seq)) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
- "%s: requested to disable seq numbers by LNS\n",
- session->name);
- session->send_seq = 0;
- } else if (session->send_seq) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
- "%s: recv data has no seq numbers when required. "
- "Discarding\n", session->name);
- session->stats.rx_seq_discards++;
- goto discard;
- }
-
- /* Store L2TP info in the skb */
- PPPOL2TP_SKB_CB(skb)->has_seq = 0;
- }
-
- /* If offset bit set, skip it. */
- if (hdrflags & L2TP_HDRFLAG_O) {
- offset = ntohs(*(__be16 *)ptr);
- ptr += 2 + offset;
- }
-
- offset = ptr - optr;
- if (!pskb_may_pull(skb, offset))
- goto discard;
-
- __skb_pull(skb, offset);
-
- /* Skip PPP header, if present. In testing, Microsoft L2TP clients
- * don't send the PPP header (PPP header compression enabled), but
- * other clients can include the header. So we cope with both cases
- * here. The PPP header is always FF03 when using L2TP.
- *
- * Note that skb->data[] isn't dereferenced from a u16 ptr here since
- * the field may be unaligned.
- */
- if (!pskb_may_pull(skb, 2))
- goto discard;
-
- if ((skb->data[0] == 0xff) && (skb->data[1] == 0x03))
- skb_pull(skb, 2);
-
- /* Prepare skb for adding to the session's reorder_q. Hold
- * packets for max reorder_timeout or 1 second if not
- * reordering.
- */
- PPPOL2TP_SKB_CB(skb)->length = length;
- PPPOL2TP_SKB_CB(skb)->expires = jiffies +
- (session->reorder_timeout ? session->reorder_timeout : HZ);
-
- /* Add packet to the session's receive queue. Reordering is done here, if
- * enabled. Saved L2TP protocol info is stored in skb->sb[].
- */
- if (PPPOL2TP_SKB_CB(skb)->has_seq) {
- if (session->reorder_timeout != 0) {
- /* Packet reordering enabled. Add skb to session's
- * reorder queue, in order of ns.
- */
- pppol2tp_recv_queue_skb(session, skb);
- } else {
- /* Packet reordering disabled. Discard out-of-sequence
- * packets
- */
- if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
- session->stats.rx_seq_discards++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: oos pkt %hu len %d discarded, "
- "waiting for %hu, reorder_q_len=%d\n",
- session->name, PPPOL2TP_SKB_CB(skb)->ns,
- PPPOL2TP_SKB_CB(skb)->length, session->nr,
- skb_queue_len(&session->reorder_q));
- goto discard;
- }
- skb_queue_tail(&session->reorder_q, skb);
- }
- } else {
- /* No sequence numbers. Add the skb to the tail of the
- * reorder queue. This ensures that it will be
- * delivered after all previous sequenced skbs.
- */
- skb_queue_tail(&session->reorder_q, skb);
- }
-
- /* Try to dequeue as many skbs from reorder_q as we can. */
- pppol2tp_recv_dequeue(session);
- sock_put(sock);
-
- return 0;
-
-discard:
- session->stats.rx_errors++;
- kfree_skb(skb);
- sock_put(session->sock);
- sock_put(sock);
-
- return 0;
-
-discard_bad_csum:
- LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
- UDP_INC_STATS_USER(&init_net, UDP_MIB_INERRORS, 0);
- tunnel->stats.rx_errors++;
- kfree_skb(skb);
- sock_put(sock);
-
- return 0;
-
-error:
- /* Put UDP header back */
- __skb_push(skb, sizeof(struct udphdr));
- sock_put(sock);
-
-no_tunnel:
- return 1;
-}
-
-/* UDP encapsulation receive handler. See net/ipv4/udp.c.
- * Return codes:
- * 0 : success.
- * <0: error
- * >0: skb should be passed up to userspace as UDP.
- */
-static int pppol2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
-{
- struct pppol2tp_tunnel *tunnel;
-
- tunnel = pppol2tp_sock_to_tunnel(sk);
- if (tunnel == NULL)
- goto pass_up;
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: received %d bytes\n", tunnel->name, skb->len);
-
- if (pppol2tp_recv_core(sk, skb))
- goto pass_up_put;
-
- sock_put(sk);
- return 0;
-
-pass_up_put:
- sock_put(sk);
-pass_up:
- return 1;
-}
-
-/* Receive message. This is the recvmsg for the PPPoL2TP socket.
- */
-static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *msg, size_t len,
- int flags)
-{
- int err;
- struct sk_buff *skb;
- struct sock *sk = sock->sk;
-
- err = -EIO;
- if (sk->sk_state & PPPOX_BOUND)
- goto end;
-
- msg->msg_namelen = 0;
-
- err = 0;
- skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
- flags & MSG_DONTWAIT, &err);
- if (!skb)
- goto end;
-
- if (len > skb->len)
- len = skb->len;
- else if (len < skb->len)
- msg->msg_flags |= MSG_TRUNC;
-
- err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
- if (likely(err == 0))
- err = len;
-
- kfree_skb(skb);
-end:
- return err;
-}
-
-/************************************************************************
- * Transmit handling
- ***********************************************************************/
-
-/* Tell how big L2TP headers are for a particular session. This
- * depends on whether sequence numbers are being used.
- */
-static inline int pppol2tp_l2tp_header_len(struct pppol2tp_session *session)
-{
- if (session->send_seq)
- return PPPOL2TP_L2TP_HDR_SIZE_SEQ;
-
- return PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
-}
-
-/* Build an L2TP header for the session into the buffer provided.
- */
-static void pppol2tp_build_l2tp_header(struct pppol2tp_session *session,
- void *buf)
-{
- __be16 *bufp = buf;
- u16 flags = L2TP_HDR_VER;
-
- if (session->send_seq)
- flags |= L2TP_HDRFLAG_S;
-
- /* Setup L2TP header.
- * FIXME: Can this ever be unaligned? Is direct dereferencing of
- * 16-bit header fields safe here for all architectures?
- */
- *bufp++ = htons(flags);
- *bufp++ = htons(session->tunnel_addr.d_tunnel);
- *bufp++ = htons(session->tunnel_addr.d_session);
- if (session->send_seq) {
- *bufp++ = htons(session->ns);
- *bufp++ = 0;
- session->ns++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: updated ns to %hu\n", session->name, session->ns);
- }
-}
-
-/* This is the sendmsg for the PPPoL2TP pppol2tp_session socket. We come here
- * when a user application does a sendmsg() on the session socket. L2TP and
- * PPP headers must be inserted into the user's data.
- */
-static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
- size_t total_len)
-{
- static const unsigned char ppph[2] = { 0xff, 0x03 };
- struct sock *sk = sock->sk;
- struct inet_sock *inet;
- __wsum csum;
- struct sk_buff *skb;
- int error;
- int hdr_len;
- struct pppol2tp_session *session;
- struct pppol2tp_tunnel *tunnel;
- struct udphdr *uh;
- unsigned int len;
- struct sock *sk_tun;
- u16 udp_len;
-
- error = -ENOTCONN;
- if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
- goto error;
-
- /* Get session and tunnel contexts */
- error = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto error;
-
- sk_tun = session->tunnel_sock;
- tunnel = pppol2tp_sock_to_tunnel(sk_tun);
- if (tunnel == NULL)
- goto error_put_sess;
-
- /* What header length is configured for this session? */
- hdr_len = pppol2tp_l2tp_header_len(session);
-
- /* Allocate a socket buffer */
- error = -ENOMEM;
- skb = sock_wmalloc(sk, NET_SKB_PAD + sizeof(struct iphdr) +
- sizeof(struct udphdr) + hdr_len +
- sizeof(ppph) + total_len,
- 0, GFP_KERNEL);
- if (!skb)
- goto error_put_sess_tun;
-
- /* Reserve space for headers. */
- skb_reserve(skb, NET_SKB_PAD);
- skb_reset_network_header(skb);
- skb_reserve(skb, sizeof(struct iphdr));
- skb_reset_transport_header(skb);
-
- /* Build UDP header */
- inet = inet_sk(sk_tun);
- udp_len = hdr_len + sizeof(ppph) + total_len;
- uh = (struct udphdr *) skb->data;
- uh->source = inet->inet_sport;
- uh->dest = inet->inet_dport;
- uh->len = htons(udp_len);
- uh->check = 0;
- skb_put(skb, sizeof(struct udphdr));
-
- /* Build L2TP header */
- pppol2tp_build_l2tp_header(session, skb->data);
- skb_put(skb, hdr_len);
-
- /* Add PPP header */
- skb->data[0] = ppph[0];
- skb->data[1] = ppph[1];
- skb_put(skb, 2);
-
- /* Copy user data into skb */
- error = memcpy_fromiovec(skb->data, m->msg_iov, total_len);
- if (error < 0) {
- kfree_skb(skb);
- goto error_put_sess_tun;
- }
- skb_put(skb, total_len);
-
- /* Calculate UDP checksum if configured to do so */
- if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
- skb->ip_summed = CHECKSUM_NONE;
- else if (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
- skb->ip_summed = CHECKSUM_COMPLETE;
- csum = skb_checksum(skb, 0, udp_len, 0);
- uh->check = csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, csum);
- if (uh->check == 0)
- uh->check = CSUM_MANGLED_0;
- } else {
- skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, 0);
- }
-
- /* Debug */
- if (session->send_seq)
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %Zd bytes, ns=%hu\n", session->name,
- total_len, session->ns - 1);
- else
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %Zd bytes\n", session->name, total_len);
-
- if (session->debug & PPPOL2TP_MSG_DATA) {
- int i;
- unsigned char *datap = skb->data;
-
- printk(KERN_DEBUG "%s: xmit:", session->name);
- for (i = 0; i < total_len; i++) {
- printk(" %02X", *datap++);
- if (i == 15) {
- printk(" ...");
- break;
- }
- }
- printk("\n");
- }
-
- /* Queue the packet to IP for output */
- len = skb->len;
- error = ip_queue_xmit(skb, 1);
-
- /* Update stats */
- if (error >= 0) {
- tunnel->stats.tx_packets++;
- tunnel->stats.tx_bytes += len;
- session->stats.tx_packets++;
- session->stats.tx_bytes += len;
- } else {
- tunnel->stats.tx_errors++;
- session->stats.tx_errors++;
- }
-
- return error;
-
-error_put_sess_tun:
- sock_put(session->tunnel_sock);
-error_put_sess:
- sock_put(sk);
-error:
- return error;
-}
-
-/* Automatically called when the skb is freed.
- */
-static void pppol2tp_sock_wfree(struct sk_buff *skb)
-{
- sock_put(skb->sk);
-}
-
-/* For data skbs that we transmit, we associate with the tunnel socket
- * but don't do accounting.
- */
-static inline void pppol2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
-{
- sock_hold(sk);
- skb->sk = sk;
- skb->destructor = pppol2tp_sock_wfree;
-}
-
-/* Transmit function called by generic PPP driver. Sends PPP frame
- * over PPPoL2TP socket.
- *
- * This is almost the same as pppol2tp_sendmsg(), but rather than
- * being called with a msghdr from userspace, it is called with a skb
- * from the kernel.
- *
- * The supplied skb from ppp doesn't have enough headroom for the
- * insertion of L2TP, UDP and IP headers so we need to allocate more
- * headroom in the skb. This will create a cloned skb. But we must be
- * careful in the error case because the caller will expect to free
- * the skb it supplied, not our cloned skb. So we take care to always
- * leave the original skb unfreed if we return an error.
- */
-static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
-{
- static const u8 ppph[2] = { 0xff, 0x03 };
- struct sock *sk = (struct sock *) chan->private;
- struct sock *sk_tun;
- int hdr_len;
- u16 udp_len;
- struct pppol2tp_session *session;
- struct pppol2tp_tunnel *tunnel;
- int rc;
- int headroom;
- int data_len = skb->len;
- struct inet_sock *inet;
- __wsum csum;
- struct udphdr *uh;
- unsigned int len;
- int old_headroom;
- int new_headroom;
-
- if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
- goto abort;
-
- /* Get session and tunnel contexts from the socket */
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto abort;
-
- sk_tun = session->tunnel_sock;
- if (sk_tun == NULL)
- goto abort_put_sess;
- tunnel = pppol2tp_sock_to_tunnel(sk_tun);
- if (tunnel == NULL)
- goto abort_put_sess;
-
- /* What header length is configured for this session? */
- hdr_len = pppol2tp_l2tp_header_len(session);
-
- /* Check that there's enough headroom in the skb to insert IP,
- * UDP and L2TP and PPP headers. If not enough, expand it to
- * make room. Adjust truesize.
- */
- headroom = NET_SKB_PAD + sizeof(struct iphdr) +
- sizeof(struct udphdr) + hdr_len + sizeof(ppph);
- old_headroom = skb_headroom(skb);
- if (skb_cow_head(skb, headroom))
- goto abort_put_sess_tun;
-
- new_headroom = skb_headroom(skb);
- skb_orphan(skb);
- skb->truesize += new_headroom - old_headroom;
-
- /* Setup PPP header */
- __skb_push(skb, sizeof(ppph));
- skb->data[0] = ppph[0];
- skb->data[1] = ppph[1];
-
- /* Setup L2TP header */
- pppol2tp_build_l2tp_header(session, __skb_push(skb, hdr_len));
-
- udp_len = sizeof(struct udphdr) + hdr_len + sizeof(ppph) + data_len;
-
- /* Setup UDP header */
- inet = inet_sk(sk_tun);
- __skb_push(skb, sizeof(*uh));
- skb_reset_transport_header(skb);
- uh = udp_hdr(skb);
- uh->source = inet->inet_sport;
- uh->dest = inet->inet_dport;
- uh->len = htons(udp_len);
- uh->check = 0;
-
- /* Debug */
- if (session->send_seq)
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %d bytes, ns=%hu\n", session->name,
- data_len, session->ns - 1);
- else
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %d bytes\n", session->name, data_len);
-
- if (session->debug & PPPOL2TP_MSG_DATA) {
- int i;
- unsigned char *datap = skb->data;
-
- printk(KERN_DEBUG "%s: xmit:", session->name);
- for (i = 0; i < data_len; i++) {
- printk(" %02X", *datap++);
- if (i == 31) {
- printk(" ...");
- break;
- }
- }
- printk("\n");
- }
-
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
- IPSKB_REROUTED);
- nf_reset(skb);
-
- /* Get routing info from the tunnel socket */
- skb_dst_drop(skb);
- skb_dst_set(skb, dst_clone(__sk_dst_get(sk_tun)));
- pppol2tp_skb_set_owner_w(skb, sk_tun);
-
- /* Calculate UDP checksum if configured to do so */
- if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
- skb->ip_summed = CHECKSUM_NONE;
- else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
- (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
- skb->ip_summed = CHECKSUM_COMPLETE;
- csum = skb_checksum(skb, 0, udp_len, 0);
- uh->check = csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, csum);
- if (uh->check == 0)
- uh->check = CSUM_MANGLED_0;
- } else {
- skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, 0);
- }
-
- /* Queue the packet to IP for output */
- len = skb->len;
- rc = ip_queue_xmit(skb, 1);
-
- /* Update stats */
- if (rc >= 0) {
- tunnel->stats.tx_packets++;
- tunnel->stats.tx_bytes += len;
- session->stats.tx_packets++;
- session->stats.tx_bytes += len;
- } else {
- tunnel->stats.tx_errors++;
- session->stats.tx_errors++;
- }
-
- sock_put(sk_tun);
- sock_put(sk);
- return 1;
-
-abort_put_sess_tun:
- sock_put(sk_tun);
-abort_put_sess:
- sock_put(sk);
-abort:
- /* Free the original skb */
- kfree_skb(skb);
- return 1;
-}
-
-/*****************************************************************************
- * Session (and tunnel control) socket create/destroy.
- *****************************************************************************/
-
-/* When the tunnel UDP socket is closed, all the attached sockets need to go
- * too.
- */
-static void pppol2tp_tunnel_closeall(struct pppol2tp_tunnel *tunnel)
-{
- int hash;
- struct hlist_node *walk;
- struct hlist_node *tmp;
- struct pppol2tp_session *session;
- struct sock *sk;
-
- BUG_ON(tunnel == NULL);
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: closing all sessions...\n", tunnel->name);
-
- write_lock_bh(&tunnel->hlist_lock);
- for (hash = 0; hash < PPPOL2TP_HASH_SIZE; hash++) {
-again:
- hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
- struct sk_buff *skb;
-
- session = hlist_entry(walk, struct pppol2tp_session, hlist);
-
- sk = session->sock;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: closing session\n", session->name);
-
- hlist_del_init(&session->hlist);
-
- /* Since we should hold the sock lock while
- * doing any unbinding, we need to release the
- * lock we're holding before taking that lock.
- * Hold a reference to the sock so it doesn't
- * disappear as we're jumping between locks.
- */
- sock_hold(sk);
- write_unlock_bh(&tunnel->hlist_lock);
- lock_sock(sk);
-
- if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
- pppox_unbind_sock(sk);
- sk->sk_state = PPPOX_DEAD;
- sk->sk_state_change(sk);
- }
-
- /* Purge any queued data */
- skb_queue_purge(&sk->sk_receive_queue);
- skb_queue_purge(&sk->sk_write_queue);
- while ((skb = skb_dequeue(&session->reorder_q))) {
- kfree_skb(skb);
- sock_put(sk);
- }
-
- release_sock(sk);
- sock_put(sk);
-
- /* Now restart from the beginning of this hash
- * chain. We always remove a session from the
- * list so we are guaranteed to make forward
- * progress.
- */
- write_lock_bh(&tunnel->hlist_lock);
- goto again;
- }
- }
- write_unlock_bh(&tunnel->hlist_lock);
-}
-
-/* Really kill the tunnel.
- * Come here only when all sessions have been cleared from the tunnel.
- */
-static void pppol2tp_tunnel_free(struct pppol2tp_tunnel *tunnel)
-{
- struct pppol2tp_net *pn = pppol2tp_pernet(tunnel->pppol2tp_net);
-
- /* Remove from socket list */
- write_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- list_del_init(&tunnel->list);
- write_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
-
- atomic_dec(&pppol2tp_tunnel_count);
- kfree(tunnel);
-}
-
-/* Tunnel UDP socket destruct hook.
- * The tunnel context is deleted only when all session sockets have been
- * closed.
- */
-static void pppol2tp_tunnel_destruct(struct sock *sk)
-{
- struct pppol2tp_tunnel *tunnel;
-
- tunnel = sk->sk_user_data;
- if (tunnel == NULL)
- goto end;
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: closing...\n", tunnel->name);
-
- /* Close all sessions */
- pppol2tp_tunnel_closeall(tunnel);
-
- /* No longer an encapsulation socket. See net/ipv4/udp.c */
- (udp_sk(sk))->encap_type = 0;
- (udp_sk(sk))->encap_rcv = NULL;
-
- /* Remove hooks into tunnel socket */
- tunnel->sock = NULL;
- sk->sk_destruct = tunnel->old_sk_destruct;
- sk->sk_user_data = NULL;
-
- /* Call original (UDP) socket descructor */
- if (sk->sk_destruct != NULL)
- (*sk->sk_destruct)(sk);
-
- pppol2tp_tunnel_dec_refcount(tunnel);
-
-end:
- return;
-}
-
-/* Really kill the session socket. (Called from sock_put() if
- * refcnt == 0.)
- */
-static void pppol2tp_session_destruct(struct sock *sk)
-{
- struct pppol2tp_session *session = NULL;
-
- if (sk->sk_user_data != NULL) {
- struct pppol2tp_tunnel *tunnel;
-
- session = sk->sk_user_data;
- if (session == NULL)
- goto out;
-
- BUG_ON(session->magic != L2TP_SESSION_MAGIC);
-
- /* Don't use pppol2tp_sock_to_tunnel() here to
- * get the tunnel context because the tunnel
- * socket might have already been closed (its
- * sk->sk_user_data will be NULL) so use the
- * session's private tunnel ptr instead.
- */
- tunnel = session->tunnel;
- if (tunnel != NULL) {
- BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-
- /* If session_id is zero, this is a null
- * session context, which was created for a
- * socket that is being used only to manage
- * tunnels.
- */
- if (session->tunnel_addr.s_session != 0) {
- /* Delete the session socket from the
- * hash
- */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_del_init(&session->hlist);
- write_unlock_bh(&tunnel->hlist_lock);
-
- atomic_dec(&pppol2tp_session_count);
- }
-
- /* This will delete the tunnel context if this
- * is the last session on the tunnel.
- */
- session->tunnel = NULL;
- session->tunnel_sock = NULL;
- pppol2tp_tunnel_dec_refcount(tunnel);
- }
- }
-
- kfree(session);
-out:
- return;
-}
-
-/* Called when the PPPoX socket (session) is closed.
- */
-static int pppol2tp_release(struct socket *sock)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session;
- int error;
-
- if (!sk)
- return 0;
-
- error = -EBADF;
- lock_sock(sk);
- if (sock_flag(sk, SOCK_DEAD) != 0)
- goto error;
-
- pppox_unbind_sock(sk);
-
- /* Signal the death of the socket. */
- sk->sk_state = PPPOX_DEAD;
- sock_orphan(sk);
- sock->sk = NULL;
-
- session = pppol2tp_sock_to_session(sk);
-
- /* Purge any queued data */
- skb_queue_purge(&sk->sk_receive_queue);
- skb_queue_purge(&sk->sk_write_queue);
- if (session != NULL) {
- struct sk_buff *skb;
- while ((skb = skb_dequeue(&session->reorder_q))) {
- kfree_skb(skb);
- sock_put(sk);
- }
- sock_put(sk);
- }
-
- release_sock(sk);
-
- /* This will delete the session context via
- * pppol2tp_session_destruct() if the socket's refcnt drops to
- * zero.
- */
- sock_put(sk);
-
- return 0;
-
-error:
- release_sock(sk);
- return error;
-}
-
-/* Internal function to prepare a tunnel (UDP) socket to have PPPoX
- * sockets attached to it.
- */
-static struct sock *pppol2tp_prepare_tunnel_socket(struct net *net,
- int fd, u16 tunnel_id, int *error)
-{
- int err;
- struct socket *sock = NULL;
- struct sock *sk;
- struct pppol2tp_tunnel *tunnel;
- struct pppol2tp_net *pn;
- struct sock *ret = NULL;
-
- /* Get the tunnel UDP socket from the fd, which was opened by
- * the userspace L2TP daemon.
- */
- err = -EBADF;
- sock = sockfd_lookup(fd, &err);
- if (!sock) {
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
- "tunl %hu: sockfd_lookup(fd=%d) returned %d\n",
- tunnel_id, fd, err);
- goto err;
- }
-
- sk = sock->sk;
-
- /* Quick sanity checks */
- err = -EPROTONOSUPPORT;
- if (sk->sk_protocol != IPPROTO_UDP) {
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
- "tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
- tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
- goto err;
- }
- err = -EAFNOSUPPORT;
- if (sock->ops->family != AF_INET) {
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
- "tunl %hu: fd %d wrong family, got %d, expected %d\n",
- tunnel_id, fd, sock->ops->family, AF_INET);
- goto err;
- }
-
- err = -ENOTCONN;
-
- /* Check if this socket has already been prepped */
- tunnel = (struct pppol2tp_tunnel *)sk->sk_user_data;
- if (tunnel != NULL) {
- /* User-data field already set */
- err = -EBUSY;
- BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-
- /* This socket has already been prepped */
- ret = tunnel->sock;
- goto out;
- }
-
- /* This socket is available and needs prepping. Create a new tunnel
- * context and init it.
- */
- sk->sk_user_data = tunnel = kzalloc(sizeof(struct pppol2tp_tunnel), GFP_KERNEL);
- if (sk->sk_user_data == NULL) {
- err = -ENOMEM;
- goto err;
- }
-
- tunnel->magic = L2TP_TUNNEL_MAGIC;
- sprintf(&tunnel->name[0], "tunl %hu", tunnel_id);
-
- tunnel->stats.tunnel_id = tunnel_id;
- tunnel->debug = PPPOL2TP_DEFAULT_DEBUG_FLAGS;
-
- /* Hook on the tunnel socket destructor so that we can cleanup
- * if the tunnel socket goes away.
- */
- tunnel->old_sk_destruct = sk->sk_destruct;
- sk->sk_destruct = pppol2tp_tunnel_destruct;
-
- tunnel->sock = sk;
- sk->sk_allocation = GFP_ATOMIC;
-
- /* Misc init */
- rwlock_init(&tunnel->hlist_lock);
-
- /* The net we belong to */
- tunnel->pppol2tp_net = net;
- pn = pppol2tp_pernet(net);
-
- /* Add tunnel to our list */
- INIT_LIST_HEAD(&tunnel->list);
- write_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- list_add(&tunnel->list, &pn->pppol2tp_tunnel_list);
- write_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
- atomic_inc(&pppol2tp_tunnel_count);
-
- /* Bump the reference count. The tunnel context is deleted
- * only when this drops to zero.
- */
- pppol2tp_tunnel_inc_refcount(tunnel);
-
- /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
- (udp_sk(sk))->encap_type = UDP_ENCAP_L2TPINUDP;
- (udp_sk(sk))->encap_rcv = pppol2tp_udp_encap_recv;
-
- ret = tunnel->sock;
-
- *error = 0;
-out:
- if (sock)
- sockfd_put(sock);
-
- return ret;
-
-err:
- *error = err;
- goto out;
-}
-
-static struct proto pppol2tp_sk_proto = {
- .name = "PPPOL2TP",
- .owner = THIS_MODULE,
- .obj_size = sizeof(struct pppox_sock),
-};
-
-/* socket() handler. Initialize a new struct sock.
- */
-static int pppol2tp_create(struct net *net, struct socket *sock)
-{
- int error = -ENOMEM;
- struct sock *sk;
-
- sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto);
- if (!sk)
- goto out;
-
- sock_init_data(sock, sk);
-
- sock->state = SS_UNCONNECTED;
- sock->ops = &pppol2tp_ops;
-
- sk->sk_backlog_rcv = pppol2tp_recv_core;
- sk->sk_protocol = PX_PROTO_OL2TP;
- sk->sk_family = PF_PPPOX;
- sk->sk_state = PPPOX_NONE;
- sk->sk_type = SOCK_STREAM;
- sk->sk_destruct = pppol2tp_session_destruct;
-
- error = 0;
-
-out:
- return error;
-}
-
-/* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
- */
-static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
- int sockaddr_len, int flags)
-{
- struct sock *sk = sock->sk;
- struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
- struct pppox_sock *po = pppox_sk(sk);
- struct sock *tunnel_sock = NULL;
- struct pppol2tp_session *session = NULL;
- struct pppol2tp_tunnel *tunnel;
- struct dst_entry *dst;
- int error = 0;
-
- lock_sock(sk);
-
- error = -EINVAL;
- if (sp->sa_protocol != PX_PROTO_OL2TP)
- goto end;
-
- /* Check for already bound sockets */
- error = -EBUSY;
- if (sk->sk_state & PPPOX_CONNECTED)
- goto end;
-
- /* We don't supporting rebinding anyway */
- error = -EALREADY;
- if (sk->sk_user_data)
- goto end; /* socket is already attached */
-
- /* Don't bind if s_tunnel is 0 */
- error = -EINVAL;
- if (sp->pppol2tp.s_tunnel == 0)
- goto end;
-
- /* Special case: prepare tunnel socket if s_session and
- * d_session is 0. Otherwise look up tunnel using supplied
- * tunnel id.
- */
- if ((sp->pppol2tp.s_session == 0) && (sp->pppol2tp.d_session == 0)) {
- tunnel_sock = pppol2tp_prepare_tunnel_socket(sock_net(sk),
- sp->pppol2tp.fd,
- sp->pppol2tp.s_tunnel,
- &error);
- if (tunnel_sock == NULL)
- goto end;
-
- sock_hold(tunnel_sock);
- tunnel = tunnel_sock->sk_user_data;
- } else {
- tunnel = pppol2tp_tunnel_find(sock_net(sk), sp->pppol2tp.s_tunnel);
-
- /* Error if we can't find the tunnel */
- error = -ENOENT;
- if (tunnel == NULL)
- goto end;
-
- tunnel_sock = tunnel->sock;
- }
-
- /* Check that this session doesn't already exist */
- error = -EEXIST;
- session = pppol2tp_session_find(tunnel, sp->pppol2tp.s_session);
- if (session != NULL)
- goto end;
-
- /* Allocate and initialize a new session context. */
- session = kzalloc(sizeof(struct pppol2tp_session), GFP_KERNEL);
- if (session == NULL) {
- error = -ENOMEM;
- goto end;
- }
-
- skb_queue_head_init(&session->reorder_q);
-
- session->magic = L2TP_SESSION_MAGIC;
- session->owner = current->pid;
- session->sock = sk;
- session->tunnel = tunnel;
- session->tunnel_sock = tunnel_sock;
- session->tunnel_addr = sp->pppol2tp;
- sprintf(&session->name[0], "sess %hu/%hu",
- session->tunnel_addr.s_tunnel,
- session->tunnel_addr.s_session);
-
- session->stats.tunnel_id = session->tunnel_addr.s_tunnel;
- session->stats.session_id = session->tunnel_addr.s_session;
-
- INIT_HLIST_NODE(&session->hlist);
-
- /* Inherit debug options from tunnel */
- session->debug = tunnel->debug;
-
- /* Default MTU must allow space for UDP/L2TP/PPP
- * headers.
- */
- session->mtu = session->mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
-
- /* If PMTU discovery was enabled, use the MTU that was discovered */
- dst = sk_dst_get(sk);
- if (dst != NULL) {
- u32 pmtu = dst_mtu(__sk_dst_get(sk));
- if (pmtu != 0)
- session->mtu = session->mru = pmtu -
- PPPOL2TP_HEADER_OVERHEAD;
- dst_release(dst);
- }
-
- /* Special case: if source & dest session_id == 0x0000, this socket is
- * being created to manage the tunnel. Don't add the session to the
- * session hash list, just set up the internal context for use by
- * ioctl() and sockopt() handlers.
- */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- error = 0;
- sk->sk_user_data = session;
- goto out_no_ppp;
- }
-
- /* Get tunnel context from the tunnel socket */
- tunnel = pppol2tp_sock_to_tunnel(tunnel_sock);
- if (tunnel == NULL) {
- error = -EBADF;
- goto end;
- }
-
- /* Right now, because we don't have a way to push the incoming skb's
- * straight through the UDP layer, the only header we need to worry
- * about is the L2TP header. This size is different depending on
- * whether sequence numbers are enabled for the data channel.
- */
- po->chan.hdrlen = PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
-
- po->chan.private = sk;
- po->chan.ops = &pppol2tp_chan_ops;
- po->chan.mtu = session->mtu;
-
- error = ppp_register_net_channel(sock_net(sk), &po->chan);
- if (error)
- goto end_put_tun;
-
- /* This is how we get the session context from the socket. */
- sk->sk_user_data = session;
-
- /* Add session to the tunnel's hash list */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_add_head(&session->hlist,
- pppol2tp_session_id_hash(tunnel,
- session->tunnel_addr.s_session));
- write_unlock_bh(&tunnel->hlist_lock);
-
- atomic_inc(&pppol2tp_session_count);
-
-out_no_ppp:
- pppol2tp_tunnel_inc_refcount(tunnel);
- sk->sk_state = PPPOX_CONNECTED;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: created\n", session->name);
-
-end_put_tun:
- sock_put(tunnel_sock);
-end:
- release_sock(sk);
-
- if (error != 0) {
- if (session)
- PRINTK(session->debug,
- PPPOL2TP_MSG_CONTROL, KERN_WARNING,
- "%s: connect failed: %d\n",
- session->name, error);
- else
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_WARNING,
- "connect failed: %d\n", error);
- }
-
- return error;
-}
-
-/* getname() support.
- */
-static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
- int *usockaddr_len, int peer)
-{
- int len = sizeof(struct sockaddr_pppol2tp);
- struct sockaddr_pppol2tp sp;
- int error = 0;
- struct pppol2tp_session *session;
-
- error = -ENOTCONN;
- if (sock->sk->sk_state != PPPOX_CONNECTED)
- goto end;
-
- session = pppol2tp_sock_to_session(sock->sk);
- if (session == NULL) {
- error = -EBADF;
- goto end;
- }
-
- sp.sa_family = AF_PPPOX;
- sp.sa_protocol = PX_PROTO_OL2TP;
- memcpy(&sp.pppol2tp, &session->tunnel_addr,
- sizeof(struct pppol2tp_addr));
-
- memcpy(uaddr, &sp, len);
-
- *usockaddr_len = len;
-
- error = 0;
- sock_put(sock->sk);
-
-end:
- return error;
-}
-
-/****************************************************************************
- * ioctl() handlers.
- *
- * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
- * sockets. However, in order to control kernel tunnel features, we allow
- * userspace to create a special "tunnel" PPPoX socket which is used for
- * control only. Tunnel PPPoX sockets have session_id == 0 and simply allow
- * the user application to issue L2TP setsockopt(), getsockopt() and ioctl()
- * calls.
- ****************************************************************************/
-
-/* Session ioctl helper.
- */
-static int pppol2tp_session_ioctl(struct pppol2tp_session *session,
- unsigned int cmd, unsigned long arg)
-{
- struct ifreq ifr;
- int err = 0;
- struct sock *sk = session->sock;
- int val = (int) arg;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
- "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
- session->name, cmd, arg);
-
- sock_hold(sk);
-
- switch (cmd) {
- case SIOCGIFMTU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
- break;
- ifr.ifr_mtu = session->mtu;
- if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq)))
- break;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get mtu=%d\n", session->name, session->mtu);
- err = 0;
- break;
-
- case SIOCSIFMTU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
- break;
-
- session->mtu = ifr.ifr_mtu;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set mtu=%d\n", session->name, session->mtu);
- err = 0;
- break;
-
- case PPPIOCGMRU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (put_user(session->mru, (int __user *) arg))
- break;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get mru=%d\n", session->name, session->mru);
- err = 0;
- break;
-
- case PPPIOCSMRU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (get_user(val,(int __user *) arg))
- break;
-
- session->mru = val;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set mru=%d\n", session->name, session->mru);
- err = 0;
- break;
-
- case PPPIOCGFLAGS:
- err = -EFAULT;
- if (put_user(session->flags, (int __user *) arg))
- break;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get flags=%d\n", session->name, session->flags);
- err = 0;
- break;
-
- case PPPIOCSFLAGS:
- err = -EFAULT;
- if (get_user(val, (int __user *) arg))
- break;
- session->flags = val;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set flags=%d\n", session->name, session->flags);
- err = 0;
- break;
-
- case PPPIOCGL2TPSTATS:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- if (copy_to_user((void __user *) arg, &session->stats,
- sizeof(session->stats)))
- break;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get L2TP stats\n", session->name);
- err = 0;
- break;
-
- default:
- err = -ENOSYS;
- break;
- }
-
- sock_put(sk);
-
- return err;
-}
-
-/* Tunnel ioctl helper.
- *
- * Note the special handling for PPPIOCGL2TPSTATS below. If the ioctl data
- * specifies a session_id, the session ioctl handler is called. This allows an
- * application to retrieve session stats via a tunnel socket.
- */
-static int pppol2tp_tunnel_ioctl(struct pppol2tp_tunnel *tunnel,
- unsigned int cmd, unsigned long arg)
-{
- int err = 0;
- struct sock *sk = tunnel->sock;
- struct pppol2tp_ioc_stats stats_req;
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
- "%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n", tunnel->name,
- cmd, arg);
-
- sock_hold(sk);
-
- switch (cmd) {
- case PPPIOCGL2TPSTATS:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- if (copy_from_user(&stats_req, (void __user *) arg,
- sizeof(stats_req))) {
- err = -EFAULT;
- break;
- }
- if (stats_req.session_id != 0) {
- /* resend to session ioctl handler */
- struct pppol2tp_session *session =
- pppol2tp_session_find(tunnel, stats_req.session_id);
- if (session != NULL)
- err = pppol2tp_session_ioctl(session, cmd, arg);
- else
- err = -EBADR;
- break;
- }
-#ifdef CONFIG_XFRM
- tunnel->stats.using_ipsec = (sk->sk_policy[0] || sk->sk_policy[1]) ? 1 : 0;
-#endif
- if (copy_to_user((void __user *) arg, &tunnel->stats,
- sizeof(tunnel->stats))) {
- err = -EFAULT;
- break;
- }
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get L2TP stats\n", tunnel->name);
- err = 0;
- break;
-
- default:
- err = -ENOSYS;
- break;
- }
-
- sock_put(sk);
-
- return err;
-}
-
-/* Main ioctl() handler.
- * Dispatch to tunnel or session helpers depending on the socket.
- */
-static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
- unsigned long arg)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session;
- struct pppol2tp_tunnel *tunnel;
- int err;
-
- if (!sk)
- return 0;
-
- err = -EBADF;
- if (sock_flag(sk, SOCK_DEAD) != 0)
- goto end;
-
- err = -ENOTCONN;
- if ((sk->sk_user_data == NULL) ||
- (!(sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND))))
- goto end;
-
- /* Get session context from the socket */
- err = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto end;
-
- /* Special case: if session's session_id is zero, treat ioctl as a
- * tunnel ioctl
- */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- err = -EBADF;
- tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
- if (tunnel == NULL)
- goto end_put_sess;
-
- err = pppol2tp_tunnel_ioctl(tunnel, cmd, arg);
- sock_put(session->tunnel_sock);
- goto end_put_sess;
- }
-
- err = pppol2tp_session_ioctl(session, cmd, arg);
-
-end_put_sess:
- sock_put(sk);
-end:
- return err;
-}
-
-/*****************************************************************************
- * setsockopt() / getsockopt() support.
- *
- * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
- * sockets. In order to control kernel tunnel features, we allow userspace to
- * create a special "tunnel" PPPoX socket which is used for control only.
- * Tunnel PPPoX sockets have session_id == 0 and simply allow the user
- * application to issue L2TP setsockopt(), getsockopt() and ioctl() calls.
- *****************************************************************************/
-
-/* Tunnel setsockopt() helper.
- */
-static int pppol2tp_tunnel_setsockopt(struct sock *sk,
- struct pppol2tp_tunnel *tunnel,
- int optname, int val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_DEBUG:
- tunnel->debug = val;
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set debug=%x\n", tunnel->name, tunnel->debug);
- break;
-
- default:
- err = -ENOPROTOOPT;
- break;
- }
-
- return err;
-}
-
-/* Session setsockopt helper.
- */
-static int pppol2tp_session_setsockopt(struct sock *sk,
- struct pppol2tp_session *session,
- int optname, int val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_RECVSEQ:
- if ((val != 0) && (val != 1)) {
- err = -EINVAL;
- break;
- }
- session->recv_seq = val ? -1 : 0;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set recv_seq=%d\n", session->name,
- session->recv_seq);
- break;
-
- case PPPOL2TP_SO_SENDSEQ:
- if ((val != 0) && (val != 1)) {
- err = -EINVAL;
- break;
- }
- session->send_seq = val ? -1 : 0;
- {
- struct sock *ssk = session->sock;
- struct pppox_sock *po = pppox_sk(ssk);
- po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
- PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
- }
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set send_seq=%d\n", session->name, session->send_seq);
- break;
-
- case PPPOL2TP_SO_LNSMODE:
- if ((val != 0) && (val != 1)) {
- err = -EINVAL;
- break;
- }
- session->lns_mode = val ? -1 : 0;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set lns_mode=%d\n", session->name,
- session->lns_mode);
- break;
-
- case PPPOL2TP_SO_DEBUG:
- session->debug = val;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set debug=%x\n", session->name, session->debug);
- break;
-
- case PPPOL2TP_SO_REORDERTO:
- session->reorder_timeout = msecs_to_jiffies(val);
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set reorder_timeout=%d\n", session->name,
- session->reorder_timeout);
- break;
-
- default:
- err = -ENOPROTOOPT;
- break;
- }
-
- return err;
-}
-
-/* Main setsockopt() entry point.
- * Does API checks, then calls either the tunnel or session setsockopt
- * handler, according to whether the PPPoL2TP socket is a for a regular
- * session or the special tunnel type.
- */
-static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session = sk->sk_user_data;
- struct pppol2tp_tunnel *tunnel;
- int val;
- int err;
-
- if (level != SOL_PPPOL2TP)
- return udp_prot.setsockopt(sk, level, optname, optval, optlen);
-
- if (optlen < sizeof(int))
- return -EINVAL;
-
- if (get_user(val, (int __user *)optval))
- return -EFAULT;
-
- err = -ENOTCONN;
- if (sk->sk_user_data == NULL)
- goto end;
-
- /* Get session context from the socket */
- err = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto end;
-
- /* Special case: if session_id == 0x0000, treat as operation on tunnel
- */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- err = -EBADF;
- tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
- if (tunnel == NULL)
- goto end_put_sess;
-
- err = pppol2tp_tunnel_setsockopt(sk, tunnel, optname, val);
- sock_put(session->tunnel_sock);
- } else
- err = pppol2tp_session_setsockopt(sk, session, optname, val);
-
- err = 0;
-
-end_put_sess:
- sock_put(sk);
-end:
- return err;
-}
-
-/* Tunnel getsockopt helper. Called with sock locked.
- */
-static int pppol2tp_tunnel_getsockopt(struct sock *sk,
- struct pppol2tp_tunnel *tunnel,
- int optname, int *val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_DEBUG:
- *val = tunnel->debug;
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get debug=%x\n", tunnel->name, tunnel->debug);
- break;
-
- default:
- err = -ENOPROTOOPT;
- break;
- }
-
- return err;
-}
-
-/* Session getsockopt helper. Called with sock locked.
- */
-static int pppol2tp_session_getsockopt(struct sock *sk,
- struct pppol2tp_session *session,
- int optname, int *val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_RECVSEQ:
- *val = session->recv_seq;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get recv_seq=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_SENDSEQ:
- *val = session->send_seq;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get send_seq=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_LNSMODE:
- *val = session->lns_mode;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get lns_mode=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_DEBUG:
- *val = session->debug;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get debug=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_REORDERTO:
- *val = (int) jiffies_to_msecs(session->reorder_timeout);
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get reorder_timeout=%d\n", session->name, *val);
- break;
-
- default:
- err = -ENOPROTOOPT;
- }
-
- return err;
-}
-
-/* Main getsockopt() entry point.
- * Does API checks, then calls either the tunnel or session getsockopt
- * handler, according to whether the PPPoX socket is a for a regular session
- * or the special tunnel type.
- */
-static int pppol2tp_getsockopt(struct socket *sock, int level,
- int optname, char __user *optval, int __user *optlen)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session = sk->sk_user_data;
- struct pppol2tp_tunnel *tunnel;
- int val, len;
- int err;
-
- if (level != SOL_PPPOL2TP)
- return udp_prot.getsockopt(sk, level, optname, optval, optlen);
-
- if (get_user(len, (int __user *) optlen))
- return -EFAULT;
-
- len = min_t(unsigned int, len, sizeof(int));
-
- if (len < 0)
- return -EINVAL;
-
- err = -ENOTCONN;
- if (sk->sk_user_data == NULL)
- goto end;
-
- /* Get the session context */
- err = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto end;
-
- /* Special case: if session_id == 0x0000, treat as operation on tunnel */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- err = -EBADF;
- tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
- if (tunnel == NULL)
- goto end_put_sess;
-
- err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val);
- sock_put(session->tunnel_sock);
- } else
- err = pppol2tp_session_getsockopt(sk, session, optname, &val);
-
- err = -EFAULT;
- if (put_user(len, (int __user *) optlen))
- goto end_put_sess;
-
- if (copy_to_user((void __user *) optval, &val, len))
- goto end_put_sess;
-
- err = 0;
-
-end_put_sess:
- sock_put(sk);
-end:
- return err;
-}
-
-/*****************************************************************************
- * /proc filesystem for debug
- *****************************************************************************/
-
-#ifdef CONFIG_PROC_FS
-
-#include <linux/seq_file.h>
-
-struct pppol2tp_seq_data {
- struct seq_net_private p;
- struct pppol2tp_tunnel *tunnel; /* current tunnel */
- struct pppol2tp_session *session; /* NULL means get first session in tunnel */
-};
-
-static struct pppol2tp_session *next_session(struct pppol2tp_tunnel *tunnel, struct pppol2tp_session *curr)
-{
- struct pppol2tp_session *session = NULL;
- struct hlist_node *walk;
- int found = 0;
- int next = 0;
- int i;
-
- read_lock_bh(&tunnel->hlist_lock);
- for (i = 0; i < PPPOL2TP_HASH_SIZE; i++) {
- hlist_for_each_entry(session, walk, &tunnel->session_hlist[i], hlist) {
- if (curr == NULL) {
- found = 1;
- goto out;
- }
- if (session == curr) {
- next = 1;
- continue;
- }
- if (next) {
- found = 1;
- goto out;
- }
- }
- }
-out:
- read_unlock_bh(&tunnel->hlist_lock);
- if (!found)
- session = NULL;
-
- return session;
-}
-
-static struct pppol2tp_tunnel *next_tunnel(struct pppol2tp_net *pn,
- struct pppol2tp_tunnel *curr)
-{
- struct pppol2tp_tunnel *tunnel = NULL;
-
- read_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- if (list_is_last(&curr->list, &pn->pppol2tp_tunnel_list)) {
- goto out;
- }
- tunnel = list_entry(curr->list.next, struct pppol2tp_tunnel, list);
-out:
- read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
-
- return tunnel;
-}
-
-static void *pppol2tp_seq_start(struct seq_file *m, loff_t *offs)
-{
- struct pppol2tp_seq_data *pd = SEQ_START_TOKEN;
- struct pppol2tp_net *pn;
- loff_t pos = *offs;
-
- if (!pos)
- goto out;
-
- BUG_ON(m->private == NULL);
- pd = m->private;
- pn = pppol2tp_pernet(seq_file_net(m));
-
- if (pd->tunnel == NULL) {
- if (!list_empty(&pn->pppol2tp_tunnel_list))
- pd->tunnel = list_entry(pn->pppol2tp_tunnel_list.next, struct pppol2tp_tunnel, list);
- } else {
- pd->session = next_session(pd->tunnel, pd->session);
- if (pd->session == NULL) {
- pd->tunnel = next_tunnel(pn, pd->tunnel);
- }
- }
-
- /* NULL tunnel and session indicates end of list */
- if ((pd->tunnel == NULL) && (pd->session == NULL))
- pd = NULL;
-
-out:
- return pd;
-}
-
-static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
-{
- (*pos)++;
- return NULL;
-}
-
-static void pppol2tp_seq_stop(struct seq_file *p, void *v)
-{
- /* nothing to do */
-}
-
-static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
-{
- struct pppol2tp_tunnel *tunnel = v;
-
- seq_printf(m, "\nTUNNEL '%s', %c %d\n",
- tunnel->name,
- (tunnel == tunnel->sock->sk_user_data) ? 'Y':'N',
- atomic_read(&tunnel->ref_count) - 1);
- seq_printf(m, " %08x %llu/%llu/%llu %llu/%llu/%llu\n",
- tunnel->debug,
- (unsigned long long)tunnel->stats.tx_packets,
- (unsigned long long)tunnel->stats.tx_bytes,
- (unsigned long long)tunnel->stats.tx_errors,
- (unsigned long long)tunnel->stats.rx_packets,
- (unsigned long long)tunnel->stats.rx_bytes,
- (unsigned long long)tunnel->stats.rx_errors);
-}
-
-static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
-{
- struct pppol2tp_session *session = v;
-
- seq_printf(m, " SESSION '%s' %08X/%d %04X/%04X -> "
- "%04X/%04X %d %c\n",
- session->name,
- ntohl(session->tunnel_addr.addr.sin_addr.s_addr),
- ntohs(session->tunnel_addr.addr.sin_port),
- session->tunnel_addr.s_tunnel,
- session->tunnel_addr.s_session,
- session->tunnel_addr.d_tunnel,
- session->tunnel_addr.d_session,
- session->sock->sk_state,
- (session == session->sock->sk_user_data) ?
- 'Y' : 'N');
- seq_printf(m, " %d/%d/%c/%c/%s %08x %u\n",
- session->mtu, session->mru,
- session->recv_seq ? 'R' : '-',
- session->send_seq ? 'S' : '-',
- session->lns_mode ? "LNS" : "LAC",
- session->debug,
- jiffies_to_msecs(session->reorder_timeout));
- seq_printf(m, " %hu/%hu %llu/%llu/%llu %llu/%llu/%llu\n",
- session->nr, session->ns,
- (unsigned long long)session->stats.tx_packets,
- (unsigned long long)session->stats.tx_bytes,
- (unsigned long long)session->stats.tx_errors,
- (unsigned long long)session->stats.rx_packets,
- (unsigned long long)session->stats.rx_bytes,
- (unsigned long long)session->stats.rx_errors);
-}
-
-static int pppol2tp_seq_show(struct seq_file *m, void *v)
-{
- struct pppol2tp_seq_data *pd = v;
-
- /* display header on line 1 */
- if (v == SEQ_START_TOKEN) {
- seq_puts(m, "PPPoL2TP driver info, " PPPOL2TP_DRV_VERSION "\n");
- seq_puts(m, "TUNNEL name, user-data-ok session-count\n");
- seq_puts(m, " debug tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
- seq_puts(m, " SESSION name, addr/port src-tid/sid "
- "dest-tid/sid state user-data-ok\n");
- seq_puts(m, " mtu/mru/rcvseq/sendseq/lns debug reorderto\n");
- seq_puts(m, " nr/ns tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
- goto out;
- }
-
- /* Show the tunnel or session context.
- */
- if (pd->session == NULL)
- pppol2tp_seq_tunnel_show(m, pd->tunnel);
- else
- pppol2tp_seq_session_show(m, pd->session);
-
-out:
- return 0;
-}
-
-static const struct seq_operations pppol2tp_seq_ops = {
- .start = pppol2tp_seq_start,
- .next = pppol2tp_seq_next,
- .stop = pppol2tp_seq_stop,
- .show = pppol2tp_seq_show,
-};
-
-/* Called when our /proc file is opened. We allocate data for use when
- * iterating our tunnel / session contexts and store it in the private
- * data of the seq_file.
- */
-static int pppol2tp_proc_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &pppol2tp_seq_ops,
- sizeof(struct pppol2tp_seq_data));
-}
-
-static const struct file_operations pppol2tp_proc_fops = {
- .owner = THIS_MODULE,
- .open = pppol2tp_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-#endif /* CONFIG_PROC_FS */
-
-/*****************************************************************************
- * Init and cleanup
- *****************************************************************************/
-
-static const struct proto_ops pppol2tp_ops = {
- .family = AF_PPPOX,
- .owner = THIS_MODULE,
- .release = pppol2tp_release,
- .bind = sock_no_bind,
- .connect = pppol2tp_connect,
- .socketpair = sock_no_socketpair,
- .accept = sock_no_accept,
- .getname = pppol2tp_getname,
- .poll = datagram_poll,
- .listen = sock_no_listen,
- .shutdown = sock_no_shutdown,
- .setsockopt = pppol2tp_setsockopt,
- .getsockopt = pppol2tp_getsockopt,
- .sendmsg = pppol2tp_sendmsg,
- .recvmsg = pppol2tp_recvmsg,
- .mmap = sock_no_mmap,
- .ioctl = pppox_ioctl,
-};
-
-static struct pppox_proto pppol2tp_proto = {
- .create = pppol2tp_create,
- .ioctl = pppol2tp_ioctl
-};
-
-static __net_init int pppol2tp_init_net(struct net *net)
-{
- struct pppol2tp_net *pn = pppol2tp_pernet(net);
- struct proc_dir_entry *pde;
-
- INIT_LIST_HEAD(&pn->pppol2tp_tunnel_list);
- rwlock_init(&pn->pppol2tp_tunnel_list_lock);
-
- pde = proc_net_fops_create(net, "pppol2tp", S_IRUGO, &pppol2tp_proc_fops);
-#ifdef CONFIG_PROC_FS
- if (!pde)
- return -ENOMEM;
-#endif
-
- return 0;
-}
-
-static __net_exit void pppol2tp_exit_net(struct net *net)
-{
- proc_net_remove(net, "pppol2tp");
-}
-
-static struct pernet_operations pppol2tp_net_ops = {
- .init = pppol2tp_init_net,
- .exit = pppol2tp_exit_net,
- .id = &pppol2tp_net_id,
- .size = sizeof(struct pppol2tp_net),
-};
-
-static int __init pppol2tp_init(void)
-{
- int err;
-
- err = proto_register(&pppol2tp_sk_proto, 0);
- if (err)
- goto out;
- err = register_pppox_proto(PX_PROTO_OL2TP, &pppol2tp_proto);
- if (err)
- goto out_unregister_pppol2tp_proto;
-
- err = register_pernet_device(&pppol2tp_net_ops);
- if (err)
- goto out_unregister_pppox_proto;
-
- printk(KERN_INFO "PPPoL2TP kernel driver, %s\n",
- PPPOL2TP_DRV_VERSION);
-
-out:
- return err;
-out_unregister_pppox_proto:
- unregister_pppox_proto(PX_PROTO_OL2TP);
-out_unregister_pppol2tp_proto:
- proto_unregister(&pppol2tp_sk_proto);
- goto out;
-}
-
-static void __exit pppol2tp_exit(void)
-{
- unregister_pppox_proto(PX_PROTO_OL2TP);
- unregister_pernet_device(&pppol2tp_net_ops);
- proto_unregister(&pppol2tp_sk_proto);
-}
-
-module_init(pppol2tp_init);
-module_exit(pppol2tp_exit);
-
-MODULE_AUTHOR("Martijn van Oosterhout <kleptog@svana.org>, "
- "James Chapman <jchapman@katalix.com>");
-MODULE_DESCRIPTION("PPP over L2TP over UDP");
-MODULE_LICENSE("GPL");
-MODULE_VERSION(PPPOL2TP_DRV_VERSION);
diff --git a/net/Makefile b/net/Makefile
index 1542e72..16d29aa 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_BT) += bluetooth/
obj-$(CONFIG_SUNRPC) += sunrpc/
obj-$(CONFIG_AF_RXRPC) += rxrpc/
obj-$(CONFIG_ATM) += atm/
+obj-$(CONFIG_PPPOL2TP) += l2tp/
obj-$(CONFIG_DECNET) += decnet/
obj-$(CONFIG_ECONET) += econet/
obj-$(CONFIG_PHONET) += phonet/
diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
new file mode 100644
index 0000000..9af41e8
--- /dev/null
+++ b/net/l2tp/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the L2TP.
+#
+
+obj-$(CONFIG_PPPOL2TP) += pppol2tp.o
diff --git a/net/l2tp/pppol2tp.c b/net/l2tp/pppol2tp.c
new file mode 100644
index 0000000..449a982
--- /dev/null
+++ b/net/l2tp/pppol2tp.c
@@ -0,0 +1,2680 @@
+/*****************************************************************************
+ * Linux PPP over L2TP (PPPoX/PPPoL2TP) Sockets
+ *
+ * PPPoX --- Generic PPP encapsulation socket family
+ * PPPoL2TP --- PPP over L2TP (RFC 2661)
+ *
+ * Version: 1.0.0
+ *
+ * Authors: Martijn van Oosterhout <kleptog@svana.org>
+ * James Chapman (jchapman@katalix.com)
+ * Contributors:
+ * Michal Ostrowski <mostrows@speakeasy.net>
+ * Arnaldo Carvalho de Melo <acme@xconectiva.com.br>
+ * David S. Miller (davem@redhat.com)
+ *
+ * License:
+ * 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.
+ *
+ */
+
+/* This driver handles only L2TP data frames; control frames are handled by a
+ * userspace application.
+ *
+ * To send data in an L2TP session, userspace opens a PPPoL2TP socket and
+ * attaches it to a bound UDP socket with local tunnel_id / session_id and
+ * peer tunnel_id / session_id set. Data can then be sent or received using
+ * regular socket sendmsg() / recvmsg() calls. Kernel parameters of the socket
+ * can be read or modified using ioctl() or [gs]etsockopt() calls.
+ *
+ * When a PPPoL2TP socket is connected with local and peer session_id values
+ * zero, the socket is treated as a special tunnel management socket.
+ *
+ * Here's example userspace code to create a socket for sending/receiving data
+ * over an L2TP session:-
+ *
+ * struct sockaddr_pppol2tp sax;
+ * int fd;
+ * int session_fd;
+ *
+ * fd = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP);
+ *
+ * sax.sa_family = AF_PPPOX;
+ * sax.sa_protocol = PX_PROTO_OL2TP;
+ * sax.pppol2tp.fd = tunnel_fd; // bound UDP socket
+ * sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr;
+ * sax.pppol2tp.addr.sin_port = addr->sin_port;
+ * sax.pppol2tp.addr.sin_family = AF_INET;
+ * sax.pppol2tp.s_tunnel = tunnel_id;
+ * sax.pppol2tp.s_session = session_id;
+ * sax.pppol2tp.d_tunnel = peer_tunnel_id;
+ * sax.pppol2tp.d_session = peer_session_id;
+ *
+ * session_fd = connect(fd, (struct sockaddr *)&sax, sizeof(sax));
+ *
+ * A pppd plugin that allows PPP traffic to be carried over L2TP using
+ * this driver is available from the OpenL2TP project at
+ * http://openl2tp.sourceforge.net.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include <asm/uaccess.h>
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/jiffies.h>
+
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/if_pppox.h>
+#include <linux/if_pppol2tp.h>
+#include <net/sock.h>
+#include <linux/ppp_channel.h>
+#include <linux/ppp_defs.h>
+#include <linux/if_ppp.h>
+#include <linux/file.h>
+#include <linux/hash.h>
+#include <linux/sort.h>
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include <asm/byteorder.h>
+#include <asm/atomic.h>
+
+
+#define PPPOL2TP_DRV_VERSION "V1.0"
+
+/* L2TP header constants */
+#define L2TP_HDRFLAG_T 0x8000
+#define L2TP_HDRFLAG_L 0x4000
+#define L2TP_HDRFLAG_S 0x0800
+#define L2TP_HDRFLAG_O 0x0200
+#define L2TP_HDRFLAG_P 0x0100
+
+#define L2TP_HDR_VER_MASK 0x000F
+#define L2TP_HDR_VER 0x0002
+
+/* Space for UDP, L2TP and PPP headers */
+#define PPPOL2TP_HEADER_OVERHEAD 40
+
+/* Just some random numbers */
+#define L2TP_TUNNEL_MAGIC 0x42114DDA
+#define L2TP_SESSION_MAGIC 0x0C04EB7D
+
+#define PPPOL2TP_HASH_BITS 4
+#define PPPOL2TP_HASH_SIZE (1 << PPPOL2TP_HASH_BITS)
+
+/* Default trace flags */
+#define PPPOL2TP_DEFAULT_DEBUG_FLAGS 0
+
+#define PRINTK(_mask, _type, _lvl, _fmt, args...) \
+ do { \
+ if ((_mask) & (_type)) \
+ printk(_lvl "PPPOL2TP: " _fmt, ##args); \
+ } while(0)
+
+/* Number of bytes to build transmit L2TP headers.
+ * Unfortunately the size is different depending on whether sequence numbers
+ * are enabled.
+ */
+#define PPPOL2TP_L2TP_HDR_SIZE_SEQ 10
+#define PPPOL2TP_L2TP_HDR_SIZE_NOSEQ 6
+
+struct pppol2tp_tunnel;
+
+/* Describes a session. It is the sk_user_data field in the PPPoL2TP
+ * socket. Contains information to determine incoming packets and transmit
+ * outgoing ones.
+ */
+struct pppol2tp_session
+{
+ int magic; /* should be
+ * L2TP_SESSION_MAGIC */
+ int owner; /* pid that opened the socket */
+
+ struct sock *sock; /* Pointer to the session
+ * PPPoX socket */
+ struct sock *tunnel_sock; /* Pointer to the tunnel UDP
+ * socket */
+
+ struct pppol2tp_addr tunnel_addr; /* Description of tunnel */
+
+ struct pppol2tp_tunnel *tunnel; /* back pointer to tunnel
+ * context */
+
+ char name[20]; /* "sess xxxxx/yyyyy", where
+ * x=tunnel_id, y=session_id */
+ int mtu;
+ int mru;
+ int flags; /* accessed by PPPIOCGFLAGS.
+ * Unused. */
+ unsigned recv_seq:1; /* expect receive packets with
+ * sequence numbers? */
+ unsigned send_seq:1; /* send packets with sequence
+ * numbers? */
+ unsigned lns_mode:1; /* behave as LNS? LAC enables
+ * sequence numbers under
+ * control of LNS. */
+ int debug; /* bitmask of debug message
+ * categories */
+ int reorder_timeout; /* configured reorder timeout
+ * (in jiffies) */
+ u16 nr; /* session NR state (receive) */
+ u16 ns; /* session NR state (send) */
+ struct sk_buff_head reorder_q; /* receive reorder queue */
+ struct pppol2tp_ioc_stats stats;
+ struct hlist_node hlist; /* Hash list node */
+};
+
+/* The sk_user_data field of the tunnel's UDP socket. It contains info to track
+ * all the associated sessions so incoming packets can be sorted out
+ */
+struct pppol2tp_tunnel
+{
+ int magic; /* Should be L2TP_TUNNEL_MAGIC */
+ rwlock_t hlist_lock; /* protect session_hlist */
+ struct hlist_head session_hlist[PPPOL2TP_HASH_SIZE];
+ /* hashed list of sessions,
+ * hashed by id */
+ int debug; /* bitmask of debug message
+ * categories */
+ char name[12]; /* "tunl xxxxx" */
+ struct pppol2tp_ioc_stats stats;
+
+ void (*old_sk_destruct)(struct sock *);
+
+ struct sock *sock; /* Parent socket */
+ struct list_head list; /* Keep a list of all open
+ * prepared sockets */
+ struct net *pppol2tp_net; /* the net we belong to */
+
+ atomic_t ref_count;
+};
+
+/* Private data stored for received packets in the skb.
+ */
+struct pppol2tp_skb_cb {
+ u16 ns;
+ u16 nr;
+ u16 has_seq;
+ u16 length;
+ unsigned long expires;
+};
+
+#define PPPOL2TP_SKB_CB(skb) ((struct pppol2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)])
+
+static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb);
+static void pppol2tp_tunnel_free(struct pppol2tp_tunnel *tunnel);
+
+static atomic_t pppol2tp_tunnel_count;
+static atomic_t pppol2tp_session_count;
+static struct ppp_channel_ops pppol2tp_chan_ops = { pppol2tp_xmit , NULL };
+static const struct proto_ops pppol2tp_ops;
+
+/* per-net private data for this module */
+static int pppol2tp_net_id __read_mostly;
+struct pppol2tp_net {
+ struct list_head pppol2tp_tunnel_list;
+ rwlock_t pppol2tp_tunnel_list_lock;
+};
+
+static inline struct pppol2tp_net *pppol2tp_pernet(struct net *net)
+{
+ BUG_ON(!net);
+
+ return net_generic(net, pppol2tp_net_id);
+}
+
+/* Helpers to obtain tunnel/session contexts from sockets.
+ */
+static inline struct pppol2tp_session *pppol2tp_sock_to_session(struct sock *sk)
+{
+ struct pppol2tp_session *session;
+
+ if (sk == NULL)
+ return NULL;
+
+ sock_hold(sk);
+ session = (struct pppol2tp_session *)(sk->sk_user_data);
+ if (session == NULL) {
+ sock_put(sk);
+ goto out;
+ }
+
+ BUG_ON(session->magic != L2TP_SESSION_MAGIC);
+out:
+ return session;
+}
+
+static inline struct pppol2tp_tunnel *pppol2tp_sock_to_tunnel(struct sock *sk)
+{
+ struct pppol2tp_tunnel *tunnel;
+
+ if (sk == NULL)
+ return NULL;
+
+ sock_hold(sk);
+ tunnel = (struct pppol2tp_tunnel *)(sk->sk_user_data);
+ if (tunnel == NULL) {
+ sock_put(sk);
+ goto out;
+ }
+
+ BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
+out:
+ return tunnel;
+}
+
+/* Tunnel reference counts. Incremented per session that is added to
+ * the tunnel.
+ */
+static inline void pppol2tp_tunnel_inc_refcount(struct pppol2tp_tunnel *tunnel)
+{
+ atomic_inc(&tunnel->ref_count);
+}
+
+static inline void pppol2tp_tunnel_dec_refcount(struct pppol2tp_tunnel *tunnel)
+{
+ if (atomic_dec_and_test(&tunnel->ref_count))
+ pppol2tp_tunnel_free(tunnel);
+}
+
+/* Session hash list.
+ * The session_id SHOULD be random according to RFC2661, but several
+ * L2TP implementations (Cisco and Microsoft) use incrementing
+ * session_ids. So we do a real hash on the session_id, rather than a
+ * simple bitmask.
+ */
+static inline struct hlist_head *
+pppol2tp_session_id_hash(struct pppol2tp_tunnel *tunnel, u16 session_id)
+{
+ unsigned long hash_val = (unsigned long) session_id;
+ return &tunnel->session_hlist[hash_long(hash_val, PPPOL2TP_HASH_BITS)];
+}
+
+/* Lookup a session by id
+ */
+static struct pppol2tp_session *
+pppol2tp_session_find(struct pppol2tp_tunnel *tunnel, u16 session_id)
+{
+ struct hlist_head *session_list =
+ pppol2tp_session_id_hash(tunnel, session_id);
+ struct pppol2tp_session *session;
+ struct hlist_node *walk;
+
+ read_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session, walk, session_list, hlist) {
+ if (session->tunnel_addr.s_session == session_id) {
+ read_unlock_bh(&tunnel->hlist_lock);
+ return session;
+ }
+ }
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return NULL;
+}
+
+/* Lookup a tunnel by id
+ */
+static struct pppol2tp_tunnel *pppol2tp_tunnel_find(struct net *net, u16 tunnel_id)
+{
+ struct pppol2tp_tunnel *tunnel;
+ struct pppol2tp_net *pn = pppol2tp_pernet(net);
+
+ read_lock_bh(&pn->pppol2tp_tunnel_list_lock);
+ list_for_each_entry(tunnel, &pn->pppol2tp_tunnel_list, list) {
+ if (tunnel->stats.tunnel_id == tunnel_id) {
+ read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
+ return tunnel;
+ }
+ }
+ read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
+
+ return NULL;
+}
+
+/*****************************************************************************
+ * Receive data handling
+ *****************************************************************************/
+
+/* Queue a skb in order. We come here only if the skb has an L2TP sequence
+ * number.
+ */
+static void pppol2tp_recv_queue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
+{
+ struct sk_buff *skbp;
+ struct sk_buff *tmp;
+ u16 ns = PPPOL2TP_SKB_CB(skb)->ns;
+
+ spin_lock_bh(&session->reorder_q.lock);
+ skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
+ if (PPPOL2TP_SKB_CB(skbp)->ns > ns) {
+ __skb_queue_before(&session->reorder_q, skbp, skb);
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n",
+ session->name, ns, PPPOL2TP_SKB_CB(skbp)->ns,
+ skb_queue_len(&session->reorder_q));
+ session->stats.rx_oos_packets++;
+ goto out;
+ }
+ }
+
+ __skb_queue_tail(&session->reorder_q, skb);
+
+out:
+ spin_unlock_bh(&session->reorder_q.lock);
+}
+
+/* Dequeue a single skb.
+ */
+static void pppol2tp_recv_dequeue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
+{
+ struct pppol2tp_tunnel *tunnel = session->tunnel;
+ int length = PPPOL2TP_SKB_CB(skb)->length;
+ struct sock *session_sock = NULL;
+
+ /* We're about to requeue the skb, so return resources
+ * to its current owner (a socket receive buffer).
+ */
+ skb_orphan(skb);
+
+ tunnel->stats.rx_packets++;
+ tunnel->stats.rx_bytes += length;
+ session->stats.rx_packets++;
+ session->stats.rx_bytes += length;
+
+ if (PPPOL2TP_SKB_CB(skb)->has_seq) {
+ /* Bump our Nr */
+ session->nr++;
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: updated nr to %hu\n", session->name, session->nr);
+ }
+
+ /* If the socket is bound, send it in to PPP's input queue. Otherwise
+ * queue it on the session socket.
+ */
+ session_sock = session->sock;
+ if (session_sock->sk_state & PPPOX_BOUND) {
+ struct pppox_sock *po;
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: recv %d byte data frame, passing to ppp\n",
+ session->name, length);
+
+ /* We need to forget all info related to the L2TP packet
+ * gathered in the skb as we are going to reuse the same
+ * skb for the inner packet.
+ * Namely we need to:
+ * - reset xfrm (IPSec) information as it applies to
+ * the outer L2TP packet and not to the inner one
+ * - release the dst to force a route lookup on the inner
+ * IP packet since skb->dst currently points to the dst
+ * of the UDP tunnel
+ * - reset netfilter information as it doesn't apply
+ * to the inner packet either
+ */
+ secpath_reset(skb);
+ skb_dst_drop(skb);
+ nf_reset(skb);
+
+ po = pppox_sk(session_sock);
+ ppp_input(&po->chan, skb);
+ } else {
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+ "%s: socket not bound\n", session->name);
+
+ /* Not bound. Nothing we can do, so discard. */
+ session->stats.rx_errors++;
+ kfree_skb(skb);
+ }
+
+ sock_put(session->sock);
+}
+
+/* Dequeue skbs from the session's reorder_q, subject to packet order.
+ * Skbs that have been in the queue for too long are simply discarded.
+ */
+static void pppol2tp_recv_dequeue(struct pppol2tp_session *session)
+{
+ struct sk_buff *skb;
+ struct sk_buff *tmp;
+
+ /* If the pkt at the head of the queue has the nr that we
+ * expect to send up next, dequeue it and any other
+ * in-sequence packets behind it.
+ */
+ spin_lock_bh(&session->reorder_q.lock);
+ skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
+ if (time_after(jiffies, PPPOL2TP_SKB_CB(skb)->expires)) {
+ session->stats.rx_seq_discards++;
+ session->stats.rx_errors++;
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: oos pkt %hu len %d discarded (too old), "
+ "waiting for %hu, reorder_q_len=%d\n",
+ session->name, PPPOL2TP_SKB_CB(skb)->ns,
+ PPPOL2TP_SKB_CB(skb)->length, session->nr,
+ skb_queue_len(&session->reorder_q));
+ __skb_unlink(skb, &session->reorder_q);
+ kfree_skb(skb);
+ sock_put(session->sock);
+ continue;
+ }
+
+ if (PPPOL2TP_SKB_CB(skb)->has_seq) {
+ if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: holding oos pkt %hu len %d, "
+ "waiting for %hu, reorder_q_len=%d\n",
+ session->name, PPPOL2TP_SKB_CB(skb)->ns,
+ PPPOL2TP_SKB_CB(skb)->length, session->nr,
+ skb_queue_len(&session->reorder_q));
+ goto out;
+ }
+ }
+ __skb_unlink(skb, &session->reorder_q);
+
+ /* Process the skb. We release the queue lock while we
+ * do so to let other contexts process the queue.
+ */
+ spin_unlock_bh(&session->reorder_q.lock);
+ pppol2tp_recv_dequeue_skb(session, skb);
+ spin_lock_bh(&session->reorder_q.lock);
+ }
+
+out:
+ spin_unlock_bh(&session->reorder_q.lock);
+}
+
+static inline int pppol2tp_verify_udp_checksum(struct sock *sk,
+ struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_hdr(skb);
+ u16 ulen = ntohs(uh->len);
+ struct inet_sock *inet;
+ __wsum psum;
+
+ if (sk->sk_no_check || skb_csum_unnecessary(skb) || !uh->check)
+ return 0;
+
+ inet = inet_sk(sk);
+ psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr, ulen,
+ IPPROTO_UDP, 0);
+
+ if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !csum_fold(csum_add(psum, skb->csum)))
+ return 0;
+
+ skb->csum = psum;
+
+ return __skb_checksum_complete(skb);
+}
+
+/* Internal receive frame. Do the real work of receiving an L2TP data frame
+ * here. The skb is not on a list when we get here.
+ * Returns 0 if the packet was a data packet and was successfully passed on.
+ * Returns 1 if the packet was not a good data packet and could not be
+ * forwarded. All such packets are passed up to userspace to deal with.
+ */
+static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb)
+{
+ struct pppol2tp_session *session = NULL;
+ struct pppol2tp_tunnel *tunnel;
+ unsigned char *ptr, *optr;
+ u16 hdrflags;
+ u16 tunnel_id, session_id;
+ int length;
+ int offset;
+
+ tunnel = pppol2tp_sock_to_tunnel(sock);
+ if (tunnel == NULL)
+ goto no_tunnel;
+
+ if (tunnel->sock && pppol2tp_verify_udp_checksum(tunnel->sock, skb))
+ goto discard_bad_csum;
+
+ /* UDP always verifies the packet length. */
+ __skb_pull(skb, sizeof(struct udphdr));
+
+ /* Short packet? */
+ if (!pskb_may_pull(skb, 12)) {
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+ "%s: recv short packet (len=%d)\n", tunnel->name, skb->len);
+ goto error;
+ }
+
+ /* Point to L2TP header */
+ optr = ptr = skb->data;
+
+ /* Get L2TP header flags */
+ hdrflags = ntohs(*(__be16*)ptr);
+
+ /* Trace packet contents, if enabled */
+ if (tunnel->debug & PPPOL2TP_MSG_DATA) {
+ length = min(16u, skb->len);
+ if (!pskb_may_pull(skb, length))
+ goto error;
+
+ printk(KERN_DEBUG "%s: recv: ", tunnel->name);
+
+ offset = 0;
+ do {
+ printk(" %02X", ptr[offset]);
+ } while (++offset < length);
+
+ printk("\n");
+ }
+
+ /* Get length of L2TP packet */
+ length = skb->len;
+
+ /* If type is control packet, it is handled by userspace. */
+ if (hdrflags & L2TP_HDRFLAG_T) {
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: recv control packet, len=%d\n", tunnel->name, length);
+ goto error;
+ }
+
+ /* Skip flags */
+ ptr += 2;
+
+ /* If length is present, skip it */
+ if (hdrflags & L2TP_HDRFLAG_L)
+ ptr += 2;
+
+ /* Extract tunnel and session ID */
+ tunnel_id = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+ session_id = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+
+ /* Find the session context */
+ session = pppol2tp_session_find(tunnel, session_id);
+ if (!session) {
+ /* Not found? Pass to userspace to deal with */
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+ "%s: no socket found (%hu/%hu). Passing up.\n",
+ tunnel->name, tunnel_id, session_id);
+ goto error;
+ }
+ sock_hold(session->sock);
+
+ /* The ref count on the socket was increased by the above call since
+ * we now hold a pointer to the session. Take care to do sock_put()
+ * when exiting this function from now on...
+ */
+
+ /* Handle the optional sequence numbers. If we are the LAC,
+ * enable/disable sequence numbers under the control of the LNS. If
+ * no sequence numbers present but we were expecting them, discard
+ * frame.
+ */
+ if (hdrflags & L2TP_HDRFLAG_S) {
+ u16 ns, nr;
+ ns = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+ nr = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+
+ /* Received a packet with sequence numbers. If we're the LNS,
+ * check if we sre sending sequence numbers and if not,
+ * configure it so.
+ */
+ if ((!session->lns_mode) && (!session->send_seq)) {
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
+ "%s: requested to enable seq numbers by LNS\n",
+ session->name);
+ session->send_seq = -1;
+ }
+
+ /* Store L2TP info in the skb */
+ PPPOL2TP_SKB_CB(skb)->ns = ns;
+ PPPOL2TP_SKB_CB(skb)->nr = nr;
+ PPPOL2TP_SKB_CB(skb)->has_seq = 1;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: recv data ns=%hu, nr=%hu, session nr=%hu\n",
+ session->name, ns, nr, session->nr);
+ } else {
+ /* No sequence numbers.
+ * If user has configured mandatory sequence numbers, discard.
+ */
+ if (session->recv_seq) {
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
+ "%s: recv data has no seq numbers when required. "
+ "Discarding\n", session->name);
+ session->stats.rx_seq_discards++;
+ goto discard;
+ }
+
+ /* If we're the LAC and we're sending sequence numbers, the
+ * LNS has requested that we no longer send sequence numbers.
+ * If we're the LNS and we're sending sequence numbers, the
+ * LAC is broken. Discard the frame.
+ */
+ if ((!session->lns_mode) && (session->send_seq)) {
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
+ "%s: requested to disable seq numbers by LNS\n",
+ session->name);
+ session->send_seq = 0;
+ } else if (session->send_seq) {
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
+ "%s: recv data has no seq numbers when required. "
+ "Discarding\n", session->name);
+ session->stats.rx_seq_discards++;
+ goto discard;
+ }
+
+ /* Store L2TP info in the skb */
+ PPPOL2TP_SKB_CB(skb)->has_seq = 0;
+ }
+
+ /* If offset bit set, skip it. */
+ if (hdrflags & L2TP_HDRFLAG_O) {
+ offset = ntohs(*(__be16 *)ptr);
+ ptr += 2 + offset;
+ }
+
+ offset = ptr - optr;
+ if (!pskb_may_pull(skb, offset))
+ goto discard;
+
+ __skb_pull(skb, offset);
+
+ /* Skip PPP header, if present. In testing, Microsoft L2TP clients
+ * don't send the PPP header (PPP header compression enabled), but
+ * other clients can include the header. So we cope with both cases
+ * here. The PPP header is always FF03 when using L2TP.
+ *
+ * Note that skb->data[] isn't dereferenced from a u16 ptr here since
+ * the field may be unaligned.
+ */
+ if (!pskb_may_pull(skb, 2))
+ goto discard;
+
+ if ((skb->data[0] == 0xff) && (skb->data[1] == 0x03))
+ skb_pull(skb, 2);
+
+ /* Prepare skb for adding to the session's reorder_q. Hold
+ * packets for max reorder_timeout or 1 second if not
+ * reordering.
+ */
+ PPPOL2TP_SKB_CB(skb)->length = length;
+ PPPOL2TP_SKB_CB(skb)->expires = jiffies +
+ (session->reorder_timeout ? session->reorder_timeout : HZ);
+
+ /* Add packet to the session's receive queue. Reordering is done here, if
+ * enabled. Saved L2TP protocol info is stored in skb->sb[].
+ */
+ if (PPPOL2TP_SKB_CB(skb)->has_seq) {
+ if (session->reorder_timeout != 0) {
+ /* Packet reordering enabled. Add skb to session's
+ * reorder queue, in order of ns.
+ */
+ pppol2tp_recv_queue_skb(session, skb);
+ } else {
+ /* Packet reordering disabled. Discard out-of-sequence
+ * packets
+ */
+ if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
+ session->stats.rx_seq_discards++;
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: oos pkt %hu len %d discarded, "
+ "waiting for %hu, reorder_q_len=%d\n",
+ session->name, PPPOL2TP_SKB_CB(skb)->ns,
+ PPPOL2TP_SKB_CB(skb)->length, session->nr,
+ skb_queue_len(&session->reorder_q));
+ goto discard;
+ }
+ skb_queue_tail(&session->reorder_q, skb);
+ }
+ } else {
+ /* No sequence numbers. Add the skb to the tail of the
+ * reorder queue. This ensures that it will be
+ * delivered after all previous sequenced skbs.
+ */
+ skb_queue_tail(&session->reorder_q, skb);
+ }
+
+ /* Try to dequeue as many skbs from reorder_q as we can. */
+ pppol2tp_recv_dequeue(session);
+ sock_put(sock);
+
+ return 0;
+
+discard:
+ session->stats.rx_errors++;
+ kfree_skb(skb);
+ sock_put(session->sock);
+ sock_put(sock);
+
+ return 0;
+
+discard_bad_csum:
+ LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
+ UDP_INC_STATS_USER(&init_net, UDP_MIB_INERRORS, 0);
+ tunnel->stats.rx_errors++;
+ kfree_skb(skb);
+ sock_put(sock);
+
+ return 0;
+
+error:
+ /* Put UDP header back */
+ __skb_push(skb, sizeof(struct udphdr));
+ sock_put(sock);
+
+no_tunnel:
+ return 1;
+}
+
+/* UDP encapsulation receive handler. See net/ipv4/udp.c.
+ * Return codes:
+ * 0 : success.
+ * <0: error
+ * >0: skb should be passed up to userspace as UDP.
+ */
+static int pppol2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+ struct pppol2tp_tunnel *tunnel;
+
+ tunnel = pppol2tp_sock_to_tunnel(sk);
+ if (tunnel == NULL)
+ goto pass_up;
+
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: received %d bytes\n", tunnel->name, skb->len);
+
+ if (pppol2tp_recv_core(sk, skb))
+ goto pass_up_put;
+
+ sock_put(sk);
+ return 0;
+
+pass_up_put:
+ sock_put(sk);
+pass_up:
+ return 1;
+}
+
+/* Receive message. This is the recvmsg for the PPPoL2TP socket.
+ */
+static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *msg, size_t len,
+ int flags)
+{
+ int err;
+ struct sk_buff *skb;
+ struct sock *sk = sock->sk;
+
+ err = -EIO;
+ if (sk->sk_state & PPPOX_BOUND)
+ goto end;
+
+ msg->msg_namelen = 0;
+
+ err = 0;
+ skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
+ flags & MSG_DONTWAIT, &err);
+ if (!skb)
+ goto end;
+
+ if (len > skb->len)
+ len = skb->len;
+ else if (len < skb->len)
+ msg->msg_flags |= MSG_TRUNC;
+
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
+ if (likely(err == 0))
+ err = len;
+
+ kfree_skb(skb);
+end:
+ return err;
+}
+
+/************************************************************************
+ * Transmit handling
+ ***********************************************************************/
+
+/* Tell how big L2TP headers are for a particular session. This
+ * depends on whether sequence numbers are being used.
+ */
+static inline int pppol2tp_l2tp_header_len(struct pppol2tp_session *session)
+{
+ if (session->send_seq)
+ return PPPOL2TP_L2TP_HDR_SIZE_SEQ;
+
+ return PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+}
+
+/* Build an L2TP header for the session into the buffer provided.
+ */
+static void pppol2tp_build_l2tp_header(struct pppol2tp_session *session,
+ void *buf)
+{
+ __be16 *bufp = buf;
+ u16 flags = L2TP_HDR_VER;
+
+ if (session->send_seq)
+ flags |= L2TP_HDRFLAG_S;
+
+ /* Setup L2TP header.
+ * FIXME: Can this ever be unaligned? Is direct dereferencing of
+ * 16-bit header fields safe here for all architectures?
+ */
+ *bufp++ = htons(flags);
+ *bufp++ = htons(session->tunnel_addr.d_tunnel);
+ *bufp++ = htons(session->tunnel_addr.d_session);
+ if (session->send_seq) {
+ *bufp++ = htons(session->ns);
+ *bufp++ = 0;
+ session->ns++;
+ PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: updated ns to %hu\n", session->name, session->ns);
+ }
+}
+
+/* This is the sendmsg for the PPPoL2TP pppol2tp_session socket. We come here
+ * when a user application does a sendmsg() on the session socket. L2TP and
+ * PPP headers must be inserted into the user's data.
+ */
+static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
+ size_t total_len)
+{
+ static const unsigned char ppph[2] = { 0xff, 0x03 };
+ struct sock *sk = sock->sk;
+ struct inet_sock *inet;
+ __wsum csum;
+ struct sk_buff *skb;
+ int error;
+ int hdr_len;
+ struct pppol2tp_session *session;
+ struct pppol2tp_tunnel *tunnel;
+ struct udphdr *uh;
+ unsigned int len;
+ struct sock *sk_tun;
+ u16 udp_len;
+
+ error = -ENOTCONN;
+ if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+ goto error;
+
+ /* Get session and tunnel contexts */
+ error = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto error;
+
+ sk_tun = session->tunnel_sock;
+ tunnel = pppol2tp_sock_to_tunnel(sk_tun);
+ if (tunnel == NULL)
+ goto error_put_sess;
+
+ /* What header length is configured for this session? */
+ hdr_len = pppol2tp_l2tp_header_len(session);
+
+ /* Allocate a socket buffer */
+ error = -ENOMEM;
+ skb = sock_wmalloc(sk, NET_SKB_PAD + sizeof(struct iphdr) +
+ sizeof(struct udphdr) + hdr_len +
+ sizeof(ppph) + total_len,
+ 0, GFP_KERNEL);
+ if (!skb)
+ goto error_put_sess_tun;
+
+ /* Reserve space for headers. */
+ skb_reserve(skb, NET_SKB_PAD);
+ skb_reset_network_header(skb);
+ skb_reserve(skb, sizeof(struct iphdr));
+ skb_reset_transport_header(skb);
+
+ /* Build UDP header */
+ inet = inet_sk(sk_tun);
+ udp_len = hdr_len + sizeof(ppph) + total_len;
+ uh = (struct udphdr *) skb->data;
+ uh->source = inet->inet_sport;
+ uh->dest = inet->inet_dport;
+ uh->len = htons(udp_len);
+ uh->check = 0;
+ skb_put(skb, sizeof(struct udphdr));
+
+ /* Build L2TP header */
+ pppol2tp_build_l2tp_header(session, skb->data);
+ skb_put(skb, hdr_len);
+
+ /* Add PPP header */
+ skb->data[0] = ppph[0];
+ skb->data[1] = ppph[1];
+ skb_put(skb, 2);
+
+ /* Copy user data into skb */
+ error = memcpy_fromiovec(skb->data, m->msg_iov, total_len);
+ if (error < 0) {
+ kfree_skb(skb);
+ goto error_put_sess_tun;
+ }
+ skb_put(skb, total_len);
+
+ /* Calculate UDP checksum if configured to do so */
+ if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
+ skb->ip_summed = CHECKSUM_NONE;
+ else if (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ csum = skb_checksum(skb, 0, udp_len, 0);
+ uh->check = csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, 0);
+ }
+
+ /* Debug */
+ if (session->send_seq)
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: send %Zd bytes, ns=%hu\n", session->name,
+ total_len, session->ns - 1);
+ else
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: send %Zd bytes\n", session->name, total_len);
+
+ if (session->debug & PPPOL2TP_MSG_DATA) {
+ int i;
+ unsigned char *datap = skb->data;
+
+ printk(KERN_DEBUG "%s: xmit:", session->name);
+ for (i = 0; i < total_len; i++) {
+ printk(" %02X", *datap++);
+ if (i == 15) {
+ printk(" ...");
+ break;
+ }
+ }
+ printk("\n");
+ }
+
+ /* Queue the packet to IP for output */
+ len = skb->len;
+ error = ip_queue_xmit(skb, 1);
+
+ /* Update stats */
+ if (error >= 0) {
+ tunnel->stats.tx_packets++;
+ tunnel->stats.tx_bytes += len;
+ session->stats.tx_packets++;
+ session->stats.tx_bytes += len;
+ } else {
+ tunnel->stats.tx_errors++;
+ session->stats.tx_errors++;
+ }
+
+ return error;
+
+error_put_sess_tun:
+ sock_put(session->tunnel_sock);
+error_put_sess:
+ sock_put(sk);
+error:
+ return error;
+}
+
+/* Automatically called when the skb is freed.
+ */
+static void pppol2tp_sock_wfree(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+
+/* For data skbs that we transmit, we associate with the tunnel socket
+ * but don't do accounting.
+ */
+static inline void pppol2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
+{
+ sock_hold(sk);
+ skb->sk = sk;
+ skb->destructor = pppol2tp_sock_wfree;
+}
+
+/* Transmit function called by generic PPP driver. Sends PPP frame
+ * over PPPoL2TP socket.
+ *
+ * This is almost the same as pppol2tp_sendmsg(), but rather than
+ * being called with a msghdr from userspace, it is called with a skb
+ * from the kernel.
+ *
+ * The supplied skb from ppp doesn't have enough headroom for the
+ * insertion of L2TP, UDP and IP headers so we need to allocate more
+ * headroom in the skb. This will create a cloned skb. But we must be
+ * careful in the error case because the caller will expect to free
+ * the skb it supplied, not our cloned skb. So we take care to always
+ * leave the original skb unfreed if we return an error.
+ */
+static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+ static const u8 ppph[2] = { 0xff, 0x03 };
+ struct sock *sk = (struct sock *) chan->private;
+ struct sock *sk_tun;
+ int hdr_len;
+ u16 udp_len;
+ struct pppol2tp_session *session;
+ struct pppol2tp_tunnel *tunnel;
+ int rc;
+ int headroom;
+ int data_len = skb->len;
+ struct inet_sock *inet;
+ __wsum csum;
+ struct udphdr *uh;
+ unsigned int len;
+ int old_headroom;
+ int new_headroom;
+
+ if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+ goto abort;
+
+ /* Get session and tunnel contexts from the socket */
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto abort;
+
+ sk_tun = session->tunnel_sock;
+ if (sk_tun == NULL)
+ goto abort_put_sess;
+ tunnel = pppol2tp_sock_to_tunnel(sk_tun);
+ if (tunnel == NULL)
+ goto abort_put_sess;
+
+ /* What header length is configured for this session? */
+ hdr_len = pppol2tp_l2tp_header_len(session);
+
+ /* Check that there's enough headroom in the skb to insert IP,
+ * UDP and L2TP and PPP headers. If not enough, expand it to
+ * make room. Adjust truesize.
+ */
+ headroom = NET_SKB_PAD + sizeof(struct iphdr) +
+ sizeof(struct udphdr) + hdr_len + sizeof(ppph);
+ old_headroom = skb_headroom(skb);
+ if (skb_cow_head(skb, headroom))
+ goto abort_put_sess_tun;
+
+ new_headroom = skb_headroom(skb);
+ skb_orphan(skb);
+ skb->truesize += new_headroom - old_headroom;
+
+ /* Setup PPP header */
+ __skb_push(skb, sizeof(ppph));
+ skb->data[0] = ppph[0];
+ skb->data[1] = ppph[1];
+
+ /* Setup L2TP header */
+ pppol2tp_build_l2tp_header(session, __skb_push(skb, hdr_len));
+
+ udp_len = sizeof(struct udphdr) + hdr_len + sizeof(ppph) + data_len;
+
+ /* Setup UDP header */
+ inet = inet_sk(sk_tun);
+ __skb_push(skb, sizeof(*uh));
+ skb_reset_transport_header(skb);
+ uh = udp_hdr(skb);
+ uh->source = inet->inet_sport;
+ uh->dest = inet->inet_dport;
+ uh->len = htons(udp_len);
+ uh->check = 0;
+
+ /* Debug */
+ if (session->send_seq)
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: send %d bytes, ns=%hu\n", session->name,
+ data_len, session->ns - 1);
+ else
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: send %d bytes\n", session->name, data_len);
+
+ if (session->debug & PPPOL2TP_MSG_DATA) {
+ int i;
+ unsigned char *datap = skb->data;
+
+ printk(KERN_DEBUG "%s: xmit:", session->name);
+ for (i = 0; i < data_len; i++) {
+ printk(" %02X", *datap++);
+ if (i == 31) {
+ printk(" ...");
+ break;
+ }
+ }
+ printk("\n");
+ }
+
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+ IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
+ IPSKB_REROUTED);
+ nf_reset(skb);
+
+ /* Get routing info from the tunnel socket */
+ skb_dst_drop(skb);
+ skb_dst_set(skb, dst_clone(__sk_dst_get(sk_tun)));
+ pppol2tp_skb_set_owner_w(skb, sk_tun);
+
+ /* Calculate UDP checksum if configured to do so */
+ if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
+ skb->ip_summed = CHECKSUM_NONE;
+ else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
+ (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ csum = skb_checksum(skb, 0, udp_len, 0);
+ uh->check = csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, 0);
+ }
+
+ /* Queue the packet to IP for output */
+ len = skb->len;
+ rc = ip_queue_xmit(skb, 1);
+
+ /* Update stats */
+ if (rc >= 0) {
+ tunnel->stats.tx_packets++;
+ tunnel->stats.tx_bytes += len;
+ session->stats.tx_packets++;
+ session->stats.tx_bytes += len;
+ } else {
+ tunnel->stats.tx_errors++;
+ session->stats.tx_errors++;
+ }
+
+ sock_put(sk_tun);
+ sock_put(sk);
+ return 1;
+
+abort_put_sess_tun:
+ sock_put(sk_tun);
+abort_put_sess:
+ sock_put(sk);
+abort:
+ /* Free the original skb */
+ kfree_skb(skb);
+ return 1;
+}
+
+/*****************************************************************************
+ * Session (and tunnel control) socket create/destroy.
+ *****************************************************************************/
+
+/* When the tunnel UDP socket is closed, all the attached sockets need to go
+ * too.
+ */
+static void pppol2tp_tunnel_closeall(struct pppol2tp_tunnel *tunnel)
+{
+ int hash;
+ struct hlist_node *walk;
+ struct hlist_node *tmp;
+ struct pppol2tp_session *session;
+ struct sock *sk;
+
+ BUG_ON(tunnel == NULL);
+
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: closing all sessions...\n", tunnel->name);
+
+ write_lock_bh(&tunnel->hlist_lock);
+ for (hash = 0; hash < PPPOL2TP_HASH_SIZE; hash++) {
+again:
+ hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
+ struct sk_buff *skb;
+
+ session = hlist_entry(walk, struct pppol2tp_session, hlist);
+
+ sk = session->sock;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: closing session\n", session->name);
+
+ hlist_del_init(&session->hlist);
+
+ /* Since we should hold the sock lock while
+ * doing any unbinding, we need to release the
+ * lock we're holding before taking that lock.
+ * Hold a reference to the sock so it doesn't
+ * disappear as we're jumping between locks.
+ */
+ sock_hold(sk);
+ write_unlock_bh(&tunnel->hlist_lock);
+ lock_sock(sk);
+
+ if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
+ pppox_unbind_sock(sk);
+ sk->sk_state = PPPOX_DEAD;
+ sk->sk_state_change(sk);
+ }
+
+ /* Purge any queued data */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_queue_purge(&sk->sk_write_queue);
+ while ((skb = skb_dequeue(&session->reorder_q))) {
+ kfree_skb(skb);
+ sock_put(sk);
+ }
+
+ release_sock(sk);
+ sock_put(sk);
+
+ /* Now restart from the beginning of this hash
+ * chain. We always remove a session from the
+ * list so we are guaranteed to make forward
+ * progress.
+ */
+ write_lock_bh(&tunnel->hlist_lock);
+ goto again;
+ }
+ }
+ write_unlock_bh(&tunnel->hlist_lock);
+}
+
+/* Really kill the tunnel.
+ * Come here only when all sessions have been cleared from the tunnel.
+ */
+static void pppol2tp_tunnel_free(struct pppol2tp_tunnel *tunnel)
+{
+ struct pppol2tp_net *pn = pppol2tp_pernet(tunnel->pppol2tp_net);
+
+ /* Remove from socket list */
+ write_lock_bh(&pn->pppol2tp_tunnel_list_lock);
+ list_del_init(&tunnel->list);
+ write_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
+
+ atomic_dec(&pppol2tp_tunnel_count);
+ kfree(tunnel);
+}
+
+/* Tunnel UDP socket destruct hook.
+ * The tunnel context is deleted only when all session sockets have been
+ * closed.
+ */
+static void pppol2tp_tunnel_destruct(struct sock *sk)
+{
+ struct pppol2tp_tunnel *tunnel;
+
+ tunnel = sk->sk_user_data;
+ if (tunnel == NULL)
+ goto end;
+
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: closing...\n", tunnel->name);
+
+ /* Close all sessions */
+ pppol2tp_tunnel_closeall(tunnel);
+
+ /* No longer an encapsulation socket. See net/ipv4/udp.c */
+ (udp_sk(sk))->encap_type = 0;
+ (udp_sk(sk))->encap_rcv = NULL;
+
+ /* Remove hooks into tunnel socket */
+ tunnel->sock = NULL;
+ sk->sk_destruct = tunnel->old_sk_destruct;
+ sk->sk_user_data = NULL;
+
+ /* Call original (UDP) socket descructor */
+ if (sk->sk_destruct != NULL)
+ (*sk->sk_destruct)(sk);
+
+ pppol2tp_tunnel_dec_refcount(tunnel);
+
+end:
+ return;
+}
+
+/* Really kill the session socket. (Called from sock_put() if
+ * refcnt == 0.)
+ */
+static void pppol2tp_session_destruct(struct sock *sk)
+{
+ struct pppol2tp_session *session = NULL;
+
+ if (sk->sk_user_data != NULL) {
+ struct pppol2tp_tunnel *tunnel;
+
+ session = sk->sk_user_data;
+ if (session == NULL)
+ goto out;
+
+ BUG_ON(session->magic != L2TP_SESSION_MAGIC);
+
+ /* Don't use pppol2tp_sock_to_tunnel() here to
+ * get the tunnel context because the tunnel
+ * socket might have already been closed (its
+ * sk->sk_user_data will be NULL) so use the
+ * session's private tunnel ptr instead.
+ */
+ tunnel = session->tunnel;
+ if (tunnel != NULL) {
+ BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
+
+ /* If session_id is zero, this is a null
+ * session context, which was created for a
+ * socket that is being used only to manage
+ * tunnels.
+ */
+ if (session->tunnel_addr.s_session != 0) {
+ /* Delete the session socket from the
+ * hash
+ */
+ write_lock_bh(&tunnel->hlist_lock);
+ hlist_del_init(&session->hlist);
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ atomic_dec(&pppol2tp_session_count);
+ }
+
+ /* This will delete the tunnel context if this
+ * is the last session on the tunnel.
+ */
+ session->tunnel = NULL;
+ session->tunnel_sock = NULL;
+ pppol2tp_tunnel_dec_refcount(tunnel);
+ }
+ }
+
+ kfree(session);
+out:
+ return;
+}
+
+/* Called when the PPPoX socket (session) is closed.
+ */
+static int pppol2tp_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct pppol2tp_session *session;
+ int error;
+
+ if (!sk)
+ return 0;
+
+ error = -EBADF;
+ lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD) != 0)
+ goto error;
+
+ pppox_unbind_sock(sk);
+
+ /* Signal the death of the socket. */
+ sk->sk_state = PPPOX_DEAD;
+ sock_orphan(sk);
+ sock->sk = NULL;
+
+ session = pppol2tp_sock_to_session(sk);
+
+ /* Purge any queued data */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_queue_purge(&sk->sk_write_queue);
+ if (session != NULL) {
+ struct sk_buff *skb;
+ while ((skb = skb_dequeue(&session->reorder_q))) {
+ kfree_skb(skb);
+ sock_put(sk);
+ }
+ sock_put(sk);
+ }
+
+ release_sock(sk);
+
+ /* This will delete the session context via
+ * pppol2tp_session_destruct() if the socket's refcnt drops to
+ * zero.
+ */
+ sock_put(sk);
+
+ return 0;
+
+error:
+ release_sock(sk);
+ return error;
+}
+
+/* Internal function to prepare a tunnel (UDP) socket to have PPPoX
+ * sockets attached to it.
+ */
+static struct sock *pppol2tp_prepare_tunnel_socket(struct net *net,
+ int fd, u16 tunnel_id, int *error)
+{
+ int err;
+ struct socket *sock = NULL;
+ struct sock *sk;
+ struct pppol2tp_tunnel *tunnel;
+ struct pppol2tp_net *pn;
+ struct sock *ret = NULL;
+
+ /* Get the tunnel UDP socket from the fd, which was opened by
+ * the userspace L2TP daemon.
+ */
+ err = -EBADF;
+ sock = sockfd_lookup(fd, &err);
+ if (!sock) {
+ PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
+ "tunl %hu: sockfd_lookup(fd=%d) returned %d\n",
+ tunnel_id, fd, err);
+ goto err;
+ }
+
+ sk = sock->sk;
+
+ /* Quick sanity checks */
+ err = -EPROTONOSUPPORT;
+ if (sk->sk_protocol != IPPROTO_UDP) {
+ PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
+ "tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
+ tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
+ goto err;
+ }
+ err = -EAFNOSUPPORT;
+ if (sock->ops->family != AF_INET) {
+ PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
+ "tunl %hu: fd %d wrong family, got %d, expected %d\n",
+ tunnel_id, fd, sock->ops->family, AF_INET);
+ goto err;
+ }
+
+ err = -ENOTCONN;
+
+ /* Check if this socket has already been prepped */
+ tunnel = (struct pppol2tp_tunnel *)sk->sk_user_data;
+ if (tunnel != NULL) {
+ /* User-data field already set */
+ err = -EBUSY;
+ BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
+
+ /* This socket has already been prepped */
+ ret = tunnel->sock;
+ goto out;
+ }
+
+ /* This socket is available and needs prepping. Create a new tunnel
+ * context and init it.
+ */
+ sk->sk_user_data = tunnel = kzalloc(sizeof(struct pppol2tp_tunnel), GFP_KERNEL);
+ if (sk->sk_user_data == NULL) {
+ err = -ENOMEM;
+ goto err;
+ }
+
+ tunnel->magic = L2TP_TUNNEL_MAGIC;
+ sprintf(&tunnel->name[0], "tunl %hu", tunnel_id);
+
+ tunnel->stats.tunnel_id = tunnel_id;
+ tunnel->debug = PPPOL2TP_DEFAULT_DEBUG_FLAGS;
+
+ /* Hook on the tunnel socket destructor so that we can cleanup
+ * if the tunnel socket goes away.
+ */
+ tunnel->old_sk_destruct = sk->sk_destruct;
+ sk->sk_destruct = pppol2tp_tunnel_destruct;
+
+ tunnel->sock = sk;
+ sk->sk_allocation = GFP_ATOMIC;
+
+ /* Misc init */
+ rwlock_init(&tunnel->hlist_lock);
+
+ /* The net we belong to */
+ tunnel->pppol2tp_net = net;
+ pn = pppol2tp_pernet(net);
+
+ /* Add tunnel to our list */
+ INIT_LIST_HEAD(&tunnel->list);
+ write_lock_bh(&pn->pppol2tp_tunnel_list_lock);
+ list_add(&tunnel->list, &pn->pppol2tp_tunnel_list);
+ write_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
+ atomic_inc(&pppol2tp_tunnel_count);
+
+ /* Bump the reference count. The tunnel context is deleted
+ * only when this drops to zero.
+ */
+ pppol2tp_tunnel_inc_refcount(tunnel);
+
+ /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
+ (udp_sk(sk))->encap_type = UDP_ENCAP_L2TPINUDP;
+ (udp_sk(sk))->encap_rcv = pppol2tp_udp_encap_recv;
+
+ ret = tunnel->sock;
+
+ *error = 0;
+out:
+ if (sock)
+ sockfd_put(sock);
+
+ return ret;
+
+err:
+ *error = err;
+ goto out;
+}
+
+static struct proto pppol2tp_sk_proto = {
+ .name = "PPPOL2TP",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct pppox_sock),
+};
+
+/* socket() handler. Initialize a new struct sock.
+ */
+static int pppol2tp_create(struct net *net, struct socket *sock)
+{
+ int error = -ENOMEM;
+ struct sock *sk;
+
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto);
+ if (!sk)
+ goto out;
+
+ sock_init_data(sock, sk);
+
+ sock->state = SS_UNCONNECTED;
+ sock->ops = &pppol2tp_ops;
+
+ sk->sk_backlog_rcv = pppol2tp_recv_core;
+ sk->sk_protocol = PX_PROTO_OL2TP;
+ sk->sk_family = PF_PPPOX;
+ sk->sk_state = PPPOX_NONE;
+ sk->sk_type = SOCK_STREAM;
+ sk->sk_destruct = pppol2tp_session_destruct;
+
+ error = 0;
+
+out:
+ return error;
+}
+
+/* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
+ */
+static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
+ int sockaddr_len, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
+ struct pppox_sock *po = pppox_sk(sk);
+ struct sock *tunnel_sock = NULL;
+ struct pppol2tp_session *session = NULL;
+ struct pppol2tp_tunnel *tunnel;
+ struct dst_entry *dst;
+ int error = 0;
+
+ lock_sock(sk);
+
+ error = -EINVAL;
+ if (sp->sa_protocol != PX_PROTO_OL2TP)
+ goto end;
+
+ /* Check for already bound sockets */
+ error = -EBUSY;
+ if (sk->sk_state & PPPOX_CONNECTED)
+ goto end;
+
+ /* We don't supporting rebinding anyway */
+ error = -EALREADY;
+ if (sk->sk_user_data)
+ goto end; /* socket is already attached */
+
+ /* Don't bind if s_tunnel is 0 */
+ error = -EINVAL;
+ if (sp->pppol2tp.s_tunnel == 0)
+ goto end;
+
+ /* Special case: prepare tunnel socket if s_session and
+ * d_session is 0. Otherwise look up tunnel using supplied
+ * tunnel id.
+ */
+ if ((sp->pppol2tp.s_session == 0) && (sp->pppol2tp.d_session == 0)) {
+ tunnel_sock = pppol2tp_prepare_tunnel_socket(sock_net(sk),
+ sp->pppol2tp.fd,
+ sp->pppol2tp.s_tunnel,
+ &error);
+ if (tunnel_sock == NULL)
+ goto end;
+
+ sock_hold(tunnel_sock);
+ tunnel = tunnel_sock->sk_user_data;
+ } else {
+ tunnel = pppol2tp_tunnel_find(sock_net(sk), sp->pppol2tp.s_tunnel);
+
+ /* Error if we can't find the tunnel */
+ error = -ENOENT;
+ if (tunnel == NULL)
+ goto end;
+
+ tunnel_sock = tunnel->sock;
+ }
+
+ /* Check that this session doesn't already exist */
+ error = -EEXIST;
+ session = pppol2tp_session_find(tunnel, sp->pppol2tp.s_session);
+ if (session != NULL)
+ goto end;
+
+ /* Allocate and initialize a new session context. */
+ session = kzalloc(sizeof(struct pppol2tp_session), GFP_KERNEL);
+ if (session == NULL) {
+ error = -ENOMEM;
+ goto end;
+ }
+
+ skb_queue_head_init(&session->reorder_q);
+
+ session->magic = L2TP_SESSION_MAGIC;
+ session->owner = current->pid;
+ session->sock = sk;
+ session->tunnel = tunnel;
+ session->tunnel_sock = tunnel_sock;
+ session->tunnel_addr = sp->pppol2tp;
+ sprintf(&session->name[0], "sess %hu/%hu",
+ session->tunnel_addr.s_tunnel,
+ session->tunnel_addr.s_session);
+
+ session->stats.tunnel_id = session->tunnel_addr.s_tunnel;
+ session->stats.session_id = session->tunnel_addr.s_session;
+
+ INIT_HLIST_NODE(&session->hlist);
+
+ /* Inherit debug options from tunnel */
+ session->debug = tunnel->debug;
+
+ /* Default MTU must allow space for UDP/L2TP/PPP
+ * headers.
+ */
+ session->mtu = session->mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+
+ /* If PMTU discovery was enabled, use the MTU that was discovered */
+ dst = sk_dst_get(sk);
+ if (dst != NULL) {
+ u32 pmtu = dst_mtu(__sk_dst_get(sk));
+ if (pmtu != 0)
+ session->mtu = session->mru = pmtu -
+ PPPOL2TP_HEADER_OVERHEAD;
+ dst_release(dst);
+ }
+
+ /* Special case: if source & dest session_id == 0x0000, this socket is
+ * being created to manage the tunnel. Don't add the session to the
+ * session hash list, just set up the internal context for use by
+ * ioctl() and sockopt() handlers.
+ */
+ if ((session->tunnel_addr.s_session == 0) &&
+ (session->tunnel_addr.d_session == 0)) {
+ error = 0;
+ sk->sk_user_data = session;
+ goto out_no_ppp;
+ }
+
+ /* Get tunnel context from the tunnel socket */
+ tunnel = pppol2tp_sock_to_tunnel(tunnel_sock);
+ if (tunnel == NULL) {
+ error = -EBADF;
+ goto end;
+ }
+
+ /* Right now, because we don't have a way to push the incoming skb's
+ * straight through the UDP layer, the only header we need to worry
+ * about is the L2TP header. This size is different depending on
+ * whether sequence numbers are enabled for the data channel.
+ */
+ po->chan.hdrlen = PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+
+ po->chan.private = sk;
+ po->chan.ops = &pppol2tp_chan_ops;
+ po->chan.mtu = session->mtu;
+
+ error = ppp_register_net_channel(sock_net(sk), &po->chan);
+ if (error)
+ goto end_put_tun;
+
+ /* This is how we get the session context from the socket. */
+ sk->sk_user_data = session;
+
+ /* Add session to the tunnel's hash list */
+ write_lock_bh(&tunnel->hlist_lock);
+ hlist_add_head(&session->hlist,
+ pppol2tp_session_id_hash(tunnel,
+ session->tunnel_addr.s_session));
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ atomic_inc(&pppol2tp_session_count);
+
+out_no_ppp:
+ pppol2tp_tunnel_inc_refcount(tunnel);
+ sk->sk_state = PPPOX_CONNECTED;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: created\n", session->name);
+
+end_put_tun:
+ sock_put(tunnel_sock);
+end:
+ release_sock(sk);
+
+ if (error != 0) {
+ if (session)
+ PRINTK(session->debug,
+ PPPOL2TP_MSG_CONTROL, KERN_WARNING,
+ "%s: connect failed: %d\n",
+ session->name, error);
+ else
+ PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_WARNING,
+ "connect failed: %d\n", error);
+ }
+
+ return error;
+}
+
+/* getname() support.
+ */
+static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
+ int *usockaddr_len, int peer)
+{
+ int len = sizeof(struct sockaddr_pppol2tp);
+ struct sockaddr_pppol2tp sp;
+ int error = 0;
+ struct pppol2tp_session *session;
+
+ error = -ENOTCONN;
+ if (sock->sk->sk_state != PPPOX_CONNECTED)
+ goto end;
+
+ session = pppol2tp_sock_to_session(sock->sk);
+ if (session == NULL) {
+ error = -EBADF;
+ goto end;
+ }
+
+ sp.sa_family = AF_PPPOX;
+ sp.sa_protocol = PX_PROTO_OL2TP;
+ memcpy(&sp.pppol2tp, &session->tunnel_addr,
+ sizeof(struct pppol2tp_addr));
+
+ memcpy(uaddr, &sp, len);
+
+ *usockaddr_len = len;
+
+ error = 0;
+ sock_put(sock->sk);
+
+end:
+ return error;
+}
+
+/****************************************************************************
+ * ioctl() handlers.
+ *
+ * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
+ * sockets. However, in order to control kernel tunnel features, we allow
+ * userspace to create a special "tunnel" PPPoX socket which is used for
+ * control only. Tunnel PPPoX sockets have session_id == 0 and simply allow
+ * the user application to issue L2TP setsockopt(), getsockopt() and ioctl()
+ * calls.
+ ****************************************************************************/
+
+/* Session ioctl helper.
+ */
+static int pppol2tp_session_ioctl(struct pppol2tp_session *session,
+ unsigned int cmd, unsigned long arg)
+{
+ struct ifreq ifr;
+ int err = 0;
+ struct sock *sk = session->sock;
+ int val = (int) arg;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
+ "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
+ session->name, cmd, arg);
+
+ sock_hold(sk);
+
+ switch (cmd) {
+ case SIOCGIFMTU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
+ break;
+ ifr.ifr_mtu = session->mtu;
+ if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq)))
+ break;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get mtu=%d\n", session->name, session->mtu);
+ err = 0;
+ break;
+
+ case SIOCSIFMTU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
+ break;
+
+ session->mtu = ifr.ifr_mtu;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set mtu=%d\n", session->name, session->mtu);
+ err = 0;
+ break;
+
+ case PPPIOCGMRU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (put_user(session->mru, (int __user *) arg))
+ break;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get mru=%d\n", session->name, session->mru);
+ err = 0;
+ break;
+
+ case PPPIOCSMRU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (get_user(val,(int __user *) arg))
+ break;
+
+ session->mru = val;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set mru=%d\n", session->name, session->mru);
+ err = 0;
+ break;
+
+ case PPPIOCGFLAGS:
+ err = -EFAULT;
+ if (put_user(session->flags, (int __user *) arg))
+ break;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get flags=%d\n", session->name, session->flags);
+ err = 0;
+ break;
+
+ case PPPIOCSFLAGS:
+ err = -EFAULT;
+ if (get_user(val, (int __user *) arg))
+ break;
+ session->flags = val;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set flags=%d\n", session->name, session->flags);
+ err = 0;
+ break;
+
+ case PPPIOCGL2TPSTATS:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ if (copy_to_user((void __user *) arg, &session->stats,
+ sizeof(session->stats)))
+ break;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get L2TP stats\n", session->name);
+ err = 0;
+ break;
+
+ default:
+ err = -ENOSYS;
+ break;
+ }
+
+ sock_put(sk);
+
+ return err;
+}
+
+/* Tunnel ioctl helper.
+ *
+ * Note the special handling for PPPIOCGL2TPSTATS below. If the ioctl data
+ * specifies a session_id, the session ioctl handler is called. This allows an
+ * application to retrieve session stats via a tunnel socket.
+ */
+static int pppol2tp_tunnel_ioctl(struct pppol2tp_tunnel *tunnel,
+ unsigned int cmd, unsigned long arg)
+{
+ int err = 0;
+ struct sock *sk = tunnel->sock;
+ struct pppol2tp_ioc_stats stats_req;
+
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
+ "%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n", tunnel->name,
+ cmd, arg);
+
+ sock_hold(sk);
+
+ switch (cmd) {
+ case PPPIOCGL2TPSTATS:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ if (copy_from_user(&stats_req, (void __user *) arg,
+ sizeof(stats_req))) {
+ err = -EFAULT;
+ break;
+ }
+ if (stats_req.session_id != 0) {
+ /* resend to session ioctl handler */
+ struct pppol2tp_session *session =
+ pppol2tp_session_find(tunnel, stats_req.session_id);
+ if (session != NULL)
+ err = pppol2tp_session_ioctl(session, cmd, arg);
+ else
+ err = -EBADR;
+ break;
+ }
+#ifdef CONFIG_XFRM
+ tunnel->stats.using_ipsec = (sk->sk_policy[0] || sk->sk_policy[1]) ? 1 : 0;
+#endif
+ if (copy_to_user((void __user *) arg, &tunnel->stats,
+ sizeof(tunnel->stats))) {
+ err = -EFAULT;
+ break;
+ }
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get L2TP stats\n", tunnel->name);
+ err = 0;
+ break;
+
+ default:
+ err = -ENOSYS;
+ break;
+ }
+
+ sock_put(sk);
+
+ return err;
+}
+
+/* Main ioctl() handler.
+ * Dispatch to tunnel or session helpers depending on the socket.
+ */
+static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
+ unsigned long arg)
+{
+ struct sock *sk = sock->sk;
+ struct pppol2tp_session *session;
+ struct pppol2tp_tunnel *tunnel;
+ int err;
+
+ if (!sk)
+ return 0;
+
+ err = -EBADF;
+ if (sock_flag(sk, SOCK_DEAD) != 0)
+ goto end;
+
+ err = -ENOTCONN;
+ if ((sk->sk_user_data == NULL) ||
+ (!(sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND))))
+ goto end;
+
+ /* Get session context from the socket */
+ err = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto end;
+
+ /* Special case: if session's session_id is zero, treat ioctl as a
+ * tunnel ioctl
+ */
+ if ((session->tunnel_addr.s_session == 0) &&
+ (session->tunnel_addr.d_session == 0)) {
+ err = -EBADF;
+ tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
+ if (tunnel == NULL)
+ goto end_put_sess;
+
+ err = pppol2tp_tunnel_ioctl(tunnel, cmd, arg);
+ sock_put(session->tunnel_sock);
+ goto end_put_sess;
+ }
+
+ err = pppol2tp_session_ioctl(session, cmd, arg);
+
+end_put_sess:
+ sock_put(sk);
+end:
+ return err;
+}
+
+/*****************************************************************************
+ * setsockopt() / getsockopt() support.
+ *
+ * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
+ * sockets. In order to control kernel tunnel features, we allow userspace to
+ * create a special "tunnel" PPPoX socket which is used for control only.
+ * Tunnel PPPoX sockets have session_id == 0 and simply allow the user
+ * application to issue L2TP setsockopt(), getsockopt() and ioctl() calls.
+ *****************************************************************************/
+
+/* Tunnel setsockopt() helper.
+ */
+static int pppol2tp_tunnel_setsockopt(struct sock *sk,
+ struct pppol2tp_tunnel *tunnel,
+ int optname, int val)
+{
+ int err = 0;
+
+ switch (optname) {
+ case PPPOL2TP_SO_DEBUG:
+ tunnel->debug = val;
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set debug=%x\n", tunnel->name, tunnel->debug);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ return err;
+}
+
+/* Session setsockopt helper.
+ */
+static int pppol2tp_session_setsockopt(struct sock *sk,
+ struct pppol2tp_session *session,
+ int optname, int val)
+{
+ int err = 0;
+
+ switch (optname) {
+ case PPPOL2TP_SO_RECVSEQ:
+ if ((val != 0) && (val != 1)) {
+ err = -EINVAL;
+ break;
+ }
+ session->recv_seq = val ? -1 : 0;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set recv_seq=%d\n", session->name,
+ session->recv_seq);
+ break;
+
+ case PPPOL2TP_SO_SENDSEQ:
+ if ((val != 0) && (val != 1)) {
+ err = -EINVAL;
+ break;
+ }
+ session->send_seq = val ? -1 : 0;
+ {
+ struct sock *ssk = session->sock;
+ struct pppox_sock *po = pppox_sk(ssk);
+ po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
+ PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+ }
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set send_seq=%d\n", session->name, session->send_seq);
+ break;
+
+ case PPPOL2TP_SO_LNSMODE:
+ if ((val != 0) && (val != 1)) {
+ err = -EINVAL;
+ break;
+ }
+ session->lns_mode = val ? -1 : 0;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set lns_mode=%d\n", session->name,
+ session->lns_mode);
+ break;
+
+ case PPPOL2TP_SO_DEBUG:
+ session->debug = val;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set debug=%x\n", session->name, session->debug);
+ break;
+
+ case PPPOL2TP_SO_REORDERTO:
+ session->reorder_timeout = msecs_to_jiffies(val);
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set reorder_timeout=%d\n", session->name,
+ session->reorder_timeout);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ return err;
+}
+
+/* Main setsockopt() entry point.
+ * Does API checks, then calls either the tunnel or session setsockopt
+ * handler, according to whether the PPPoL2TP socket is a for a regular
+ * session or the special tunnel type.
+ */
+static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct sock *sk = sock->sk;
+ struct pppol2tp_session *session = sk->sk_user_data;
+ struct pppol2tp_tunnel *tunnel;
+ int val;
+ int err;
+
+ if (level != SOL_PPPOL2TP)
+ return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+
+ if (optlen < sizeof(int))
+ return -EINVAL;
+
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+
+ err = -ENOTCONN;
+ if (sk->sk_user_data == NULL)
+ goto end;
+
+ /* Get session context from the socket */
+ err = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto end;
+
+ /* Special case: if session_id == 0x0000, treat as operation on tunnel
+ */
+ if ((session->tunnel_addr.s_session == 0) &&
+ (session->tunnel_addr.d_session == 0)) {
+ err = -EBADF;
+ tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
+ if (tunnel == NULL)
+ goto end_put_sess;
+
+ err = pppol2tp_tunnel_setsockopt(sk, tunnel, optname, val);
+ sock_put(session->tunnel_sock);
+ } else
+ err = pppol2tp_session_setsockopt(sk, session, optname, val);
+
+ err = 0;
+
+end_put_sess:
+ sock_put(sk);
+end:
+ return err;
+}
+
+/* Tunnel getsockopt helper. Called with sock locked.
+ */
+static int pppol2tp_tunnel_getsockopt(struct sock *sk,
+ struct pppol2tp_tunnel *tunnel,
+ int optname, int *val)
+{
+ int err = 0;
+
+ switch (optname) {
+ case PPPOL2TP_SO_DEBUG:
+ *val = tunnel->debug;
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get debug=%x\n", tunnel->name, tunnel->debug);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ return err;
+}
+
+/* Session getsockopt helper. Called with sock locked.
+ */
+static int pppol2tp_session_getsockopt(struct sock *sk,
+ struct pppol2tp_session *session,
+ int optname, int *val)
+{
+ int err = 0;
+
+ switch (optname) {
+ case PPPOL2TP_SO_RECVSEQ:
+ *val = session->recv_seq;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get recv_seq=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_SENDSEQ:
+ *val = session->send_seq;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get send_seq=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_LNSMODE:
+ *val = session->lns_mode;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get lns_mode=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_DEBUG:
+ *val = session->debug;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get debug=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_REORDERTO:
+ *val = (int) jiffies_to_msecs(session->reorder_timeout);
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get reorder_timeout=%d\n", session->name, *val);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ }
+
+ return err;
+}
+
+/* Main getsockopt() entry point.
+ * Does API checks, then calls either the tunnel or session getsockopt
+ * handler, according to whether the PPPoX socket is a for a regular session
+ * or the special tunnel type.
+ */
+static int pppol2tp_getsockopt(struct socket *sock, int level,
+ int optname, char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ struct pppol2tp_session *session = sk->sk_user_data;
+ struct pppol2tp_tunnel *tunnel;
+ int val, len;
+ int err;
+
+ if (level != SOL_PPPOL2TP)
+ return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+
+ if (get_user(len, (int __user *) optlen))
+ return -EFAULT;
+
+ len = min_t(unsigned int, len, sizeof(int));
+
+ if (len < 0)
+ return -EINVAL;
+
+ err = -ENOTCONN;
+ if (sk->sk_user_data == NULL)
+ goto end;
+
+ /* Get the session context */
+ err = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto end;
+
+ /* Special case: if session_id == 0x0000, treat as operation on tunnel */
+ if ((session->tunnel_addr.s_session == 0) &&
+ (session->tunnel_addr.d_session == 0)) {
+ err = -EBADF;
+ tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
+ if (tunnel == NULL)
+ goto end_put_sess;
+
+ err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val);
+ sock_put(session->tunnel_sock);
+ } else
+ err = pppol2tp_session_getsockopt(sk, session, optname, &val);
+
+ err = -EFAULT;
+ if (put_user(len, (int __user *) optlen))
+ goto end_put_sess;
+
+ if (copy_to_user((void __user *) optval, &val, len))
+ goto end_put_sess;
+
+ err = 0;
+
+end_put_sess:
+ sock_put(sk);
+end:
+ return err;
+}
+
+/*****************************************************************************
+ * /proc filesystem for debug
+ *****************************************************************************/
+
+#ifdef CONFIG_PROC_FS
+
+#include <linux/seq_file.h>
+
+struct pppol2tp_seq_data {
+ struct seq_net_private p;
+ struct pppol2tp_tunnel *tunnel; /* current tunnel */
+ struct pppol2tp_session *session; /* NULL means get first session in tunnel */
+};
+
+static struct pppol2tp_session *next_session(struct pppol2tp_tunnel *tunnel, struct pppol2tp_session *curr)
+{
+ struct pppol2tp_session *session = NULL;
+ struct hlist_node *walk;
+ int found = 0;
+ int next = 0;
+ int i;
+
+ read_lock_bh(&tunnel->hlist_lock);
+ for (i = 0; i < PPPOL2TP_HASH_SIZE; i++) {
+ hlist_for_each_entry(session, walk, &tunnel->session_hlist[i], hlist) {
+ if (curr == NULL) {
+ found = 1;
+ goto out;
+ }
+ if (session == curr) {
+ next = 1;
+ continue;
+ }
+ if (next) {
+ found = 1;
+ goto out;
+ }
+ }
+ }
+out:
+ read_unlock_bh(&tunnel->hlist_lock);
+ if (!found)
+ session = NULL;
+
+ return session;
+}
+
+static struct pppol2tp_tunnel *next_tunnel(struct pppol2tp_net *pn,
+ struct pppol2tp_tunnel *curr)
+{
+ struct pppol2tp_tunnel *tunnel = NULL;
+
+ read_lock_bh(&pn->pppol2tp_tunnel_list_lock);
+ if (list_is_last(&curr->list, &pn->pppol2tp_tunnel_list)) {
+ goto out;
+ }
+ tunnel = list_entry(curr->list.next, struct pppol2tp_tunnel, list);
+out:
+ read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
+
+ return tunnel;
+}
+
+static void *pppol2tp_seq_start(struct seq_file *m, loff_t *offs)
+{
+ struct pppol2tp_seq_data *pd = SEQ_START_TOKEN;
+ struct pppol2tp_net *pn;
+ loff_t pos = *offs;
+
+ if (!pos)
+ goto out;
+
+ BUG_ON(m->private == NULL);
+ pd = m->private;
+ pn = pppol2tp_pernet(seq_file_net(m));
+
+ if (pd->tunnel == NULL) {
+ if (!list_empty(&pn->pppol2tp_tunnel_list))
+ pd->tunnel = list_entry(pn->pppol2tp_tunnel_list.next, struct pppol2tp_tunnel, list);
+ } else {
+ pd->session = next_session(pd->tunnel, pd->session);
+ if (pd->session == NULL) {
+ pd->tunnel = next_tunnel(pn, pd->tunnel);
+ }
+ }
+
+ /* NULL tunnel and session indicates end of list */
+ if ((pd->tunnel == NULL) && (pd->session == NULL))
+ pd = NULL;
+
+out:
+ return pd;
+}
+
+static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return NULL;
+}
+
+static void pppol2tp_seq_stop(struct seq_file *p, void *v)
+{
+ /* nothing to do */
+}
+
+static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
+{
+ struct pppol2tp_tunnel *tunnel = v;
+
+ seq_printf(m, "\nTUNNEL '%s', %c %d\n",
+ tunnel->name,
+ (tunnel == tunnel->sock->sk_user_data) ? 'Y':'N',
+ atomic_read(&tunnel->ref_count) - 1);
+ seq_printf(m, " %08x %llu/%llu/%llu %llu/%llu/%llu\n",
+ tunnel->debug,
+ (unsigned long long)tunnel->stats.tx_packets,
+ (unsigned long long)tunnel->stats.tx_bytes,
+ (unsigned long long)tunnel->stats.tx_errors,
+ (unsigned long long)tunnel->stats.rx_packets,
+ (unsigned long long)tunnel->stats.rx_bytes,
+ (unsigned long long)tunnel->stats.rx_errors);
+}
+
+static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
+{
+ struct pppol2tp_session *session = v;
+
+ seq_printf(m, " SESSION '%s' %08X/%d %04X/%04X -> "
+ "%04X/%04X %d %c\n",
+ session->name,
+ ntohl(session->tunnel_addr.addr.sin_addr.s_addr),
+ ntohs(session->tunnel_addr.addr.sin_port),
+ session->tunnel_addr.s_tunnel,
+ session->tunnel_addr.s_session,
+ session->tunnel_addr.d_tunnel,
+ session->tunnel_addr.d_session,
+ session->sock->sk_state,
+ (session == session->sock->sk_user_data) ?
+ 'Y' : 'N');
+ seq_printf(m, " %d/%d/%c/%c/%s %08x %u\n",
+ session->mtu, session->mru,
+ session->recv_seq ? 'R' : '-',
+ session->send_seq ? 'S' : '-',
+ session->lns_mode ? "LNS" : "LAC",
+ session->debug,
+ jiffies_to_msecs(session->reorder_timeout));
+ seq_printf(m, " %hu/%hu %llu/%llu/%llu %llu/%llu/%llu\n",
+ session->nr, session->ns,
+ (unsigned long long)session->stats.tx_packets,
+ (unsigned long long)session->stats.tx_bytes,
+ (unsigned long long)session->stats.tx_errors,
+ (unsigned long long)session->stats.rx_packets,
+ (unsigned long long)session->stats.rx_bytes,
+ (unsigned long long)session->stats.rx_errors);
+}
+
+static int pppol2tp_seq_show(struct seq_file *m, void *v)
+{
+ struct pppol2tp_seq_data *pd = v;
+
+ /* display header on line 1 */
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(m, "PPPoL2TP driver info, " PPPOL2TP_DRV_VERSION "\n");
+ seq_puts(m, "TUNNEL name, user-data-ok session-count\n");
+ seq_puts(m, " debug tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
+ seq_puts(m, " SESSION name, addr/port src-tid/sid "
+ "dest-tid/sid state user-data-ok\n");
+ seq_puts(m, " mtu/mru/rcvseq/sendseq/lns debug reorderto\n");
+ seq_puts(m, " nr/ns tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
+ goto out;
+ }
+
+ /* Show the tunnel or session context.
+ */
+ if (pd->session == NULL)
+ pppol2tp_seq_tunnel_show(m, pd->tunnel);
+ else
+ pppol2tp_seq_session_show(m, pd->session);
+
+out:
+ return 0;
+}
+
+static const struct seq_operations pppol2tp_seq_ops = {
+ .start = pppol2tp_seq_start,
+ .next = pppol2tp_seq_next,
+ .stop = pppol2tp_seq_stop,
+ .show = pppol2tp_seq_show,
+};
+
+/* Called when our /proc file is opened. We allocate data for use when
+ * iterating our tunnel / session contexts and store it in the private
+ * data of the seq_file.
+ */
+static int pppol2tp_proc_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &pppol2tp_seq_ops,
+ sizeof(struct pppol2tp_seq_data));
+}
+
+static const struct file_operations pppol2tp_proc_fops = {
+ .owner = THIS_MODULE,
+ .open = pppol2tp_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net,
+};
+
+#endif /* CONFIG_PROC_FS */
+
+/*****************************************************************************
+ * Init and cleanup
+ *****************************************************************************/
+
+static const struct proto_ops pppol2tp_ops = {
+ .family = AF_PPPOX,
+ .owner = THIS_MODULE,
+ .release = pppol2tp_release,
+ .bind = sock_no_bind,
+ .connect = pppol2tp_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = pppol2tp_getname,
+ .poll = datagram_poll,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = pppol2tp_setsockopt,
+ .getsockopt = pppol2tp_getsockopt,
+ .sendmsg = pppol2tp_sendmsg,
+ .recvmsg = pppol2tp_recvmsg,
+ .mmap = sock_no_mmap,
+ .ioctl = pppox_ioctl,
+};
+
+static struct pppox_proto pppol2tp_proto = {
+ .create = pppol2tp_create,
+ .ioctl = pppol2tp_ioctl
+};
+
+static __net_init int pppol2tp_init_net(struct net *net)
+{
+ struct pppol2tp_net *pn = pppol2tp_pernet(net);
+ struct proc_dir_entry *pde;
+
+ INIT_LIST_HEAD(&pn->pppol2tp_tunnel_list);
+ rwlock_init(&pn->pppol2tp_tunnel_list_lock);
+
+ pde = proc_net_fops_create(net, "pppol2tp", S_IRUGO, &pppol2tp_proc_fops);
+#ifdef CONFIG_PROC_FS
+ if (!pde)
+ return -ENOMEM;
+#endif
+
+ return 0;
+}
+
+static __net_exit void pppol2tp_exit_net(struct net *net)
+{
+ proc_net_remove(net, "pppol2tp");
+}
+
+static struct pernet_operations pppol2tp_net_ops = {
+ .init = pppol2tp_init_net,
+ .exit = pppol2tp_exit_net,
+ .id = &pppol2tp_net_id,
+ .size = sizeof(struct pppol2tp_net),
+};
+
+static int __init pppol2tp_init(void)
+{
+ int err;
+
+ err = proto_register(&pppol2tp_sk_proto, 0);
+ if (err)
+ goto out;
+ err = register_pppox_proto(PX_PROTO_OL2TP, &pppol2tp_proto);
+ if (err)
+ goto out_unregister_pppol2tp_proto;
+
+ err = register_pernet_device(&pppol2tp_net_ops);
+ if (err)
+ goto out_unregister_pppox_proto;
+
+ printk(KERN_INFO "PPPoL2TP kernel driver, %s\n",
+ PPPOL2TP_DRV_VERSION);
+
+out:
+ return err;
+out_unregister_pppox_proto:
+ unregister_pppox_proto(PX_PROTO_OL2TP);
+out_unregister_pppol2tp_proto:
+ proto_unregister(&pppol2tp_sk_proto);
+ goto out;
+}
+
+static void __exit pppol2tp_exit(void)
+{
+ unregister_pppox_proto(PX_PROTO_OL2TP);
+ unregister_pernet_device(&pppol2tp_net_ops);
+ proto_unregister(&pppol2tp_sk_proto);
+}
+
+module_init(pppol2tp_init);
+module_exit(pppol2tp_exit);
+
+MODULE_AUTHOR("Martijn van Oosterhout <kleptog@svana.org>, "
+ "James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("PPP over L2TP over UDP");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(PPPOL2TP_DRV_VERSION);
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 02/12] l2tp: Split pppol2tp patch into separate l2tp and ppp parts
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
2010-03-30 16:17 ` [PATCH v3 01/12] l2tp: Relocate pppol2tp driver to new net/l2tp directory James Chapman
@ 2010-03-30 16:17 ` James Chapman
2010-03-30 16:17 ` [PATCH v3 03/12] ppp: Add ppp_dev_name() exported function James Chapman
` (9 subsequent siblings)
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:17 UTC (permalink / raw)
To: netdev
This patch splits the pppol2tp driver into separate L2TP and PPP parts
to prepare for L2TPv3 support. In L2TPv3, protocols other than PPP can
be carried, so this split creates a common L2TP core that will handle
the common L2TP bits which protocol support modules such as PPP will
use.
Note that the existing pppol2tp module is split into l2tp_core and
l2tp_ppp by this change.
There are no feature changes here. Internally, however, there are
significant changes, mostly to handle the separation of PPP-specific
data from the L2TP session and to provide hooks in the core for
modules like PPP to access.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
drivers/net/Kconfig | 7
include/linux/if_pppol2tp.h | 2
net/Kconfig | 1
net/Makefile | 2
net/l2tp/Kconfig | 28
net/l2tp/Makefile | 5
net/l2tp/l2tp_core.c | 1482 ++++++++++++++++++++++++
net/l2tp/l2tp_core.h | 258 ++++
net/l2tp/l2tp_ppp.c | 1440 +++++++++++++++++++++++
net/l2tp/pppol2tp.c | 2680 -------------------------------------------
10 files changed, 3216 insertions(+), 2689 deletions(-)
create mode 100644 net/l2tp/Kconfig
create mode 100644 net/l2tp/l2tp_core.c
create mode 100644 net/l2tp/l2tp_core.h
create mode 100644 net/l2tp/l2tp_ppp.c
delete mode 100644 net/l2tp/pppol2tp.c
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 4f1f974..06bb76e 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -3155,17 +3155,12 @@ config PPPOATM
config PPPOL2TP
tristate "PPP over L2TP (EXPERIMENTAL)"
- depends on EXPERIMENTAL && PPP && INET
+ depends on EXPERIMENTAL && L2TP && PPP
help
Support for PPP-over-L2TP socket family. L2TP is a protocol
used by ISPs and enterprises to tunnel PPP traffic over UDP
tunnels. L2TP is replacing PPTP for VPN uses.
- This kernel component handles only L2TP data packets: a
- userland daemon handles L2TP the control protocol (tunnel
- and session setup). One such daemon is OpenL2TP
- (http://openl2tp.sourceforge.net/).
-
config SLIP
tristate "SLIP (serial line) support"
---help---
diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h
index c58baea..1a1fb6e 100644
--- a/include/linux/if_pppol2tp.h
+++ b/include/linux/if_pppol2tp.h
@@ -2,7 +2,7 @@
* Linux PPP over L2TP (PPPoL2TP) Socket Implementation (RFC 2661)
*
* This file supplies definitions required by the PPP over L2TP driver
- * (pppol2tp.c). All version information wrt this file is located in pppol2tp.c
+ * (l2tp_ppp.c). All version information wrt this file is located in l2tp_ppp.c
*
* License:
* This program is free software; you can redistribute it and/or
diff --git a/net/Kconfig b/net/Kconfig
index 6851464..a9ed139 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -186,6 +186,7 @@ source "net/sctp/Kconfig"
source "net/rds/Kconfig"
source "net/tipc/Kconfig"
source "net/atm/Kconfig"
+source "net/l2tp/Kconfig"
source "net/802/Kconfig"
source "net/bridge/Kconfig"
source "net/dsa/Kconfig"
diff --git a/net/Makefile b/net/Makefile
index 16d29aa..818b3ce 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -40,7 +40,7 @@ obj-$(CONFIG_BT) += bluetooth/
obj-$(CONFIG_SUNRPC) += sunrpc/
obj-$(CONFIG_AF_RXRPC) += rxrpc/
obj-$(CONFIG_ATM) += atm/
-obj-$(CONFIG_PPPOL2TP) += l2tp/
+obj-$(CONFIG_L2TP) += l2tp/
obj-$(CONFIG_DECNET) += decnet/
obj-$(CONFIG_ECONET) += econet/
obj-$(CONFIG_PHONET) += phonet/
diff --git a/net/l2tp/Kconfig b/net/l2tp/Kconfig
new file mode 100644
index 0000000..ec88c5c
--- /dev/null
+++ b/net/l2tp/Kconfig
@@ -0,0 +1,28 @@
+#
+# Layer Two Tunneling Protocol (L2TP)
+#
+
+menuconfig L2TP
+ tristate "Layer Two Tunneling Protocol (L2TP)"
+ depends on INET
+ ---help---
+ Layer Two Tunneling Protocol
+
+ From RFC 2661 <http://www.ietf.org/rfc/rfc2661.txt>.
+
+ L2TP facilitates the tunneling of packets across an
+ intervening network in a way that is as transparent as
+ possible to both end-users and applications.
+
+ L2TP is often used to tunnel PPP traffic over IP
+ tunnels. One IP tunnel may carry thousands of individual PPP
+ connections. L2TP is also used as a VPN protocol, popular
+ with home workers to connect to their offices.
+
+ The kernel component handles only L2TP data packets: a
+ userland daemon handles L2TP the control protocol (tunnel
+ and session setup). One such daemon is OpenL2TP
+ (http://openl2tp.org/).
+
+ If you don't need L2TP, say N. To compile all L2TP code as
+ modules, choose M here.
diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
index 9af41e8..c91f208 100644
--- a/net/l2tp/Makefile
+++ b/net/l2tp/Makefile
@@ -2,4 +2,7 @@
# Makefile for the L2TP.
#
-obj-$(CONFIG_PPPOL2TP) += pppol2tp.o
+obj-$(CONFIG_L2TP) += l2tp_core.o
+
+# Build l2tp as modules if L2TP is M
+obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
new file mode 100644
index 0000000..0c1a3b7
--- /dev/null
+++ b/net/l2tp/l2tp_core.c
@@ -0,0 +1,1482 @@
+/*
+ * L2TP core.
+ *
+ * Copyright (c) 2008,2009,2010 Katalix Systems Ltd
+ *
+ * This file contains some code of the original L2TPv2 pppol2tp
+ * driver, which has the following copyright:
+ *
+ * Authors: Martijn van Oosterhout <kleptog@svana.org>
+ * James Chapman (jchapman@katalix.com)
+ * Contributors:
+ * Michal Ostrowski <mostrows@speakeasy.net>
+ * Arnaldo Carvalho de Melo <acme@xconectiva.com.br>
+ * David S. Miller (davem@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/jiffies.h>
+
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/hash.h>
+#include <linux/sort.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include <asm/byteorder.h>
+#include <asm/atomic.h>
+
+#include "l2tp_core.h"
+
+#define L2TP_DRV_VERSION "V2.0"
+
+/* L2TP header constants */
+#define L2TP_HDRFLAG_T 0x8000
+#define L2TP_HDRFLAG_L 0x4000
+#define L2TP_HDRFLAG_S 0x0800
+#define L2TP_HDRFLAG_O 0x0200
+#define L2TP_HDRFLAG_P 0x0100
+
+#define L2TP_HDR_VER_MASK 0x000F
+#define L2TP_HDR_VER_2 0x0002
+
+/* L2TPv3 default L2-specific sublayer */
+#define L2TP_SLFLAG_S 0x40000000
+#define L2TP_SL_SEQ_MASK 0x00ffffff
+
+#define L2TP_HDR_SIZE_SEQ 10
+#define L2TP_HDR_SIZE_NOSEQ 6
+
+/* Default trace flags */
+#define L2TP_DEFAULT_DEBUG_FLAGS 0
+
+#define PRINTK(_mask, _type, _lvl, _fmt, args...) \
+ do { \
+ if ((_mask) & (_type)) \
+ printk(_lvl "L2TP: " _fmt, ##args); \
+ } while (0)
+
+/* Private data stored for received packets in the skb.
+ */
+struct l2tp_skb_cb {
+ u16 ns;
+ u16 has_seq;
+ u16 length;
+ unsigned long expires;
+};
+
+#define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)])
+
+static atomic_t l2tp_tunnel_count;
+static atomic_t l2tp_session_count;
+
+/* per-net private data for this module */
+static unsigned int l2tp_net_id;
+struct l2tp_net {
+ struct list_head l2tp_tunnel_list;
+ rwlock_t l2tp_tunnel_list_lock;
+};
+
+static inline struct l2tp_net *l2tp_pernet(struct net *net)
+{
+ BUG_ON(!net);
+
+ return net_generic(net, l2tp_net_id);
+}
+
+/* Session hash list.
+ * The session_id SHOULD be random according to RFC2661, but several
+ * L2TP implementations (Cisco and Microsoft) use incrementing
+ * session_ids. So we do a real hash on the session_id, rather than a
+ * simple bitmask.
+ */
+static inline struct hlist_head *
+l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
+{
+ return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)];
+}
+
+/* Lookup a session by id
+ */
+struct l2tp_session *l2tp_session_find(struct l2tp_tunnel *tunnel, u32 session_id)
+{
+ struct hlist_head *session_list =
+ l2tp_session_id_hash(tunnel, session_id);
+ struct l2tp_session *session;
+ struct hlist_node *walk;
+
+ read_lock_bh(&tunnel->hlist_lock);
+ hlist_for_each_entry(session, walk, session_list, hlist) {
+ if (session->session_id == session_id) {
+ read_unlock_bh(&tunnel->hlist_lock);
+ return session;
+ }
+ }
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_find);
+
+struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth, int *skipped)
+{
+ int hash;
+ struct hlist_node *walk;
+ struct l2tp_session *session;
+ struct l2tp_session *ret = NULL;
+ int count = 0;
+
+ read_lock_bh(&tunnel->hlist_lock);
+ for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
+ hlist_for_each_entry(session, walk, &tunnel->session_hlist[hash], hlist) {
+ if (++count > nth) {
+ ret = session;
+ break;
+ }
+ }
+ }
+
+ if (skipped)
+ *skipped = count;
+
+ read_unlock_bh(&tunnel->hlist_lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+
+/* Lookup a tunnel by id
+ */
+struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id)
+{
+ struct l2tp_tunnel *tunnel;
+ struct l2tp_net *pn = l2tp_pernet(net);
+
+ read_lock_bh(&pn->l2tp_tunnel_list_lock);
+ list_for_each_entry(tunnel, &pn->l2tp_tunnel_list, list) {
+ if (tunnel->tunnel_id == tunnel_id) {
+ read_unlock_bh(&pn->l2tp_tunnel_list_lock);
+ return tunnel;
+ }
+ }
+ read_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_find);
+
+struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+ struct l2tp_tunnel *tunnel;
+ struct l2tp_tunnel *ret = NULL;
+ int count = 0;
+
+ read_lock_bh(&pn->l2tp_tunnel_list_lock);
+ list_for_each_entry(tunnel, &pn->l2tp_tunnel_list, list) {
+ if (++count > nth) {
+ ret = tunnel;
+ break;
+ }
+ }
+
+ read_unlock_bh(&pn->l2tp_tunnel_list_lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_find_nth);
+
+/*****************************************************************************
+ * Receive data handling
+ *****************************************************************************/
+
+/* Queue a skb in order. We come here only if the skb has an L2TP sequence
+ * number.
+ */
+static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *skb)
+{
+ struct sk_buff *skbp;
+ struct sk_buff *tmp;
+ u16 ns = L2TP_SKB_CB(skb)->ns;
+
+ spin_lock_bh(&session->reorder_q.lock);
+ skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
+ if (L2TP_SKB_CB(skbp)->ns > ns) {
+ __skb_queue_before(&session->reorder_q, skbp, skb);
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n",
+ session->name, ns, L2TP_SKB_CB(skbp)->ns,
+ skb_queue_len(&session->reorder_q));
+ session->stats.rx_oos_packets++;
+ goto out;
+ }
+ }
+
+ __skb_queue_tail(&session->reorder_q, skb);
+
+out:
+ spin_unlock_bh(&session->reorder_q.lock);
+}
+
+/* Dequeue a single skb.
+ */
+static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *skb)
+{
+ struct l2tp_tunnel *tunnel = session->tunnel;
+ int length = L2TP_SKB_CB(skb)->length;
+
+ /* We're about to requeue the skb, so return resources
+ * to its current owner (a socket receive buffer).
+ */
+ skb_orphan(skb);
+
+ tunnel->stats.rx_packets++;
+ tunnel->stats.rx_bytes += length;
+ session->stats.rx_packets++;
+ session->stats.rx_bytes += length;
+
+ if (L2TP_SKB_CB(skb)->has_seq) {
+ /* Bump our Nr */
+ session->nr++;
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: updated nr to %hu\n", session->name, session->nr);
+ }
+
+ /* call private receive handler */
+ if (session->recv_skb != NULL)
+ (*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length);
+ else
+ kfree_skb(skb);
+
+ if (session->deref)
+ (*session->deref)(session);
+}
+
+/* Dequeue skbs from the session's reorder_q, subject to packet order.
+ * Skbs that have been in the queue for too long are simply discarded.
+ */
+static void l2tp_recv_dequeue(struct l2tp_session *session)
+{
+ struct sk_buff *skb;
+ struct sk_buff *tmp;
+
+ /* If the pkt at the head of the queue has the nr that we
+ * expect to send up next, dequeue it and any other
+ * in-sequence packets behind it.
+ */
+ spin_lock_bh(&session->reorder_q.lock);
+ skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
+ if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) {
+ session->stats.rx_seq_discards++;
+ session->stats.rx_errors++;
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: oos pkt %hu len %d discarded (too old), "
+ "waiting for %hu, reorder_q_len=%d\n",
+ session->name, L2TP_SKB_CB(skb)->ns,
+ L2TP_SKB_CB(skb)->length, session->nr,
+ skb_queue_len(&session->reorder_q));
+ __skb_unlink(skb, &session->reorder_q);
+ kfree_skb(skb);
+ if (session->deref)
+ (*session->deref)(session);
+ continue;
+ }
+
+ if (L2TP_SKB_CB(skb)->has_seq) {
+ if (L2TP_SKB_CB(skb)->ns != session->nr) {
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: holding oos pkt %hu len %d, "
+ "waiting for %hu, reorder_q_len=%d\n",
+ session->name, L2TP_SKB_CB(skb)->ns,
+ L2TP_SKB_CB(skb)->length, session->nr,
+ skb_queue_len(&session->reorder_q));
+ goto out;
+ }
+ }
+ __skb_unlink(skb, &session->reorder_q);
+
+ /* Process the skb. We release the queue lock while we
+ * do so to let other contexts process the queue.
+ */
+ spin_unlock_bh(&session->reorder_q.lock);
+ l2tp_recv_dequeue_skb(session, skb);
+ spin_lock_bh(&session->reorder_q.lock);
+ }
+
+out:
+ spin_unlock_bh(&session->reorder_q.lock);
+}
+
+static inline int l2tp_verify_udp_checksum(struct sock *sk,
+ struct sk_buff *skb)
+{
+ struct udphdr *uh = udp_hdr(skb);
+ u16 ulen = ntohs(uh->len);
+ struct inet_sock *inet;
+ __wsum psum;
+
+ if (sk->sk_no_check || skb_csum_unnecessary(skb) || !uh->check)
+ return 0;
+
+ inet = inet_sk(sk);
+ psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr, ulen,
+ IPPROTO_UDP, 0);
+
+ if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
+ !csum_fold(csum_add(psum, skb->csum)))
+ return 0;
+
+ skb->csum = psum;
+
+ return __skb_checksum_complete(skb);
+}
+
+/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame
+ * here. The skb is not on a list when we get here.
+ * Returns 0 if the packet was a data packet and was successfully passed on.
+ * Returns 1 if the packet was not a good data packet and could not be
+ * forwarded. All such packets are passed up to userspace to deal with.
+ */
+int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
+ int (*payload_hook)(struct sk_buff *skb))
+{
+ struct l2tp_session *session = NULL;
+ unsigned char *ptr, *optr;
+ u16 hdrflags;
+ u32 tunnel_id, session_id;
+ int length;
+ int offset;
+ u16 version;
+ u16 ns, nr;
+
+ if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb))
+ goto discard_bad_csum;
+
+ /* UDP always verifies the packet length. */
+ __skb_pull(skb, sizeof(struct udphdr));
+
+ /* Short packet? */
+ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) {
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
+ "%s: recv short packet (len=%d)\n", tunnel->name, skb->len);
+ goto error;
+ }
+
+ /* Point to L2TP header */
+ optr = ptr = skb->data;
+
+ /* Trace packet contents, if enabled */
+ if (tunnel->debug & L2TP_MSG_DATA) {
+ length = min(32u, skb->len);
+ if (!pskb_may_pull(skb, length))
+ goto error;
+
+ printk(KERN_DEBUG "%s: recv: ", tunnel->name);
+
+ offset = 0;
+ do {
+ printk(" %02X", ptr[offset]);
+ } while (++offset < length);
+
+ printk("\n");
+ }
+
+ /* Get L2TP header flags */
+ hdrflags = ntohs(*(__be16 *)ptr);
+
+ /* Check protocol version */
+ version = hdrflags & L2TP_HDR_VER_MASK;
+ if (version != tunnel->version) {
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
+ "%s: recv protocol version mismatch: got %d expected %d\n",
+ tunnel->name, version, tunnel->version);
+ goto error;
+ }
+
+ /* Get length of L2TP packet */
+ length = skb->len;
+
+ /* If type is control packet, it is handled by userspace. */
+ if (hdrflags & L2TP_HDRFLAG_T) {
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_DEBUG,
+ "%s: recv control packet, len=%d\n", tunnel->name, length);
+ goto error;
+ }
+
+ /* Skip flags */
+ ptr += 2;
+
+ /* If length is present, skip it */
+ if (hdrflags & L2TP_HDRFLAG_L)
+ ptr += 2;
+
+ /* Extract tunnel and session ID */
+ tunnel_id = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+ session_id = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+
+ /* Find the session context */
+ session = l2tp_session_find(tunnel, session_id);
+ if (!session) {
+ /* Not found? Pass to userspace to deal with */
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
+ "%s: no session found (%hu/%hu). Passing up.\n",
+ tunnel->name, tunnel_id, session_id);
+ goto error;
+ }
+
+ /* The ref count is increased since we now hold a pointer to
+ * the session. Take care to decrement the refcnt when exiting
+ * this function from now on...
+ */
+ l2tp_session_inc_refcount(session);
+ if (session->ref)
+ (*session->ref)(session);
+
+ /* Handle the optional sequence numbers. Sequence numbers are
+ * in different places for L2TPv2 and L2TPv3.
+ *
+ * If we are the LAC, enable/disable sequence numbers under
+ * the control of the LNS. If no sequence numbers present but
+ * we were expecting them, discard frame.
+ */
+ ns = nr = 0;
+ L2TP_SKB_CB(skb)->has_seq = 0;
+ if (hdrflags & L2TP_HDRFLAG_S) {
+ ns = (u16) ntohs(*(__be16 *) ptr);
+ ptr += 2;
+ nr = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+
+ /* Store L2TP info in the skb */
+ L2TP_SKB_CB(skb)->ns = ns;
+ L2TP_SKB_CB(skb)->has_seq = 1;
+
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: recv data ns=%hu, nr=%hu, session nr=%hu\n",
+ session->name, ns, nr, session->nr);
+ }
+
+ if (L2TP_SKB_CB(skb)->has_seq) {
+ /* Received a packet with sequence numbers. If we're the LNS,
+ * check if we sre sending sequence numbers and if not,
+ * configure it so.
+ */
+ if ((!session->lns_mode) && (!session->send_seq)) {
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_INFO,
+ "%s: requested to enable seq numbers by LNS\n",
+ session->name);
+ session->send_seq = -1;
+ }
+ } else {
+ /* No sequence numbers.
+ * If user has configured mandatory sequence numbers, discard.
+ */
+ if (session->recv_seq) {
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_WARNING,
+ "%s: recv data has no seq numbers when required. "
+ "Discarding\n", session->name);
+ session->stats.rx_seq_discards++;
+ goto discard;
+ }
+
+ /* If we're the LAC and we're sending sequence numbers, the
+ * LNS has requested that we no longer send sequence numbers.
+ * If we're the LNS and we're sending sequence numbers, the
+ * LAC is broken. Discard the frame.
+ */
+ if ((!session->lns_mode) && (session->send_seq)) {
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_INFO,
+ "%s: requested to disable seq numbers by LNS\n",
+ session->name);
+ session->send_seq = 0;
+ } else if (session->send_seq) {
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_WARNING,
+ "%s: recv data has no seq numbers when required. "
+ "Discarding\n", session->name);
+ session->stats.rx_seq_discards++;
+ goto discard;
+ }
+ }
+
+ /* If offset bit set, skip it. */
+ if (hdrflags & L2TP_HDRFLAG_O) {
+ offset = ntohs(*(__be16 *)ptr);
+ ptr += 2 + offset;
+ }
+
+ offset = ptr - optr;
+ if (!pskb_may_pull(skb, offset))
+ goto discard;
+
+ __skb_pull(skb, offset);
+
+ /* If caller wants to process the payload before we queue the
+ * packet, do so now.
+ */
+ if (payload_hook)
+ if ((*payload_hook)(skb))
+ goto discard;
+
+ /* Prepare skb for adding to the session's reorder_q. Hold
+ * packets for max reorder_timeout or 1 second if not
+ * reordering.
+ */
+ L2TP_SKB_CB(skb)->length = length;
+ L2TP_SKB_CB(skb)->expires = jiffies +
+ (session->reorder_timeout ? session->reorder_timeout : HZ);
+
+ /* Add packet to the session's receive queue. Reordering is done here, if
+ * enabled. Saved L2TP protocol info is stored in skb->sb[].
+ */
+ if (L2TP_SKB_CB(skb)->has_seq) {
+ if (session->reorder_timeout != 0) {
+ /* Packet reordering enabled. Add skb to session's
+ * reorder queue, in order of ns.
+ */
+ l2tp_recv_queue_skb(session, skb);
+ } else {
+ /* Packet reordering disabled. Discard out-of-sequence
+ * packets
+ */
+ if (L2TP_SKB_CB(skb)->ns != session->nr) {
+ session->stats.rx_seq_discards++;
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: oos pkt %hu len %d discarded, "
+ "waiting for %hu, reorder_q_len=%d\n",
+ session->name, L2TP_SKB_CB(skb)->ns,
+ L2TP_SKB_CB(skb)->length, session->nr,
+ skb_queue_len(&session->reorder_q));
+ goto discard;
+ }
+ skb_queue_tail(&session->reorder_q, skb);
+ }
+ } else {
+ /* No sequence numbers. Add the skb to the tail of the
+ * reorder queue. This ensures that it will be
+ * delivered after all previous sequenced skbs.
+ */
+ skb_queue_tail(&session->reorder_q, skb);
+ }
+
+ /* Try to dequeue as many skbs from reorder_q as we can. */
+ l2tp_recv_dequeue(session);
+
+ l2tp_session_dec_refcount(session);
+
+ return 0;
+
+discard:
+ session->stats.rx_errors++;
+ kfree_skb(skb);
+
+ if (session->deref)
+ (*session->deref)(session);
+
+ l2tp_session_dec_refcount(session);
+
+ return 0;
+
+discard_bad_csum:
+ LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
+ UDP_INC_STATS_USER(tunnel->l2tp_net, UDP_MIB_INERRORS, 0);
+ tunnel->stats.rx_errors++;
+ kfree_skb(skb);
+
+ return 0;
+
+error:
+ /* Put UDP header back */
+ __skb_push(skb, sizeof(struct udphdr));
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(l2tp_udp_recv_core);
+
+/* UDP encapsulation receive handler. See net/ipv4/udp.c.
+ * Return codes:
+ * 0 : success.
+ * <0: error
+ * >0: skb should be passed up to userspace as UDP.
+ */
+int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+ struct l2tp_tunnel *tunnel;
+
+ tunnel = l2tp_sock_to_tunnel(sk);
+ if (tunnel == NULL)
+ goto pass_up;
+
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_DEBUG,
+ "%s: received %d bytes\n", tunnel->name, skb->len);
+
+ if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook))
+ goto pass_up_put;
+
+ sock_put(sk);
+ return 0;
+
+pass_up_put:
+ sock_put(sk);
+pass_up:
+ return 1;
+}
+EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv);
+
+/************************************************************************
+ * Transmit handling
+ ***********************************************************************/
+
+/* Build an L2TP header for the session into the buffer provided.
+ */
+static void l2tp_build_l2tpv2_header(struct l2tp_tunnel *tunnel,
+ struct l2tp_session *session,
+ void *buf)
+{
+ __be16 *bufp = buf;
+ u16 flags = L2TP_HDR_VER_2;
+ u32 tunnel_id = tunnel->peer_tunnel_id;
+ u32 session_id = session->peer_session_id;
+
+ if (session->send_seq)
+ flags |= L2TP_HDRFLAG_S;
+
+ /* Setup L2TP header. */
+ *bufp++ = htons(flags);
+ *bufp++ = htons(tunnel_id);
+ *bufp++ = htons(session_id);
+ if (session->send_seq) {
+ *bufp++ = htons(session->ns);
+ *bufp++ = 0;
+ session->ns++;
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: updated ns to %hu\n", session->name, session->ns);
+ }
+}
+
+void l2tp_build_l2tp_header(struct l2tp_session *session, void *buf)
+{
+ struct l2tp_tunnel *tunnel = session->tunnel;
+
+ BUG_ON(tunnel->version != L2TP_HDR_VER_2);
+ l2tp_build_l2tpv2_header(tunnel, session, buf);
+}
+EXPORT_SYMBOL_GPL(l2tp_build_l2tp_header);
+
+int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t data_len)
+{
+ struct l2tp_tunnel *tunnel = session->tunnel;
+ unsigned int len = skb->len;
+ int error;
+
+ /* Debug */
+ if (session->send_seq)
+ PRINTK(session->debug, L2TP_MSG_DATA, KERN_DEBUG,
+ "%s: send %Zd bytes, ns=%hu\n", session->name,
+ data_len, session->ns - 1);
+ else
+ PRINTK(session->debug, L2TP_MSG_DATA, KERN_DEBUG,
+ "%s: send %Zd bytes\n", session->name, data_len);
+
+ if (session->debug & L2TP_MSG_DATA) {
+ int i;
+ unsigned char *datap = skb->data + sizeof(struct udphdr);
+
+ printk(KERN_DEBUG "%s: xmit:", session->name);
+ for (i = 0; i < (len - sizeof(struct udphdr)); i++) {
+ printk(" %02X", *datap++);
+ if (i == 31) {
+ printk(" ...");
+ break;
+ }
+ }
+ printk("\n");
+ }
+
+ /* Queue the packet to IP for output */
+ error = ip_queue_xmit(skb, 1);
+
+ /* Update stats */
+ if (error >= 0) {
+ tunnel->stats.tx_packets++;
+ tunnel->stats.tx_bytes += len;
+ session->stats.tx_packets++;
+ session->stats.tx_bytes += len;
+ } else {
+ tunnel->stats.tx_errors++;
+ session->stats.tx_errors++;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(l2tp_xmit_core);
+
+/* Automatically called when the skb is freed.
+ */
+static void l2tp_sock_wfree(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+
+/* For data skbs that we transmit, we associate with the tunnel socket
+ * but don't do accounting.
+ */
+static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
+{
+ sock_hold(sk);
+ skb->sk = sk;
+ skb->destructor = l2tp_sock_wfree;
+}
+
+/* If caller requires the skb to have a ppp header, the header must be
+ * inserted in the skb data before calling this function.
+ */
+int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len)
+{
+ int data_len = skb->len;
+ struct sock *sk = session->tunnel->sock;
+ struct udphdr *uh;
+ unsigned int udp_len;
+ struct inet_sock *inet;
+ __wsum csum;
+ int old_headroom;
+ int new_headroom;
+ int headroom;
+
+ /* Check that there's enough headroom in the skb to insert IP,
+ * UDP and L2TP headers. If not enough, expand it to
+ * make room. Adjust truesize.
+ */
+ headroom = NET_SKB_PAD + sizeof(struct iphdr) +
+ sizeof(struct udphdr) + hdr_len;
+ old_headroom = skb_headroom(skb);
+ if (skb_cow_head(skb, headroom))
+ goto abort;
+
+ new_headroom = skb_headroom(skb);
+ skb_orphan(skb);
+ skb->truesize += new_headroom - old_headroom;
+
+ /* Setup L2TP header */
+ l2tp_build_l2tp_header(session, __skb_push(skb, hdr_len));
+ udp_len = sizeof(struct udphdr) + hdr_len + data_len;
+
+ /* Setup UDP header */
+ inet = inet_sk(sk);
+ __skb_push(skb, sizeof(*uh));
+ skb_reset_transport_header(skb);
+ uh = udp_hdr(skb);
+ uh->source = inet->inet_sport;
+ uh->dest = inet->inet_dport;
+ uh->len = htons(udp_len);
+
+ uh->check = 0;
+
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+ IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
+ IPSKB_REROUTED);
+ nf_reset(skb);
+
+ /* Get routing info from the tunnel socket */
+ skb_dst_drop(skb);
+ skb_dst_set(skb, dst_clone(__sk_dst_get(sk)));
+ l2tp_skb_set_owner_w(skb, sk);
+
+ /* Calculate UDP checksum if configured to do so */
+ if (sk->sk_no_check == UDP_CSUM_NOXMIT)
+ skb->ip_summed = CHECKSUM_NONE;
+ else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
+ (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ csum = skb_checksum(skb, 0, udp_len, 0);
+ uh->check = csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, 0);
+ }
+
+ l2tp_xmit_core(session, skb, data_len);
+
+abort:
+ return 0;
+}
+EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
+
+/*****************************************************************************
+ * Tinnel and session create/destroy.
+ *****************************************************************************/
+
+/* Tunnel socket destruct hook.
+ * The tunnel context is deleted only when all session sockets have been
+ * closed.
+ */
+void l2tp_tunnel_destruct(struct sock *sk)
+{
+ struct l2tp_tunnel *tunnel;
+
+ tunnel = sk->sk_user_data;
+ if (tunnel == NULL)
+ goto end;
+
+ PRINTK(tunnel->debug, L2TP_MSG_CONTROL, KERN_INFO,
+ "%s: closing...\n", tunnel->name);
+
+ /* Close all sessions */
+ l2tp_tunnel_closeall(tunnel);
+
+ /* No longer an encapsulation socket. See net/ipv4/udp.c */
+ (udp_sk(sk))->encap_type = 0;
+ (udp_sk(sk))->encap_rcv = NULL;
+
+ /* Remove hooks into tunnel socket */
+ tunnel->sock = NULL;
+ sk->sk_destruct = tunnel->old_sk_destruct;
+ sk->sk_user_data = NULL;
+
+ /* Call the original destructor */
+ if (sk->sk_destruct)
+ (*sk->sk_destruct)(sk);
+
+ /* We're finished with the socket */
+ l2tp_tunnel_dec_refcount(tunnel);
+
+end:
+ return;
+}
+EXPORT_SYMBOL(l2tp_tunnel_destruct);
+
+/* When the tunnel is closed, all the attached sessions need to go too.
+ */
+void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
+{
+ int hash;
+ struct hlist_node *walk;
+ struct hlist_node *tmp;
+ struct l2tp_session *session;
+
+ BUG_ON(tunnel == NULL);
+
+ PRINTK(tunnel->debug, L2TP_MSG_CONTROL, KERN_INFO,
+ "%s: closing all sessions...\n", tunnel->name);
+
+ write_lock_bh(&tunnel->hlist_lock);
+ for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
+again:
+ hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
+ session = hlist_entry(walk, struct l2tp_session, hlist);
+
+ PRINTK(session->debug, L2TP_MSG_CONTROL, KERN_INFO,
+ "%s: closing session\n", session->name);
+
+ hlist_del_init(&session->hlist);
+
+ /* Since we should hold the sock lock while
+ * doing any unbinding, we need to release the
+ * lock we're holding before taking that lock.
+ * Hold a reference to the sock so it doesn't
+ * disappear as we're jumping between locks.
+ */
+ if (session->ref != NULL)
+ (*session->ref)(session);
+
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ if (session->session_close != NULL)
+ (*session->session_close)(session);
+
+ if (session->deref != NULL)
+ (*session->deref)(session);
+
+ write_lock_bh(&tunnel->hlist_lock);
+
+ /* Now restart from the beginning of this hash
+ * chain. We always remove a session from the
+ * list so we are guaranteed to make forward
+ * progress.
+ */
+ goto again;
+ }
+ }
+ write_unlock_bh(&tunnel->hlist_lock);
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall);
+
+/* Really kill the tunnel.
+ * Come here only when all sessions have been cleared from the tunnel.
+ */
+void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
+{
+ struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
+
+ BUG_ON(atomic_read(&tunnel->ref_count) != 0);
+ BUG_ON(tunnel->sock != NULL);
+
+ PRINTK(tunnel->debug, L2TP_MSG_CONTROL, KERN_INFO,
+ "%s: free...\n", tunnel->name);
+
+ /* Remove from tunnel list */
+ write_lock_bh(&pn->l2tp_tunnel_list_lock);
+ list_del_init(&tunnel->list);
+ write_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+ atomic_dec(&l2tp_tunnel_count);
+ kfree(tunnel);
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_free);
+
+int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp)
+{
+ struct l2tp_tunnel *tunnel = NULL;
+ int err;
+ struct socket *sock = NULL;
+ struct sock *sk = NULL;
+ struct l2tp_net *pn;
+
+ /* Get the tunnel socket from the fd, which was opened by
+ * the userspace L2TP daemon.
+ */
+ err = -EBADF;
+ sock = sockfd_lookup(fd, &err);
+ if (!sock) {
+ printk(KERN_ERR "tunl %hu: sockfd_lookup(fd=%d) returned %d\n",
+ tunnel_id, fd, err);
+ goto err;
+ }
+
+ sk = sock->sk;
+
+ /* Quick sanity checks */
+ err = -EPROTONOSUPPORT;
+ if (sk->sk_protocol != IPPROTO_UDP) {
+ printk(KERN_ERR "tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
+ tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
+ goto err;
+ }
+ err = -EAFNOSUPPORT;
+ if (sock->ops->family != AF_INET) {
+ printk(KERN_ERR "tunl %hu: fd %d wrong family, got %d, expected %d\n",
+ tunnel_id, fd, sock->ops->family, AF_INET);
+ goto err;
+ }
+
+ /* Check if this socket has already been prepped */
+ tunnel = (struct l2tp_tunnel *)sk->sk_user_data;
+ if (tunnel != NULL) {
+ /* This socket has already been prepped */
+ err = -EBUSY;
+ goto err;
+ }
+
+ if (version != L2TP_HDR_VER_2)
+ goto err;
+
+ tunnel = kzalloc(sizeof(struct l2tp_tunnel), GFP_KERNEL);
+ if (tunnel == NULL) {
+ err = -ENOMEM;
+ goto err;
+ }
+
+ tunnel->version = version;
+ tunnel->tunnel_id = tunnel_id;
+ tunnel->peer_tunnel_id = peer_tunnel_id;
+ tunnel->debug = L2TP_DEFAULT_DEBUG_FLAGS;
+
+ tunnel->magic = L2TP_TUNNEL_MAGIC;
+ sprintf(&tunnel->name[0], "tunl %u", tunnel_id);
+ rwlock_init(&tunnel->hlist_lock);
+
+ /* The net we belong to */
+ tunnel->l2tp_net = net;
+ pn = l2tp_pernet(net);
+
+ if (cfg)
+ tunnel->debug = cfg->debug;
+
+ /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
+ udp_sk(sk)->encap_type = UDP_ENCAP_L2TPINUDP;
+ udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv;
+
+ sk->sk_user_data = tunnel;
+
+ /* Hook on the tunnel socket destructor so that we can cleanup
+ * if the tunnel socket goes away.
+ */
+ tunnel->old_sk_destruct = sk->sk_destruct;
+ sk->sk_destruct = &l2tp_tunnel_destruct;
+ tunnel->sock = sk;
+ sk->sk_allocation = GFP_ATOMIC;
+
+ /* Add tunnel to our list */
+ INIT_LIST_HEAD(&tunnel->list);
+ write_lock_bh(&pn->l2tp_tunnel_list_lock);
+ list_add(&tunnel->list, &pn->l2tp_tunnel_list);
+ write_unlock_bh(&pn->l2tp_tunnel_list_lock);
+ atomic_inc(&l2tp_tunnel_count);
+
+ /* Bump the reference count. The tunnel context is deleted
+ * only when this drops to zero.
+ */
+ l2tp_tunnel_inc_refcount(tunnel);
+
+ err = 0;
+err:
+ if (tunnelp)
+ *tunnelp = tunnel;
+
+ if (sock)
+ sockfd_put(sock);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
+
+/* Really kill the session.
+ */
+void l2tp_session_free(struct l2tp_session *session)
+{
+ struct l2tp_tunnel *tunnel;
+
+ BUG_ON(atomic_read(&session->ref_count) != 0);
+
+ tunnel = session->tunnel;
+ if (tunnel != NULL) {
+ BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
+
+ /* Delete the session from the hash */
+ write_lock_bh(&tunnel->hlist_lock);
+ hlist_del_init(&session->hlist);
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ if (session->session_id != 0)
+ atomic_dec(&l2tp_session_count);
+
+ sock_put(tunnel->sock);
+
+ /* This will delete the tunnel context if this
+ * is the last session on the tunnel.
+ */
+ session->tunnel = NULL;
+ l2tp_tunnel_dec_refcount(tunnel);
+ }
+
+ kfree(session);
+
+ return;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_free);
+
+struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
+{
+ struct l2tp_session *session;
+
+ session = kzalloc(sizeof(struct l2tp_session) + priv_size, GFP_KERNEL);
+ if (session != NULL) {
+ session->magic = L2TP_SESSION_MAGIC;
+ session->tunnel = tunnel;
+
+ session->session_id = session_id;
+ session->peer_session_id = peer_session_id;
+
+ sprintf(&session->name[0], "sess %u/%u",
+ tunnel->tunnel_id, session->session_id);
+
+ skb_queue_head_init(&session->reorder_q);
+
+ INIT_HLIST_NODE(&session->hlist);
+
+ /* Inherit debug options from tunnel */
+ session->debug = tunnel->debug;
+
+ if (cfg) {
+ session->debug = cfg->debug;
+ session->hdr_len = cfg->hdr_len;
+ session->mtu = cfg->mtu;
+ session->mru = cfg->mru;
+ session->send_seq = cfg->send_seq;
+ session->recv_seq = cfg->recv_seq;
+ session->lns_mode = cfg->lns_mode;
+ }
+
+ /* Bump the reference count. The session context is deleted
+ * only when this drops to zero.
+ */
+ l2tp_session_inc_refcount(session);
+ l2tp_tunnel_inc_refcount(tunnel);
+
+ /* Ensure tunnel socket isn't deleted */
+ sock_hold(tunnel->sock);
+
+ /* Add session to the tunnel's hash list */
+ write_lock_bh(&tunnel->hlist_lock);
+ hlist_add_head(&session->hlist,
+ l2tp_session_id_hash(tunnel, session_id));
+ write_unlock_bh(&tunnel->hlist_lock);
+
+ /* Ignore management session in session count value */
+ if (session->session_id != 0)
+ atomic_inc(&l2tp_session_count);
+ }
+
+ return session;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_create);
+
+/*****************************************************************************
+ * /proc filesystem for debug
+ *****************************************************************************/
+
+#ifdef CONFIG_PROC_FS
+
+struct l2tp_seq_data {
+ struct seq_net_private p;
+ struct l2tp_tunnel *tunnel; /* current tunnel */
+ struct l2tp_session *session; /* NULL means get first session in tunnel */
+};
+
+static struct l2tp_session *next_session(struct l2tp_tunnel *tunnel, struct l2tp_session *curr)
+{
+ struct l2tp_session *session = NULL;
+ struct hlist_node *walk;
+ int found = 0;
+ int next = 0;
+ int i;
+
+ read_lock_bh(&tunnel->hlist_lock);
+ for (i = 0; i < L2TP_HASH_SIZE; i++) {
+ hlist_for_each_entry(session, walk, &tunnel->session_hlist[i], hlist) {
+ if (session->session_id == 0)
+ continue;
+ if (curr == NULL) {
+ found = 1;
+ goto out;
+ }
+ if (session == curr) {
+ next = 1;
+ continue;
+ }
+ if (next) {
+ found = 1;
+ goto out;
+ }
+ }
+ }
+out:
+ read_unlock_bh(&tunnel->hlist_lock);
+ if (!found)
+ session = NULL;
+
+ return session;
+}
+
+static struct l2tp_tunnel *next_tunnel(struct l2tp_net *pn,
+ struct l2tp_tunnel *curr)
+{
+ struct l2tp_tunnel *tunnel = NULL;
+
+ read_lock_bh(&pn->l2tp_tunnel_list_lock);
+ if (list_is_last(&curr->list, &pn->l2tp_tunnel_list))
+ goto out;
+
+ tunnel = list_entry(curr->list.next, struct l2tp_tunnel, list);
+out:
+ read_unlock_bh(&pn->l2tp_tunnel_list_lock);
+
+ return tunnel;
+}
+
+static void *l2tp_seq_start(struct seq_file *m, loff_t *offs)
+{
+ struct l2tp_seq_data *pd = SEQ_START_TOKEN;
+ loff_t pos = *offs;
+ struct l2tp_net *pn;
+
+ if (!pos)
+ goto out;
+
+ BUG_ON(m->private == NULL);
+ pd = m->private;
+ pn = l2tp_pernet(seq_file_net(m));
+
+ if (pd->tunnel == NULL) {
+ if (!list_empty(&pn->l2tp_tunnel_list))
+ pd->tunnel = list_entry(pn->l2tp_tunnel_list.next, struct l2tp_tunnel, list);
+ } else {
+ pd->session = next_session(pd->tunnel, pd->session);
+ if (pd->session == NULL)
+ pd->tunnel = next_tunnel(pn, pd->tunnel);
+ }
+
+ /* NULL tunnel and session indicates end of list */
+ if ((pd->tunnel == NULL) && (pd->session == NULL))
+ pd = NULL;
+
+out:
+ return pd;
+}
+
+static void *l2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ (*pos)++;
+ return NULL;
+}
+
+static void l2tp_seq_stop(struct seq_file *p, void *v)
+{
+ /* nothing to do */
+}
+
+static void l2tp_seq_tunnel_show(struct seq_file *m, void *v)
+{
+ struct l2tp_tunnel *tunnel = v;
+ int session_count = 0;
+ int hash;
+ struct hlist_node *walk;
+ struct hlist_node *tmp;
+
+ read_lock_bh(&tunnel->hlist_lock);
+ for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
+ hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
+ struct l2tp_session *session;
+
+ session = hlist_entry(walk, struct l2tp_session, hlist);
+ if (session->session_id == 0)
+ continue;
+
+ session_count++;
+ }
+ }
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ seq_printf(m, "\nTUNNEL %u peer %u", tunnel->tunnel_id, tunnel->peer_tunnel_id);
+ if (tunnel->sock) {
+ struct inet_sock *inet = inet_sk(tunnel->sock);
+ seq_printf(m, " from " NIPQUAD_FMT " to " NIPQUAD_FMT "\n",
+ NIPQUAD(inet->inet_saddr), NIPQUAD(inet->inet_daddr));
+ seq_printf(m, " source port %hu, dest port %hu\n",
+ ntohs(inet->inet_sport), ntohs(inet->inet_dport));
+ }
+ seq_printf(m, " %d sessions, refcnt %d/%d\n", session_count,
+ tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0,
+ atomic_read(&tunnel->ref_count));
+
+ seq_printf(m, " %08x rx %llu/%llu/%llu rx %llu/%llu/%llu\n",
+ tunnel->debug,
+ (unsigned long long)tunnel->stats.tx_packets,
+ (unsigned long long)tunnel->stats.tx_bytes,
+ (unsigned long long)tunnel->stats.tx_errors,
+ (unsigned long long)tunnel->stats.rx_packets,
+ (unsigned long long)tunnel->stats.rx_bytes,
+ (unsigned long long)tunnel->stats.rx_errors);
+
+ if (tunnel->show != NULL)
+ tunnel->show(m, tunnel);
+}
+
+static void l2tp_seq_session_show(struct seq_file *m, void *v)
+{
+ struct l2tp_session *session = v;
+
+ seq_printf(m, " SESSION %u, peer %u\n", session->session_id, session->peer_session_id);
+ if (session->send_seq || session->recv_seq)
+ seq_printf(m, " nr %hu, ns %hu\n", session->nr, session->ns);
+ seq_printf(m, " refcnt %d\n", atomic_read(&session->ref_count));
+ seq_printf(m, " config %d/%d/%c/%c/%s %08x %u\n",
+ session->mtu, session->mru,
+ session->recv_seq ? 'R' : '-',
+ session->send_seq ? 'S' : '-',
+ session->lns_mode ? "LNS" : "LAC",
+ session->debug,
+ jiffies_to_msecs(session->reorder_timeout));
+ seq_printf(m, " %hu/%hu tx %llu/%llu/%llu rx %llu/%llu/%llu\n",
+ session->nr, session->ns,
+ (unsigned long long)session->stats.tx_packets,
+ (unsigned long long)session->stats.tx_bytes,
+ (unsigned long long)session->stats.tx_errors,
+ (unsigned long long)session->stats.rx_packets,
+ (unsigned long long)session->stats.rx_bytes,
+ (unsigned long long)session->stats.rx_errors);
+
+ if (session->show != NULL)
+ session->show(m, session);
+}
+
+static int l2tp_seq_show(struct seq_file *m, void *v)
+{
+ struct l2tp_seq_data *pd = v;
+
+ /* display header on line 1 */
+ if (v == SEQ_START_TOKEN) {
+ seq_puts(m, "L2TP driver info, " L2TP_DRV_VERSION "\n");
+ seq_puts(m, "TUNNEL ID, peer ID from IP to IP\n");
+ seq_puts(m, " sessions session-count, refcnt refcnt/sk->refcnt\n");
+ seq_puts(m, " debug tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
+ seq_puts(m, " SESSION ID, peer ID\n");
+ seq_puts(m, " refcnt cnt\n");
+ seq_puts(m, " mtu/mru/rcvseq/sendseq/lns debug reorderto\n");
+ seq_puts(m, " nr/ns tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
+
+ seq_printf(m, "tunnels %d sessions %d\n", atomic_read(&l2tp_tunnel_count), atomic_read(&l2tp_session_count));
+ goto out;
+ }
+
+ /* Show the tunnel or session context.
+ */
+ if (pd->session == NULL)
+ l2tp_seq_tunnel_show(m, pd->tunnel);
+ else
+ l2tp_seq_session_show(m, pd->session);
+
+out:
+ return 0;
+}
+
+static const struct seq_operations l2tp_seq_ops = {
+ .start = l2tp_seq_start,
+ .next = l2tp_seq_next,
+ .stop = l2tp_seq_stop,
+ .show = l2tp_seq_show,
+};
+
+/* Called when our /proc file is opened. We allocate data for use when
+ * iterating our tunnel / session contexts and store it in the private
+ * data of the seq_file.
+ */
+static int l2tp_proc_open(struct inode *inode, struct file *file)
+{
+ return seq_open_net(inode, file, &l2tp_seq_ops,
+ sizeof(struct l2tp_seq_data));
+}
+
+static const struct file_operations l2tp_proc_fops = {
+ .owner = THIS_MODULE,
+ .open = l2tp_proc_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_net,
+};
+
+#endif /* CONFIG_PROC_FS */
+
+static __net_init int l2tp_init_net(struct net *net)
+{
+ struct l2tp_net *pn;
+ struct proc_dir_entry *pde;
+ int err;
+
+ pn = kzalloc(sizeof(*pn), GFP_KERNEL);
+ if (!pn)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&pn->l2tp_tunnel_list);
+ rwlock_init(&pn->l2tp_tunnel_list_lock);
+
+ err = net_assign_generic(net, l2tp_net_id, pn);
+ if (err)
+ goto out;
+
+ pde = proc_net_fops_create(net, "l2tp", S_IRUGO, &l2tp_proc_fops);
+#ifdef CONFIG_PROC_FS
+ if (!pde) {
+ err = -ENOMEM;
+ goto out_deassign;
+ }
+#endif
+
+ return 0;
+
+#ifdef CONFIG_PROC_FS
+out_deassign:
+ net_assign_generic(net, l2tp_net_id, NULL);
+#endif
+
+out:
+ kfree(pn);
+ return err;
+}
+
+static __net_exit void l2tp_exit_net(struct net *net)
+{
+ struct l2tp_net *pn;
+
+ proc_net_remove(net, "l2tp");
+ pn = net_generic(net, l2tp_net_id);
+ /*
+ * if someone has cached our net then
+ * further net_generic call will return NULL
+ */
+ net_assign_generic(net, l2tp_net_id, NULL);
+ kfree(pn);
+}
+
+static struct pernet_operations l2tp_net_ops = {
+ .init = l2tp_init_net,
+ .exit = l2tp_exit_net,
+ .id = &l2tp_net_id,
+ .size = sizeof(struct l2tp_net),
+};
+
+/*****************************************************************************
+ * Init and cleanup
+ *****************************************************************************/
+
+static int __init l2tp_init(void)
+{
+ int rc = 0;
+
+ rc = register_pernet_device(&l2tp_net_ops);
+ if (rc)
+ goto out;
+
+ printk(KERN_INFO "L2TP core driver, %s\n", L2TP_DRV_VERSION);
+
+out:
+ return rc;
+}
+
+static void __exit l2tp_exit(void)
+{
+ unregister_pernet_device(&l2tp_net_ops);
+}
+
+module_init(l2tp_init);
+module_exit(l2tp_exit);
+
+MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("L2TP core");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(L2TP_DRV_VERSION);
+
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
new file mode 100644
index 0000000..80ce1ce
--- /dev/null
+++ b/net/l2tp/l2tp_core.h
@@ -0,0 +1,258 @@
+/*
+ * L2TP internal definitions.
+ *
+ * Copyright (c) 2008,2009 Katalix Systems Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _L2TP_CORE_H_
+#define _L2TP_CORE_H_
+
+/* Just some random numbers */
+#define L2TP_TUNNEL_MAGIC 0x42114DDA
+#define L2TP_SESSION_MAGIC 0x0C04EB7D
+
+#define L2TP_HASH_BITS 4
+#define L2TP_HASH_SIZE (1 << L2TP_HASH_BITS)
+
+/* Debug message categories for the DEBUG socket option */
+enum {
+ L2TP_MSG_DEBUG = (1 << 0), /* verbose debug (if
+ * compiled in) */
+ L2TP_MSG_CONTROL = (1 << 1), /* userspace - kernel
+ * interface */
+ L2TP_MSG_SEQ = (1 << 2), /* sequence numbers */
+ L2TP_MSG_DATA = (1 << 3), /* data packets */
+};
+
+struct sk_buff;
+
+struct l2tp_stats {
+ u64 tx_packets;
+ u64 tx_bytes;
+ u64 tx_errors;
+ u64 rx_packets;
+ u64 rx_bytes;
+ u64 rx_seq_discards;
+ u64 rx_oos_packets;
+ u64 rx_errors;
+};
+
+struct l2tp_tunnel;
+
+/* Describes a session. Contains information to determine incoming
+ * packets and transmit outgoing ones.
+ */
+struct l2tp_session_cfg {
+ unsigned data_seq:2; /* data sequencing level
+ * 0 => none, 1 => IP only,
+ * 2 => all
+ */
+ unsigned recv_seq:1; /* expect receive packets with
+ * sequence numbers? */
+ unsigned send_seq:1; /* send packets with sequence
+ * numbers? */
+ unsigned lns_mode:1; /* behave as LNS? LAC enables
+ * sequence numbers under
+ * control of LNS. */
+ int debug; /* bitmask of debug message
+ * categories */
+ int offset; /* offset to payload */
+ int reorder_timeout; /* configured reorder timeout
+ * (in jiffies) */
+ int mtu;
+ int mru;
+ int hdr_len;
+};
+
+struct l2tp_session {
+ int magic; /* should be
+ * L2TP_SESSION_MAGIC */
+
+ struct l2tp_tunnel *tunnel; /* back pointer to tunnel
+ * context */
+ u32 session_id;
+ u32 peer_session_id;
+ u16 nr; /* session NR state (receive) */
+ u16 ns; /* session NR state (send) */
+ struct sk_buff_head reorder_q; /* receive reorder queue */
+ struct hlist_node hlist; /* Hash list node */
+ atomic_t ref_count;
+
+ char name[32]; /* for logging */
+ unsigned data_seq:2; /* data sequencing level
+ * 0 => none, 1 => IP only,
+ * 2 => all
+ */
+ unsigned recv_seq:1; /* expect receive packets with
+ * sequence numbers? */
+ unsigned send_seq:1; /* send packets with sequence
+ * numbers? */
+ unsigned lns_mode:1; /* behave as LNS? LAC enables
+ * sequence numbers under
+ * control of LNS. */
+ int debug; /* bitmask of debug message
+ * categories */
+ int reorder_timeout; /* configured reorder timeout
+ * (in jiffies) */
+ int mtu;
+ int mru;
+ int hdr_len;
+ struct l2tp_stats stats;
+
+ void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len);
+ void (*session_close)(struct l2tp_session *session);
+ void (*ref)(struct l2tp_session *session);
+ void (*deref)(struct l2tp_session *session);
+#ifdef CONFIG_PROC_FS
+ void (*show)(struct seq_file *m, void *priv);
+#endif
+ uint8_t priv[0]; /* private data */
+};
+
+/* Describes the tunnel. It contains info to track all the associated
+ * sessions so incoming packets can be sorted out
+ */
+struct l2tp_tunnel_cfg {
+ int debug; /* bitmask of debug message
+ * categories */
+};
+
+struct l2tp_tunnel {
+ int magic; /* Should be L2TP_TUNNEL_MAGIC */
+ rwlock_t hlist_lock; /* protect session_hlist */
+ struct hlist_head session_hlist[L2TP_HASH_SIZE];
+ /* hashed list of sessions,
+ * hashed by id */
+ u32 tunnel_id;
+ u32 peer_tunnel_id;
+ int version; /* 2=>L2TPv2, 3=>L2TPv3 */
+
+ char name[20]; /* for logging */
+ int debug; /* bitmask of debug message
+ * categories */
+ int hdr_len;
+ struct l2tp_stats stats;
+
+ struct list_head list; /* Keep a list of all tunnels */
+ struct net *l2tp_net; /* the net we belong to */
+
+ atomic_t ref_count;
+#ifdef CONFIG_PROC_FS
+ void (*show)(struct seq_file *m, void *arg);
+#endif
+ int (*recv_payload_hook)(struct sk_buff *skb);
+ void (*old_sk_destruct)(struct sock *);
+ struct sock *sock; /* Parent socket */
+ int fd;
+
+ uint8_t priv[0]; /* private data */
+};
+
+static inline void *l2tp_tunnel_priv(struct l2tp_tunnel *tunnel)
+{
+ return &tunnel->priv[0];
+}
+
+static inline void *l2tp_session_priv(struct l2tp_session *session)
+{
+ return &session->priv[0];
+}
+
+static inline struct l2tp_tunnel *l2tp_sock_to_tunnel(struct sock *sk)
+{
+ struct l2tp_tunnel *tunnel;
+
+ if (sk == NULL)
+ return NULL;
+
+ sock_hold(sk);
+ tunnel = (struct l2tp_tunnel *)(sk->sk_user_data);
+ if (tunnel == NULL) {
+ sock_put(sk);
+ goto out;
+ }
+
+ BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
+
+out:
+ return tunnel;
+}
+
+extern struct l2tp_session *l2tp_session_find(struct l2tp_tunnel *tunnel, u32 session_id);
+extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth, int *skipped);
+extern struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
+extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth, int *skipped);
+
+extern int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp);
+extern struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg);
+extern void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
+extern void l2tp_session_free(struct l2tp_session *session);
+extern int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, int (*payload_hook)(struct sk_buff *skb));
+extern int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
+
+extern void l2tp_build_l2tp_header(struct l2tp_session *session, void *buf);
+extern int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t data_len);
+extern int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len);
+extern void l2tp_tunnel_destruct(struct sock *sk);
+extern void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
+
+/* Tunnel reference counts. Incremented per session that is added to
+ * the tunnel.
+ */
+static inline void l2tp_tunnel_inc_refcount_1(struct l2tp_tunnel *tunnel)
+{
+ atomic_inc(&tunnel->ref_count);
+}
+
+static inline void l2tp_tunnel_dec_refcount_1(struct l2tp_tunnel *tunnel)
+{
+ if (atomic_dec_and_test(&tunnel->ref_count))
+ l2tp_tunnel_free(tunnel);
+}
+#ifdef L2TP_REFCNT_DEBUG
+#define l2tp_tunnel_inc_refcount(_t) do { \
+ printk(KERN_DEBUG "l2tp_tunnel_inc_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_t)->name, atomic_read(&_t->ref_count)); \
+ l2tp_tunnel_inc_refcount_1(_t); \
+ } while (0)
+#define l2tp_tunnel_dec_refcount(_t) do { \
+ printk(KERN_DEBUG "l2tp_tunnel_dec_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_t)->name, atomic_read(&_t->ref_count)); \
+ l2tp_tunnel_dec_refcount_1(_t); \
+ } while (0)
+#else
+#define l2tp_tunnel_inc_refcount(t) l2tp_tunnel_inc_refcount_1(t)
+#define l2tp_tunnel_dec_refcount(t) l2tp_tunnel_dec_refcount_1(t)
+#endif
+
+/* Session reference counts. Incremented when code obtains a reference
+ * to a session.
+ */
+static inline void l2tp_session_inc_refcount_1(struct l2tp_session *session)
+{
+ atomic_inc(&session->ref_count);
+}
+
+static inline void l2tp_session_dec_refcount_1(struct l2tp_session *session)
+{
+ if (atomic_dec_and_test(&session->ref_count))
+ l2tp_session_free(session);
+}
+
+#ifdef L2TP_REFCNT_DEBUG
+#define l2tp_session_inc_refcount(_s) do { \
+ printk(KERN_DEBUG "l2tp_session_inc_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_s)->name, atomic_read(&_s->ref_count)); \
+ l2tp_session_inc_refcount_1(_s); \
+ } while (0)
+#define l2tp_session_dec_refcount(_s) do { \
+ printk(KERN_DEBUG "l2tp_session_dec_refcount: %s:%d %s: cnt=%d\n", __func__, __LINE__, (_s)->name, atomic_read(&_s->ref_count)); \
+ l2tp_session_dec_refcount_1(_s); \
+ } while (0)
+#else
+#define l2tp_session_inc_refcount(s) l2tp_session_inc_refcount_1(s)
+#define l2tp_session_dec_refcount(s) l2tp_session_dec_refcount_1(s)
+#endif
+
+#endif /* _L2TP_CORE_H_ */
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
new file mode 100644
index 0000000..03195ab
--- /dev/null
+++ b/net/l2tp/l2tp_ppp.c
@@ -0,0 +1,1440 @@
+/*****************************************************************************
+ * Linux PPP over L2TP (PPPoX/PPPoL2TP) Sockets
+ *
+ * PPPoX --- Generic PPP encapsulation socket family
+ * PPPoL2TP --- PPP over L2TP (RFC 2661)
+ *
+ * Version: 2.0.0
+ *
+ * Authors: James Chapman (jchapman@katalix.com)
+ *
+ * Based on original work by Martijn van Oosterhout <kleptog@svana.org>
+ *
+ * License:
+ * 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.
+ *
+ */
+
+/* This driver handles only L2TP data frames; control frames are handled by a
+ * userspace application.
+ *
+ * To send data in an L2TP session, userspace opens a PPPoL2TP socket and
+ * attaches it to a bound UDP socket with local tunnel_id / session_id and
+ * peer tunnel_id / session_id set. Data can then be sent or received using
+ * regular socket sendmsg() / recvmsg() calls. Kernel parameters of the socket
+ * can be read or modified using ioctl() or [gs]etsockopt() calls.
+ *
+ * When a PPPoL2TP socket is connected with local and peer session_id values
+ * zero, the socket is treated as a special tunnel management socket.
+ *
+ * Here's example userspace code to create a socket for sending/receiving data
+ * over an L2TP session:-
+ *
+ * struct sockaddr_pppol2tp sax;
+ * int fd;
+ * int session_fd;
+ *
+ * fd = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP);
+ *
+ * sax.sa_family = AF_PPPOX;
+ * sax.sa_protocol = PX_PROTO_OL2TP;
+ * sax.pppol2tp.fd = tunnel_fd; // bound UDP socket
+ * sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr;
+ * sax.pppol2tp.addr.sin_port = addr->sin_port;
+ * sax.pppol2tp.addr.sin_family = AF_INET;
+ * sax.pppol2tp.s_tunnel = tunnel_id;
+ * sax.pppol2tp.s_session = session_id;
+ * sax.pppol2tp.d_tunnel = peer_tunnel_id;
+ * sax.pppol2tp.d_session = peer_session_id;
+ *
+ * session_fd = connect(fd, (struct sockaddr *)&sax, sizeof(sax));
+ *
+ * A pppd plugin that allows PPP traffic to be carried over L2TP using
+ * this driver is available from the OpenL2TP project at
+ * http://openl2tp.sourceforge.net.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/jiffies.h>
+
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/if_pppox.h>
+#include <linux/if_pppol2tp.h>
+#include <net/sock.h>
+#include <linux/ppp_channel.h>
+#include <linux/ppp_defs.h>
+#include <linux/if_ppp.h>
+#include <linux/file.h>
+#include <linux/hash.h>
+#include <linux/sort.h>
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include <asm/byteorder.h>
+#include <asm/atomic.h>
+
+#include "l2tp_core.h"
+
+#define PPPOL2TP_DRV_VERSION "V2.0"
+
+/* Space for UDP, L2TP and PPP headers */
+#define PPPOL2TP_HEADER_OVERHEAD 40
+
+#define PRINTK(_mask, _type, _lvl, _fmt, args...) \
+ do { \
+ if ((_mask) & (_type)) \
+ printk(_lvl "PPPOL2TP: " _fmt, ##args); \
+ } while (0)
+
+/* Number of bytes to build transmit L2TP headers.
+ * Unfortunately the size is different depending on whether sequence numbers
+ * are enabled.
+ */
+#define PPPOL2TP_L2TP_HDR_SIZE_SEQ 10
+#define PPPOL2TP_L2TP_HDR_SIZE_NOSEQ 6
+
+/* Private data of each session. This data lives at the end of struct
+ * l2tp_session, referenced via session->priv[].
+ */
+struct pppol2tp_session {
+ int owner; /* pid that opened the socket */
+
+ struct sock *sock; /* Pointer to the session
+ * PPPoX socket */
+ struct sock *tunnel_sock; /* Pointer to the tunnel UDP
+ * socket */
+ int flags; /* accessed by PPPIOCGFLAGS.
+ * Unused. */
+};
+
+static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb);
+
+static struct ppp_channel_ops pppol2tp_chan_ops = { pppol2tp_xmit , NULL };
+static const struct proto_ops pppol2tp_ops;
+
+/* Helpers to obtain tunnel/session contexts from sockets.
+ */
+static inline struct l2tp_session *pppol2tp_sock_to_session(struct sock *sk)
+{
+ struct l2tp_session *session;
+
+ if (sk == NULL)
+ return NULL;
+
+ sock_hold(sk);
+ session = (struct l2tp_session *)(sk->sk_user_data);
+ if (session == NULL) {
+ sock_put(sk);
+ goto out;
+ }
+
+ BUG_ON(session->magic != L2TP_SESSION_MAGIC);
+
+out:
+ return session;
+}
+
+/*****************************************************************************
+ * Receive data handling
+ *****************************************************************************/
+
+static int pppol2tp_recv_payload_hook(struct sk_buff *skb)
+{
+ /* Skip PPP header, if present. In testing, Microsoft L2TP clients
+ * don't send the PPP header (PPP header compression enabled), but
+ * other clients can include the header. So we cope with both cases
+ * here. The PPP header is always FF03 when using L2TP.
+ *
+ * Note that skb->data[] isn't dereferenced from a u16 ptr here since
+ * the field may be unaligned.
+ */
+ if (!pskb_may_pull(skb, 2))
+ return 1;
+
+ if ((skb->data[0] == 0xff) && (skb->data[1] == 0x03))
+ skb_pull(skb, 2);
+
+ return 0;
+}
+
+/* Receive message. This is the recvmsg for the PPPoL2TP socket.
+ */
+static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *msg, size_t len,
+ int flags)
+{
+ int err;
+ struct sk_buff *skb;
+ struct sock *sk = sock->sk;
+
+ err = -EIO;
+ if (sk->sk_state & PPPOX_BOUND)
+ goto end;
+
+ msg->msg_namelen = 0;
+
+ err = 0;
+ skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
+ flags & MSG_DONTWAIT, &err);
+ if (!skb)
+ goto end;
+
+ if (len > skb->len)
+ len = skb->len;
+ else if (len < skb->len)
+ msg->msg_flags |= MSG_TRUNC;
+
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
+ if (likely(err == 0))
+ err = len;
+
+ kfree_skb(skb);
+end:
+ return err;
+}
+
+static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
+{
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+ struct sock *sk = NULL;
+
+ /* If the socket is bound, send it in to PPP's input queue. Otherwise
+ * queue it on the session socket.
+ */
+ sk = ps->sock;
+ if (sk == NULL)
+ goto no_sock;
+
+ if (sk->sk_state & PPPOX_BOUND) {
+ struct pppox_sock *po;
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
+ "%s: recv %d byte data frame, passing to ppp\n",
+ session->name, data_len);
+
+ /* We need to forget all info related to the L2TP packet
+ * gathered in the skb as we are going to reuse the same
+ * skb for the inner packet.
+ * Namely we need to:
+ * - reset xfrm (IPSec) information as it applies to
+ * the outer L2TP packet and not to the inner one
+ * - release the dst to force a route lookup on the inner
+ * IP packet since skb->dst currently points to the dst
+ * of the UDP tunnel
+ * - reset netfilter information as it doesn't apply
+ * to the inner packet either
+ */
+ secpath_reset(skb);
+ skb_dst_drop(skb);
+ nf_reset(skb);
+
+ po = pppox_sk(sk);
+ ppp_input(&po->chan, skb);
+ } else {
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+ "%s: socket not bound\n", session->name);
+
+ /* Not bound. Nothing we can do, so discard. */
+ session->stats.rx_errors++;
+ kfree_skb(skb);
+ }
+
+ return;
+
+no_sock:
+ PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
+ "%s: no socket\n", session->name);
+ kfree_skb(skb);
+}
+
+static void pppol2tp_session_sock_hold(struct l2tp_session *session)
+{
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+
+ if (ps->sock)
+ sock_hold(ps->sock);
+}
+
+static void pppol2tp_session_sock_put(struct l2tp_session *session)
+{
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+
+ if (ps->sock)
+ sock_put(ps->sock);
+}
+
+/************************************************************************
+ * Transmit handling
+ ***********************************************************************/
+
+/* Tell how big L2TP headers are for a particular session. This
+ * depends on whether sequence numbers are being used.
+ */
+static inline int pppol2tp_l2tp_header_len(struct l2tp_session *session)
+{
+ if (session->send_seq)
+ return PPPOL2TP_L2TP_HDR_SIZE_SEQ;
+
+ return PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+}
+
+/* This is the sendmsg for the PPPoL2TP pppol2tp_session socket. We come here
+ * when a user application does a sendmsg() on the session socket. L2TP and
+ * PPP headers must be inserted into the user's data.
+ */
+static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
+ size_t total_len)
+{
+ static const unsigned char ppph[2] = { 0xff, 0x03 };
+ struct sock *sk = sock->sk;
+ struct sk_buff *skb;
+ int error;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel;
+ struct pppol2tp_session *ps;
+
+ error = -ENOTCONN;
+ if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+ goto error;
+
+ /* Get session and tunnel contexts */
+ error = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto error;
+
+ ps = l2tp_session_priv(session);
+ tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock);
+ if (tunnel == NULL)
+ goto error_put_sess;
+
+ /* Allocate a socket buffer */
+ error = -ENOMEM;
+ skb = sock_wmalloc(sk, NET_SKB_PAD + sizeof(struct iphdr) +
+ sizeof(struct udphdr) + session->hdr_len +
+ sizeof(ppph) + total_len,
+ 0, GFP_KERNEL);
+ if (!skb)
+ goto error_put_sess_tun;
+
+ /* Reserve space for headers. */
+ skb_reserve(skb, NET_SKB_PAD);
+ skb_reset_network_header(skb);
+ skb_reserve(skb, sizeof(struct iphdr));
+ skb_reset_transport_header(skb);
+ skb_reserve(skb, sizeof(struct udphdr));
+
+ /* Add PPP header */
+ skb->data[0] = ppph[0];
+ skb->data[1] = ppph[1];
+ skb_put(skb, 2);
+
+ /* Copy user data into skb */
+ error = memcpy_fromiovec(skb->data, m->msg_iov, total_len);
+ if (error < 0) {
+ kfree_skb(skb);
+ goto error_put_sess_tun;
+ }
+ skb_put(skb, total_len);
+
+ l2tp_xmit_skb(session, skb, session->hdr_len);
+
+ sock_put(ps->tunnel_sock);
+
+ return error;
+
+error_put_sess_tun:
+ sock_put(ps->tunnel_sock);
+error_put_sess:
+ sock_put(sk);
+error:
+ return error;
+}
+
+/* Transmit function called by generic PPP driver. Sends PPP frame
+ * over PPPoL2TP socket.
+ *
+ * This is almost the same as pppol2tp_sendmsg(), but rather than
+ * being called with a msghdr from userspace, it is called with a skb
+ * from the kernel.
+ *
+ * The supplied skb from ppp doesn't have enough headroom for the
+ * insertion of L2TP, UDP and IP headers so we need to allocate more
+ * headroom in the skb. This will create a cloned skb. But we must be
+ * careful in the error case because the caller will expect to free
+ * the skb it supplied, not our cloned skb. So we take care to always
+ * leave the original skb unfreed if we return an error.
+ */
+static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+ static const u8 ppph[2] = { 0xff, 0x03 };
+ struct sock *sk = (struct sock *) chan->private;
+ struct sock *sk_tun;
+ int hdr_len;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel;
+ struct pppol2tp_session *ps;
+ int old_headroom;
+ int new_headroom;
+
+ if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+ goto abort;
+
+ /* Get session and tunnel contexts from the socket */
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto abort;
+
+ ps = l2tp_session_priv(session);
+ sk_tun = ps->tunnel_sock;
+ if (sk_tun == NULL)
+ goto abort_put_sess;
+ tunnel = l2tp_sock_to_tunnel(sk_tun);
+ if (tunnel == NULL)
+ goto abort_put_sess;
+
+ /* What header length is configured for this session? */
+ hdr_len = pppol2tp_l2tp_header_len(session);
+
+ old_headroom = skb_headroom(skb);
+ if (skb_cow_head(skb, sizeof(ppph)))
+ goto abort_put_sess_tun;
+
+ new_headroom = skb_headroom(skb);
+ skb->truesize += new_headroom - old_headroom;
+
+ /* Setup PPP header */
+ __skb_push(skb, sizeof(ppph));
+ skb->data[0] = ppph[0];
+ skb->data[1] = ppph[1];
+
+ l2tp_xmit_skb(session, skb, hdr_len);
+
+ sock_put(sk_tun);
+ sock_put(sk);
+ return 1;
+
+abort_put_sess_tun:
+ sock_put(sk_tun);
+abort_put_sess:
+ sock_put(sk);
+abort:
+ /* Free the original skb */
+ kfree_skb(skb);
+ return 1;
+}
+
+/*****************************************************************************
+ * Session (and tunnel control) socket create/destroy.
+ *****************************************************************************/
+
+/* Called by l2tp_core when a session socket is being closed.
+ */
+static void pppol2tp_session_close(struct l2tp_session *session)
+{
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+ struct sock *sk = ps->sock;
+ struct sk_buff *skb;
+
+ BUG_ON(session->magic != L2TP_SESSION_MAGIC);
+
+ if (session->session_id == 0)
+ goto out;
+
+ if (sk != NULL) {
+ lock_sock(sk);
+
+ if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
+ pppox_unbind_sock(sk);
+ sk->sk_state = PPPOX_DEAD;
+ sk->sk_state_change(sk);
+ }
+
+ /* Purge any queued data */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_queue_purge(&sk->sk_write_queue);
+ while ((skb = skb_dequeue(&session->reorder_q))) {
+ kfree_skb(skb);
+ sock_put(sk);
+ }
+
+ release_sock(sk);
+ }
+
+out:
+ return;
+}
+
+/* Really kill the session socket. (Called from sock_put() if
+ * refcnt == 0.)
+ */
+static void pppol2tp_session_destruct(struct sock *sk)
+{
+ struct l2tp_session *session;
+
+ if (sk->sk_user_data != NULL) {
+ session = sk->sk_user_data;
+ if (session == NULL)
+ goto out;
+
+ sk->sk_user_data = NULL;
+ BUG_ON(session->magic != L2TP_SESSION_MAGIC);
+ l2tp_session_dec_refcount(session);
+ }
+
+out:
+ return;
+}
+
+/* Called when the PPPoX socket (session) is closed.
+ */
+static int pppol2tp_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct l2tp_session *session;
+ int error;
+
+ if (!sk)
+ return 0;
+
+ error = -EBADF;
+ lock_sock(sk);
+ if (sock_flag(sk, SOCK_DEAD) != 0)
+ goto error;
+
+ pppox_unbind_sock(sk);
+
+ /* Signal the death of the socket. */
+ sk->sk_state = PPPOX_DEAD;
+ sock_orphan(sk);
+ sock->sk = NULL;
+
+ session = pppol2tp_sock_to_session(sk);
+
+ /* Purge any queued data */
+ skb_queue_purge(&sk->sk_receive_queue);
+ skb_queue_purge(&sk->sk_write_queue);
+ if (session != NULL) {
+ struct sk_buff *skb;
+ while ((skb = skb_dequeue(&session->reorder_q))) {
+ kfree_skb(skb);
+ sock_put(sk);
+ }
+ sock_put(sk);
+ }
+
+ release_sock(sk);
+
+ /* This will delete the session context via
+ * pppol2tp_session_destruct() if the socket's refcnt drops to
+ * zero.
+ */
+ sock_put(sk);
+
+ return 0;
+
+error:
+ release_sock(sk);
+ return error;
+}
+
+static struct proto pppol2tp_sk_proto = {
+ .name = "PPPOL2TP",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct pppox_sock),
+};
+
+static int pppol2tp_backlog_recv(struct sock *sk, struct sk_buff *skb)
+{
+ int rc;
+
+ rc = l2tp_udp_encap_recv(sk, skb);
+ if (rc)
+ kfree_skb(skb);
+
+ return NET_RX_SUCCESS;
+}
+
+/* socket() handler. Initialize a new struct sock.
+ */
+static int pppol2tp_create(struct net *net, struct socket *sock)
+{
+ int error = -ENOMEM;
+ struct sock *sk;
+
+ sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto);
+ if (!sk)
+ goto out;
+
+ sock_init_data(sock, sk);
+
+ sock->state = SS_UNCONNECTED;
+ sock->ops = &pppol2tp_ops;
+
+ sk->sk_backlog_rcv = pppol2tp_backlog_recv;
+ sk->sk_protocol = PX_PROTO_OL2TP;
+ sk->sk_family = PF_PPPOX;
+ sk->sk_state = PPPOX_NONE;
+ sk->sk_type = SOCK_STREAM;
+ sk->sk_destruct = pppol2tp_session_destruct;
+
+ error = 0;
+
+out:
+ return error;
+}
+
+/* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
+ */
+static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
+ int sockaddr_len, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
+ struct pppox_sock *po = pppox_sk(sk);
+ struct l2tp_session *session = NULL;
+ struct l2tp_tunnel *tunnel;
+ struct pppol2tp_session *ps;
+ struct dst_entry *dst;
+ struct l2tp_session_cfg cfg = { 0, };
+ int error = 0;
+
+ lock_sock(sk);
+
+ error = -EINVAL;
+ if (sp->sa_protocol != PX_PROTO_OL2TP)
+ goto end;
+
+ /* Check for already bound sockets */
+ error = -EBUSY;
+ if (sk->sk_state & PPPOX_CONNECTED)
+ goto end;
+
+ /* We don't supporting rebinding anyway */
+ error = -EALREADY;
+ if (sk->sk_user_data)
+ goto end; /* socket is already attached */
+
+ /* Don't bind if s_tunnel is 0 */
+ error = -EINVAL;
+ if (sp->pppol2tp.s_tunnel == 0)
+ goto end;
+
+ /* Special case: create tunnel context if s_session and
+ * d_session is 0. Otherwise look up tunnel using supplied
+ * tunnel id.
+ */
+ if ((sp->pppol2tp.s_session == 0) && (sp->pppol2tp.d_session == 0)) {
+ error = l2tp_tunnel_create(sock_net(sk), sp->pppol2tp.fd, 2, sp->pppol2tp.s_tunnel, sp->pppol2tp.d_tunnel, NULL, &tunnel);
+ if (error < 0)
+ goto end;
+ } else {
+ tunnel = l2tp_tunnel_find(sock_net(sk), sp->pppol2tp.s_tunnel);
+
+ /* Error if we can't find the tunnel */
+ error = -ENOENT;
+ if (tunnel == NULL)
+ goto end;
+
+ /* Error if socket is not prepped */
+ if (tunnel->sock == NULL)
+ goto end;
+ }
+
+ if (tunnel->recv_payload_hook == NULL)
+ tunnel->recv_payload_hook = pppol2tp_recv_payload_hook;
+
+ /* Check that this session doesn't already exist */
+ error = -EEXIST;
+ session = l2tp_session_find(tunnel, sp->pppol2tp.s_session);
+ if (session != NULL)
+ goto end;
+
+ /* Default MTU must allow space for UDP/L2TP/PPP
+ * headers.
+ */
+ cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ cfg.hdr_len = PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+ cfg.debug = tunnel->debug;
+
+ /* Allocate and initialize a new session context. */
+ session = l2tp_session_create(sizeof(struct pppol2tp_session),
+ tunnel, sp->pppol2tp.s_session,
+ sp->pppol2tp.d_session, &cfg);
+ if (session == NULL) {
+ error = -ENOMEM;
+ goto end;
+ }
+
+ ps = l2tp_session_priv(session);
+ ps->owner = current->pid;
+ ps->sock = sk;
+ ps->tunnel_sock = tunnel->sock;
+
+ session->recv_skb = pppol2tp_recv;
+ session->session_close = pppol2tp_session_close;
+
+ /* We need to know each time a skb is dropped from the reorder
+ * queue.
+ */
+ session->ref = pppol2tp_session_sock_hold;
+ session->deref = pppol2tp_session_sock_put;
+
+ /* If PMTU discovery was enabled, use the MTU that was discovered */
+ dst = sk_dst_get(sk);
+ if (dst != NULL) {
+ u32 pmtu = dst_mtu(__sk_dst_get(sk));
+ if (pmtu != 0)
+ session->mtu = session->mru = pmtu -
+ PPPOL2TP_HEADER_OVERHEAD;
+ dst_release(dst);
+ }
+
+ /* Special case: if source & dest session_id == 0x0000, this
+ * socket is being created to manage the tunnel. Just set up
+ * the internal context for use by ioctl() and sockopt()
+ * handlers.
+ */
+ if ((session->session_id == 0) &&
+ (session->peer_session_id == 0)) {
+ error = 0;
+ goto out_no_ppp;
+ }
+
+ /* The only header we need to worry about is the L2TP
+ * header. This size is different depending on whether
+ * sequence numbers are enabled for the data channel.
+ */
+ po->chan.hdrlen = PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+
+ po->chan.private = sk;
+ po->chan.ops = &pppol2tp_chan_ops;
+ po->chan.mtu = session->mtu;
+
+ error = ppp_register_net_channel(sock_net(sk), &po->chan);
+ if (error)
+ goto end;
+
+out_no_ppp:
+ /* This is how we get the session context from the socket. */
+ sk->sk_user_data = session;
+ sk->sk_state = PPPOX_CONNECTED;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: created\n", session->name);
+
+end:
+ release_sock(sk);
+
+ return error;
+}
+
+/* getname() support.
+ */
+static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
+ int *usockaddr_len, int peer)
+{
+ int len = sizeof(struct sockaddr_pppol2tp);
+ struct sockaddr_pppol2tp sp;
+ int error = 0;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel;
+ struct sock *sk = sock->sk;
+ struct inet_sock *inet;
+ struct pppol2tp_session *pls;
+
+ error = -ENOTCONN;
+ if (sk == NULL)
+ goto end;
+ if (sk->sk_state != PPPOX_CONNECTED)
+ goto end;
+
+ error = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto end;
+
+ pls = l2tp_session_priv(session);
+ tunnel = l2tp_sock_to_tunnel(pls->tunnel_sock);
+ if (tunnel == NULL) {
+ error = -EBADF;
+ goto end_put_sess;
+ }
+
+ memset(&sp, 0, len);
+ sp.sa_family = AF_PPPOX;
+ sp.sa_protocol = PX_PROTO_OL2TP;
+ sp.pppol2tp.fd = tunnel->fd;
+ sp.pppol2tp.pid = pls->owner;
+ sp.pppol2tp.s_tunnel = tunnel->tunnel_id;
+ sp.pppol2tp.d_tunnel = tunnel->peer_tunnel_id;
+ sp.pppol2tp.s_session = session->session_id;
+ sp.pppol2tp.d_session = session->peer_session_id;
+ inet = inet_sk(sk);
+ sp.pppol2tp.addr.sin_family = AF_INET;
+ sp.pppol2tp.addr.sin_port = inet->inet_dport;
+ sp.pppol2tp.addr.sin_addr.s_addr = inet->inet_daddr;
+
+ memcpy(uaddr, &sp, len);
+
+ *usockaddr_len = len;
+
+ sock_put(pls->tunnel_sock);
+end_put_sess:
+ sock_put(sk);
+ error = 0;
+
+end:
+ return error;
+}
+
+/****************************************************************************
+ * ioctl() handlers.
+ *
+ * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
+ * sockets. However, in order to control kernel tunnel features, we allow
+ * userspace to create a special "tunnel" PPPoX socket which is used for
+ * control only. Tunnel PPPoX sockets have session_id == 0 and simply allow
+ * the user application to issue L2TP setsockopt(), getsockopt() and ioctl()
+ * calls.
+ ****************************************************************************/
+
+static void pppol2tp_copy_stats(struct pppol2tp_ioc_stats *dest,
+ struct l2tp_stats *stats)
+{
+ dest->tx_packets = stats->tx_packets;
+ dest->tx_bytes = stats->tx_bytes;
+ dest->tx_errors = stats->tx_errors;
+ dest->rx_packets = stats->rx_packets;
+ dest->rx_bytes = stats->rx_bytes;
+ dest->rx_seq_discards = stats->rx_seq_discards;
+ dest->rx_oos_packets = stats->rx_oos_packets;
+ dest->rx_errors = stats->rx_errors;
+}
+
+/* Session ioctl helper.
+ */
+static int pppol2tp_session_ioctl(struct l2tp_session *session,
+ unsigned int cmd, unsigned long arg)
+{
+ struct ifreq ifr;
+ int err = 0;
+ struct sock *sk;
+ int val = (int) arg;
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+ struct l2tp_tunnel *tunnel = session->tunnel;
+ struct pppol2tp_ioc_stats stats;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
+ "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
+ session->name, cmd, arg);
+
+ sk = ps->sock;
+ sock_hold(sk);
+
+ switch (cmd) {
+ case SIOCGIFMTU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
+ break;
+ ifr.ifr_mtu = session->mtu;
+ if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq)))
+ break;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get mtu=%d\n", session->name, session->mtu);
+ err = 0;
+ break;
+
+ case SIOCSIFMTU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
+ break;
+
+ session->mtu = ifr.ifr_mtu;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set mtu=%d\n", session->name, session->mtu);
+ err = 0;
+ break;
+
+ case PPPIOCGMRU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (put_user(session->mru, (int __user *) arg))
+ break;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get mru=%d\n", session->name, session->mru);
+ err = 0;
+ break;
+
+ case PPPIOCSMRU:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ err = -EFAULT;
+ if (get_user(val, (int __user *) arg))
+ break;
+
+ session->mru = val;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set mru=%d\n", session->name, session->mru);
+ err = 0;
+ break;
+
+ case PPPIOCGFLAGS:
+ err = -EFAULT;
+ if (put_user(ps->flags, (int __user *) arg))
+ break;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get flags=%d\n", session->name, ps->flags);
+ err = 0;
+ break;
+
+ case PPPIOCSFLAGS:
+ err = -EFAULT;
+ if (get_user(val, (int __user *) arg))
+ break;
+ ps->flags = val;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set flags=%d\n", session->name, ps->flags);
+ err = 0;
+ break;
+
+ case PPPIOCGL2TPSTATS:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ memset(&stats, 0, sizeof(stats));
+ stats.tunnel_id = tunnel->tunnel_id;
+ stats.session_id = session->session_id;
+ pppol2tp_copy_stats(&stats, &session->stats);
+ if (copy_to_user((void __user *) arg, &stats,
+ sizeof(stats)))
+ break;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get L2TP stats\n", session->name);
+ err = 0;
+ break;
+
+ default:
+ err = -ENOSYS;
+ break;
+ }
+
+ sock_put(sk);
+
+ return err;
+}
+
+/* Tunnel ioctl helper.
+ *
+ * Note the special handling for PPPIOCGL2TPSTATS below. If the ioctl data
+ * specifies a session_id, the session ioctl handler is called. This allows an
+ * application to retrieve session stats via a tunnel socket.
+ */
+static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
+ unsigned int cmd, unsigned long arg)
+{
+ int err = 0;
+ struct sock *sk;
+ struct pppol2tp_ioc_stats stats;
+
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
+ "%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n",
+ tunnel->name, cmd, arg);
+
+ sk = tunnel->sock;
+ sock_hold(sk);
+
+ switch (cmd) {
+ case PPPIOCGL2TPSTATS:
+ err = -ENXIO;
+ if (!(sk->sk_state & PPPOX_CONNECTED))
+ break;
+
+ if (copy_from_user(&stats, (void __user *) arg,
+ sizeof(stats))) {
+ err = -EFAULT;
+ break;
+ }
+ if (stats.session_id != 0) {
+ /* resend to session ioctl handler */
+ struct l2tp_session *session =
+ l2tp_session_find(tunnel, stats.session_id);
+ if (session != NULL)
+ err = pppol2tp_session_ioctl(session, cmd, arg);
+ else
+ err = -EBADR;
+ break;
+ }
+#ifdef CONFIG_XFRM
+ stats.using_ipsec = (sk->sk_policy[0] || sk->sk_policy[1]) ? 1 : 0;
+#endif
+ pppol2tp_copy_stats(&stats, &tunnel->stats);
+ if (copy_to_user((void __user *) arg, &stats, sizeof(stats))) {
+ err = -EFAULT;
+ break;
+ }
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get L2TP stats\n", tunnel->name);
+ err = 0;
+ break;
+
+ default:
+ err = -ENOSYS;
+ break;
+ }
+
+ sock_put(sk);
+
+ return err;
+}
+
+/* Main ioctl() handler.
+ * Dispatch to tunnel or session helpers depending on the socket.
+ */
+static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
+ unsigned long arg)
+{
+ struct sock *sk = sock->sk;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel;
+ struct pppol2tp_session *ps;
+ int err;
+
+ if (!sk)
+ return 0;
+
+ err = -EBADF;
+ if (sock_flag(sk, SOCK_DEAD) != 0)
+ goto end;
+
+ err = -ENOTCONN;
+ if ((sk->sk_user_data == NULL) ||
+ (!(sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND))))
+ goto end;
+
+ /* Get session context from the socket */
+ err = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto end;
+
+ /* Special case: if session's session_id is zero, treat ioctl as a
+ * tunnel ioctl
+ */
+ ps = l2tp_session_priv(session);
+ if ((session->session_id == 0) &&
+ (session->peer_session_id == 0)) {
+ err = -EBADF;
+ tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock);
+ if (tunnel == NULL)
+ goto end_put_sess;
+
+ err = pppol2tp_tunnel_ioctl(tunnel, cmd, arg);
+ sock_put(ps->tunnel_sock);
+ goto end_put_sess;
+ }
+
+ err = pppol2tp_session_ioctl(session, cmd, arg);
+
+end_put_sess:
+ sock_put(sk);
+end:
+ return err;
+}
+
+/*****************************************************************************
+ * setsockopt() / getsockopt() support.
+ *
+ * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
+ * sockets. In order to control kernel tunnel features, we allow userspace to
+ * create a special "tunnel" PPPoX socket which is used for control only.
+ * Tunnel PPPoX sockets have session_id == 0 and simply allow the user
+ * application to issue L2TP setsockopt(), getsockopt() and ioctl() calls.
+ *****************************************************************************/
+
+/* Tunnel setsockopt() helper.
+ */
+static int pppol2tp_tunnel_setsockopt(struct sock *sk,
+ struct l2tp_tunnel *tunnel,
+ int optname, int val)
+{
+ int err = 0;
+
+ switch (optname) {
+ case PPPOL2TP_SO_DEBUG:
+ tunnel->debug = val;
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set debug=%x\n", tunnel->name, tunnel->debug);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ return err;
+}
+
+/* Session setsockopt helper.
+ */
+static int pppol2tp_session_setsockopt(struct sock *sk,
+ struct l2tp_session *session,
+ int optname, int val)
+{
+ int err = 0;
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+
+ switch (optname) {
+ case PPPOL2TP_SO_RECVSEQ:
+ if ((val != 0) && (val != 1)) {
+ err = -EINVAL;
+ break;
+ }
+ session->recv_seq = val ? -1 : 0;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set recv_seq=%d\n", session->name, session->recv_seq);
+ break;
+
+ case PPPOL2TP_SO_SENDSEQ:
+ if ((val != 0) && (val != 1)) {
+ err = -EINVAL;
+ break;
+ }
+ session->send_seq = val ? -1 : 0;
+ {
+ struct sock *ssk = ps->sock;
+ struct pppox_sock *po = pppox_sk(ssk);
+ po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
+ PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
+ }
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set send_seq=%d\n", session->name, session->send_seq);
+ break;
+
+ case PPPOL2TP_SO_LNSMODE:
+ if ((val != 0) && (val != 1)) {
+ err = -EINVAL;
+ break;
+ }
+ session->lns_mode = val ? -1 : 0;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set lns_mode=%d\n", session->name, session->lns_mode);
+ break;
+
+ case PPPOL2TP_SO_DEBUG:
+ session->debug = val;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set debug=%x\n", session->name, session->debug);
+ break;
+
+ case PPPOL2TP_SO_REORDERTO:
+ session->reorder_timeout = msecs_to_jiffies(val);
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: set reorder_timeout=%d\n", session->name, session->reorder_timeout);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ return err;
+}
+
+/* Main setsockopt() entry point.
+ * Does API checks, then calls either the tunnel or session setsockopt
+ * handler, according to whether the PPPoL2TP socket is a for a regular
+ * session or the special tunnel type.
+ */
+static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct sock *sk = sock->sk;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel;
+ struct pppol2tp_session *ps;
+ int val;
+ int err;
+
+ if (level != SOL_PPPOL2TP)
+ return udp_prot.setsockopt(sk, level, optname, optval, optlen);
+
+ if (optlen < sizeof(int))
+ return -EINVAL;
+
+ if (get_user(val, (int __user *)optval))
+ return -EFAULT;
+
+ err = -ENOTCONN;
+ if (sk->sk_user_data == NULL)
+ goto end;
+
+ /* Get session context from the socket */
+ err = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto end;
+
+ /* Special case: if session_id == 0x0000, treat as operation on tunnel
+ */
+ ps = l2tp_session_priv(session);
+ if ((session->session_id == 0) &&
+ (session->peer_session_id == 0)) {
+ err = -EBADF;
+ tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock);
+ if (tunnel == NULL)
+ goto end_put_sess;
+
+ err = pppol2tp_tunnel_setsockopt(sk, tunnel, optname, val);
+ sock_put(ps->tunnel_sock);
+ } else
+ err = pppol2tp_session_setsockopt(sk, session, optname, val);
+
+ err = 0;
+
+end_put_sess:
+ sock_put(sk);
+end:
+ return err;
+}
+
+/* Tunnel getsockopt helper. Called with sock locked.
+ */
+static int pppol2tp_tunnel_getsockopt(struct sock *sk,
+ struct l2tp_tunnel *tunnel,
+ int optname, int *val)
+{
+ int err = 0;
+
+ switch (optname) {
+ case PPPOL2TP_SO_DEBUG:
+ *val = tunnel->debug;
+ PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get debug=%x\n", tunnel->name, tunnel->debug);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ break;
+ }
+
+ return err;
+}
+
+/* Session getsockopt helper. Called with sock locked.
+ */
+static int pppol2tp_session_getsockopt(struct sock *sk,
+ struct l2tp_session *session,
+ int optname, int *val)
+{
+ int err = 0;
+
+ switch (optname) {
+ case PPPOL2TP_SO_RECVSEQ:
+ *val = session->recv_seq;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get recv_seq=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_SENDSEQ:
+ *val = session->send_seq;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get send_seq=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_LNSMODE:
+ *val = session->lns_mode;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get lns_mode=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_DEBUG:
+ *val = session->debug;
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get debug=%d\n", session->name, *val);
+ break;
+
+ case PPPOL2TP_SO_REORDERTO:
+ *val = (int) jiffies_to_msecs(session->reorder_timeout);
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: get reorder_timeout=%d\n", session->name, *val);
+ break;
+
+ default:
+ err = -ENOPROTOOPT;
+ }
+
+ return err;
+}
+
+/* Main getsockopt() entry point.
+ * Does API checks, then calls either the tunnel or session getsockopt
+ * handler, according to whether the PPPoX socket is a for a regular session
+ * or the special tunnel type.
+ */
+static int pppol2tp_getsockopt(struct socket *sock, int level,
+ int optname, char __user *optval, int __user *optlen)
+{
+ struct sock *sk = sock->sk;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel;
+ int val, len;
+ int err;
+ struct pppol2tp_session *ps;
+
+ if (level != SOL_PPPOL2TP)
+ return udp_prot.getsockopt(sk, level, optname, optval, optlen);
+
+ if (get_user(len, (int __user *) optlen))
+ return -EFAULT;
+
+ len = min_t(unsigned int, len, sizeof(int));
+
+ if (len < 0)
+ return -EINVAL;
+
+ err = -ENOTCONN;
+ if (sk->sk_user_data == NULL)
+ goto end;
+
+ /* Get the session context */
+ err = -EBADF;
+ session = pppol2tp_sock_to_session(sk);
+ if (session == NULL)
+ goto end;
+
+ /* Special case: if session_id == 0x0000, treat as operation on tunnel */
+ ps = l2tp_session_priv(session);
+ if ((session->session_id == 0) &&
+ (session->peer_session_id == 0)) {
+ err = -EBADF;
+ tunnel = l2tp_sock_to_tunnel(ps->tunnel_sock);
+ if (tunnel == NULL)
+ goto end_put_sess;
+
+ err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val);
+ sock_put(ps->tunnel_sock);
+ } else
+ err = pppol2tp_session_getsockopt(sk, session, optname, &val);
+
+ err = -EFAULT;
+ if (put_user(len, (int __user *) optlen))
+ goto end_put_sess;
+
+ if (copy_to_user((void __user *) optval, &val, len))
+ goto end_put_sess;
+
+ err = 0;
+
+end_put_sess:
+ sock_put(sk);
+end:
+ return err;
+}
+
+/*****************************************************************************
+ * Init and cleanup
+ *****************************************************************************/
+
+static const struct proto_ops pppol2tp_ops = {
+ .family = AF_PPPOX,
+ .owner = THIS_MODULE,
+ .release = pppol2tp_release,
+ .bind = sock_no_bind,
+ .connect = pppol2tp_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = pppol2tp_getname,
+ .poll = datagram_poll,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = pppol2tp_setsockopt,
+ .getsockopt = pppol2tp_getsockopt,
+ .sendmsg = pppol2tp_sendmsg,
+ .recvmsg = pppol2tp_recvmsg,
+ .mmap = sock_no_mmap,
+ .ioctl = pppox_ioctl,
+};
+
+static struct pppox_proto pppol2tp_proto = {
+ .create = pppol2tp_create,
+ .ioctl = pppol2tp_ioctl
+};
+
+static int __init pppol2tp_init(void)
+{
+ int err;
+
+ err = proto_register(&pppol2tp_sk_proto, 0);
+ if (err)
+ goto out;
+ err = register_pppox_proto(PX_PROTO_OL2TP, &pppol2tp_proto);
+ if (err)
+ goto out_unregister_pppol2tp_proto;
+
+ printk(KERN_INFO "PPPoL2TP kernel driver, %s\n",
+ PPPOL2TP_DRV_VERSION);
+
+out:
+ return err;
+out_unregister_pppol2tp_proto:
+ proto_unregister(&pppol2tp_sk_proto);
+ goto out;
+}
+
+static void __exit pppol2tp_exit(void)
+{
+ unregister_pppox_proto(PX_PROTO_OL2TP);
+
+ proto_unregister(&pppol2tp_sk_proto);
+}
+
+module_init(pppol2tp_init);
+module_exit(pppol2tp_exit);
+
+MODULE_AUTHOR("Martijn van Oosterhout <kleptog@svana.org>, "
+ "James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("PPP over L2TP over UDP");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(PPPOL2TP_DRV_VERSION);
diff --git a/net/l2tp/pppol2tp.c b/net/l2tp/pppol2tp.c
deleted file mode 100644
index 449a982..0000000
--- a/net/l2tp/pppol2tp.c
+++ /dev/null
@@ -1,2680 +0,0 @@
-/*****************************************************************************
- * Linux PPP over L2TP (PPPoX/PPPoL2TP) Sockets
- *
- * PPPoX --- Generic PPP encapsulation socket family
- * PPPoL2TP --- PPP over L2TP (RFC 2661)
- *
- * Version: 1.0.0
- *
- * Authors: Martijn van Oosterhout <kleptog@svana.org>
- * James Chapman (jchapman@katalix.com)
- * Contributors:
- * Michal Ostrowski <mostrows@speakeasy.net>
- * Arnaldo Carvalho de Melo <acme@xconectiva.com.br>
- * David S. Miller (davem@redhat.com)
- *
- * License:
- * 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.
- *
- */
-
-/* This driver handles only L2TP data frames; control frames are handled by a
- * userspace application.
- *
- * To send data in an L2TP session, userspace opens a PPPoL2TP socket and
- * attaches it to a bound UDP socket with local tunnel_id / session_id and
- * peer tunnel_id / session_id set. Data can then be sent or received using
- * regular socket sendmsg() / recvmsg() calls. Kernel parameters of the socket
- * can be read or modified using ioctl() or [gs]etsockopt() calls.
- *
- * When a PPPoL2TP socket is connected with local and peer session_id values
- * zero, the socket is treated as a special tunnel management socket.
- *
- * Here's example userspace code to create a socket for sending/receiving data
- * over an L2TP session:-
- *
- * struct sockaddr_pppol2tp sax;
- * int fd;
- * int session_fd;
- *
- * fd = socket(AF_PPPOX, SOCK_DGRAM, PX_PROTO_OL2TP);
- *
- * sax.sa_family = AF_PPPOX;
- * sax.sa_protocol = PX_PROTO_OL2TP;
- * sax.pppol2tp.fd = tunnel_fd; // bound UDP socket
- * sax.pppol2tp.addr.sin_addr.s_addr = addr->sin_addr.s_addr;
- * sax.pppol2tp.addr.sin_port = addr->sin_port;
- * sax.pppol2tp.addr.sin_family = AF_INET;
- * sax.pppol2tp.s_tunnel = tunnel_id;
- * sax.pppol2tp.s_session = session_id;
- * sax.pppol2tp.d_tunnel = peer_tunnel_id;
- * sax.pppol2tp.d_session = peer_session_id;
- *
- * session_fd = connect(fd, (struct sockaddr *)&sax, sizeof(sax));
- *
- * A pppd plugin that allows PPP traffic to be carried over L2TP using
- * this driver is available from the OpenL2TP project at
- * http://openl2tp.sourceforge.net.
- */
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/list.h>
-#include <asm/uaccess.h>
-
-#include <linux/kernel.h>
-#include <linux/spinlock.h>
-#include <linux/kthread.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/errno.h>
-#include <linux/jiffies.h>
-
-#include <linux/netdevice.h>
-#include <linux/net.h>
-#include <linux/inetdevice.h>
-#include <linux/skbuff.h>
-#include <linux/init.h>
-#include <linux/ip.h>
-#include <linux/udp.h>
-#include <linux/if_pppox.h>
-#include <linux/if_pppol2tp.h>
-#include <net/sock.h>
-#include <linux/ppp_channel.h>
-#include <linux/ppp_defs.h>
-#include <linux/if_ppp.h>
-#include <linux/file.h>
-#include <linux/hash.h>
-#include <linux/sort.h>
-#include <linux/proc_fs.h>
-#include <linux/nsproxy.h>
-#include <net/net_namespace.h>
-#include <net/netns/generic.h>
-#include <net/dst.h>
-#include <net/ip.h>
-#include <net/udp.h>
-#include <net/xfrm.h>
-
-#include <asm/byteorder.h>
-#include <asm/atomic.h>
-
-
-#define PPPOL2TP_DRV_VERSION "V1.0"
-
-/* L2TP header constants */
-#define L2TP_HDRFLAG_T 0x8000
-#define L2TP_HDRFLAG_L 0x4000
-#define L2TP_HDRFLAG_S 0x0800
-#define L2TP_HDRFLAG_O 0x0200
-#define L2TP_HDRFLAG_P 0x0100
-
-#define L2TP_HDR_VER_MASK 0x000F
-#define L2TP_HDR_VER 0x0002
-
-/* Space for UDP, L2TP and PPP headers */
-#define PPPOL2TP_HEADER_OVERHEAD 40
-
-/* Just some random numbers */
-#define L2TP_TUNNEL_MAGIC 0x42114DDA
-#define L2TP_SESSION_MAGIC 0x0C04EB7D
-
-#define PPPOL2TP_HASH_BITS 4
-#define PPPOL2TP_HASH_SIZE (1 << PPPOL2TP_HASH_BITS)
-
-/* Default trace flags */
-#define PPPOL2TP_DEFAULT_DEBUG_FLAGS 0
-
-#define PRINTK(_mask, _type, _lvl, _fmt, args...) \
- do { \
- if ((_mask) & (_type)) \
- printk(_lvl "PPPOL2TP: " _fmt, ##args); \
- } while(0)
-
-/* Number of bytes to build transmit L2TP headers.
- * Unfortunately the size is different depending on whether sequence numbers
- * are enabled.
- */
-#define PPPOL2TP_L2TP_HDR_SIZE_SEQ 10
-#define PPPOL2TP_L2TP_HDR_SIZE_NOSEQ 6
-
-struct pppol2tp_tunnel;
-
-/* Describes a session. It is the sk_user_data field in the PPPoL2TP
- * socket. Contains information to determine incoming packets and transmit
- * outgoing ones.
- */
-struct pppol2tp_session
-{
- int magic; /* should be
- * L2TP_SESSION_MAGIC */
- int owner; /* pid that opened the socket */
-
- struct sock *sock; /* Pointer to the session
- * PPPoX socket */
- struct sock *tunnel_sock; /* Pointer to the tunnel UDP
- * socket */
-
- struct pppol2tp_addr tunnel_addr; /* Description of tunnel */
-
- struct pppol2tp_tunnel *tunnel; /* back pointer to tunnel
- * context */
-
- char name[20]; /* "sess xxxxx/yyyyy", where
- * x=tunnel_id, y=session_id */
- int mtu;
- int mru;
- int flags; /* accessed by PPPIOCGFLAGS.
- * Unused. */
- unsigned recv_seq:1; /* expect receive packets with
- * sequence numbers? */
- unsigned send_seq:1; /* send packets with sequence
- * numbers? */
- unsigned lns_mode:1; /* behave as LNS? LAC enables
- * sequence numbers under
- * control of LNS. */
- int debug; /* bitmask of debug message
- * categories */
- int reorder_timeout; /* configured reorder timeout
- * (in jiffies) */
- u16 nr; /* session NR state (receive) */
- u16 ns; /* session NR state (send) */
- struct sk_buff_head reorder_q; /* receive reorder queue */
- struct pppol2tp_ioc_stats stats;
- struct hlist_node hlist; /* Hash list node */
-};
-
-/* The sk_user_data field of the tunnel's UDP socket. It contains info to track
- * all the associated sessions so incoming packets can be sorted out
- */
-struct pppol2tp_tunnel
-{
- int magic; /* Should be L2TP_TUNNEL_MAGIC */
- rwlock_t hlist_lock; /* protect session_hlist */
- struct hlist_head session_hlist[PPPOL2TP_HASH_SIZE];
- /* hashed list of sessions,
- * hashed by id */
- int debug; /* bitmask of debug message
- * categories */
- char name[12]; /* "tunl xxxxx" */
- struct pppol2tp_ioc_stats stats;
-
- void (*old_sk_destruct)(struct sock *);
-
- struct sock *sock; /* Parent socket */
- struct list_head list; /* Keep a list of all open
- * prepared sockets */
- struct net *pppol2tp_net; /* the net we belong to */
-
- atomic_t ref_count;
-};
-
-/* Private data stored for received packets in the skb.
- */
-struct pppol2tp_skb_cb {
- u16 ns;
- u16 nr;
- u16 has_seq;
- u16 length;
- unsigned long expires;
-};
-
-#define PPPOL2TP_SKB_CB(skb) ((struct pppol2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)])
-
-static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb);
-static void pppol2tp_tunnel_free(struct pppol2tp_tunnel *tunnel);
-
-static atomic_t pppol2tp_tunnel_count;
-static atomic_t pppol2tp_session_count;
-static struct ppp_channel_ops pppol2tp_chan_ops = { pppol2tp_xmit , NULL };
-static const struct proto_ops pppol2tp_ops;
-
-/* per-net private data for this module */
-static int pppol2tp_net_id __read_mostly;
-struct pppol2tp_net {
- struct list_head pppol2tp_tunnel_list;
- rwlock_t pppol2tp_tunnel_list_lock;
-};
-
-static inline struct pppol2tp_net *pppol2tp_pernet(struct net *net)
-{
- BUG_ON(!net);
-
- return net_generic(net, pppol2tp_net_id);
-}
-
-/* Helpers to obtain tunnel/session contexts from sockets.
- */
-static inline struct pppol2tp_session *pppol2tp_sock_to_session(struct sock *sk)
-{
- struct pppol2tp_session *session;
-
- if (sk == NULL)
- return NULL;
-
- sock_hold(sk);
- session = (struct pppol2tp_session *)(sk->sk_user_data);
- if (session == NULL) {
- sock_put(sk);
- goto out;
- }
-
- BUG_ON(session->magic != L2TP_SESSION_MAGIC);
-out:
- return session;
-}
-
-static inline struct pppol2tp_tunnel *pppol2tp_sock_to_tunnel(struct sock *sk)
-{
- struct pppol2tp_tunnel *tunnel;
-
- if (sk == NULL)
- return NULL;
-
- sock_hold(sk);
- tunnel = (struct pppol2tp_tunnel *)(sk->sk_user_data);
- if (tunnel == NULL) {
- sock_put(sk);
- goto out;
- }
-
- BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-out:
- return tunnel;
-}
-
-/* Tunnel reference counts. Incremented per session that is added to
- * the tunnel.
- */
-static inline void pppol2tp_tunnel_inc_refcount(struct pppol2tp_tunnel *tunnel)
-{
- atomic_inc(&tunnel->ref_count);
-}
-
-static inline void pppol2tp_tunnel_dec_refcount(struct pppol2tp_tunnel *tunnel)
-{
- if (atomic_dec_and_test(&tunnel->ref_count))
- pppol2tp_tunnel_free(tunnel);
-}
-
-/* Session hash list.
- * The session_id SHOULD be random according to RFC2661, but several
- * L2TP implementations (Cisco and Microsoft) use incrementing
- * session_ids. So we do a real hash on the session_id, rather than a
- * simple bitmask.
- */
-static inline struct hlist_head *
-pppol2tp_session_id_hash(struct pppol2tp_tunnel *tunnel, u16 session_id)
-{
- unsigned long hash_val = (unsigned long) session_id;
- return &tunnel->session_hlist[hash_long(hash_val, PPPOL2TP_HASH_BITS)];
-}
-
-/* Lookup a session by id
- */
-static struct pppol2tp_session *
-pppol2tp_session_find(struct pppol2tp_tunnel *tunnel, u16 session_id)
-{
- struct hlist_head *session_list =
- pppol2tp_session_id_hash(tunnel, session_id);
- struct pppol2tp_session *session;
- struct hlist_node *walk;
-
- read_lock_bh(&tunnel->hlist_lock);
- hlist_for_each_entry(session, walk, session_list, hlist) {
- if (session->tunnel_addr.s_session == session_id) {
- read_unlock_bh(&tunnel->hlist_lock);
- return session;
- }
- }
- read_unlock_bh(&tunnel->hlist_lock);
-
- return NULL;
-}
-
-/* Lookup a tunnel by id
- */
-static struct pppol2tp_tunnel *pppol2tp_tunnel_find(struct net *net, u16 tunnel_id)
-{
- struct pppol2tp_tunnel *tunnel;
- struct pppol2tp_net *pn = pppol2tp_pernet(net);
-
- read_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- list_for_each_entry(tunnel, &pn->pppol2tp_tunnel_list, list) {
- if (tunnel->stats.tunnel_id == tunnel_id) {
- read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
- return tunnel;
- }
- }
- read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
-
- return NULL;
-}
-
-/*****************************************************************************
- * Receive data handling
- *****************************************************************************/
-
-/* Queue a skb in order. We come here only if the skb has an L2TP sequence
- * number.
- */
-static void pppol2tp_recv_queue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
-{
- struct sk_buff *skbp;
- struct sk_buff *tmp;
- u16 ns = PPPOL2TP_SKB_CB(skb)->ns;
-
- spin_lock_bh(&session->reorder_q.lock);
- skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
- if (PPPOL2TP_SKB_CB(skbp)->ns > ns) {
- __skb_queue_before(&session->reorder_q, skbp, skb);
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n",
- session->name, ns, PPPOL2TP_SKB_CB(skbp)->ns,
- skb_queue_len(&session->reorder_q));
- session->stats.rx_oos_packets++;
- goto out;
- }
- }
-
- __skb_queue_tail(&session->reorder_q, skb);
-
-out:
- spin_unlock_bh(&session->reorder_q.lock);
-}
-
-/* Dequeue a single skb.
- */
-static void pppol2tp_recv_dequeue_skb(struct pppol2tp_session *session, struct sk_buff *skb)
-{
- struct pppol2tp_tunnel *tunnel = session->tunnel;
- int length = PPPOL2TP_SKB_CB(skb)->length;
- struct sock *session_sock = NULL;
-
- /* We're about to requeue the skb, so return resources
- * to its current owner (a socket receive buffer).
- */
- skb_orphan(skb);
-
- tunnel->stats.rx_packets++;
- tunnel->stats.rx_bytes += length;
- session->stats.rx_packets++;
- session->stats.rx_bytes += length;
-
- if (PPPOL2TP_SKB_CB(skb)->has_seq) {
- /* Bump our Nr */
- session->nr++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: updated nr to %hu\n", session->name, session->nr);
- }
-
- /* If the socket is bound, send it in to PPP's input queue. Otherwise
- * queue it on the session socket.
- */
- session_sock = session->sock;
- if (session_sock->sk_state & PPPOX_BOUND) {
- struct pppox_sock *po;
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: recv %d byte data frame, passing to ppp\n",
- session->name, length);
-
- /* We need to forget all info related to the L2TP packet
- * gathered in the skb as we are going to reuse the same
- * skb for the inner packet.
- * Namely we need to:
- * - reset xfrm (IPSec) information as it applies to
- * the outer L2TP packet and not to the inner one
- * - release the dst to force a route lookup on the inner
- * IP packet since skb->dst currently points to the dst
- * of the UDP tunnel
- * - reset netfilter information as it doesn't apply
- * to the inner packet either
- */
- secpath_reset(skb);
- skb_dst_drop(skb);
- nf_reset(skb);
-
- po = pppox_sk(session_sock);
- ppp_input(&po->chan, skb);
- } else {
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
- "%s: socket not bound\n", session->name);
-
- /* Not bound. Nothing we can do, so discard. */
- session->stats.rx_errors++;
- kfree_skb(skb);
- }
-
- sock_put(session->sock);
-}
-
-/* Dequeue skbs from the session's reorder_q, subject to packet order.
- * Skbs that have been in the queue for too long are simply discarded.
- */
-static void pppol2tp_recv_dequeue(struct pppol2tp_session *session)
-{
- struct sk_buff *skb;
- struct sk_buff *tmp;
-
- /* If the pkt at the head of the queue has the nr that we
- * expect to send up next, dequeue it and any other
- * in-sequence packets behind it.
- */
- spin_lock_bh(&session->reorder_q.lock);
- skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
- if (time_after(jiffies, PPPOL2TP_SKB_CB(skb)->expires)) {
- session->stats.rx_seq_discards++;
- session->stats.rx_errors++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: oos pkt %hu len %d discarded (too old), "
- "waiting for %hu, reorder_q_len=%d\n",
- session->name, PPPOL2TP_SKB_CB(skb)->ns,
- PPPOL2TP_SKB_CB(skb)->length, session->nr,
- skb_queue_len(&session->reorder_q));
- __skb_unlink(skb, &session->reorder_q);
- kfree_skb(skb);
- sock_put(session->sock);
- continue;
- }
-
- if (PPPOL2TP_SKB_CB(skb)->has_seq) {
- if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: holding oos pkt %hu len %d, "
- "waiting for %hu, reorder_q_len=%d\n",
- session->name, PPPOL2TP_SKB_CB(skb)->ns,
- PPPOL2TP_SKB_CB(skb)->length, session->nr,
- skb_queue_len(&session->reorder_q));
- goto out;
- }
- }
- __skb_unlink(skb, &session->reorder_q);
-
- /* Process the skb. We release the queue lock while we
- * do so to let other contexts process the queue.
- */
- spin_unlock_bh(&session->reorder_q.lock);
- pppol2tp_recv_dequeue_skb(session, skb);
- spin_lock_bh(&session->reorder_q.lock);
- }
-
-out:
- spin_unlock_bh(&session->reorder_q.lock);
-}
-
-static inline int pppol2tp_verify_udp_checksum(struct sock *sk,
- struct sk_buff *skb)
-{
- struct udphdr *uh = udp_hdr(skb);
- u16 ulen = ntohs(uh->len);
- struct inet_sock *inet;
- __wsum psum;
-
- if (sk->sk_no_check || skb_csum_unnecessary(skb) || !uh->check)
- return 0;
-
- inet = inet_sk(sk);
- psum = csum_tcpudp_nofold(inet->inet_saddr, inet->inet_daddr, ulen,
- IPPROTO_UDP, 0);
-
- if ((skb->ip_summed == CHECKSUM_COMPLETE) &&
- !csum_fold(csum_add(psum, skb->csum)))
- return 0;
-
- skb->csum = psum;
-
- return __skb_checksum_complete(skb);
-}
-
-/* Internal receive frame. Do the real work of receiving an L2TP data frame
- * here. The skb is not on a list when we get here.
- * Returns 0 if the packet was a data packet and was successfully passed on.
- * Returns 1 if the packet was not a good data packet and could not be
- * forwarded. All such packets are passed up to userspace to deal with.
- */
-static int pppol2tp_recv_core(struct sock *sock, struct sk_buff *skb)
-{
- struct pppol2tp_session *session = NULL;
- struct pppol2tp_tunnel *tunnel;
- unsigned char *ptr, *optr;
- u16 hdrflags;
- u16 tunnel_id, session_id;
- int length;
- int offset;
-
- tunnel = pppol2tp_sock_to_tunnel(sock);
- if (tunnel == NULL)
- goto no_tunnel;
-
- if (tunnel->sock && pppol2tp_verify_udp_checksum(tunnel->sock, skb))
- goto discard_bad_csum;
-
- /* UDP always verifies the packet length. */
- __skb_pull(skb, sizeof(struct udphdr));
-
- /* Short packet? */
- if (!pskb_may_pull(skb, 12)) {
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
- "%s: recv short packet (len=%d)\n", tunnel->name, skb->len);
- goto error;
- }
-
- /* Point to L2TP header */
- optr = ptr = skb->data;
-
- /* Get L2TP header flags */
- hdrflags = ntohs(*(__be16*)ptr);
-
- /* Trace packet contents, if enabled */
- if (tunnel->debug & PPPOL2TP_MSG_DATA) {
- length = min(16u, skb->len);
- if (!pskb_may_pull(skb, length))
- goto error;
-
- printk(KERN_DEBUG "%s: recv: ", tunnel->name);
-
- offset = 0;
- do {
- printk(" %02X", ptr[offset]);
- } while (++offset < length);
-
- printk("\n");
- }
-
- /* Get length of L2TP packet */
- length = skb->len;
-
- /* If type is control packet, it is handled by userspace. */
- if (hdrflags & L2TP_HDRFLAG_T) {
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: recv control packet, len=%d\n", tunnel->name, length);
- goto error;
- }
-
- /* Skip flags */
- ptr += 2;
-
- /* If length is present, skip it */
- if (hdrflags & L2TP_HDRFLAG_L)
- ptr += 2;
-
- /* Extract tunnel and session ID */
- tunnel_id = ntohs(*(__be16 *) ptr);
- ptr += 2;
- session_id = ntohs(*(__be16 *) ptr);
- ptr += 2;
-
- /* Find the session context */
- session = pppol2tp_session_find(tunnel, session_id);
- if (!session) {
- /* Not found? Pass to userspace to deal with */
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_INFO,
- "%s: no socket found (%hu/%hu). Passing up.\n",
- tunnel->name, tunnel_id, session_id);
- goto error;
- }
- sock_hold(session->sock);
-
- /* The ref count on the socket was increased by the above call since
- * we now hold a pointer to the session. Take care to do sock_put()
- * when exiting this function from now on...
- */
-
- /* Handle the optional sequence numbers. If we are the LAC,
- * enable/disable sequence numbers under the control of the LNS. If
- * no sequence numbers present but we were expecting them, discard
- * frame.
- */
- if (hdrflags & L2TP_HDRFLAG_S) {
- u16 ns, nr;
- ns = ntohs(*(__be16 *) ptr);
- ptr += 2;
- nr = ntohs(*(__be16 *) ptr);
- ptr += 2;
-
- /* Received a packet with sequence numbers. If we're the LNS,
- * check if we sre sending sequence numbers and if not,
- * configure it so.
- */
- if ((!session->lns_mode) && (!session->send_seq)) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
- "%s: requested to enable seq numbers by LNS\n",
- session->name);
- session->send_seq = -1;
- }
-
- /* Store L2TP info in the skb */
- PPPOL2TP_SKB_CB(skb)->ns = ns;
- PPPOL2TP_SKB_CB(skb)->nr = nr;
- PPPOL2TP_SKB_CB(skb)->has_seq = 1;
-
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: recv data ns=%hu, nr=%hu, session nr=%hu\n",
- session->name, ns, nr, session->nr);
- } else {
- /* No sequence numbers.
- * If user has configured mandatory sequence numbers, discard.
- */
- if (session->recv_seq) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
- "%s: recv data has no seq numbers when required. "
- "Discarding\n", session->name);
- session->stats.rx_seq_discards++;
- goto discard;
- }
-
- /* If we're the LAC and we're sending sequence numbers, the
- * LNS has requested that we no longer send sequence numbers.
- * If we're the LNS and we're sending sequence numbers, the
- * LAC is broken. Discard the frame.
- */
- if ((!session->lns_mode) && (session->send_seq)) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_INFO,
- "%s: requested to disable seq numbers by LNS\n",
- session->name);
- session->send_seq = 0;
- } else if (session->send_seq) {
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_WARNING,
- "%s: recv data has no seq numbers when required. "
- "Discarding\n", session->name);
- session->stats.rx_seq_discards++;
- goto discard;
- }
-
- /* Store L2TP info in the skb */
- PPPOL2TP_SKB_CB(skb)->has_seq = 0;
- }
-
- /* If offset bit set, skip it. */
- if (hdrflags & L2TP_HDRFLAG_O) {
- offset = ntohs(*(__be16 *)ptr);
- ptr += 2 + offset;
- }
-
- offset = ptr - optr;
- if (!pskb_may_pull(skb, offset))
- goto discard;
-
- __skb_pull(skb, offset);
-
- /* Skip PPP header, if present. In testing, Microsoft L2TP clients
- * don't send the PPP header (PPP header compression enabled), but
- * other clients can include the header. So we cope with both cases
- * here. The PPP header is always FF03 when using L2TP.
- *
- * Note that skb->data[] isn't dereferenced from a u16 ptr here since
- * the field may be unaligned.
- */
- if (!pskb_may_pull(skb, 2))
- goto discard;
-
- if ((skb->data[0] == 0xff) && (skb->data[1] == 0x03))
- skb_pull(skb, 2);
-
- /* Prepare skb for adding to the session's reorder_q. Hold
- * packets for max reorder_timeout or 1 second if not
- * reordering.
- */
- PPPOL2TP_SKB_CB(skb)->length = length;
- PPPOL2TP_SKB_CB(skb)->expires = jiffies +
- (session->reorder_timeout ? session->reorder_timeout : HZ);
-
- /* Add packet to the session's receive queue. Reordering is done here, if
- * enabled. Saved L2TP protocol info is stored in skb->sb[].
- */
- if (PPPOL2TP_SKB_CB(skb)->has_seq) {
- if (session->reorder_timeout != 0) {
- /* Packet reordering enabled. Add skb to session's
- * reorder queue, in order of ns.
- */
- pppol2tp_recv_queue_skb(session, skb);
- } else {
- /* Packet reordering disabled. Discard out-of-sequence
- * packets
- */
- if (PPPOL2TP_SKB_CB(skb)->ns != session->nr) {
- session->stats.rx_seq_discards++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: oos pkt %hu len %d discarded, "
- "waiting for %hu, reorder_q_len=%d\n",
- session->name, PPPOL2TP_SKB_CB(skb)->ns,
- PPPOL2TP_SKB_CB(skb)->length, session->nr,
- skb_queue_len(&session->reorder_q));
- goto discard;
- }
- skb_queue_tail(&session->reorder_q, skb);
- }
- } else {
- /* No sequence numbers. Add the skb to the tail of the
- * reorder queue. This ensures that it will be
- * delivered after all previous sequenced skbs.
- */
- skb_queue_tail(&session->reorder_q, skb);
- }
-
- /* Try to dequeue as many skbs from reorder_q as we can. */
- pppol2tp_recv_dequeue(session);
- sock_put(sock);
-
- return 0;
-
-discard:
- session->stats.rx_errors++;
- kfree_skb(skb);
- sock_put(session->sock);
- sock_put(sock);
-
- return 0;
-
-discard_bad_csum:
- LIMIT_NETDEBUG("%s: UDP: bad checksum\n", tunnel->name);
- UDP_INC_STATS_USER(&init_net, UDP_MIB_INERRORS, 0);
- tunnel->stats.rx_errors++;
- kfree_skb(skb);
- sock_put(sock);
-
- return 0;
-
-error:
- /* Put UDP header back */
- __skb_push(skb, sizeof(struct udphdr));
- sock_put(sock);
-
-no_tunnel:
- return 1;
-}
-
-/* UDP encapsulation receive handler. See net/ipv4/udp.c.
- * Return codes:
- * 0 : success.
- * <0: error
- * >0: skb should be passed up to userspace as UDP.
- */
-static int pppol2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
-{
- struct pppol2tp_tunnel *tunnel;
-
- tunnel = pppol2tp_sock_to_tunnel(sk);
- if (tunnel == NULL)
- goto pass_up;
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: received %d bytes\n", tunnel->name, skb->len);
-
- if (pppol2tp_recv_core(sk, skb))
- goto pass_up_put;
-
- sock_put(sk);
- return 0;
-
-pass_up_put:
- sock_put(sk);
-pass_up:
- return 1;
-}
-
-/* Receive message. This is the recvmsg for the PPPoL2TP socket.
- */
-static int pppol2tp_recvmsg(struct kiocb *iocb, struct socket *sock,
- struct msghdr *msg, size_t len,
- int flags)
-{
- int err;
- struct sk_buff *skb;
- struct sock *sk = sock->sk;
-
- err = -EIO;
- if (sk->sk_state & PPPOX_BOUND)
- goto end;
-
- msg->msg_namelen = 0;
-
- err = 0;
- skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
- flags & MSG_DONTWAIT, &err);
- if (!skb)
- goto end;
-
- if (len > skb->len)
- len = skb->len;
- else if (len < skb->len)
- msg->msg_flags |= MSG_TRUNC;
-
- err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len);
- if (likely(err == 0))
- err = len;
-
- kfree_skb(skb);
-end:
- return err;
-}
-
-/************************************************************************
- * Transmit handling
- ***********************************************************************/
-
-/* Tell how big L2TP headers are for a particular session. This
- * depends on whether sequence numbers are being used.
- */
-static inline int pppol2tp_l2tp_header_len(struct pppol2tp_session *session)
-{
- if (session->send_seq)
- return PPPOL2TP_L2TP_HDR_SIZE_SEQ;
-
- return PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
-}
-
-/* Build an L2TP header for the session into the buffer provided.
- */
-static void pppol2tp_build_l2tp_header(struct pppol2tp_session *session,
- void *buf)
-{
- __be16 *bufp = buf;
- u16 flags = L2TP_HDR_VER;
-
- if (session->send_seq)
- flags |= L2TP_HDRFLAG_S;
-
- /* Setup L2TP header.
- * FIXME: Can this ever be unaligned? Is direct dereferencing of
- * 16-bit header fields safe here for all architectures?
- */
- *bufp++ = htons(flags);
- *bufp++ = htons(session->tunnel_addr.d_tunnel);
- *bufp++ = htons(session->tunnel_addr.d_session);
- if (session->send_seq) {
- *bufp++ = htons(session->ns);
- *bufp++ = 0;
- session->ns++;
- PRINTK(session->debug, PPPOL2TP_MSG_SEQ, KERN_DEBUG,
- "%s: updated ns to %hu\n", session->name, session->ns);
- }
-}
-
-/* This is the sendmsg for the PPPoL2TP pppol2tp_session socket. We come here
- * when a user application does a sendmsg() on the session socket. L2TP and
- * PPP headers must be inserted into the user's data.
- */
-static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
- size_t total_len)
-{
- static const unsigned char ppph[2] = { 0xff, 0x03 };
- struct sock *sk = sock->sk;
- struct inet_sock *inet;
- __wsum csum;
- struct sk_buff *skb;
- int error;
- int hdr_len;
- struct pppol2tp_session *session;
- struct pppol2tp_tunnel *tunnel;
- struct udphdr *uh;
- unsigned int len;
- struct sock *sk_tun;
- u16 udp_len;
-
- error = -ENOTCONN;
- if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
- goto error;
-
- /* Get session and tunnel contexts */
- error = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto error;
-
- sk_tun = session->tunnel_sock;
- tunnel = pppol2tp_sock_to_tunnel(sk_tun);
- if (tunnel == NULL)
- goto error_put_sess;
-
- /* What header length is configured for this session? */
- hdr_len = pppol2tp_l2tp_header_len(session);
-
- /* Allocate a socket buffer */
- error = -ENOMEM;
- skb = sock_wmalloc(sk, NET_SKB_PAD + sizeof(struct iphdr) +
- sizeof(struct udphdr) + hdr_len +
- sizeof(ppph) + total_len,
- 0, GFP_KERNEL);
- if (!skb)
- goto error_put_sess_tun;
-
- /* Reserve space for headers. */
- skb_reserve(skb, NET_SKB_PAD);
- skb_reset_network_header(skb);
- skb_reserve(skb, sizeof(struct iphdr));
- skb_reset_transport_header(skb);
-
- /* Build UDP header */
- inet = inet_sk(sk_tun);
- udp_len = hdr_len + sizeof(ppph) + total_len;
- uh = (struct udphdr *) skb->data;
- uh->source = inet->inet_sport;
- uh->dest = inet->inet_dport;
- uh->len = htons(udp_len);
- uh->check = 0;
- skb_put(skb, sizeof(struct udphdr));
-
- /* Build L2TP header */
- pppol2tp_build_l2tp_header(session, skb->data);
- skb_put(skb, hdr_len);
-
- /* Add PPP header */
- skb->data[0] = ppph[0];
- skb->data[1] = ppph[1];
- skb_put(skb, 2);
-
- /* Copy user data into skb */
- error = memcpy_fromiovec(skb->data, m->msg_iov, total_len);
- if (error < 0) {
- kfree_skb(skb);
- goto error_put_sess_tun;
- }
- skb_put(skb, total_len);
-
- /* Calculate UDP checksum if configured to do so */
- if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
- skb->ip_summed = CHECKSUM_NONE;
- else if (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
- skb->ip_summed = CHECKSUM_COMPLETE;
- csum = skb_checksum(skb, 0, udp_len, 0);
- uh->check = csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, csum);
- if (uh->check == 0)
- uh->check = CSUM_MANGLED_0;
- } else {
- skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, 0);
- }
-
- /* Debug */
- if (session->send_seq)
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %Zd bytes, ns=%hu\n", session->name,
- total_len, session->ns - 1);
- else
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %Zd bytes\n", session->name, total_len);
-
- if (session->debug & PPPOL2TP_MSG_DATA) {
- int i;
- unsigned char *datap = skb->data;
-
- printk(KERN_DEBUG "%s: xmit:", session->name);
- for (i = 0; i < total_len; i++) {
- printk(" %02X", *datap++);
- if (i == 15) {
- printk(" ...");
- break;
- }
- }
- printk("\n");
- }
-
- /* Queue the packet to IP for output */
- len = skb->len;
- error = ip_queue_xmit(skb, 1);
-
- /* Update stats */
- if (error >= 0) {
- tunnel->stats.tx_packets++;
- tunnel->stats.tx_bytes += len;
- session->stats.tx_packets++;
- session->stats.tx_bytes += len;
- } else {
- tunnel->stats.tx_errors++;
- session->stats.tx_errors++;
- }
-
- return error;
-
-error_put_sess_tun:
- sock_put(session->tunnel_sock);
-error_put_sess:
- sock_put(sk);
-error:
- return error;
-}
-
-/* Automatically called when the skb is freed.
- */
-static void pppol2tp_sock_wfree(struct sk_buff *skb)
-{
- sock_put(skb->sk);
-}
-
-/* For data skbs that we transmit, we associate with the tunnel socket
- * but don't do accounting.
- */
-static inline void pppol2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
-{
- sock_hold(sk);
- skb->sk = sk;
- skb->destructor = pppol2tp_sock_wfree;
-}
-
-/* Transmit function called by generic PPP driver. Sends PPP frame
- * over PPPoL2TP socket.
- *
- * This is almost the same as pppol2tp_sendmsg(), but rather than
- * being called with a msghdr from userspace, it is called with a skb
- * from the kernel.
- *
- * The supplied skb from ppp doesn't have enough headroom for the
- * insertion of L2TP, UDP and IP headers so we need to allocate more
- * headroom in the skb. This will create a cloned skb. But we must be
- * careful in the error case because the caller will expect to free
- * the skb it supplied, not our cloned skb. So we take care to always
- * leave the original skb unfreed if we return an error.
- */
-static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
-{
- static const u8 ppph[2] = { 0xff, 0x03 };
- struct sock *sk = (struct sock *) chan->private;
- struct sock *sk_tun;
- int hdr_len;
- u16 udp_len;
- struct pppol2tp_session *session;
- struct pppol2tp_tunnel *tunnel;
- int rc;
- int headroom;
- int data_len = skb->len;
- struct inet_sock *inet;
- __wsum csum;
- struct udphdr *uh;
- unsigned int len;
- int old_headroom;
- int new_headroom;
-
- if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
- goto abort;
-
- /* Get session and tunnel contexts from the socket */
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto abort;
-
- sk_tun = session->tunnel_sock;
- if (sk_tun == NULL)
- goto abort_put_sess;
- tunnel = pppol2tp_sock_to_tunnel(sk_tun);
- if (tunnel == NULL)
- goto abort_put_sess;
-
- /* What header length is configured for this session? */
- hdr_len = pppol2tp_l2tp_header_len(session);
-
- /* Check that there's enough headroom in the skb to insert IP,
- * UDP and L2TP and PPP headers. If not enough, expand it to
- * make room. Adjust truesize.
- */
- headroom = NET_SKB_PAD + sizeof(struct iphdr) +
- sizeof(struct udphdr) + hdr_len + sizeof(ppph);
- old_headroom = skb_headroom(skb);
- if (skb_cow_head(skb, headroom))
- goto abort_put_sess_tun;
-
- new_headroom = skb_headroom(skb);
- skb_orphan(skb);
- skb->truesize += new_headroom - old_headroom;
-
- /* Setup PPP header */
- __skb_push(skb, sizeof(ppph));
- skb->data[0] = ppph[0];
- skb->data[1] = ppph[1];
-
- /* Setup L2TP header */
- pppol2tp_build_l2tp_header(session, __skb_push(skb, hdr_len));
-
- udp_len = sizeof(struct udphdr) + hdr_len + sizeof(ppph) + data_len;
-
- /* Setup UDP header */
- inet = inet_sk(sk_tun);
- __skb_push(skb, sizeof(*uh));
- skb_reset_transport_header(skb);
- uh = udp_hdr(skb);
- uh->source = inet->inet_sport;
- uh->dest = inet->inet_dport;
- uh->len = htons(udp_len);
- uh->check = 0;
-
- /* Debug */
- if (session->send_seq)
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %d bytes, ns=%hu\n", session->name,
- data_len, session->ns - 1);
- else
- PRINTK(session->debug, PPPOL2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %d bytes\n", session->name, data_len);
-
- if (session->debug & PPPOL2TP_MSG_DATA) {
- int i;
- unsigned char *datap = skb->data;
-
- printk(KERN_DEBUG "%s: xmit:", session->name);
- for (i = 0; i < data_len; i++) {
- printk(" %02X", *datap++);
- if (i == 31) {
- printk(" ...");
- break;
- }
- }
- printk("\n");
- }
-
- memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
- IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
- IPSKB_REROUTED);
- nf_reset(skb);
-
- /* Get routing info from the tunnel socket */
- skb_dst_drop(skb);
- skb_dst_set(skb, dst_clone(__sk_dst_get(sk_tun)));
- pppol2tp_skb_set_owner_w(skb, sk_tun);
-
- /* Calculate UDP checksum if configured to do so */
- if (sk_tun->sk_no_check == UDP_CSUM_NOXMIT)
- skb->ip_summed = CHECKSUM_NONE;
- else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
- (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
- skb->ip_summed = CHECKSUM_COMPLETE;
- csum = skb_checksum(skb, 0, udp_len, 0);
- uh->check = csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, csum);
- if (uh->check == 0)
- uh->check = CSUM_MANGLED_0;
- } else {
- skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, 0);
- }
-
- /* Queue the packet to IP for output */
- len = skb->len;
- rc = ip_queue_xmit(skb, 1);
-
- /* Update stats */
- if (rc >= 0) {
- tunnel->stats.tx_packets++;
- tunnel->stats.tx_bytes += len;
- session->stats.tx_packets++;
- session->stats.tx_bytes += len;
- } else {
- tunnel->stats.tx_errors++;
- session->stats.tx_errors++;
- }
-
- sock_put(sk_tun);
- sock_put(sk);
- return 1;
-
-abort_put_sess_tun:
- sock_put(sk_tun);
-abort_put_sess:
- sock_put(sk);
-abort:
- /* Free the original skb */
- kfree_skb(skb);
- return 1;
-}
-
-/*****************************************************************************
- * Session (and tunnel control) socket create/destroy.
- *****************************************************************************/
-
-/* When the tunnel UDP socket is closed, all the attached sockets need to go
- * too.
- */
-static void pppol2tp_tunnel_closeall(struct pppol2tp_tunnel *tunnel)
-{
- int hash;
- struct hlist_node *walk;
- struct hlist_node *tmp;
- struct pppol2tp_session *session;
- struct sock *sk;
-
- BUG_ON(tunnel == NULL);
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: closing all sessions...\n", tunnel->name);
-
- write_lock_bh(&tunnel->hlist_lock);
- for (hash = 0; hash < PPPOL2TP_HASH_SIZE; hash++) {
-again:
- hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
- struct sk_buff *skb;
-
- session = hlist_entry(walk, struct pppol2tp_session, hlist);
-
- sk = session->sock;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: closing session\n", session->name);
-
- hlist_del_init(&session->hlist);
-
- /* Since we should hold the sock lock while
- * doing any unbinding, we need to release the
- * lock we're holding before taking that lock.
- * Hold a reference to the sock so it doesn't
- * disappear as we're jumping between locks.
- */
- sock_hold(sk);
- write_unlock_bh(&tunnel->hlist_lock);
- lock_sock(sk);
-
- if (sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
- pppox_unbind_sock(sk);
- sk->sk_state = PPPOX_DEAD;
- sk->sk_state_change(sk);
- }
-
- /* Purge any queued data */
- skb_queue_purge(&sk->sk_receive_queue);
- skb_queue_purge(&sk->sk_write_queue);
- while ((skb = skb_dequeue(&session->reorder_q))) {
- kfree_skb(skb);
- sock_put(sk);
- }
-
- release_sock(sk);
- sock_put(sk);
-
- /* Now restart from the beginning of this hash
- * chain. We always remove a session from the
- * list so we are guaranteed to make forward
- * progress.
- */
- write_lock_bh(&tunnel->hlist_lock);
- goto again;
- }
- }
- write_unlock_bh(&tunnel->hlist_lock);
-}
-
-/* Really kill the tunnel.
- * Come here only when all sessions have been cleared from the tunnel.
- */
-static void pppol2tp_tunnel_free(struct pppol2tp_tunnel *tunnel)
-{
- struct pppol2tp_net *pn = pppol2tp_pernet(tunnel->pppol2tp_net);
-
- /* Remove from socket list */
- write_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- list_del_init(&tunnel->list);
- write_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
-
- atomic_dec(&pppol2tp_tunnel_count);
- kfree(tunnel);
-}
-
-/* Tunnel UDP socket destruct hook.
- * The tunnel context is deleted only when all session sockets have been
- * closed.
- */
-static void pppol2tp_tunnel_destruct(struct sock *sk)
-{
- struct pppol2tp_tunnel *tunnel;
-
- tunnel = sk->sk_user_data;
- if (tunnel == NULL)
- goto end;
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: closing...\n", tunnel->name);
-
- /* Close all sessions */
- pppol2tp_tunnel_closeall(tunnel);
-
- /* No longer an encapsulation socket. See net/ipv4/udp.c */
- (udp_sk(sk))->encap_type = 0;
- (udp_sk(sk))->encap_rcv = NULL;
-
- /* Remove hooks into tunnel socket */
- tunnel->sock = NULL;
- sk->sk_destruct = tunnel->old_sk_destruct;
- sk->sk_user_data = NULL;
-
- /* Call original (UDP) socket descructor */
- if (sk->sk_destruct != NULL)
- (*sk->sk_destruct)(sk);
-
- pppol2tp_tunnel_dec_refcount(tunnel);
-
-end:
- return;
-}
-
-/* Really kill the session socket. (Called from sock_put() if
- * refcnt == 0.)
- */
-static void pppol2tp_session_destruct(struct sock *sk)
-{
- struct pppol2tp_session *session = NULL;
-
- if (sk->sk_user_data != NULL) {
- struct pppol2tp_tunnel *tunnel;
-
- session = sk->sk_user_data;
- if (session == NULL)
- goto out;
-
- BUG_ON(session->magic != L2TP_SESSION_MAGIC);
-
- /* Don't use pppol2tp_sock_to_tunnel() here to
- * get the tunnel context because the tunnel
- * socket might have already been closed (its
- * sk->sk_user_data will be NULL) so use the
- * session's private tunnel ptr instead.
- */
- tunnel = session->tunnel;
- if (tunnel != NULL) {
- BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-
- /* If session_id is zero, this is a null
- * session context, which was created for a
- * socket that is being used only to manage
- * tunnels.
- */
- if (session->tunnel_addr.s_session != 0) {
- /* Delete the session socket from the
- * hash
- */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_del_init(&session->hlist);
- write_unlock_bh(&tunnel->hlist_lock);
-
- atomic_dec(&pppol2tp_session_count);
- }
-
- /* This will delete the tunnel context if this
- * is the last session on the tunnel.
- */
- session->tunnel = NULL;
- session->tunnel_sock = NULL;
- pppol2tp_tunnel_dec_refcount(tunnel);
- }
- }
-
- kfree(session);
-out:
- return;
-}
-
-/* Called when the PPPoX socket (session) is closed.
- */
-static int pppol2tp_release(struct socket *sock)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session;
- int error;
-
- if (!sk)
- return 0;
-
- error = -EBADF;
- lock_sock(sk);
- if (sock_flag(sk, SOCK_DEAD) != 0)
- goto error;
-
- pppox_unbind_sock(sk);
-
- /* Signal the death of the socket. */
- sk->sk_state = PPPOX_DEAD;
- sock_orphan(sk);
- sock->sk = NULL;
-
- session = pppol2tp_sock_to_session(sk);
-
- /* Purge any queued data */
- skb_queue_purge(&sk->sk_receive_queue);
- skb_queue_purge(&sk->sk_write_queue);
- if (session != NULL) {
- struct sk_buff *skb;
- while ((skb = skb_dequeue(&session->reorder_q))) {
- kfree_skb(skb);
- sock_put(sk);
- }
- sock_put(sk);
- }
-
- release_sock(sk);
-
- /* This will delete the session context via
- * pppol2tp_session_destruct() if the socket's refcnt drops to
- * zero.
- */
- sock_put(sk);
-
- return 0;
-
-error:
- release_sock(sk);
- return error;
-}
-
-/* Internal function to prepare a tunnel (UDP) socket to have PPPoX
- * sockets attached to it.
- */
-static struct sock *pppol2tp_prepare_tunnel_socket(struct net *net,
- int fd, u16 tunnel_id, int *error)
-{
- int err;
- struct socket *sock = NULL;
- struct sock *sk;
- struct pppol2tp_tunnel *tunnel;
- struct pppol2tp_net *pn;
- struct sock *ret = NULL;
-
- /* Get the tunnel UDP socket from the fd, which was opened by
- * the userspace L2TP daemon.
- */
- err = -EBADF;
- sock = sockfd_lookup(fd, &err);
- if (!sock) {
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
- "tunl %hu: sockfd_lookup(fd=%d) returned %d\n",
- tunnel_id, fd, err);
- goto err;
- }
-
- sk = sock->sk;
-
- /* Quick sanity checks */
- err = -EPROTONOSUPPORT;
- if (sk->sk_protocol != IPPROTO_UDP) {
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
- "tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
- tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
- goto err;
- }
- err = -EAFNOSUPPORT;
- if (sock->ops->family != AF_INET) {
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_ERR,
- "tunl %hu: fd %d wrong family, got %d, expected %d\n",
- tunnel_id, fd, sock->ops->family, AF_INET);
- goto err;
- }
-
- err = -ENOTCONN;
-
- /* Check if this socket has already been prepped */
- tunnel = (struct pppol2tp_tunnel *)sk->sk_user_data;
- if (tunnel != NULL) {
- /* User-data field already set */
- err = -EBUSY;
- BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC);
-
- /* This socket has already been prepped */
- ret = tunnel->sock;
- goto out;
- }
-
- /* This socket is available and needs prepping. Create a new tunnel
- * context and init it.
- */
- sk->sk_user_data = tunnel = kzalloc(sizeof(struct pppol2tp_tunnel), GFP_KERNEL);
- if (sk->sk_user_data == NULL) {
- err = -ENOMEM;
- goto err;
- }
-
- tunnel->magic = L2TP_TUNNEL_MAGIC;
- sprintf(&tunnel->name[0], "tunl %hu", tunnel_id);
-
- tunnel->stats.tunnel_id = tunnel_id;
- tunnel->debug = PPPOL2TP_DEFAULT_DEBUG_FLAGS;
-
- /* Hook on the tunnel socket destructor so that we can cleanup
- * if the tunnel socket goes away.
- */
- tunnel->old_sk_destruct = sk->sk_destruct;
- sk->sk_destruct = pppol2tp_tunnel_destruct;
-
- tunnel->sock = sk;
- sk->sk_allocation = GFP_ATOMIC;
-
- /* Misc init */
- rwlock_init(&tunnel->hlist_lock);
-
- /* The net we belong to */
- tunnel->pppol2tp_net = net;
- pn = pppol2tp_pernet(net);
-
- /* Add tunnel to our list */
- INIT_LIST_HEAD(&tunnel->list);
- write_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- list_add(&tunnel->list, &pn->pppol2tp_tunnel_list);
- write_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
- atomic_inc(&pppol2tp_tunnel_count);
-
- /* Bump the reference count. The tunnel context is deleted
- * only when this drops to zero.
- */
- pppol2tp_tunnel_inc_refcount(tunnel);
-
- /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
- (udp_sk(sk))->encap_type = UDP_ENCAP_L2TPINUDP;
- (udp_sk(sk))->encap_rcv = pppol2tp_udp_encap_recv;
-
- ret = tunnel->sock;
-
- *error = 0;
-out:
- if (sock)
- sockfd_put(sock);
-
- return ret;
-
-err:
- *error = err;
- goto out;
-}
-
-static struct proto pppol2tp_sk_proto = {
- .name = "PPPOL2TP",
- .owner = THIS_MODULE,
- .obj_size = sizeof(struct pppox_sock),
-};
-
-/* socket() handler. Initialize a new struct sock.
- */
-static int pppol2tp_create(struct net *net, struct socket *sock)
-{
- int error = -ENOMEM;
- struct sock *sk;
-
- sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppol2tp_sk_proto);
- if (!sk)
- goto out;
-
- sock_init_data(sock, sk);
-
- sock->state = SS_UNCONNECTED;
- sock->ops = &pppol2tp_ops;
-
- sk->sk_backlog_rcv = pppol2tp_recv_core;
- sk->sk_protocol = PX_PROTO_OL2TP;
- sk->sk_family = PF_PPPOX;
- sk->sk_state = PPPOX_NONE;
- sk->sk_type = SOCK_STREAM;
- sk->sk_destruct = pppol2tp_session_destruct;
-
- error = 0;
-
-out:
- return error;
-}
-
-/* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
- */
-static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
- int sockaddr_len, int flags)
-{
- struct sock *sk = sock->sk;
- struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
- struct pppox_sock *po = pppox_sk(sk);
- struct sock *tunnel_sock = NULL;
- struct pppol2tp_session *session = NULL;
- struct pppol2tp_tunnel *tunnel;
- struct dst_entry *dst;
- int error = 0;
-
- lock_sock(sk);
-
- error = -EINVAL;
- if (sp->sa_protocol != PX_PROTO_OL2TP)
- goto end;
-
- /* Check for already bound sockets */
- error = -EBUSY;
- if (sk->sk_state & PPPOX_CONNECTED)
- goto end;
-
- /* We don't supporting rebinding anyway */
- error = -EALREADY;
- if (sk->sk_user_data)
- goto end; /* socket is already attached */
-
- /* Don't bind if s_tunnel is 0 */
- error = -EINVAL;
- if (sp->pppol2tp.s_tunnel == 0)
- goto end;
-
- /* Special case: prepare tunnel socket if s_session and
- * d_session is 0. Otherwise look up tunnel using supplied
- * tunnel id.
- */
- if ((sp->pppol2tp.s_session == 0) && (sp->pppol2tp.d_session == 0)) {
- tunnel_sock = pppol2tp_prepare_tunnel_socket(sock_net(sk),
- sp->pppol2tp.fd,
- sp->pppol2tp.s_tunnel,
- &error);
- if (tunnel_sock == NULL)
- goto end;
-
- sock_hold(tunnel_sock);
- tunnel = tunnel_sock->sk_user_data;
- } else {
- tunnel = pppol2tp_tunnel_find(sock_net(sk), sp->pppol2tp.s_tunnel);
-
- /* Error if we can't find the tunnel */
- error = -ENOENT;
- if (tunnel == NULL)
- goto end;
-
- tunnel_sock = tunnel->sock;
- }
-
- /* Check that this session doesn't already exist */
- error = -EEXIST;
- session = pppol2tp_session_find(tunnel, sp->pppol2tp.s_session);
- if (session != NULL)
- goto end;
-
- /* Allocate and initialize a new session context. */
- session = kzalloc(sizeof(struct pppol2tp_session), GFP_KERNEL);
- if (session == NULL) {
- error = -ENOMEM;
- goto end;
- }
-
- skb_queue_head_init(&session->reorder_q);
-
- session->magic = L2TP_SESSION_MAGIC;
- session->owner = current->pid;
- session->sock = sk;
- session->tunnel = tunnel;
- session->tunnel_sock = tunnel_sock;
- session->tunnel_addr = sp->pppol2tp;
- sprintf(&session->name[0], "sess %hu/%hu",
- session->tunnel_addr.s_tunnel,
- session->tunnel_addr.s_session);
-
- session->stats.tunnel_id = session->tunnel_addr.s_tunnel;
- session->stats.session_id = session->tunnel_addr.s_session;
-
- INIT_HLIST_NODE(&session->hlist);
-
- /* Inherit debug options from tunnel */
- session->debug = tunnel->debug;
-
- /* Default MTU must allow space for UDP/L2TP/PPP
- * headers.
- */
- session->mtu = session->mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
-
- /* If PMTU discovery was enabled, use the MTU that was discovered */
- dst = sk_dst_get(sk);
- if (dst != NULL) {
- u32 pmtu = dst_mtu(__sk_dst_get(sk));
- if (pmtu != 0)
- session->mtu = session->mru = pmtu -
- PPPOL2TP_HEADER_OVERHEAD;
- dst_release(dst);
- }
-
- /* Special case: if source & dest session_id == 0x0000, this socket is
- * being created to manage the tunnel. Don't add the session to the
- * session hash list, just set up the internal context for use by
- * ioctl() and sockopt() handlers.
- */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- error = 0;
- sk->sk_user_data = session;
- goto out_no_ppp;
- }
-
- /* Get tunnel context from the tunnel socket */
- tunnel = pppol2tp_sock_to_tunnel(tunnel_sock);
- if (tunnel == NULL) {
- error = -EBADF;
- goto end;
- }
-
- /* Right now, because we don't have a way to push the incoming skb's
- * straight through the UDP layer, the only header we need to worry
- * about is the L2TP header. This size is different depending on
- * whether sequence numbers are enabled for the data channel.
- */
- po->chan.hdrlen = PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
-
- po->chan.private = sk;
- po->chan.ops = &pppol2tp_chan_ops;
- po->chan.mtu = session->mtu;
-
- error = ppp_register_net_channel(sock_net(sk), &po->chan);
- if (error)
- goto end_put_tun;
-
- /* This is how we get the session context from the socket. */
- sk->sk_user_data = session;
-
- /* Add session to the tunnel's hash list */
- write_lock_bh(&tunnel->hlist_lock);
- hlist_add_head(&session->hlist,
- pppol2tp_session_id_hash(tunnel,
- session->tunnel_addr.s_session));
- write_unlock_bh(&tunnel->hlist_lock);
-
- atomic_inc(&pppol2tp_session_count);
-
-out_no_ppp:
- pppol2tp_tunnel_inc_refcount(tunnel);
- sk->sk_state = PPPOX_CONNECTED;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: created\n", session->name);
-
-end_put_tun:
- sock_put(tunnel_sock);
-end:
- release_sock(sk);
-
- if (error != 0) {
- if (session)
- PRINTK(session->debug,
- PPPOL2TP_MSG_CONTROL, KERN_WARNING,
- "%s: connect failed: %d\n",
- session->name, error);
- else
- PRINTK(-1, PPPOL2TP_MSG_CONTROL, KERN_WARNING,
- "connect failed: %d\n", error);
- }
-
- return error;
-}
-
-/* getname() support.
- */
-static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
- int *usockaddr_len, int peer)
-{
- int len = sizeof(struct sockaddr_pppol2tp);
- struct sockaddr_pppol2tp sp;
- int error = 0;
- struct pppol2tp_session *session;
-
- error = -ENOTCONN;
- if (sock->sk->sk_state != PPPOX_CONNECTED)
- goto end;
-
- session = pppol2tp_sock_to_session(sock->sk);
- if (session == NULL) {
- error = -EBADF;
- goto end;
- }
-
- sp.sa_family = AF_PPPOX;
- sp.sa_protocol = PX_PROTO_OL2TP;
- memcpy(&sp.pppol2tp, &session->tunnel_addr,
- sizeof(struct pppol2tp_addr));
-
- memcpy(uaddr, &sp, len);
-
- *usockaddr_len = len;
-
- error = 0;
- sock_put(sock->sk);
-
-end:
- return error;
-}
-
-/****************************************************************************
- * ioctl() handlers.
- *
- * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
- * sockets. However, in order to control kernel tunnel features, we allow
- * userspace to create a special "tunnel" PPPoX socket which is used for
- * control only. Tunnel PPPoX sockets have session_id == 0 and simply allow
- * the user application to issue L2TP setsockopt(), getsockopt() and ioctl()
- * calls.
- ****************************************************************************/
-
-/* Session ioctl helper.
- */
-static int pppol2tp_session_ioctl(struct pppol2tp_session *session,
- unsigned int cmd, unsigned long arg)
-{
- struct ifreq ifr;
- int err = 0;
- struct sock *sk = session->sock;
- int val = (int) arg;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
- "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
- session->name, cmd, arg);
-
- sock_hold(sk);
-
- switch (cmd) {
- case SIOCGIFMTU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
- break;
- ifr.ifr_mtu = session->mtu;
- if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq)))
- break;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get mtu=%d\n", session->name, session->mtu);
- err = 0;
- break;
-
- case SIOCSIFMTU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
- break;
-
- session->mtu = ifr.ifr_mtu;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set mtu=%d\n", session->name, session->mtu);
- err = 0;
- break;
-
- case PPPIOCGMRU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (put_user(session->mru, (int __user *) arg))
- break;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get mru=%d\n", session->name, session->mru);
- err = 0;
- break;
-
- case PPPIOCSMRU:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- err = -EFAULT;
- if (get_user(val,(int __user *) arg))
- break;
-
- session->mru = val;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set mru=%d\n", session->name, session->mru);
- err = 0;
- break;
-
- case PPPIOCGFLAGS:
- err = -EFAULT;
- if (put_user(session->flags, (int __user *) arg))
- break;
-
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get flags=%d\n", session->name, session->flags);
- err = 0;
- break;
-
- case PPPIOCSFLAGS:
- err = -EFAULT;
- if (get_user(val, (int __user *) arg))
- break;
- session->flags = val;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set flags=%d\n", session->name, session->flags);
- err = 0;
- break;
-
- case PPPIOCGL2TPSTATS:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- if (copy_to_user((void __user *) arg, &session->stats,
- sizeof(session->stats)))
- break;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get L2TP stats\n", session->name);
- err = 0;
- break;
-
- default:
- err = -ENOSYS;
- break;
- }
-
- sock_put(sk);
-
- return err;
-}
-
-/* Tunnel ioctl helper.
- *
- * Note the special handling for PPPIOCGL2TPSTATS below. If the ioctl data
- * specifies a session_id, the session ioctl handler is called. This allows an
- * application to retrieve session stats via a tunnel socket.
- */
-static int pppol2tp_tunnel_ioctl(struct pppol2tp_tunnel *tunnel,
- unsigned int cmd, unsigned long arg)
-{
- int err = 0;
- struct sock *sk = tunnel->sock;
- struct pppol2tp_ioc_stats stats_req;
-
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_DEBUG,
- "%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n", tunnel->name,
- cmd, arg);
-
- sock_hold(sk);
-
- switch (cmd) {
- case PPPIOCGL2TPSTATS:
- err = -ENXIO;
- if (!(sk->sk_state & PPPOX_CONNECTED))
- break;
-
- if (copy_from_user(&stats_req, (void __user *) arg,
- sizeof(stats_req))) {
- err = -EFAULT;
- break;
- }
- if (stats_req.session_id != 0) {
- /* resend to session ioctl handler */
- struct pppol2tp_session *session =
- pppol2tp_session_find(tunnel, stats_req.session_id);
- if (session != NULL)
- err = pppol2tp_session_ioctl(session, cmd, arg);
- else
- err = -EBADR;
- break;
- }
-#ifdef CONFIG_XFRM
- tunnel->stats.using_ipsec = (sk->sk_policy[0] || sk->sk_policy[1]) ? 1 : 0;
-#endif
- if (copy_to_user((void __user *) arg, &tunnel->stats,
- sizeof(tunnel->stats))) {
- err = -EFAULT;
- break;
- }
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get L2TP stats\n", tunnel->name);
- err = 0;
- break;
-
- default:
- err = -ENOSYS;
- break;
- }
-
- sock_put(sk);
-
- return err;
-}
-
-/* Main ioctl() handler.
- * Dispatch to tunnel or session helpers depending on the socket.
- */
-static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
- unsigned long arg)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session;
- struct pppol2tp_tunnel *tunnel;
- int err;
-
- if (!sk)
- return 0;
-
- err = -EBADF;
- if (sock_flag(sk, SOCK_DEAD) != 0)
- goto end;
-
- err = -ENOTCONN;
- if ((sk->sk_user_data == NULL) ||
- (!(sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND))))
- goto end;
-
- /* Get session context from the socket */
- err = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto end;
-
- /* Special case: if session's session_id is zero, treat ioctl as a
- * tunnel ioctl
- */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- err = -EBADF;
- tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
- if (tunnel == NULL)
- goto end_put_sess;
-
- err = pppol2tp_tunnel_ioctl(tunnel, cmd, arg);
- sock_put(session->tunnel_sock);
- goto end_put_sess;
- }
-
- err = pppol2tp_session_ioctl(session, cmd, arg);
-
-end_put_sess:
- sock_put(sk);
-end:
- return err;
-}
-
-/*****************************************************************************
- * setsockopt() / getsockopt() support.
- *
- * The PPPoX socket is created for L2TP sessions: tunnels have their own UDP
- * sockets. In order to control kernel tunnel features, we allow userspace to
- * create a special "tunnel" PPPoX socket which is used for control only.
- * Tunnel PPPoX sockets have session_id == 0 and simply allow the user
- * application to issue L2TP setsockopt(), getsockopt() and ioctl() calls.
- *****************************************************************************/
-
-/* Tunnel setsockopt() helper.
- */
-static int pppol2tp_tunnel_setsockopt(struct sock *sk,
- struct pppol2tp_tunnel *tunnel,
- int optname, int val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_DEBUG:
- tunnel->debug = val;
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set debug=%x\n", tunnel->name, tunnel->debug);
- break;
-
- default:
- err = -ENOPROTOOPT;
- break;
- }
-
- return err;
-}
-
-/* Session setsockopt helper.
- */
-static int pppol2tp_session_setsockopt(struct sock *sk,
- struct pppol2tp_session *session,
- int optname, int val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_RECVSEQ:
- if ((val != 0) && (val != 1)) {
- err = -EINVAL;
- break;
- }
- session->recv_seq = val ? -1 : 0;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set recv_seq=%d\n", session->name,
- session->recv_seq);
- break;
-
- case PPPOL2TP_SO_SENDSEQ:
- if ((val != 0) && (val != 1)) {
- err = -EINVAL;
- break;
- }
- session->send_seq = val ? -1 : 0;
- {
- struct sock *ssk = session->sock;
- struct pppox_sock *po = pppox_sk(ssk);
- po->chan.hdrlen = val ? PPPOL2TP_L2TP_HDR_SIZE_SEQ :
- PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
- }
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set send_seq=%d\n", session->name, session->send_seq);
- break;
-
- case PPPOL2TP_SO_LNSMODE:
- if ((val != 0) && (val != 1)) {
- err = -EINVAL;
- break;
- }
- session->lns_mode = val ? -1 : 0;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set lns_mode=%d\n", session->name,
- session->lns_mode);
- break;
-
- case PPPOL2TP_SO_DEBUG:
- session->debug = val;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set debug=%x\n", session->name, session->debug);
- break;
-
- case PPPOL2TP_SO_REORDERTO:
- session->reorder_timeout = msecs_to_jiffies(val);
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: set reorder_timeout=%d\n", session->name,
- session->reorder_timeout);
- break;
-
- default:
- err = -ENOPROTOOPT;
- break;
- }
-
- return err;
-}
-
-/* Main setsockopt() entry point.
- * Does API checks, then calls either the tunnel or session setsockopt
- * handler, according to whether the PPPoL2TP socket is a for a regular
- * session or the special tunnel type.
- */
-static int pppol2tp_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, unsigned int optlen)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session = sk->sk_user_data;
- struct pppol2tp_tunnel *tunnel;
- int val;
- int err;
-
- if (level != SOL_PPPOL2TP)
- return udp_prot.setsockopt(sk, level, optname, optval, optlen);
-
- if (optlen < sizeof(int))
- return -EINVAL;
-
- if (get_user(val, (int __user *)optval))
- return -EFAULT;
-
- err = -ENOTCONN;
- if (sk->sk_user_data == NULL)
- goto end;
-
- /* Get session context from the socket */
- err = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto end;
-
- /* Special case: if session_id == 0x0000, treat as operation on tunnel
- */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- err = -EBADF;
- tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
- if (tunnel == NULL)
- goto end_put_sess;
-
- err = pppol2tp_tunnel_setsockopt(sk, tunnel, optname, val);
- sock_put(session->tunnel_sock);
- } else
- err = pppol2tp_session_setsockopt(sk, session, optname, val);
-
- err = 0;
-
-end_put_sess:
- sock_put(sk);
-end:
- return err;
-}
-
-/* Tunnel getsockopt helper. Called with sock locked.
- */
-static int pppol2tp_tunnel_getsockopt(struct sock *sk,
- struct pppol2tp_tunnel *tunnel,
- int optname, int *val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_DEBUG:
- *val = tunnel->debug;
- PRINTK(tunnel->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get debug=%x\n", tunnel->name, tunnel->debug);
- break;
-
- default:
- err = -ENOPROTOOPT;
- break;
- }
-
- return err;
-}
-
-/* Session getsockopt helper. Called with sock locked.
- */
-static int pppol2tp_session_getsockopt(struct sock *sk,
- struct pppol2tp_session *session,
- int optname, int *val)
-{
- int err = 0;
-
- switch (optname) {
- case PPPOL2TP_SO_RECVSEQ:
- *val = session->recv_seq;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get recv_seq=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_SENDSEQ:
- *val = session->send_seq;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get send_seq=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_LNSMODE:
- *val = session->lns_mode;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get lns_mode=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_DEBUG:
- *val = session->debug;
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get debug=%d\n", session->name, *val);
- break;
-
- case PPPOL2TP_SO_REORDERTO:
- *val = (int) jiffies_to_msecs(session->reorder_timeout);
- PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
- "%s: get reorder_timeout=%d\n", session->name, *val);
- break;
-
- default:
- err = -ENOPROTOOPT;
- }
-
- return err;
-}
-
-/* Main getsockopt() entry point.
- * Does API checks, then calls either the tunnel or session getsockopt
- * handler, according to whether the PPPoX socket is a for a regular session
- * or the special tunnel type.
- */
-static int pppol2tp_getsockopt(struct socket *sock, int level,
- int optname, char __user *optval, int __user *optlen)
-{
- struct sock *sk = sock->sk;
- struct pppol2tp_session *session = sk->sk_user_data;
- struct pppol2tp_tunnel *tunnel;
- int val, len;
- int err;
-
- if (level != SOL_PPPOL2TP)
- return udp_prot.getsockopt(sk, level, optname, optval, optlen);
-
- if (get_user(len, (int __user *) optlen))
- return -EFAULT;
-
- len = min_t(unsigned int, len, sizeof(int));
-
- if (len < 0)
- return -EINVAL;
-
- err = -ENOTCONN;
- if (sk->sk_user_data == NULL)
- goto end;
-
- /* Get the session context */
- err = -EBADF;
- session = pppol2tp_sock_to_session(sk);
- if (session == NULL)
- goto end;
-
- /* Special case: if session_id == 0x0000, treat as operation on tunnel */
- if ((session->tunnel_addr.s_session == 0) &&
- (session->tunnel_addr.d_session == 0)) {
- err = -EBADF;
- tunnel = pppol2tp_sock_to_tunnel(session->tunnel_sock);
- if (tunnel == NULL)
- goto end_put_sess;
-
- err = pppol2tp_tunnel_getsockopt(sk, tunnel, optname, &val);
- sock_put(session->tunnel_sock);
- } else
- err = pppol2tp_session_getsockopt(sk, session, optname, &val);
-
- err = -EFAULT;
- if (put_user(len, (int __user *) optlen))
- goto end_put_sess;
-
- if (copy_to_user((void __user *) optval, &val, len))
- goto end_put_sess;
-
- err = 0;
-
-end_put_sess:
- sock_put(sk);
-end:
- return err;
-}
-
-/*****************************************************************************
- * /proc filesystem for debug
- *****************************************************************************/
-
-#ifdef CONFIG_PROC_FS
-
-#include <linux/seq_file.h>
-
-struct pppol2tp_seq_data {
- struct seq_net_private p;
- struct pppol2tp_tunnel *tunnel; /* current tunnel */
- struct pppol2tp_session *session; /* NULL means get first session in tunnel */
-};
-
-static struct pppol2tp_session *next_session(struct pppol2tp_tunnel *tunnel, struct pppol2tp_session *curr)
-{
- struct pppol2tp_session *session = NULL;
- struct hlist_node *walk;
- int found = 0;
- int next = 0;
- int i;
-
- read_lock_bh(&tunnel->hlist_lock);
- for (i = 0; i < PPPOL2TP_HASH_SIZE; i++) {
- hlist_for_each_entry(session, walk, &tunnel->session_hlist[i], hlist) {
- if (curr == NULL) {
- found = 1;
- goto out;
- }
- if (session == curr) {
- next = 1;
- continue;
- }
- if (next) {
- found = 1;
- goto out;
- }
- }
- }
-out:
- read_unlock_bh(&tunnel->hlist_lock);
- if (!found)
- session = NULL;
-
- return session;
-}
-
-static struct pppol2tp_tunnel *next_tunnel(struct pppol2tp_net *pn,
- struct pppol2tp_tunnel *curr)
-{
- struct pppol2tp_tunnel *tunnel = NULL;
-
- read_lock_bh(&pn->pppol2tp_tunnel_list_lock);
- if (list_is_last(&curr->list, &pn->pppol2tp_tunnel_list)) {
- goto out;
- }
- tunnel = list_entry(curr->list.next, struct pppol2tp_tunnel, list);
-out:
- read_unlock_bh(&pn->pppol2tp_tunnel_list_lock);
-
- return tunnel;
-}
-
-static void *pppol2tp_seq_start(struct seq_file *m, loff_t *offs)
-{
- struct pppol2tp_seq_data *pd = SEQ_START_TOKEN;
- struct pppol2tp_net *pn;
- loff_t pos = *offs;
-
- if (!pos)
- goto out;
-
- BUG_ON(m->private == NULL);
- pd = m->private;
- pn = pppol2tp_pernet(seq_file_net(m));
-
- if (pd->tunnel == NULL) {
- if (!list_empty(&pn->pppol2tp_tunnel_list))
- pd->tunnel = list_entry(pn->pppol2tp_tunnel_list.next, struct pppol2tp_tunnel, list);
- } else {
- pd->session = next_session(pd->tunnel, pd->session);
- if (pd->session == NULL) {
- pd->tunnel = next_tunnel(pn, pd->tunnel);
- }
- }
-
- /* NULL tunnel and session indicates end of list */
- if ((pd->tunnel == NULL) && (pd->session == NULL))
- pd = NULL;
-
-out:
- return pd;
-}
-
-static void *pppol2tp_seq_next(struct seq_file *m, void *v, loff_t *pos)
-{
- (*pos)++;
- return NULL;
-}
-
-static void pppol2tp_seq_stop(struct seq_file *p, void *v)
-{
- /* nothing to do */
-}
-
-static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
-{
- struct pppol2tp_tunnel *tunnel = v;
-
- seq_printf(m, "\nTUNNEL '%s', %c %d\n",
- tunnel->name,
- (tunnel == tunnel->sock->sk_user_data) ? 'Y':'N',
- atomic_read(&tunnel->ref_count) - 1);
- seq_printf(m, " %08x %llu/%llu/%llu %llu/%llu/%llu\n",
- tunnel->debug,
- (unsigned long long)tunnel->stats.tx_packets,
- (unsigned long long)tunnel->stats.tx_bytes,
- (unsigned long long)tunnel->stats.tx_errors,
- (unsigned long long)tunnel->stats.rx_packets,
- (unsigned long long)tunnel->stats.rx_bytes,
- (unsigned long long)tunnel->stats.rx_errors);
-}
-
-static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
-{
- struct pppol2tp_session *session = v;
-
- seq_printf(m, " SESSION '%s' %08X/%d %04X/%04X -> "
- "%04X/%04X %d %c\n",
- session->name,
- ntohl(session->tunnel_addr.addr.sin_addr.s_addr),
- ntohs(session->tunnel_addr.addr.sin_port),
- session->tunnel_addr.s_tunnel,
- session->tunnel_addr.s_session,
- session->tunnel_addr.d_tunnel,
- session->tunnel_addr.d_session,
- session->sock->sk_state,
- (session == session->sock->sk_user_data) ?
- 'Y' : 'N');
- seq_printf(m, " %d/%d/%c/%c/%s %08x %u\n",
- session->mtu, session->mru,
- session->recv_seq ? 'R' : '-',
- session->send_seq ? 'S' : '-',
- session->lns_mode ? "LNS" : "LAC",
- session->debug,
- jiffies_to_msecs(session->reorder_timeout));
- seq_printf(m, " %hu/%hu %llu/%llu/%llu %llu/%llu/%llu\n",
- session->nr, session->ns,
- (unsigned long long)session->stats.tx_packets,
- (unsigned long long)session->stats.tx_bytes,
- (unsigned long long)session->stats.tx_errors,
- (unsigned long long)session->stats.rx_packets,
- (unsigned long long)session->stats.rx_bytes,
- (unsigned long long)session->stats.rx_errors);
-}
-
-static int pppol2tp_seq_show(struct seq_file *m, void *v)
-{
- struct pppol2tp_seq_data *pd = v;
-
- /* display header on line 1 */
- if (v == SEQ_START_TOKEN) {
- seq_puts(m, "PPPoL2TP driver info, " PPPOL2TP_DRV_VERSION "\n");
- seq_puts(m, "TUNNEL name, user-data-ok session-count\n");
- seq_puts(m, " debug tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
- seq_puts(m, " SESSION name, addr/port src-tid/sid "
- "dest-tid/sid state user-data-ok\n");
- seq_puts(m, " mtu/mru/rcvseq/sendseq/lns debug reorderto\n");
- seq_puts(m, " nr/ns tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
- goto out;
- }
-
- /* Show the tunnel or session context.
- */
- if (pd->session == NULL)
- pppol2tp_seq_tunnel_show(m, pd->tunnel);
- else
- pppol2tp_seq_session_show(m, pd->session);
-
-out:
- return 0;
-}
-
-static const struct seq_operations pppol2tp_seq_ops = {
- .start = pppol2tp_seq_start,
- .next = pppol2tp_seq_next,
- .stop = pppol2tp_seq_stop,
- .show = pppol2tp_seq_show,
-};
-
-/* Called when our /proc file is opened. We allocate data for use when
- * iterating our tunnel / session contexts and store it in the private
- * data of the seq_file.
- */
-static int pppol2tp_proc_open(struct inode *inode, struct file *file)
-{
- return seq_open_net(inode, file, &pppol2tp_seq_ops,
- sizeof(struct pppol2tp_seq_data));
-}
-
-static const struct file_operations pppol2tp_proc_fops = {
- .owner = THIS_MODULE,
- .open = pppol2tp_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
-#endif /* CONFIG_PROC_FS */
-
-/*****************************************************************************
- * Init and cleanup
- *****************************************************************************/
-
-static const struct proto_ops pppol2tp_ops = {
- .family = AF_PPPOX,
- .owner = THIS_MODULE,
- .release = pppol2tp_release,
- .bind = sock_no_bind,
- .connect = pppol2tp_connect,
- .socketpair = sock_no_socketpair,
- .accept = sock_no_accept,
- .getname = pppol2tp_getname,
- .poll = datagram_poll,
- .listen = sock_no_listen,
- .shutdown = sock_no_shutdown,
- .setsockopt = pppol2tp_setsockopt,
- .getsockopt = pppol2tp_getsockopt,
- .sendmsg = pppol2tp_sendmsg,
- .recvmsg = pppol2tp_recvmsg,
- .mmap = sock_no_mmap,
- .ioctl = pppox_ioctl,
-};
-
-static struct pppox_proto pppol2tp_proto = {
- .create = pppol2tp_create,
- .ioctl = pppol2tp_ioctl
-};
-
-static __net_init int pppol2tp_init_net(struct net *net)
-{
- struct pppol2tp_net *pn = pppol2tp_pernet(net);
- struct proc_dir_entry *pde;
-
- INIT_LIST_HEAD(&pn->pppol2tp_tunnel_list);
- rwlock_init(&pn->pppol2tp_tunnel_list_lock);
-
- pde = proc_net_fops_create(net, "pppol2tp", S_IRUGO, &pppol2tp_proc_fops);
-#ifdef CONFIG_PROC_FS
- if (!pde)
- return -ENOMEM;
-#endif
-
- return 0;
-}
-
-static __net_exit void pppol2tp_exit_net(struct net *net)
-{
- proc_net_remove(net, "pppol2tp");
-}
-
-static struct pernet_operations pppol2tp_net_ops = {
- .init = pppol2tp_init_net,
- .exit = pppol2tp_exit_net,
- .id = &pppol2tp_net_id,
- .size = sizeof(struct pppol2tp_net),
-};
-
-static int __init pppol2tp_init(void)
-{
- int err;
-
- err = proto_register(&pppol2tp_sk_proto, 0);
- if (err)
- goto out;
- err = register_pppox_proto(PX_PROTO_OL2TP, &pppol2tp_proto);
- if (err)
- goto out_unregister_pppol2tp_proto;
-
- err = register_pernet_device(&pppol2tp_net_ops);
- if (err)
- goto out_unregister_pppox_proto;
-
- printk(KERN_INFO "PPPoL2TP kernel driver, %s\n",
- PPPOL2TP_DRV_VERSION);
-
-out:
- return err;
-out_unregister_pppox_proto:
- unregister_pppox_proto(PX_PROTO_OL2TP);
-out_unregister_pppol2tp_proto:
- proto_unregister(&pppol2tp_sk_proto);
- goto out;
-}
-
-static void __exit pppol2tp_exit(void)
-{
- unregister_pppox_proto(PX_PROTO_OL2TP);
- unregister_pernet_device(&pppol2tp_net_ops);
- proto_unregister(&pppol2tp_sk_proto);
-}
-
-module_init(pppol2tp_init);
-module_exit(pppol2tp_exit);
-
-MODULE_AUTHOR("Martijn van Oosterhout <kleptog@svana.org>, "
- "James Chapman <jchapman@katalix.com>");
-MODULE_DESCRIPTION("PPP over L2TP over UDP");
-MODULE_LICENSE("GPL");
-MODULE_VERSION(PPPOL2TP_DRV_VERSION);
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 03/12] ppp: Add ppp_dev_name() exported function
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
2010-03-30 16:17 ` [PATCH v3 01/12] l2tp: Relocate pppol2tp driver to new net/l2tp directory James Chapman
2010-03-30 16:17 ` [PATCH v3 02/12] l2tp: Split pppol2tp patch into separate l2tp and ppp parts James Chapman
@ 2010-03-30 16:17 ` James Chapman
2010-03-30 16:17 ` [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data James Chapman
` (8 subsequent siblings)
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:17 UTC (permalink / raw)
To: netdev
ppp_dev_name() gives PPP users visibility of a ppp channel's device
name. This can be used by L2TP drivers to dump the assigned PPP
interface name.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
drivers/net/ppp_generic.c | 19 +++++++++++++++++++
include/linux/ppp_channel.h | 3 +++
2 files changed, 22 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c
index 6d61602..8a0dd8a 100644
--- a/drivers/net/ppp_generic.c
+++ b/drivers/net/ppp_generic.c
@@ -2163,6 +2163,24 @@ int ppp_unit_number(struct ppp_channel *chan)
}
/*
+ * Return the PPP device interface name of a channel.
+ */
+char *ppp_dev_name(struct ppp_channel *chan)
+{
+ struct channel *pch = chan->ppp;
+ char *name = NULL;
+
+ if (pch) {
+ read_lock_bh(&pch->upl);
+ if (pch->ppp && pch->ppp->dev)
+ name = pch->ppp->dev->name;
+ read_unlock_bh(&pch->upl);
+ }
+ return name;
+}
+
+
+/*
* Disconnect a channel from the generic layer.
* This must be called in process context.
*/
@@ -2890,6 +2908,7 @@ EXPORT_SYMBOL(ppp_register_channel);
EXPORT_SYMBOL(ppp_unregister_channel);
EXPORT_SYMBOL(ppp_channel_index);
EXPORT_SYMBOL(ppp_unit_number);
+EXPORT_SYMBOL(ppp_dev_name);
EXPORT_SYMBOL(ppp_input);
EXPORT_SYMBOL(ppp_input_error);
EXPORT_SYMBOL(ppp_output_wakeup);
diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h
index 0d3fa63..bff98ec 100644
--- a/include/linux/ppp_channel.h
+++ b/include/linux/ppp_channel.h
@@ -72,6 +72,9 @@ extern int ppp_channel_index(struct ppp_channel *);
/* Get the unit number associated with a channel, or -1 if none */
extern int ppp_unit_number(struct ppp_channel *);
+/* Get the device name associated with a channel, or NULL if none */
+extern char *ppp_dev_name(struct ppp_channel *);
+
/*
* SMP locking notes:
* The channel code must ensure that when it calls ppp_unregister_channel,
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (2 preceding siblings ...)
2010-03-30 16:17 ` [PATCH v3 03/12] ppp: Add ppp_dev_name() exported function James Chapman
@ 2010-03-30 16:17 ` James Chapman
2010-03-30 16:29 ` Stephen Hemminger
2010-03-30 16:17 ` [PATCH v3 05/12] l2tp: Add L2TPv3 protocol support James Chapman
` (7 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:17 UTC (permalink / raw)
To: netdev
When dumping L2TP PPP sessions using /proc/net/l2tp, get
the assigned PPP device name from PPP using ppp_dev_name().
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
net/l2tp/l2tp_ppp.c | 17 +++++++++++++++++
1 files changed, 17 insertions(+), 0 deletions(-)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 03195ab..8f78c27 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -608,6 +608,20 @@ out:
return error;
}
+#ifdef CONFIG_PROC_FS
+static void pppol2tp_show(struct seq_file *m, void *arg)
+{
+ struct l2tp_session *session = arg;
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+
+ if (ps) {
+ struct pppox_sock *po = pppox_sk(ps->sock);
+ if (po)
+ seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan));
+ }
+}
+#endif
+
/* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
*/
static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
@@ -697,6 +711,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
session->recv_skb = pppol2tp_recv;
session->session_close = pppol2tp_session_close;
+#ifdef CONFIG_PROC_FS
+ session->show = pppol2tp_show;
+#endif
/* We need to know each time a skb is dropped from the reorder
* queue.
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-03-30 16:17 ` [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data James Chapman
@ 2010-03-30 16:29 ` Stephen Hemminger
2010-03-31 7:43 ` James Chapman
0 siblings, 1 reply; 32+ messages in thread
From: Stephen Hemminger @ 2010-03-30 16:29 UTC (permalink / raw)
To: James Chapman; +Cc: netdev
On Tue, 30 Mar 2010 17:17:46 +0100
James Chapman <jchapman@katalix.com> wrote:
> When dumping L2TP PPP sessions using /proc/net/l2tp, get
> the assigned PPP device name from PPP using ppp_dev_name().
>
> Signed-off-by: James Chapman <jchapman@katalix.com>
> Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
>
Why is this a necessary API?
Why not put it in debugfs if just a debugging tool?
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-03-30 16:29 ` Stephen Hemminger
@ 2010-03-31 7:43 ` James Chapman
2010-03-31 8:46 ` David Miller
2010-03-31 23:08 ` Stephen Hemminger
0 siblings, 2 replies; 32+ messages in thread
From: James Chapman @ 2010-03-31 7:43 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
Stephen Hemminger wrote:
> On Tue, 30 Mar 2010 17:17:46 +0100
> James Chapman <jchapman@katalix.com> wrote:
>
>> When dumping L2TP PPP sessions using /proc/net/l2tp, get
>> the assigned PPP device name from PPP using ppp_dev_name().
>>
>> Signed-off-by: James Chapman <jchapman@katalix.com>
>> Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
>>
>
> Why is this a necessary API?
> Why not put it in debugfs if just a debugging tool?
With the original driver (merged in 2.6.23), some people use horrible
hacks in scripts to derive info about their L2TP connections from /proc.
So I was reluctant to move it to debugfs in the new driver. If it is ok
to move an existing /proc file to debugfs, I'm happy to do so. People
should obtain such info from their L2TP userspace daemon, or through
netlink anyway.
--
James Chapman
Katalix Systems Ltd
http://www.katalix.com
Catalysts for your Embedded Linux software development
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-03-31 7:43 ` James Chapman
@ 2010-03-31 8:46 ` David Miller
2010-03-31 23:08 ` Stephen Hemminger
1 sibling, 0 replies; 32+ messages in thread
From: David Miller @ 2010-03-31 8:46 UTC (permalink / raw)
To: jchapman; +Cc: shemminger, netdev
From: James Chapman <jchapman@katalix.com>
Date: Wed, 31 Mar 2010 08:43:09 +0100
> Stephen Hemminger wrote:
>> On Tue, 30 Mar 2010 17:17:46 +0100
>> James Chapman <jchapman@katalix.com> wrote:
>>
>>> When dumping L2TP PPP sessions using /proc/net/l2tp, get
>>> the assigned PPP device name from PPP using ppp_dev_name().
>>>
>>> Signed-off-by: James Chapman <jchapman@katalix.com>
>>> Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
>>>
>>
>> Why is this a necessary API?
>> Why not put it in debugfs if just a debugging tool?
>
> With the original driver (merged in 2.6.23), some people use horrible
> hacks in scripts to derive info about their L2TP connections from /proc.
> So I was reluctant to move it to debugfs in the new driver. If it is ok
> to move an existing /proc file to debugfs, I'm happy to do so. People
> should obtain such info from their L2TP userspace daemon, or through
> netlink anyway.
Existing stuff you shouldn't move around, people do depend on it
and thus it has to be retained.
But for new stuff, we can try to think about better ways to export the
information if possible.
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-03-31 7:43 ` James Chapman
2010-03-31 8:46 ` David Miller
@ 2010-03-31 23:08 ` Stephen Hemminger
2010-04-01 7:19 ` James Chapman
1 sibling, 1 reply; 32+ messages in thread
From: Stephen Hemminger @ 2010-03-31 23:08 UTC (permalink / raw)
To: James Chapman; +Cc: netdev
On Wed, 31 Mar 2010 08:43:09 +0100
James Chapman <jchapman@katalix.com> wrote:
> Stephen Hemminger wrote:
> > On Tue, 30 Mar 2010 17:17:46 +0100
> > James Chapman <jchapman@katalix.com> wrote:
> >
> >> When dumping L2TP PPP sessions using /proc/net/l2tp, get
> >> the assigned PPP device name from PPP using ppp_dev_name().
> >>
> >> Signed-off-by: James Chapman <jchapman@katalix.com>
> >> Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
> >>
> >
> > Why is this a necessary API?
> > Why not put it in debugfs if just a debugging tool?
>
> With the original driver (merged in 2.6.23), some people use horrible
> hacks in scripts to derive info about their L2TP connections from /proc.
> So I was reluctant to move it to debugfs in the new driver. If it is ok
> to move an existing /proc file to debugfs, I'm happy to do so. People
> should obtain such info from their L2TP userspace daemon, or through
> netlink anyway.
>
>
Sounds like a good use of sysfs either with attribute or symlink
back to underlying device
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-03-31 23:08 ` Stephen Hemminger
@ 2010-04-01 7:19 ` James Chapman
2010-04-01 7:30 ` Eric Dumazet
2010-04-01 7:34 ` David Miller
0 siblings, 2 replies; 32+ messages in thread
From: James Chapman @ 2010-04-01 7:19 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
Stephen Hemminger wrote:
> On Wed, 31 Mar 2010 08:43:09 +0100
> James Chapman <jchapman@katalix.com> wrote:
>
>> Stephen Hemminger wrote:
>>> On Tue, 30 Mar 2010 17:17:46 +0100
>>> James Chapman <jchapman@katalix.com> wrote:
>>>
>>>> When dumping L2TP PPP sessions using /proc/net/l2tp, get
>>>> the assigned PPP device name from PPP using ppp_dev_name().
>>>>
>>>> Signed-off-by: James Chapman <jchapman@katalix.com>
>>>> Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
>>>>
>>> Why is this a necessary API?
>>> Why not put it in debugfs if just a debugging tool?
>> With the original driver (merged in 2.6.23), some people use horrible
>> hacks in scripts to derive info about their L2TP connections from /proc.
>> So I was reluctant to move it to debugfs in the new driver. If it is ok
>> to move an existing /proc file to debugfs, I'm happy to do so. People
>> should obtain such info from their L2TP userspace daemon, or through
>> netlink anyway.
>>
>>
> Sounds like a good use of sysfs either with attribute or symlink
> back to underlying device
>
There might be thousands of L2TP sessions in some setups. Populating
sysfs with a link for each of those sessions isn't practical. The
existing /proc file dumps its info as a single text file for this
reason. I'd also like to provide the device name in the session netlink
message, which is the interface used by l2tp userspace, so I need a
kernel API to retrieve the device name from ppp.
I like the suggestion of using debugfs for access to driver debug info
though. I propose leaving the /proc file for L2TPv2 only, removing the
L2TPv3 data that I added to the proc file in this patch series, to
retain compatibility with the existing driver. This would show only
L2TPv2 sessions and tunnels. For new driver functionality (L2TPv3 etc),
use debugfs. The debugfs files would dump lists in a similar form to the
current code, listing all tunnels (L2TPv2 and L2TPv3) in a single file.
Using debugfs gives more flexibility for adding additional info later,
as required. How does that sound?
--
James Chapman
Katalix Systems Ltd
http://www.katalix.com
Catalysts for your Embedded Linux software development
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-04-01 7:19 ` James Chapman
@ 2010-04-01 7:30 ` Eric Dumazet
2010-04-01 8:55 ` James Chapman
2010-04-01 7:34 ` David Miller
1 sibling, 1 reply; 32+ messages in thread
From: Eric Dumazet @ 2010-04-01 7:30 UTC (permalink / raw)
To: James Chapman; +Cc: Stephen Hemminger, netdev
Le jeudi 01 avril 2010 à 08:19 +0100, James Chapman a écrit :
> There might be thousands of L2TP sessions in some setups. Populating
> sysfs with a link for each of those sessions isn't practical. The
> existing /proc file dumps its info as a single text file for this
> reason. I'd also like to provide the device name in the session netlink
> message, which is the interface used by l2tp userspace, so I need a
> kernel API to retrieve the device name from ppp.
>
> I like the suggestion of using debugfs for access to driver debug info
> though. I propose leaving the /proc file for L2TPv2 only, removing the
> L2TPv3 data that I added to the proc file in this patch series, to
> retain compatibility with the existing driver. This would show only
> L2TPv2 sessions and tunnels. For new driver functionality (L2TPv3 etc),
> use debugfs. The debugfs files would dump lists in a similar form to the
> current code, listing all tunnels (L2TPv2 and L2TPv3) in a single file.
> Using debugfs gives more flexibility for adding additional info later,
> as required. How does that sound?
>
debugfs ? I dont get it, sorry.
Why not using netlink, as most iproute2 utilities do ?
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-04-01 7:30 ` Eric Dumazet
@ 2010-04-01 8:55 ` James Chapman
0 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-04-01 8:55 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Stephen Hemminger, netdev
Eric Dumazet wrote:
> Le jeudi 01 avril 2010 à 08:19 +0100, James Chapman a écrit :
>
>> There might be thousands of L2TP sessions in some setups. Populating
>> sysfs with a link for each of those sessions isn't practical. The
>> existing /proc file dumps its info as a single text file for this
>> reason. I'd also like to provide the device name in the session netlink
>> message, which is the interface used by l2tp userspace, so I need a
>> kernel API to retrieve the device name from ppp.
>>
>> I like the suggestion of using debugfs for access to driver debug info
>> though. I propose leaving the /proc file for L2TPv2 only, removing the
>> L2TPv3 data that I added to the proc file in this patch series, to
>> retain compatibility with the existing driver. This would show only
>> L2TPv2 sessions and tunnels. For new driver functionality (L2TPv3 etc),
>> use debugfs. The debugfs files would dump lists in a similar form to the
>> current code, listing all tunnels (L2TPv2 and L2TPv3) in a single file.
>> Using debugfs gives more flexibility for adding additional info later,
>> as required. How does that sound?
>>
>
> debugfs ? I dont get it, sorry.
>
> Why not using netlink, as most iproute2 utilities do ?
I am using netlink. This is only for providing extra (convenience) debug
info from the kernel drivers. It's something I can easily ask users to
do if they have a problem.
--
James Chapman
Katalix Systems Ltd
http://www.katalix.com
Catalysts for your Embedded Linux software development
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-04-01 7:19 ` James Chapman
2010-04-01 7:30 ` Eric Dumazet
@ 2010-04-01 7:34 ` David Miller
2010-04-01 8:59 ` James Chapman
1 sibling, 1 reply; 32+ messages in thread
From: David Miller @ 2010-04-01 7:34 UTC (permalink / raw)
To: jchapman; +Cc: shemminger, netdev
From: James Chapman <jchapman@katalix.com>
Date: Thu, 01 Apr 2010 08:19:43 +0100
> There might be thousands of L2TP sessions in some setups. Populating
> sysfs with a link for each of those sessions isn't practical. The
> existing /proc file dumps its info as a single text file for this
> reason. I'd also like to provide the device name in the session netlink
> message, which is the interface used by l2tp userspace, so I need a
> kernel API to retrieve the device name from ppp.
Scalability concerns are also another reason _not_ to use
procfs.
Use netlink or similar, which can dump with filtering and
proper queueing.
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-04-01 7:34 ` David Miller
@ 2010-04-01 8:59 ` James Chapman
2010-04-01 9:04 ` David Miller
0 siblings, 1 reply; 32+ messages in thread
From: James Chapman @ 2010-04-01 8:59 UTC (permalink / raw)
To: David Miller; +Cc: shemminger, netdev
David Miller wrote:
> From: James Chapman <jchapman@katalix.com>
> Date: Thu, 01 Apr 2010 08:19:43 +0100
>
>> There might be thousands of L2TP sessions in some setups. Populating
>> sysfs with a link for each of those sessions isn't practical. The
>> existing /proc file dumps its info as a single text file for this
>> reason. I'd also like to provide the device name in the session netlink
>> message, which is the interface used by l2tp userspace, so I need a
>> kernel API to retrieve the device name from ppp.
>
> Scalability concerns are also another reason _not_ to use
> procfs.
>
> Use netlink or similar, which can dump with filtering and
> proper queueing.
See previous reply to Eric. The original /proc API was originally
intended for debug, but users have been using it in hacky scripts
instead of using proper socket interfaces to get the data they need. So
I'm proposing to retain the existing proc file for compatibility but put
other (new) driver-private debug info into debugfs.
--
James Chapman
Katalix Systems Ltd
http://www.katalix.com
Catalysts for your Embedded Linux software development
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data
2010-04-01 8:59 ` James Chapman
@ 2010-04-01 9:04 ` David Miller
0 siblings, 0 replies; 32+ messages in thread
From: David Miller @ 2010-04-01 9:04 UTC (permalink / raw)
To: jchapman; +Cc: shemminger, netdev
From: James Chapman <jchapman@katalix.com>
Date: Thu, 01 Apr 2010 09:59:48 +0100
> The original /proc API was originally intended for debug, but users
> have been using it in hacky scripts instead of using proper socket
> interfaces to get the data they need. So I'm proposing to retain the
> existing proc file for compatibility but put other (new)
> driver-private debug info into debugfs.
Fair enough.
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH v3 05/12] l2tp: Add L2TPv3 protocol support
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (3 preceding siblings ...)
2010-03-30 16:17 ` [PATCH v3 04/12] l2tp: Add ppp device name to L2TP ppp session data James Chapman
@ 2010-03-30 16:17 ` James Chapman
2010-03-30 16:17 ` [PATCH v3 06/12] l2tp: Update PPP-over-L2TP driver to work over L2TPv3 James Chapman
` (6 subsequent siblings)
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:17 UTC (permalink / raw)
To: netdev
The L2TPv3 protocol changes the layout of the L2TP packet
header. Tunnel and session ids change from 16-bit to 32-bit values,
data sequence numbers change from 16-bit to 24-bit values and PPP-specific
fields are moved into protocol-specific subheaders.
Although this patch introduces L2TPv3 protocol support, there are no
userspace interfaces to create L2TPv3 sessions yet.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
net/l2tp/Kconfig | 25 ++
net/l2tp/l2tp_core.c | 574 ++++++++++++++++++++++++++++++++++++++------------
net/l2tp/l2tp_core.h | 54 ++++-
net/l2tp/l2tp_ppp.c | 5
4 files changed, 508 insertions(+), 150 deletions(-)
diff --git a/net/l2tp/Kconfig b/net/l2tp/Kconfig
index ec88c5c..d60758d 100644
--- a/net/l2tp/Kconfig
+++ b/net/l2tp/Kconfig
@@ -19,6 +19,10 @@ menuconfig L2TP
connections. L2TP is also used as a VPN protocol, popular
with home workers to connect to their offices.
+ L2TPv3 allows other protocols as well as PPP to be carried
+ over L2TP tunnels. L2TPv3 is defined in RFC 3931
+ <http://www.ietf.org/rfc/rfc3931.txt>.
+
The kernel component handles only L2TP data packets: a
userland daemon handles L2TP the control protocol (tunnel
and session setup). One such daemon is OpenL2TP
@@ -26,3 +30,24 @@ menuconfig L2TP
If you don't need L2TP, say N. To compile all L2TP code as
modules, choose M here.
+
+config L2TP_V3
+ bool "L2TPv3 support (EXPERIMENTAL)"
+ depends on EXPERIMENTAL && L2TP
+ help
+ Layer Two Tunneling Protocol Version 3
+
+ From RFC 3931 <http://www.ietf.org/rfc/rfc3931.txt>.
+
+ The Layer Two Tunneling Protocol (L2TP) provides a dynamic
+ mechanism for tunneling Layer 2 (L2) "circuits" across a
+ packet-oriented data network (e.g., over IP). L2TP, as
+ originally defined in RFC 2661, is a standard method for
+ tunneling Point-to-Point Protocol (PPP) [RFC1661] sessions.
+ L2TP has since been adopted for tunneling a number of other
+ L2 protocols, including ATM, Frame Relay, HDLC and even raw
+ ethernet frames.
+
+ If you are connecting to L2TPv3 equipment, or you want to
+ tunnel raw ethernet frames using L2TP, say Y here. If
+ unsure, say N.
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 0c1a3b7..1ed7cce 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -66,6 +66,7 @@
#define L2TP_HDR_VER_MASK 0x000F
#define L2TP_HDR_VER_2 0x0002
+#define L2TP_HDR_VER_3 0x0003
/* L2TPv3 default L2-specific sublayer */
#define L2TP_SLFLAG_S 0x40000000
@@ -86,7 +87,7 @@
/* Private data stored for received packets in the skb.
*/
struct l2tp_skb_cb {
- u16 ns;
+ u32 ns;
u16 has_seq;
u16 length;
unsigned long expires;
@@ -102,6 +103,8 @@ static unsigned int l2tp_net_id;
struct l2tp_net {
struct list_head l2tp_tunnel_list;
rwlock_t l2tp_tunnel_list_lock;
+ struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2];
+ rwlock_t l2tp_session_hlist_lock;
};
static inline struct l2tp_net *l2tp_pernet(struct net *net)
@@ -111,6 +114,40 @@ static inline struct l2tp_net *l2tp_pernet(struct net *net)
return net_generic(net, l2tp_net_id);
}
+/* Session hash global list for L2TPv3.
+ * The session_id SHOULD be random according to RFC3931, but several
+ * L2TP implementations use incrementing session_ids. So we do a real
+ * hash on the session_id, rather than a simple bitmask.
+ */
+static inline struct hlist_head *
+l2tp_session_id_hash_2(struct l2tp_net *pn, u32 session_id)
+{
+ return &pn->l2tp_session_hlist[hash_32(session_id, L2TP_HASH_BITS_2)];
+
+}
+
+/* Lookup a session by id in the global session list
+ */
+static struct l2tp_session *l2tp_session_find_2(struct net *net, u32 session_id)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+ struct hlist_head *session_list =
+ l2tp_session_id_hash_2(pn, session_id);
+ struct l2tp_session *session;
+ struct hlist_node *walk;
+
+ read_lock_bh(&pn->l2tp_session_hlist_lock);
+ hlist_for_each_entry(session, walk, session_list, global_hlist) {
+ if (session->session_id == session_id) {
+ read_unlock_bh(&pn->l2tp_session_hlist_lock);
+ return session;
+ }
+ }
+ read_unlock_bh(&pn->l2tp_session_hlist_lock);
+
+ return NULL;
+}
+
/* Session hash list.
* The session_id SHOULD be random according to RFC2661, but several
* L2TP implementations (Cisco and Microsoft) use incrementing
@@ -125,13 +162,20 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
/* Lookup a session by id
*/
-struct l2tp_session *l2tp_session_find(struct l2tp_tunnel *tunnel, u32 session_id)
+struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id)
{
- struct hlist_head *session_list =
- l2tp_session_id_hash(tunnel, session_id);
+ struct hlist_head *session_list;
struct l2tp_session *session;
struct hlist_node *walk;
+ /* In L2TPv3, session_ids are unique over all tunnels and we
+ * sometimes need to look them up before we know the
+ * tunnel.
+ */
+ if (tunnel == NULL)
+ return l2tp_session_find_2(net, session_id);
+
+ session_list = l2tp_session_id_hash(tunnel, session_id);
read_lock_bh(&tunnel->hlist_lock);
hlist_for_each_entry(session, walk, session_list, hlist) {
if (session->session_id == session_id) {
@@ -222,7 +266,7 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk
{
struct sk_buff *skbp;
struct sk_buff *tmp;
- u16 ns = L2TP_SKB_CB(skb)->ns;
+ u32 ns = L2TP_SKB_CB(skb)->ns;
spin_lock_bh(&session->reorder_q.lock);
skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
@@ -263,6 +307,11 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *
if (L2TP_SKB_CB(skb)->has_seq) {
/* Bump our Nr */
session->nr++;
+ if (tunnel->version == L2TP_HDR_VER_2)
+ session->nr &= 0xffff;
+ else
+ session->nr &= 0xffffff;
+
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
"%s: updated nr to %hu\n", session->name, session->nr);
}
@@ -295,8 +344,8 @@ static void l2tp_recv_dequeue(struct l2tp_session *session)
session->stats.rx_seq_discards++;
session->stats.rx_errors++;
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
- "%s: oos pkt %hu len %d discarded (too old), "
- "waiting for %hu, reorder_q_len=%d\n",
+ "%s: oos pkt %u len %d discarded (too old), "
+ "waiting for %u, reorder_q_len=%d\n",
session->name, L2TP_SKB_CB(skb)->ns,
L2TP_SKB_CB(skb)->length, session->nr,
skb_queue_len(&session->reorder_q));
@@ -310,8 +359,8 @@ static void l2tp_recv_dequeue(struct l2tp_session *session)
if (L2TP_SKB_CB(skb)->has_seq) {
if (L2TP_SKB_CB(skb)->ns != session->nr) {
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
- "%s: holding oos pkt %hu len %d, "
- "waiting for %hu, reorder_q_len=%d\n",
+ "%s: holding oos pkt %u len %d, "
+ "waiting for %u, reorder_q_len=%d\n",
session->name, L2TP_SKB_CB(skb)->ns,
L2TP_SKB_CB(skb)->length, session->nr,
skb_queue_len(&session->reorder_q));
@@ -356,100 +405,73 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk,
return __skb_checksum_complete(skb);
}
-/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame
- * here. The skb is not on a list when we get here.
- * Returns 0 if the packet was a data packet and was successfully passed on.
- * Returns 1 if the packet was not a good data packet and could not be
- * forwarded. All such packets are passed up to userspace to deal with.
+/* Do receive processing of L2TP data frames. We handle both L2TPv2
+ * and L2TPv3 data frames here.
+ *
+ * L2TPv2 Data Message Header
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |T|L|x|x|S|x|O|P|x|x|x|x| Ver | Length (opt) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Tunnel ID | Session ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Ns (opt) | Nr (opt) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Offset Size (opt) | Offset pad... (opt)
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Data frames are marked by T=0. All other fields are the same as
+ * those in L2TP control frames.
+ *
+ * L2TPv3 Data Message Header
+ *
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | L2TP Session Header |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | L2-Specific Sublayer |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Tunnel Payload ...
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * L2TPv3 Session Header Over IP
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Session ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Cookie (optional, maximum 64 bits)...
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * L2TPv3 L2-Specific Sublayer Format
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |x|S|x|x|x|x|x|x| Sequence Number |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * Cookie value, sublayer format and offset (pad) are negotiated with
+ * the peer when the session is set up. Unlike L2TPv2, we do not need
+ * to parse the packet header to determine if optional fields are
+ * present.
+ *
+ * Caller must already have parsed the frame and determined that it is
+ * a data (not control) frame before coming here. Fields up to the
+ * session-id have already been parsed and ptr points to the data
+ * after the session-id.
*/
-int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
- int (*payload_hook)(struct sk_buff *skb))
+void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
+ unsigned char *ptr, unsigned char *optr, u16 hdrflags,
+ int length, int (*payload_hook)(struct sk_buff *skb))
{
- struct l2tp_session *session = NULL;
- unsigned char *ptr, *optr;
- u16 hdrflags;
- u32 tunnel_id, session_id;
- int length;
+ struct l2tp_tunnel *tunnel = session->tunnel;
int offset;
- u16 version;
- u16 ns, nr;
-
- if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb))
- goto discard_bad_csum;
-
- /* UDP always verifies the packet length. */
- __skb_pull(skb, sizeof(struct udphdr));
-
- /* Short packet? */
- if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) {
- PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
- "%s: recv short packet (len=%d)\n", tunnel->name, skb->len);
- goto error;
- }
-
- /* Point to L2TP header */
- optr = ptr = skb->data;
-
- /* Trace packet contents, if enabled */
- if (tunnel->debug & L2TP_MSG_DATA) {
- length = min(32u, skb->len);
- if (!pskb_may_pull(skb, length))
- goto error;
-
- printk(KERN_DEBUG "%s: recv: ", tunnel->name);
-
- offset = 0;
- do {
- printk(" %02X", ptr[offset]);
- } while (++offset < length);
-
- printk("\n");
- }
-
- /* Get L2TP header flags */
- hdrflags = ntohs(*(__be16 *)ptr);
-
- /* Check protocol version */
- version = hdrflags & L2TP_HDR_VER_MASK;
- if (version != tunnel->version) {
- PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
- "%s: recv protocol version mismatch: got %d expected %d\n",
- tunnel->name, version, tunnel->version);
- goto error;
- }
-
- /* Get length of L2TP packet */
- length = skb->len;
-
- /* If type is control packet, it is handled by userspace. */
- if (hdrflags & L2TP_HDRFLAG_T) {
- PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_DEBUG,
- "%s: recv control packet, len=%d\n", tunnel->name, length);
- goto error;
- }
-
- /* Skip flags */
- ptr += 2;
-
- /* If length is present, skip it */
- if (hdrflags & L2TP_HDRFLAG_L)
- ptr += 2;
-
- /* Extract tunnel and session ID */
- tunnel_id = ntohs(*(__be16 *) ptr);
- ptr += 2;
- session_id = ntohs(*(__be16 *) ptr);
- ptr += 2;
-
- /* Find the session context */
- session = l2tp_session_find(tunnel, session_id);
- if (!session) {
- /* Not found? Pass to userspace to deal with */
- PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
- "%s: no session found (%hu/%hu). Passing up.\n",
- tunnel->name, tunnel_id, session_id);
- goto error;
- }
+ u32 ns, nr;
/* The ref count is increased since we now hold a pointer to
* the session. Take care to decrement the refcnt when exiting
@@ -459,6 +481,18 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
if (session->ref)
(*session->ref)(session);
+ /* Parse and check optional cookie */
+ if (session->peer_cookie_len > 0) {
+ if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
+ "%s: cookie mismatch (%u/%u). Discarding.\n",
+ tunnel->name, tunnel->tunnel_id, session->session_id);
+ session->stats.rx_cookie_discards++;
+ goto discard;
+ }
+ ptr += session->peer_cookie_len;
+ }
+
/* Handle the optional sequence numbers. Sequence numbers are
* in different places for L2TPv2 and L2TPv3.
*
@@ -468,21 +502,40 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
*/
ns = nr = 0;
L2TP_SKB_CB(skb)->has_seq = 0;
- if (hdrflags & L2TP_HDRFLAG_S) {
- ns = (u16) ntohs(*(__be16 *) ptr);
- ptr += 2;
- nr = ntohs(*(__be16 *) ptr);
- ptr += 2;
+ if (tunnel->version == L2TP_HDR_VER_2) {
+ if (hdrflags & L2TP_HDRFLAG_S) {
+ ns = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+ nr = ntohs(*(__be16 *) ptr);
+ ptr += 2;
- /* Store L2TP info in the skb */
- L2TP_SKB_CB(skb)->ns = ns;
- L2TP_SKB_CB(skb)->has_seq = 1;
+ /* Store L2TP info in the skb */
+ L2TP_SKB_CB(skb)->ns = ns;
+ L2TP_SKB_CB(skb)->has_seq = 1;
- PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
- "%s: recv data ns=%hu, nr=%hu, session nr=%hu\n",
- session->name, ns, nr, session->nr);
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: recv data ns=%u, nr=%u, session nr=%u\n",
+ session->name, ns, nr, session->nr);
+ }
+ } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) {
+ u32 l2h = ntohl(*(__be32 *) ptr);
+
+ if (l2h & 0x40000000) {
+ ns = l2h & 0x00ffffff;
+
+ /* Store L2TP info in the skb */
+ L2TP_SKB_CB(skb)->ns = ns;
+ L2TP_SKB_CB(skb)->has_seq = 1;
+
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: recv data ns=%u, session nr=%u\n",
+ session->name, ns, session->nr);
+ }
}
+ /* Advance past L2-specific header, if present */
+ ptr += session->l2specific_len;
+
if (L2TP_SKB_CB(skb)->has_seq) {
/* Received a packet with sequence numbers. If we're the LNS,
* check if we sre sending sequence numbers and if not,
@@ -493,6 +546,7 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
"%s: requested to enable seq numbers by LNS\n",
session->name);
session->send_seq = -1;
+ l2tp_session_set_header_len(session, tunnel->version);
}
} else {
/* No sequence numbers.
@@ -516,6 +570,7 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
"%s: requested to disable seq numbers by LNS\n",
session->name);
session->send_seq = 0;
+ l2tp_session_set_header_len(session, tunnel->version);
} else if (session->send_seq) {
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_WARNING,
"%s: recv data has no seq numbers when required. "
@@ -525,11 +580,19 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
}
}
- /* If offset bit set, skip it. */
- if (hdrflags & L2TP_HDRFLAG_O) {
- offset = ntohs(*(__be16 *)ptr);
- ptr += 2 + offset;
- }
+ /* Session data offset is handled differently for L2TPv2 and
+ * L2TPv3. For L2TPv2, there is an optional 16-bit value in
+ * the header. For L2TPv3, the offset is negotiated using AVPs
+ * in the session setup control protocol.
+ */
+ if (tunnel->version == L2TP_HDR_VER_2) {
+ /* If offset bit set, skip it. */
+ if (hdrflags & L2TP_HDRFLAG_O) {
+ offset = ntohs(*(__be16 *)ptr);
+ ptr += 2 + offset;
+ }
+ } else
+ ptr += session->offset;
offset = ptr - optr;
if (!pskb_may_pull(skb, offset))
@@ -568,8 +631,8 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
if (L2TP_SKB_CB(skb)->ns != session->nr) {
session->stats.rx_seq_discards++;
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
- "%s: oos pkt %hu len %d discarded, "
- "waiting for %hu, reorder_q_len=%d\n",
+ "%s: oos pkt %u len %d discarded, "
+ "waiting for %u, reorder_q_len=%d\n",
session->name, L2TP_SKB_CB(skb)->ns,
L2TP_SKB_CB(skb)->length, session->nr,
skb_queue_len(&session->reorder_q));
@@ -590,7 +653,7 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
l2tp_session_dec_refcount(session);
- return 0;
+ return;
discard:
session->stats.rx_errors++;
@@ -600,6 +663,111 @@ discard:
(*session->deref)(session);
l2tp_session_dec_refcount(session);
+}
+EXPORT_SYMBOL(l2tp_recv_common);
+
+/* Internal UDP receive frame. Do the real work of receiving an L2TP data frame
+ * here. The skb is not on a list when we get here.
+ * Returns 0 if the packet was a data packet and was successfully passed on.
+ * Returns 1 if the packet was not a good data packet and could not be
+ * forwarded. All such packets are passed up to userspace to deal with.
+ */
+int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
+ int (*payload_hook)(struct sk_buff *skb))
+{
+ struct l2tp_session *session = NULL;
+ unsigned char *ptr, *optr;
+ u16 hdrflags;
+ u32 tunnel_id, session_id;
+ int offset;
+ u16 version;
+ int length;
+
+ if (tunnel->sock && l2tp_verify_udp_checksum(tunnel->sock, skb))
+ goto discard_bad_csum;
+
+ /* UDP always verifies the packet length. */
+ __skb_pull(skb, sizeof(struct udphdr));
+
+ /* Short packet? */
+ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) {
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
+ "%s: recv short packet (len=%d)\n", tunnel->name, skb->len);
+ goto error;
+ }
+
+ /* Point to L2TP header */
+ optr = ptr = skb->data;
+
+ /* Trace packet contents, if enabled */
+ if (tunnel->debug & L2TP_MSG_DATA) {
+ length = min(32u, skb->len);
+ if (!pskb_may_pull(skb, length))
+ goto error;
+
+ printk(KERN_DEBUG "%s: recv: ", tunnel->name);
+
+ offset = 0;
+ do {
+ printk(" %02X", ptr[offset]);
+ } while (++offset < length);
+
+ printk("\n");
+ }
+
+ /* Get L2TP header flags */
+ hdrflags = ntohs(*(__be16 *) ptr);
+
+ /* Check protocol version */
+ version = hdrflags & L2TP_HDR_VER_MASK;
+ if (version != tunnel->version) {
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
+ "%s: recv protocol version mismatch: got %d expected %d\n",
+ tunnel->name, version, tunnel->version);
+ goto error;
+ }
+
+ /* Get length of L2TP packet */
+ length = skb->len;
+
+ /* If type is control packet, it is handled by userspace. */
+ if (hdrflags & L2TP_HDRFLAG_T) {
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_DEBUG,
+ "%s: recv control packet, len=%d\n", tunnel->name, length);
+ goto error;
+ }
+
+ /* Skip flags */
+ ptr += 2;
+
+ if (tunnel->version == L2TP_HDR_VER_2) {
+ /* If length is present, skip it */
+ if (hdrflags & L2TP_HDRFLAG_L)
+ ptr += 2;
+
+ /* Extract tunnel and session ID */
+ tunnel_id = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+ session_id = ntohs(*(__be16 *) ptr);
+ ptr += 2;
+ } else {
+ ptr += 2; /* skip reserved bits */
+ tunnel_id = tunnel->tunnel_id;
+ session_id = ntohl(*(__be32 *) ptr);
+ ptr += 4;
+ }
+
+ /* Find the session context */
+ session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id);
+ if (!session) {
+ /* Not found? Pass to userspace to deal with */
+ PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
+ "%s: no session found (%u/%u). Passing up.\n",
+ tunnel->name, tunnel_id, session_id);
+ goto error;
+ }
+
+ l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook);
return 0;
@@ -655,11 +823,11 @@ EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv);
/* Build an L2TP header for the session into the buffer provided.
*/
-static void l2tp_build_l2tpv2_header(struct l2tp_tunnel *tunnel,
- struct l2tp_session *session,
- void *buf)
+static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf)
{
+ struct l2tp_tunnel *tunnel = session->tunnel;
__be16 *bufp = buf;
+ __be16 *optr = buf;
u16 flags = L2TP_HDR_VER_2;
u32 tunnel_id = tunnel->peer_tunnel_id;
u32 session_id = session->peer_session_id;
@@ -675,19 +843,51 @@ static void l2tp_build_l2tpv2_header(struct l2tp_tunnel *tunnel,
*bufp++ = htons(session->ns);
*bufp++ = 0;
session->ns++;
+ session->ns &= 0xffff;
PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
- "%s: updated ns to %hu\n", session->name, session->ns);
+ "%s: updated ns to %u\n", session->name, session->ns);
}
+
+ return bufp - optr;
}
-void l2tp_build_l2tp_header(struct l2tp_session *session, void *buf)
+static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
{
- struct l2tp_tunnel *tunnel = session->tunnel;
+ char *bufp = buf;
+ char *optr = bufp;
+ u16 flags = L2TP_HDR_VER_3;
+
+ /* Setup L2TP header. */
+ *((__be16 *) bufp) = htons(flags);
+ bufp += 2;
+ *((__be16 *) bufp) = 0;
+ bufp += 2;
+ *((__be32 *) bufp) = htonl(session->peer_session_id);
+ bufp += 4;
+ if (session->cookie_len) {
+ memcpy(bufp, &session->cookie[0], session->cookie_len);
+ bufp += session->cookie_len;
+ }
+ if (session->l2specific_len) {
+ if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) {
+ u32 l2h = 0;
+ if (session->send_seq) {
+ l2h = 0x40000000 | session->ns;
+ session->ns++;
+ session->ns &= 0xffffff;
+ PRINTK(session->debug, L2TP_MSG_SEQ, KERN_DEBUG,
+ "%s: updated ns to %u\n", session->name, session->ns);
+ }
- BUG_ON(tunnel->version != L2TP_HDR_VER_2);
- l2tp_build_l2tpv2_header(tunnel, session, buf);
+ *((__be32 *) bufp) = htonl(l2h);
+ }
+ bufp += session->l2specific_len;
+ }
+ if (session->offset)
+ bufp += session->offset;
+
+ return bufp - optr;
}
-EXPORT_SYMBOL_GPL(l2tp_build_l2tp_header);
int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t data_len)
{
@@ -698,7 +898,7 @@ int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t dat
/* Debug */
if (session->send_seq)
PRINTK(session->debug, L2TP_MSG_DATA, KERN_DEBUG,
- "%s: send %Zd bytes, ns=%hu\n", session->name,
+ "%s: send %Zd bytes, ns=%u\n", session->name,
data_len, session->ns - 1);
else
PRINTK(session->debug, L2TP_MSG_DATA, KERN_DEBUG,
@@ -784,7 +984,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
skb->truesize += new_headroom - old_headroom;
/* Setup L2TP header */
- l2tp_build_l2tp_header(session, __skb_push(skb, hdr_len));
+ session->build_header(session, __skb_push(skb, hdr_len));
udp_len = sizeof(struct udphdr) + hdr_len + data_len;
/* Setup UDP header */
@@ -795,7 +995,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
uh->source = inet->inet_sport;
uh->dest = inet->inet_dport;
uh->len = htons(udp_len);
-
uh->check = 0;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
@@ -915,6 +1114,14 @@ again:
write_unlock_bh(&tunnel->hlist_lock);
+ if (tunnel->version != L2TP_HDR_VER_2) {
+ struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
+
+ write_lock_bh(&pn->l2tp_session_hlist_lock);
+ hlist_del_init(&session->global_hlist);
+ write_unlock_bh(&pn->l2tp_session_hlist_lock);
+ }
+
if (session->session_close != NULL)
(*session->session_close)(session);
@@ -1001,9 +1208,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
goto err;
}
- if (version != L2TP_HDR_VER_2)
- goto err;
-
tunnel = kzalloc(sizeof(struct l2tp_tunnel), GFP_KERNEL);
if (tunnel == NULL) {
err = -ENOMEM;
@@ -1081,6 +1285,15 @@ void l2tp_session_free(struct l2tp_session *session)
hlist_del_init(&session->hlist);
write_unlock_bh(&tunnel->hlist_lock);
+ /* Unlink from the global hash if not L2TPv2 */
+ if (tunnel->version != L2TP_HDR_VER_2) {
+ struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
+
+ write_lock_bh(&pn->l2tp_session_hlist_lock);
+ hlist_del_init(&session->global_hlist);
+ write_unlock_bh(&pn->l2tp_session_hlist_lock);
+ }
+
if (session->session_id != 0)
atomic_dec(&l2tp_session_count);
@@ -1099,6 +1312,22 @@ void l2tp_session_free(struct l2tp_session *session)
}
EXPORT_SYMBOL_GPL(l2tp_session_free);
+/* We come here whenever a session's send_seq, cookie_len or
+ * l2specific_len parameters are set.
+ */
+void l2tp_session_set_header_len(struct l2tp_session *session, int version)
+{
+ if (version == L2TP_HDR_VER_2) {
+ session->hdr_len = 6;
+ if (session->send_seq)
+ session->hdr_len += 4;
+ } else {
+ session->hdr_len = 8 + session->cookie_len + session->l2specific_len + session->offset;
+ }
+
+}
+EXPORT_SYMBOL_GPL(l2tp_session_set_header_len);
+
struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
{
struct l2tp_session *session;
@@ -1110,6 +1339,7 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
session->session_id = session_id;
session->peer_session_id = peer_session_id;
+ session->nr = 1;
sprintf(&session->name[0], "sess %u/%u",
tunnel->tunnel_id, session->session_id);
@@ -1117,20 +1347,36 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
skb_queue_head_init(&session->reorder_q);
INIT_HLIST_NODE(&session->hlist);
+ INIT_HLIST_NODE(&session->global_hlist);
/* Inherit debug options from tunnel */
session->debug = tunnel->debug;
if (cfg) {
+ session->pwtype = cfg->pw_type;
session->debug = cfg->debug;
- session->hdr_len = cfg->hdr_len;
session->mtu = cfg->mtu;
session->mru = cfg->mru;
session->send_seq = cfg->send_seq;
session->recv_seq = cfg->recv_seq;
session->lns_mode = cfg->lns_mode;
+ session->reorder_timeout = cfg->reorder_timeout;
+ session->offset = cfg->offset;
+ session->l2specific_type = cfg->l2specific_type;
+ session->l2specific_len = cfg->l2specific_len;
+ session->cookie_len = cfg->cookie_len;
+ memcpy(&session->cookie[0], &cfg->cookie[0], cfg->cookie_len);
+ session->peer_cookie_len = cfg->peer_cookie_len;
+ memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len);
}
+ if (tunnel->version == L2TP_HDR_VER_2)
+ session->build_header = l2tp_build_l2tpv2_header;
+ else
+ session->build_header = l2tp_build_l2tpv3_header;
+
+ l2tp_session_set_header_len(session, tunnel->version);
+
/* Bump the reference count. The session context is deleted
* only when this drops to zero.
*/
@@ -1146,6 +1392,16 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
l2tp_session_id_hash(tunnel, session_id));
write_unlock_bh(&tunnel->hlist_lock);
+ /* And to the global session list if L2TPv3 */
+ if (tunnel->version != L2TP_HDR_VER_2) {
+ struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net);
+
+ write_lock_bh(&pn->l2tp_session_hlist_lock);
+ hlist_add_head(&session->global_hlist,
+ l2tp_session_id_hash_2(pn, session_id));
+ write_unlock_bh(&pn->l2tp_session_hlist_lock);
+ }
+
/* Ignore management session in session count value */
if (session->session_id != 0)
atomic_inc(&l2tp_session_count);
@@ -1289,6 +1545,7 @@ static void l2tp_seq_tunnel_show(struct seq_file *m, void *v)
seq_printf(m, " source port %hu, dest port %hu\n",
ntohs(inet->inet_sport), ntohs(inet->inet_dport));
}
+ seq_printf(m, " L2TPv%d\n", tunnel->version);
seq_printf(m, " %d sessions, refcnt %d/%d\n", session_count,
tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0,
atomic_read(&tunnel->ref_count));
@@ -1310,17 +1567,46 @@ static void l2tp_seq_session_show(struct seq_file *m, void *v)
{
struct l2tp_session *session = v;
- seq_printf(m, " SESSION %u, peer %u\n", session->session_id, session->peer_session_id);
+ seq_printf(m, " SESSION %u, peer %u, %s\n", session->session_id,
+ session->peer_session_id,
+ session->pwtype == L2TP_PWTYPE_ETH ? "ETH" :
+ session->pwtype == L2TP_PWTYPE_PPP ? "PPP" :
+ "");
if (session->send_seq || session->recv_seq)
seq_printf(m, " nr %hu, ns %hu\n", session->nr, session->ns);
seq_printf(m, " refcnt %d\n", atomic_read(&session->ref_count));
- seq_printf(m, " config %d/%d/%c/%c/%s %08x %u\n",
+ seq_printf(m, " config %d/%d/%c/%c/%s/%s %08x %u\n",
session->mtu, session->mru,
session->recv_seq ? 'R' : '-',
session->send_seq ? 'S' : '-',
+ session->data_seq == 1 ? "IPSEQ" :
+ session->data_seq == 2 ? "DATASEQ" : "-",
session->lns_mode ? "LNS" : "LAC",
session->debug,
jiffies_to_msecs(session->reorder_timeout));
+ seq_printf(m, " offset %hu l2specific %hu/%hu\n",
+ session->offset, session->l2specific_type, session->l2specific_len);
+ if (session->cookie_len) {
+ seq_printf(m, " cookie %02x%02x%02x%02x",
+ session->cookie[0], session->cookie[1],
+ session->cookie[2], session->cookie[3]);
+ if (session->cookie_len == 8)
+ seq_printf(m, "%02x%02x%02x%02x",
+ session->cookie[4], session->cookie[5],
+ session->cookie[6], session->cookie[7]);
+ seq_printf(m, "\n");
+ }
+ if (session->peer_cookie_len) {
+ seq_printf(m, " peer cookie %02x%02x%02x%02x",
+ session->peer_cookie[0], session->peer_cookie[1],
+ session->peer_cookie[2], session->peer_cookie[3]);
+ if (session->peer_cookie_len == 8)
+ seq_printf(m, "%02x%02x%02x%02x",
+ session->peer_cookie[4], session->peer_cookie[5],
+ session->peer_cookie[6], session->peer_cookie[7]);
+ seq_printf(m, "\n");
+ }
+
seq_printf(m, " %hu/%hu tx %llu/%llu/%llu rx %llu/%llu/%llu\n",
session->nr, session->ns,
(unsigned long long)session->stats.tx_packets,
@@ -1342,11 +1628,15 @@ static int l2tp_seq_show(struct seq_file *m, void *v)
if (v == SEQ_START_TOKEN) {
seq_puts(m, "L2TP driver info, " L2TP_DRV_VERSION "\n");
seq_puts(m, "TUNNEL ID, peer ID from IP to IP\n");
+ seq_puts(m, " L2TPv2/L2TPv3\n");
seq_puts(m, " sessions session-count, refcnt refcnt/sk->refcnt\n");
seq_puts(m, " debug tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
- seq_puts(m, " SESSION ID, peer ID\n");
+ seq_puts(m, " SESSION ID, peer ID, PWTYPE\n");
seq_puts(m, " refcnt cnt\n");
- seq_puts(m, " mtu/mru/rcvseq/sendseq/lns debug reorderto\n");
+ seq_puts(m, " offset OFFSET l2specific TYPE/LEN\n");
+ seq_puts(m, " [ cookie ]\n");
+ seq_puts(m, " [ peer cookie ]\n");
+ seq_puts(m, " config mtu/mru/rcvseq/sendseq/dataseq/lns debug reorderto\n");
seq_puts(m, " nr/ns tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
seq_printf(m, "tunnels %d sessions %d\n", atomic_read(&l2tp_tunnel_count), atomic_read(&l2tp_session_count));
@@ -1396,6 +1686,7 @@ static __net_init int l2tp_init_net(struct net *net)
struct l2tp_net *pn;
struct proc_dir_entry *pde;
int err;
+ int hash;
pn = kzalloc(sizeof(*pn), GFP_KERNEL);
if (!pn)
@@ -1404,6 +1695,11 @@ static __net_init int l2tp_init_net(struct net *net)
INIT_LIST_HEAD(&pn->l2tp_tunnel_list);
rwlock_init(&pn->l2tp_tunnel_list_lock);
+ for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++)
+ INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]);
+
+ rwlock_init(&pn->l2tp_session_hlist_lock);
+
err = net_assign_generic(net, l2tp_net_id, pn);
if (err)
goto out;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 80ce1ce..87a06b2 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -15,9 +15,14 @@
#define L2TP_TUNNEL_MAGIC 0x42114DDA
#define L2TP_SESSION_MAGIC 0x0C04EB7D
+/* Per tunnel, session hash table size */
#define L2TP_HASH_BITS 4
#define L2TP_HASH_SIZE (1 << L2TP_HASH_BITS)
+/* System-wide, session hash table size */
+#define L2TP_HASH_BITS_2 8
+#define L2TP_HASH_SIZE_2 (1 << L2TP_HASH_BITS_2)
+
/* Debug message categories for the DEBUG socket option */
enum {
L2TP_MSG_DEBUG = (1 << 0), /* verbose debug (if
@@ -28,6 +33,21 @@ enum {
L2TP_MSG_DATA = (1 << 3), /* data packets */
};
+enum l2tp_pwtype {
+ L2TP_PWTYPE_NONE = 0x0000,
+ L2TP_PWTYPE_ETH_VLAN = 0x0004,
+ L2TP_PWTYPE_ETH = 0x0005,
+ L2TP_PWTYPE_PPP = 0x0007,
+ L2TP_PWTYPE_PPP_AC = 0x0008,
+ L2TP_PWTYPE_IP = 0x000b,
+ __L2TP_PWTYPE_MAX
+};
+
+enum l2tp_l2spec_type {
+ L2TP_L2SPECTYPE_NONE,
+ L2TP_L2SPECTYPE_DEFAULT,
+};
+
struct sk_buff;
struct l2tp_stats {
@@ -39,6 +59,7 @@ struct l2tp_stats {
u64 rx_seq_discards;
u64 rx_oos_packets;
u64 rx_errors;
+ u64 rx_cookie_discards;
};
struct l2tp_tunnel;
@@ -47,6 +68,7 @@ struct l2tp_tunnel;
* packets and transmit outgoing ones.
*/
struct l2tp_session_cfg {
+ enum l2tp_pwtype pw_type;
unsigned data_seq:2; /* data sequencing level
* 0 => none, 1 => IP only,
* 2 => all
@@ -60,12 +82,17 @@ struct l2tp_session_cfg {
* control of LNS. */
int debug; /* bitmask of debug message
* categories */
- int offset; /* offset to payload */
+ u16 offset; /* offset to payload */
+ u16 l2specific_len; /* Layer 2 specific length */
+ u16 l2specific_type; /* Layer 2 specific type */
+ u8 cookie[8]; /* optional cookie */
+ int cookie_len; /* 0, 4 or 8 bytes */
+ u8 peer_cookie[8]; /* peer's cookie */
+ int peer_cookie_len; /* 0, 4 or 8 bytes */
int reorder_timeout; /* configured reorder timeout
* (in jiffies) */
int mtu;
int mru;
- int hdr_len;
};
struct l2tp_session {
@@ -76,8 +103,17 @@ struct l2tp_session {
* context */
u32 session_id;
u32 peer_session_id;
- u16 nr; /* session NR state (receive) */
- u16 ns; /* session NR state (send) */
+ u8 cookie[8];
+ int cookie_len;
+ u8 peer_cookie[8];
+ int peer_cookie_len;
+ u16 offset; /* offset from end of L2TP header
+ to beginning of data */
+ u16 l2specific_len;
+ u16 l2specific_type;
+ u16 hdr_len;
+ u32 nr; /* session NR state (receive) */
+ u32 ns; /* session NR state (send) */
struct sk_buff_head reorder_q; /* receive reorder queue */
struct hlist_node hlist; /* Hash list node */
atomic_t ref_count;
@@ -100,9 +136,11 @@ struct l2tp_session {
* (in jiffies) */
int mtu;
int mru;
- int hdr_len;
+ enum l2tp_pwtype pwtype;
struct l2tp_stats stats;
+ struct hlist_node global_hlist; /* Global hash list node */
+ int (*build_header)(struct l2tp_session *session, void *buf);
void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len);
void (*session_close)(struct l2tp_session *session);
void (*ref)(struct l2tp_session *session);
@@ -134,7 +172,6 @@ struct l2tp_tunnel {
char name[20]; /* for logging */
int debug; /* bitmask of debug message
* categories */
- int hdr_len;
struct l2tp_stats stats;
struct list_head list; /* Keep a list of all tunnels */
@@ -182,7 +219,7 @@ out:
return tunnel;
}
-extern struct l2tp_session *l2tp_session_find(struct l2tp_tunnel *tunnel, u32 session_id);
+extern struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id);
extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth, int *skipped);
extern struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth, int *skipped);
@@ -191,14 +228,15 @@ extern int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_i
extern struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg);
extern void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
extern void l2tp_session_free(struct l2tp_session *session);
+extern void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length, int (*payload_hook)(struct sk_buff *skb));
extern int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, int (*payload_hook)(struct sk_buff *skb));
extern int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
-extern void l2tp_build_l2tp_header(struct l2tp_session *session, void *buf);
extern int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t data_len);
extern int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len);
extern void l2tp_tunnel_destruct(struct sock *sk);
extern void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
+extern void l2tp_session_set_header_len(struct l2tp_session *session, int version);
/* Tunnel reference counts. Incremented per session that is added to
* the tunnel.
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 8f78c27..dc27543 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -684,7 +684,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
/* Check that this session doesn't already exist */
error = -EEXIST;
- session = l2tp_session_find(tunnel, sp->pppol2tp.s_session);
+ session = l2tp_session_find(sock_net(sk), tunnel, sp->pppol2tp.s_session);
if (session != NULL)
goto end;
@@ -692,7 +692,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
* headers.
*/
cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
- cfg.hdr_len = PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
cfg.debug = tunnel->debug;
/* Allocate and initialize a new session context. */
@@ -1016,7 +1015,7 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
if (stats.session_id != 0) {
/* resend to session ioctl handler */
struct l2tp_session *session =
- l2tp_session_find(tunnel, stats.session_id);
+ l2tp_session_find(sock_net(sk), tunnel, stats.session_id);
if (session != NULL)
err = pppol2tp_session_ioctl(session, cmd, arg);
else
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 06/12] l2tp: Update PPP-over-L2TP driver to work over L2TPv3
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (4 preceding siblings ...)
2010-03-30 16:17 ` [PATCH v3 05/12] l2tp: Add L2TPv3 protocol support James Chapman
@ 2010-03-30 16:17 ` James Chapman
2010-03-30 16:18 ` [PATCH v3 07/12] l2tp: Add L2TPv3 IP encapsulation (no UDP) support James Chapman
` (5 subsequent siblings)
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:17 UTC (permalink / raw)
To: netdev
This patch makes changes to the L2TP PPP code for L2TPv3.
The existing code has some assumptions about the L2TP header which are
broken by L2TPv3. Also the sockaddr_pppol2tp structure of the original
code is too small to support the increased size of the L2TPv3 tunnel
and session id, so a new sockaddr_pppol2tpv3 structure is needed. In
the socket calls, the size of this structure is used to tell if the
operation is for L2TPv2 or L2TPv3.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
include/linux/if_pppol2tp.h | 14 +++++
include/linux/if_pppox.h | 9 +++
net/l2tp/l2tp_ppp.c | 120 +++++++++++++++++++++++++++----------------
3 files changed, 97 insertions(+), 46 deletions(-)
diff --git a/include/linux/if_pppol2tp.h b/include/linux/if_pppol2tp.h
index 1a1fb6e..184bc55 100644
--- a/include/linux/if_pppol2tp.h
+++ b/include/linux/if_pppol2tp.h
@@ -35,6 +35,20 @@ struct pppol2tp_addr {
__u16 d_tunnel, d_session; /* For sending outgoing packets */
};
+/* The L2TPv3 protocol changes tunnel and session ids from 16 to 32
+ * bits. So we need a different sockaddr structure.
+ */
+struct pppol2tpv3_addr {
+ pid_t pid; /* pid that owns the fd.
+ * 0 => current */
+ int fd; /* FD of UDP or IP socket to use */
+
+ struct sockaddr_in addr; /* IP address and port to send to */
+
+ __u32 s_tunnel, s_session; /* For matching incoming packets */
+ __u32 d_tunnel, d_session; /* For sending outgoing packets */
+};
+
/* Socket options:
* DEBUG - bitmask of debug message categories
* SENDSEQ - 0 => don't send packets with sequence numbers
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index 90b5fae..a6577af 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -72,6 +72,15 @@ struct sockaddr_pppol2tp {
struct pppol2tp_addr pppol2tp;
}__attribute__ ((packed));
+/* The L2TPv3 protocol changes tunnel and session ids from 16 to 32
+ * bits. So we need a different sockaddr structure.
+ */
+struct sockaddr_pppol2tpv3 {
+ sa_family_t sa_family; /* address family, AF_PPPOX */
+ unsigned int sa_protocol; /* protocol identifier */
+ struct pppol2tpv3_addr pppol2tp;
+} __attribute__ ((packed));
+
/*********************************************************************
*
* ioctl interface for defining forwarding of connections
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index dc27543..907cfbd 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -291,17 +291,6 @@ static void pppol2tp_session_sock_put(struct l2tp_session *session)
* Transmit handling
***********************************************************************/
-/* Tell how big L2TP headers are for a particular session. This
- * depends on whether sequence numbers are being used.
- */
-static inline int pppol2tp_l2tp_header_len(struct l2tp_session *session)
-{
- if (session->send_seq)
- return PPPOL2TP_L2TP_HDR_SIZE_SEQ;
-
- return PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
-}
-
/* This is the sendmsg for the PPPoL2TP pppol2tp_session socket. We come here
* when a user application does a sendmsg() on the session socket. L2TP and
* PPP headers must be inserted into the user's data.
@@ -394,7 +383,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
static const u8 ppph[2] = { 0xff, 0x03 };
struct sock *sk = (struct sock *) chan->private;
struct sock *sk_tun;
- int hdr_len;
struct l2tp_session *session;
struct l2tp_tunnel *tunnel;
struct pppol2tp_session *ps;
@@ -417,9 +405,6 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
if (tunnel == NULL)
goto abort_put_sess;
- /* What header length is configured for this session? */
- hdr_len = pppol2tp_l2tp_header_len(session);
-
old_headroom = skb_headroom(skb);
if (skb_cow_head(skb, sizeof(ppph)))
goto abort_put_sess_tun;
@@ -432,7 +417,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
skb->data[0] = ppph[0];
skb->data[1] = ppph[1];
- l2tp_xmit_skb(session, skb, hdr_len);
+ l2tp_xmit_skb(session, skb, session->hdr_len);
sock_put(sk_tun);
sock_put(sk);
@@ -629,6 +614,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
{
struct sock *sk = sock->sk;
struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
+ struct sockaddr_pppol2tpv3 *sp3 = (struct sockaddr_pppol2tpv3 *) uservaddr;
struct pppox_sock *po = pppox_sk(sk);
struct l2tp_session *session = NULL;
struct l2tp_tunnel *tunnel;
@@ -636,6 +622,10 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
struct dst_entry *dst;
struct l2tp_session_cfg cfg = { 0, };
int error = 0;
+ u32 tunnel_id, peer_tunnel_id;
+ u32 session_id, peer_session_id;
+ int ver = 2;
+ int fd;
lock_sock(sk);
@@ -653,21 +643,40 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
if (sk->sk_user_data)
goto end; /* socket is already attached */
- /* Don't bind if s_tunnel is 0 */
+ /* Get params from socket address. Handle L2TPv2 and L2TPv3 */
+ if (sockaddr_len == sizeof(struct sockaddr_pppol2tp)) {
+ fd = sp->pppol2tp.fd;
+ tunnel_id = sp->pppol2tp.s_tunnel;
+ peer_tunnel_id = sp->pppol2tp.d_tunnel;
+ session_id = sp->pppol2tp.s_session;
+ peer_session_id = sp->pppol2tp.d_session;
+ } else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3)) {
+ ver = 3;
+ fd = sp3->pppol2tp.fd;
+ tunnel_id = sp3->pppol2tp.s_tunnel;
+ peer_tunnel_id = sp3->pppol2tp.d_tunnel;
+ session_id = sp3->pppol2tp.s_session;
+ peer_session_id = sp3->pppol2tp.d_session;
+ } else {
+ error = -EINVAL;
+ goto end; /* bad socket address */
+ }
+
+ /* Don't bind if tunnel_id is 0 */
error = -EINVAL;
- if (sp->pppol2tp.s_tunnel == 0)
+ if (tunnel_id == 0)
goto end;
- /* Special case: create tunnel context if s_session and
- * d_session is 0. Otherwise look up tunnel using supplied
+ /* Special case: create tunnel context if session_id and
+ * peer_session_id is 0. Otherwise look up tunnel using supplied
* tunnel id.
*/
- if ((sp->pppol2tp.s_session == 0) && (sp->pppol2tp.d_session == 0)) {
- error = l2tp_tunnel_create(sock_net(sk), sp->pppol2tp.fd, 2, sp->pppol2tp.s_tunnel, sp->pppol2tp.d_tunnel, NULL, &tunnel);
+ if ((session_id == 0) && (peer_session_id == 0)) {
+ error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, NULL, &tunnel);
if (error < 0)
goto end;
} else {
- tunnel = l2tp_tunnel_find(sock_net(sk), sp->pppol2tp.s_tunnel);
+ tunnel = l2tp_tunnel_find(sock_net(sk), tunnel_id);
/* Error if we can't find the tunnel */
error = -ENOENT;
@@ -684,20 +693,21 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
/* Check that this session doesn't already exist */
error = -EEXIST;
- session = l2tp_session_find(sock_net(sk), tunnel, sp->pppol2tp.s_session);
+ session = l2tp_session_find(sock_net(sk), tunnel, session_id);
if (session != NULL)
goto end;
- /* Default MTU must allow space for UDP/L2TP/PPP
- * headers.
- */
- cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ /* Default MTU values. */
+ if (cfg.mtu == 0)
+ cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ if (cfg.mru == 0)
+ cfg.mru = cfg.mtu;
cfg.debug = tunnel->debug;
/* Allocate and initialize a new session context. */
session = l2tp_session_create(sizeof(struct pppol2tp_session),
- tunnel, sp->pppol2tp.s_session,
- sp->pppol2tp.d_session, &cfg);
+ tunnel, session_id,
+ peer_session_id, &cfg);
if (session == NULL) {
error = -ENOMEM;
goto end;
@@ -773,8 +783,7 @@ end:
static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
int *usockaddr_len, int peer)
{
- int len = sizeof(struct sockaddr_pppol2tp);
- struct sockaddr_pppol2tp sp;
+ int len = 0;
int error = 0;
struct l2tp_session *session;
struct l2tp_tunnel *tunnel;
@@ -800,21 +809,40 @@ static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
goto end_put_sess;
}
- memset(&sp, 0, len);
- sp.sa_family = AF_PPPOX;
- sp.sa_protocol = PX_PROTO_OL2TP;
- sp.pppol2tp.fd = tunnel->fd;
- sp.pppol2tp.pid = pls->owner;
- sp.pppol2tp.s_tunnel = tunnel->tunnel_id;
- sp.pppol2tp.d_tunnel = tunnel->peer_tunnel_id;
- sp.pppol2tp.s_session = session->session_id;
- sp.pppol2tp.d_session = session->peer_session_id;
inet = inet_sk(sk);
- sp.pppol2tp.addr.sin_family = AF_INET;
- sp.pppol2tp.addr.sin_port = inet->inet_dport;
- sp.pppol2tp.addr.sin_addr.s_addr = inet->inet_daddr;
-
- memcpy(uaddr, &sp, len);
+ if (tunnel->version == 2) {
+ struct sockaddr_pppol2tp sp;
+ len = sizeof(sp);
+ memset(&sp, 0, len);
+ sp.sa_family = AF_PPPOX;
+ sp.sa_protocol = PX_PROTO_OL2TP;
+ sp.pppol2tp.fd = tunnel->fd;
+ sp.pppol2tp.pid = pls->owner;
+ sp.pppol2tp.s_tunnel = tunnel->tunnel_id;
+ sp.pppol2tp.d_tunnel = tunnel->peer_tunnel_id;
+ sp.pppol2tp.s_session = session->session_id;
+ sp.pppol2tp.d_session = session->peer_session_id;
+ sp.pppol2tp.addr.sin_family = AF_INET;
+ sp.pppol2tp.addr.sin_port = inet->inet_dport;
+ sp.pppol2tp.addr.sin_addr.s_addr = inet->inet_daddr;
+ memcpy(uaddr, &sp, len);
+ } else if (tunnel->version == 3) {
+ struct sockaddr_pppol2tpv3 sp;
+ len = sizeof(sp);
+ memset(&sp, 0, len);
+ sp.sa_family = AF_PPPOX;
+ sp.sa_protocol = PX_PROTO_OL2TP;
+ sp.pppol2tp.fd = tunnel->fd;
+ sp.pppol2tp.pid = pls->owner;
+ sp.pppol2tp.s_tunnel = tunnel->tunnel_id;
+ sp.pppol2tp.d_tunnel = tunnel->peer_tunnel_id;
+ sp.pppol2tp.s_session = session->session_id;
+ sp.pppol2tp.d_session = session->peer_session_id;
+ sp.pppol2tp.addr.sin_family = AF_INET;
+ sp.pppol2tp.addr.sin_port = inet->inet_dport;
+ sp.pppol2tp.addr.sin_addr.s_addr = inet->inet_daddr;
+ memcpy(uaddr, &sp, len);
+ }
*usockaddr_len = len;
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 07/12] l2tp: Add L2TPv3 IP encapsulation (no UDP) support
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (5 preceding siblings ...)
2010-03-30 16:17 ` [PATCH v3 06/12] l2tp: Update PPP-over-L2TP driver to work over L2TPv3 James Chapman
@ 2010-03-30 16:18 ` James Chapman
2010-03-30 16:18 ` [PATCH v3 08/12] netlink: Export genl_lock() API for use by modules James Chapman
` (4 subsequent siblings)
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:18 UTC (permalink / raw)
To: netdev
This patch adds a new L2TPIP socket family and modifies the core to
handle the case where there is no UDP header in the L2TP
packet. L2TP/IP uses IP protocol 115. Since L2TP/UDP and L2TP/IP
packets differ in layout, the datapath packet handling code needs
changes too. Userspace uses an L2TPIP socket instead of a UDP socket
when IP encapsulation is required.
We can't use raw sockets for this because the semantics of raw sockets
don't lend themselves to the socket-per-tunnel model - we need to
differentiate sockets between the same IP peers by L2TP tunnel ids.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
include/linux/l2tp.h | 38 +++
net/l2tp/Kconfig | 17 +
net/l2tp/Makefile | 1
net/l2tp/l2tp_core.c | 175 ++++++++-----
net/l2tp/l2tp_core.h | 7 +
net/l2tp/l2tp_ip.c | 679 ++++++++++++++++++++++++++++++++++++++++++++++++++
net/l2tp/l2tp_ppp.c | 7 -
7 files changed, 858 insertions(+), 66 deletions(-)
create mode 100644 include/linux/l2tp.h
create mode 100644 net/l2tp/l2tp_ip.c
diff --git a/include/linux/l2tp.h b/include/linux/l2tp.h
new file mode 100644
index 0000000..deff7bc
--- /dev/null
+++ b/include/linux/l2tp.h
@@ -0,0 +1,38 @@
+/*
+ * L2TP-over-IP socket for L2TPv3.
+ *
+ * Author: James Chapman <jchapman@katalix.com>
+ */
+
+#ifndef _LINUX_L2TP_H_
+#define _LINUX_L2TP_H_
+
+#include <linux/types.h>
+#ifdef __KERNEL__
+#include <linux/socket.h>
+#include <linux/in.h>
+#endif
+
+#define IPPROTO_L2TP 115
+
+/**
+ * struct sockaddr_l2tpip - the sockaddr structure for L2TP-over-IP sockets
+ * @l2tp_family: address family number AF_L2TPIP.
+ * @l2tp_addr: protocol specific address information
+ * @l2tp_conn_id: connection id of tunnel
+ */
+struct sockaddr_l2tpip {
+ /* The first fields must match struct sockaddr_in */
+ sa_family_t l2tp_family; /* AF_INET */
+ __be16 l2tp_unused; /* INET port number (unused) */
+ struct in_addr l2tp_addr; /* Internet address */
+
+ __u32 l2tp_conn_id; /* Connection ID of tunnel */
+
+ /* Pad to size of `struct sockaddr'. */
+ unsigned char __pad[sizeof(struct sockaddr) - sizeof(sa_family_t) -
+ sizeof(__be16) - sizeof(struct in_addr) -
+ sizeof(__u32)];
+};
+
+#endif
diff --git a/net/l2tp/Kconfig b/net/l2tp/Kconfig
index d60758d..0a11ccf 100644
--- a/net/l2tp/Kconfig
+++ b/net/l2tp/Kconfig
@@ -51,3 +51,20 @@ config L2TP_V3
If you are connecting to L2TPv3 equipment, or you want to
tunnel raw ethernet frames using L2TP, say Y here. If
unsure, say N.
+
+config L2TP_IP
+ tristate "L2TP IP encapsulation for L2TPv3"
+ depends on L2TP_V3
+ help
+ Support for L2TP-over-IP socket family.
+
+ The L2TPv3 protocol defines two possible encapsulations for
+ L2TP frames, namely UDP and plain IP (without UDP). This
+ driver provides a new L2TPIP socket family with which
+ userspace L2TPv3 daemons may create L2TP/IP tunnel sockets
+ when UDP encapsulation is not required. When L2TP is carried
+ in IP packets, it used IP protocol number 115, so this port
+ must be enabled in firewalls.
+
+ To compile this driver as a module, choose M here. The module
+ will be called l2tp_ip.
diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
index c91f208..ef28b16 100644
--- a/net/l2tp/Makefile
+++ b/net/l2tp/Makefile
@@ -6,3 +6,4 @@ obj-$(CONFIG_L2TP) += l2tp_core.o
# Build l2tp as modules if L2TP is M
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o
+obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1ed7cce..2272272 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -36,12 +36,14 @@
#include <linux/inetdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
+#include <linux/in.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/hash.h>
#include <linux/sort.h>
#include <linux/file.h>
#include <linux/proc_fs.h>
+#include <linux/l2tp.h>
#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
@@ -49,6 +51,7 @@
#include <net/ip.h>
#include <net/udp.h>
#include <net/xfrm.h>
+#include <net/protocol.h>
#include <asm/byteorder.h>
#include <asm/atomic.h>
@@ -853,15 +856,21 @@ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf)
static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
{
+ struct l2tp_tunnel *tunnel = session->tunnel;
char *bufp = buf;
char *optr = bufp;
- u16 flags = L2TP_HDR_VER_3;
- /* Setup L2TP header. */
- *((__be16 *) bufp) = htons(flags);
- bufp += 2;
- *((__be16 *) bufp) = 0;
- bufp += 2;
+ /* Setup L2TP header. The header differs slightly for UDP and
+ * IP encapsulations. For UDP, there is 4 bytes of flags.
+ */
+ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
+ u16 flags = L2TP_HDR_VER_3;
+ *((__be16 *) bufp) = htons(flags);
+ bufp += 2;
+ *((__be16 *) bufp) = 0;
+ bufp += 2;
+ }
+
*((__be32 *) bufp) = htonl(session->peer_session_id);
bufp += 4;
if (session->cookie_len) {
@@ -906,10 +915,11 @@ int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, size_t dat
if (session->debug & L2TP_MSG_DATA) {
int i;
- unsigned char *datap = skb->data + sizeof(struct udphdr);
+ int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
+ unsigned char *datap = skb->data + uhlen;
printk(KERN_DEBUG "%s: xmit:", session->name);
- for (i = 0; i < (len - sizeof(struct udphdr)); i++) {
+ for (i = 0; i < (len - uhlen); i++) {
printk(" %02X", *datap++);
if (i == 31) {
printk(" ...");
@@ -960,21 +970,23 @@ static inline void l2tp_skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len)
{
int data_len = skb->len;
- struct sock *sk = session->tunnel->sock;
+ struct l2tp_tunnel *tunnel = session->tunnel;
+ struct sock *sk = tunnel->sock;
struct udphdr *uh;
- unsigned int udp_len;
struct inet_sock *inet;
__wsum csum;
int old_headroom;
int new_headroom;
int headroom;
+ int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
+ int udp_len;
/* Check that there's enough headroom in the skb to insert IP,
* UDP and L2TP headers. If not enough, expand it to
* make room. Adjust truesize.
*/
headroom = NET_SKB_PAD + sizeof(struct iphdr) +
- sizeof(struct udphdr) + hdr_len;
+ uhlen + hdr_len;
old_headroom = skb_headroom(skb);
if (skb_cow_head(skb, headroom))
goto abort;
@@ -985,18 +997,8 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
/* Setup L2TP header */
session->build_header(session, __skb_push(skb, hdr_len));
- udp_len = sizeof(struct udphdr) + hdr_len + data_len;
-
- /* Setup UDP header */
- inet = inet_sk(sk);
- __skb_push(skb, sizeof(*uh));
- skb_reset_transport_header(skb);
- uh = udp_hdr(skb);
- uh->source = inet->inet_sport;
- uh->dest = inet->inet_dport;
- uh->len = htons(udp_len);
- uh->check = 0;
+ /* Reset skb netfilter state */
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
@@ -1005,29 +1007,48 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
/* Get routing info from the tunnel socket */
skb_dst_drop(skb);
skb_dst_set(skb, dst_clone(__sk_dst_get(sk)));
- l2tp_skb_set_owner_w(skb, sk);
- /* Calculate UDP checksum if configured to do so */
- if (sk->sk_no_check == UDP_CSUM_NOXMIT)
- skb->ip_summed = CHECKSUM_NONE;
- else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
- (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
- skb->ip_summed = CHECKSUM_COMPLETE;
- csum = skb_checksum(skb, 0, udp_len, 0);
- uh->check = csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, csum);
- if (uh->check == 0)
- uh->check = CSUM_MANGLED_0;
- } else {
- skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = offsetof(struct udphdr, check);
- uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
- inet->inet_daddr,
- udp_len, IPPROTO_UDP, 0);
+ switch (tunnel->encap) {
+ case L2TP_ENCAPTYPE_UDP:
+ /* Setup UDP header */
+ inet = inet_sk(sk);
+ __skb_push(skb, sizeof(*uh));
+ skb_reset_transport_header(skb);
+ uh = udp_hdr(skb);
+ uh->source = inet->inet_sport;
+ uh->dest = inet->inet_dport;
+ udp_len = uhlen + hdr_len + data_len;
+ uh->len = htons(udp_len);
+ uh->check = 0;
+
+ /* Calculate UDP checksum if configured to do so */
+ if (sk->sk_no_check == UDP_CSUM_NOXMIT)
+ skb->ip_summed = CHECKSUM_NONE;
+ else if ((skb_dst(skb) && skb_dst(skb)->dev) &&
+ (!(skb_dst(skb)->dev->features & NETIF_F_V4_CSUM))) {
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ csum = skb_checksum(skb, 0, udp_len, 0);
+ uh->check = csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, csum);
+ if (uh->check == 0)
+ uh->check = CSUM_MANGLED_0;
+ } else {
+ skb->ip_summed = CHECKSUM_PARTIAL;
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = offsetof(struct udphdr, check);
+ uh->check = ~csum_tcpudp_magic(inet->inet_saddr,
+ inet->inet_daddr,
+ udp_len, IPPROTO_UDP, 0);
+ }
+ break;
+
+ case L2TP_ENCAPTYPE_IP:
+ break;
}
+ l2tp_skb_set_owner_w(skb, sk);
+
l2tp_xmit_core(session, skb, data_len);
abort:
@@ -1057,9 +1078,15 @@ void l2tp_tunnel_destruct(struct sock *sk)
/* Close all sessions */
l2tp_tunnel_closeall(tunnel);
- /* No longer an encapsulation socket. See net/ipv4/udp.c */
- (udp_sk(sk))->encap_type = 0;
- (udp_sk(sk))->encap_rcv = NULL;
+ switch (tunnel->encap) {
+ case L2TP_ENCAPTYPE_UDP:
+ /* No longer an encapsulation socket. See net/ipv4/udp.c */
+ (udp_sk(sk))->encap_type = 0;
+ (udp_sk(sk))->encap_rcv = NULL;
+ break;
+ case L2TP_ENCAPTYPE_IP:
+ break;
+ }
/* Remove hooks into tunnel socket */
tunnel->sock = NULL;
@@ -1172,6 +1199,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
struct socket *sock = NULL;
struct sock *sk = NULL;
struct l2tp_net *pn;
+ enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP;
/* Get the tunnel socket from the fd, which was opened by
* the userspace L2TP daemon.
@@ -1186,18 +1214,27 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
sk = sock->sk;
+ if (cfg != NULL)
+ encap = cfg->encap;
+
/* Quick sanity checks */
- err = -EPROTONOSUPPORT;
- if (sk->sk_protocol != IPPROTO_UDP) {
- printk(KERN_ERR "tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
- tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
- goto err;
- }
- err = -EAFNOSUPPORT;
- if (sock->ops->family != AF_INET) {
- printk(KERN_ERR "tunl %hu: fd %d wrong family, got %d, expected %d\n",
- tunnel_id, fd, sock->ops->family, AF_INET);
- goto err;
+ switch (encap) {
+ case L2TP_ENCAPTYPE_UDP:
+ err = -EPROTONOSUPPORT;
+ if (sk->sk_protocol != IPPROTO_UDP) {
+ printk(KERN_ERR "tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
+ tunnel_id, fd, sk->sk_protocol, IPPROTO_UDP);
+ goto err;
+ }
+ break;
+ case L2TP_ENCAPTYPE_IP:
+ err = -EPROTONOSUPPORT;
+ if (sk->sk_protocol != IPPROTO_L2TP) {
+ printk(KERN_ERR "tunl %hu: fd %d wrong protocol, got %d, expected %d\n",
+ tunnel_id, fd, sk->sk_protocol, IPPROTO_L2TP);
+ goto err;
+ }
+ break;
}
/* Check if this socket has already been prepped */
@@ -1227,12 +1264,16 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
tunnel->l2tp_net = net;
pn = l2tp_pernet(net);
- if (cfg)
+ if (cfg != NULL)
tunnel->debug = cfg->debug;
/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
- udp_sk(sk)->encap_type = UDP_ENCAP_L2TPINUDP;
- udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv;
+ tunnel->encap = encap;
+ if (encap == L2TP_ENCAPTYPE_UDP) {
+ /* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
+ udp_sk(sk)->encap_type = UDP_ENCAP_L2TPINUDP;
+ udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv;
+ }
sk->sk_user_data = tunnel;
@@ -1322,7 +1363,9 @@ void l2tp_session_set_header_len(struct l2tp_session *session, int version)
if (session->send_seq)
session->hdr_len += 4;
} else {
- session->hdr_len = 8 + session->cookie_len + session->l2specific_len + session->offset;
+ session->hdr_len = 4 + session->cookie_len + session->l2specific_len + session->offset;
+ if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP)
+ session->hdr_len += 4;
}
}
@@ -1542,10 +1585,14 @@ static void l2tp_seq_tunnel_show(struct seq_file *m, void *v)
struct inet_sock *inet = inet_sk(tunnel->sock);
seq_printf(m, " from " NIPQUAD_FMT " to " NIPQUAD_FMT "\n",
NIPQUAD(inet->inet_saddr), NIPQUAD(inet->inet_daddr));
- seq_printf(m, " source port %hu, dest port %hu\n",
- ntohs(inet->inet_sport), ntohs(inet->inet_dport));
+ if (tunnel->encap == L2TP_ENCAPTYPE_UDP)
+ seq_printf(m, " source port %hu, dest port %hu\n",
+ ntohs(inet->inet_sport), ntohs(inet->inet_dport));
}
- seq_printf(m, " L2TPv%d\n", tunnel->version);
+ seq_printf(m, " L2TPv%d, %s\n", tunnel->version,
+ tunnel->encap == L2TP_ENCAPTYPE_UDP ? "UDP" :
+ tunnel->encap == L2TP_ENCAPTYPE_IP ? "IP" :
+ "");
seq_printf(m, " %d sessions, refcnt %d/%d\n", session_count,
tunnel->sock ? atomic_read(&tunnel->sock->sk_refcnt) : 0,
atomic_read(&tunnel->ref_count));
@@ -1628,7 +1675,7 @@ static int l2tp_seq_show(struct seq_file *m, void *v)
if (v == SEQ_START_TOKEN) {
seq_puts(m, "L2TP driver info, " L2TP_DRV_VERSION "\n");
seq_puts(m, "TUNNEL ID, peer ID from IP to IP\n");
- seq_puts(m, " L2TPv2/L2TPv3\n");
+ seq_puts(m, " L2TPv2/L2TPv3, UDP/IP\n");
seq_puts(m, " sessions session-count, refcnt refcnt/sk->refcnt\n");
seq_puts(m, " debug tx-pkts/bytes/errs rx-pkts/bytes/errs\n");
seq_puts(m, " SESSION ID, peer ID, PWTYPE\n");
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 87a06b2..3002ca8 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -48,6 +48,11 @@ enum l2tp_l2spec_type {
L2TP_L2SPECTYPE_DEFAULT,
};
+enum l2tp_encap_type {
+ L2TP_ENCAPTYPE_UDP,
+ L2TP_ENCAPTYPE_IP,
+};
+
struct sk_buff;
struct l2tp_stats {
@@ -157,6 +162,7 @@ struct l2tp_session {
struct l2tp_tunnel_cfg {
int debug; /* bitmask of debug message
* categories */
+ enum l2tp_encap_type encap;
};
struct l2tp_tunnel {
@@ -172,6 +178,7 @@ struct l2tp_tunnel {
char name[20]; /* for logging */
int debug; /* bitmask of debug message
* categories */
+ enum l2tp_encap_type encap;
struct l2tp_stats stats;
struct list_head list; /* Keep a list of all tunnels */
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
new file mode 100644
index 0000000..75bf784
--- /dev/null
+++ b/net/l2tp/l2tp_ip.c
@@ -0,0 +1,679 @@
+/*
+ * L2TPv3 IP encapsulation support
+ *
+ * Copyright (c) 2008,2009,2010 Katalix Systems Ltd
+ *
+ * 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/icmp.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/random.h>
+#include <linux/socket.h>
+#include <linux/l2tp.h>
+#include <linux/in.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/udp.h>
+#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
+#include <net/tcp_states.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+
+#include "l2tp_core.h"
+
+struct l2tp_ip_sock {
+ /* inet_sock has to be the first member of l2tp_ip_sock */
+ struct inet_sock inet;
+
+ __u32 conn_id;
+ __u32 peer_conn_id;
+
+ __u64 tx_packets;
+ __u64 tx_bytes;
+ __u64 tx_errors;
+ __u64 rx_packets;
+ __u64 rx_bytes;
+ __u64 rx_errors;
+};
+
+static DEFINE_RWLOCK(l2tp_ip_lock);
+static struct hlist_head l2tp_ip_table;
+static struct hlist_head l2tp_ip_bind_table;
+
+static inline struct l2tp_ip_sock *l2tp_ip_sk(const struct sock *sk)
+{
+ return (struct l2tp_ip_sock *)sk;
+}
+
+static struct sock *__l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif, u32 tunnel_id)
+{
+ struct hlist_node *node;
+ struct sock *sk;
+
+ sk_for_each_bound(sk, node, &l2tp_ip_bind_table) {
+ struct inet_sock *inet = inet_sk(sk);
+ struct l2tp_ip_sock *l2tp = l2tp_ip_sk(sk);
+
+ if (l2tp == NULL)
+ continue;
+
+ if ((l2tp->conn_id == tunnel_id) &&
+#ifdef CONFIG_NET_NS
+ (sk->sk_net == net) &&
+#endif
+ !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
+ !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+ goto found;
+ }
+
+ sk = NULL;
+found:
+ return sk;
+}
+
+static inline struct sock *l2tp_ip_bind_lookup(struct net *net, __be32 laddr, int dif, u32 tunnel_id)
+{
+ struct sock *sk = __l2tp_ip_bind_lookup(net, laddr, dif, tunnel_id);
+ if (sk)
+ sock_hold(sk);
+
+ return sk;
+}
+
+/* When processing receive frames, there are two cases to
+ * consider. Data frames consist of a non-zero session-id and an
+ * optional cookie. Control frames consist of a regular L2TP header
+ * preceded by 32-bits of zeros.
+ *
+ * L2TPv3 Session Header Over IP
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Session ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Cookie (optional, maximum 64 bits)...
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * L2TPv3 Control Message Header Over IP
+ *
+ * 0 1 2 3
+ * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | (32 bits of zeros) |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |T|L|x|x|S|x|x|x|x|x|x|x| Ver | Length |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Control Connection ID |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * | Ns | Nr |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * All control frames are passed to userspace.
+ */
+static int l2tp_ip_recv(struct sk_buff *skb)
+{
+ struct sock *sk;
+ u32 session_id;
+ u32 tunnel_id;
+ unsigned char *ptr, *optr;
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel = NULL;
+ int length;
+ int offset;
+
+ /* Point to L2TP header */
+ optr = ptr = skb->data;
+
+ if (!pskb_may_pull(skb, 4))
+ goto discard;
+
+ session_id = ntohl(*((__be32 *) ptr));
+ ptr += 4;
+
+ /* RFC3931: L2TP/IP packets have the first 4 bytes containing
+ * the session_id. If it is 0, the packet is a L2TP control
+ * frame and the session_id value can be discarded.
+ */
+ if (session_id == 0) {
+ __skb_pull(skb, 4);
+ goto pass_up;
+ }
+
+ /* Ok, this is a data packet. Lookup the session. */
+ session = l2tp_session_find(&init_net, NULL, session_id);
+ if (session == NULL)
+ goto discard;
+
+ tunnel = session->tunnel;
+ if (tunnel == NULL)
+ goto discard;
+
+ /* Trace packet contents, if enabled */
+ if (tunnel->debug & L2TP_MSG_DATA) {
+ length = min(32u, skb->len);
+ if (!pskb_may_pull(skb, length))
+ goto discard;
+
+ printk(KERN_DEBUG "%s: ip recv: ", tunnel->name);
+
+ offset = 0;
+ do {
+ printk(" %02X", ptr[offset]);
+ } while (++offset < length);
+
+ printk("\n");
+ }
+
+ l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
+
+ return 0;
+
+pass_up:
+ /* Get the tunnel_id from the L2TP header */
+ if (!pskb_may_pull(skb, 12))
+ goto discard;
+
+ if ((skb->data[0] & 0xc0) != 0xc0)
+ goto discard;
+
+ tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
+ tunnel = l2tp_tunnel_find(&init_net, tunnel_id);
+ if (tunnel != NULL)
+ sk = tunnel->sock;
+ else {
+ struct iphdr *iph = (struct iphdr *) skb_network_header(skb);
+
+ read_lock_bh(&l2tp_ip_lock);
+ sk = __l2tp_ip_bind_lookup(&init_net, iph->daddr, 0, tunnel_id);
+ read_unlock_bh(&l2tp_ip_lock);
+ }
+
+ if (sk == NULL)
+ goto discard;
+
+ sock_hold(sk);
+
+ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+ goto discard_put;
+
+ nf_reset(skb);
+
+ return sk_receive_skb(sk, skb, 1);
+
+discard_put:
+ sock_put(sk);
+
+discard:
+ kfree_skb(skb);
+ return 0;
+}
+
+static int l2tp_ip_open(struct sock *sk)
+{
+ /* Prevent autobind. We don't have ports. */
+ inet_sk(sk)->inet_num = IPPROTO_L2TP;
+
+ write_lock_bh(&l2tp_ip_lock);
+ sk_add_node(sk, &l2tp_ip_table);
+ write_unlock_bh(&l2tp_ip_lock);
+
+ return 0;
+}
+
+static void l2tp_ip_close(struct sock *sk, long timeout)
+{
+ write_lock_bh(&l2tp_ip_lock);
+ hlist_del_init(&sk->sk_bind_node);
+ hlist_del_init(&sk->sk_node);
+ write_unlock_bh(&l2tp_ip_lock);
+ sk_common_release(sk);
+}
+
+static void l2tp_ip_destroy_sock(struct sock *sk)
+{
+ struct sk_buff *skb;
+
+ while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
+ kfree_skb(skb);
+
+ sk_refcnt_debug_dec(sk);
+}
+
+static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *) uaddr;
+ int ret = -EINVAL;
+ int chk_addr_ret;
+
+ ret = -EADDRINUSE;
+ read_lock_bh(&l2tp_ip_lock);
+ if (__l2tp_ip_bind_lookup(&init_net, addr->l2tp_addr.s_addr, sk->sk_bound_dev_if, addr->l2tp_conn_id))
+ goto out_in_use;
+
+ read_unlock_bh(&l2tp_ip_lock);
+
+ lock_sock(sk);
+ if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_l2tpip))
+ goto out;
+
+ chk_addr_ret = inet_addr_type(&init_net, addr->l2tp_addr.s_addr);
+ ret = -EADDRNOTAVAIL;
+ if (addr->l2tp_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
+ chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
+ goto out;
+
+ inet->inet_rcv_saddr = inet->inet_saddr = addr->l2tp_addr.s_addr;
+ if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
+ inet->inet_saddr = 0; /* Use device */
+ sk_dst_reset(sk);
+
+ l2tp_ip_sk(sk)->conn_id = addr->l2tp_conn_id;
+
+ write_lock_bh(&l2tp_ip_lock);
+ sk_add_bind_node(sk, &l2tp_ip_bind_table);
+ sk_del_node_init(sk);
+ write_unlock_bh(&l2tp_ip_lock);
+ ret = 0;
+out:
+ release_sock(sk);
+
+ return ret;
+
+out_in_use:
+ read_unlock_bh(&l2tp_ip_lock);
+
+ return ret;
+}
+
+static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ int rc;
+ struct inet_sock *inet = inet_sk(sk);
+ struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *) uaddr;
+ struct rtable *rt;
+ __be32 saddr;
+ int oif;
+
+ rc = -EINVAL;
+ if (addr_len < sizeof(*lsa))
+ goto out;
+
+ rc = -EAFNOSUPPORT;
+ if (lsa->l2tp_family != AF_INET)
+ goto out;
+
+ sk_dst_reset(sk);
+
+ oif = sk->sk_bound_dev_if;
+ saddr = inet->inet_saddr;
+
+ rc = -EINVAL;
+ if (ipv4_is_multicast(lsa->l2tp_addr.s_addr))
+ goto out;
+
+ rc = ip_route_connect(&rt, lsa->l2tp_addr.s_addr, saddr,
+ RT_CONN_FLAGS(sk), oif,
+ IPPROTO_L2TP,
+ 0, 0, sk, 1);
+ if (rc) {
+ if (rc == -ENETUNREACH)
+ IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES);
+ goto out;
+ }
+
+ rc = -ENETUNREACH;
+ if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
+ ip_rt_put(rt);
+ goto out;
+ }
+
+ l2tp_ip_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;
+
+ if (!inet->inet_saddr)
+ inet->inet_saddr = rt->rt_src;
+ if (!inet->inet_rcv_saddr)
+ inet->inet_rcv_saddr = rt->rt_src;
+ inet->inet_daddr = rt->rt_dst;
+ sk->sk_state = TCP_ESTABLISHED;
+ inet->inet_id = jiffies;
+
+ sk_dst_set(sk, &rt->u.dst);
+
+ write_lock_bh(&l2tp_ip_lock);
+ hlist_del_init(&sk->sk_bind_node);
+ sk_add_bind_node(sk, &l2tp_ip_bind_table);
+ write_unlock_bh(&l2tp_ip_lock);
+
+ rc = 0;
+out:
+ return rc;
+}
+
+static int l2tp_ip_getname(struct socket *sock, struct sockaddr *uaddr,
+ int *uaddr_len, int peer)
+{
+ struct sock *sk = sock->sk;
+ struct inet_sock *inet = inet_sk(sk);
+ struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk);
+ struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr;
+
+ memset(lsa, 0, sizeof(*lsa));
+ lsa->l2tp_family = AF_INET;
+ if (peer) {
+ if (!inet->inet_dport)
+ return -ENOTCONN;
+ lsa->l2tp_conn_id = lsk->peer_conn_id;
+ lsa->l2tp_addr.s_addr = inet->inet_daddr;
+ } else {
+ __be32 addr = inet->inet_rcv_saddr;
+ if (!addr)
+ addr = inet->inet_saddr;
+ lsa->l2tp_conn_id = lsk->conn_id;
+ lsa->l2tp_addr.s_addr = addr;
+ }
+ *uaddr_len = sizeof(*lsa);
+ return 0;
+}
+
+static int l2tp_ip_backlog_recv(struct sock *sk, struct sk_buff *skb)
+{
+ int rc;
+
+ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ nf_reset(skb);
+
+ /* Charge it to the socket, dropping if the queue is full. */
+ rc = sock_queue_rcv_skb(sk, skb);
+ if (rc < 0)
+ goto drop;
+
+ return 0;
+
+drop:
+ IP_INC_STATS(&init_net, IPSTATS_MIB_INDISCARDS);
+ kfree_skb(skb);
+ return -1;
+}
+
+/* Userspace will call sendmsg() on the tunnel socket to send L2TP
+ * control frames.
+ */
+static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len)
+{
+ struct sk_buff *skb;
+ int rc;
+ struct l2tp_ip_sock *lsa = l2tp_ip_sk(sk);
+ struct inet_sock *inet = inet_sk(sk);
+ struct ip_options *opt = inet->opt;
+ struct rtable *rt = NULL;
+ int connected = 0;
+ __be32 daddr;
+
+ if (sock_flag(sk, SOCK_DEAD))
+ return -ENOTCONN;
+
+ /* Get and verify the address. */
+ if (msg->msg_name) {
+ struct sockaddr_l2tpip *lip = (struct sockaddr_l2tpip *) msg->msg_name;
+ if (msg->msg_namelen < sizeof(*lip))
+ return -EINVAL;
+
+ if (lip->l2tp_family != AF_INET) {
+ if (lip->l2tp_family != AF_UNSPEC)
+ return -EAFNOSUPPORT;
+ }
+
+ daddr = lip->l2tp_addr.s_addr;
+ } else {
+ if (sk->sk_state != TCP_ESTABLISHED)
+ return -EDESTADDRREQ;
+
+ daddr = inet->inet_daddr;
+ connected = 1;
+ }
+
+ /* Allocate a socket buffer */
+ rc = -ENOMEM;
+ skb = sock_wmalloc(sk, 2 + NET_SKB_PAD + sizeof(struct iphdr) +
+ 4 + len, 0, GFP_KERNEL);
+ if (!skb)
+ goto error;
+
+ /* Reserve space for headers, putting IP header on 4-byte boundary. */
+ skb_reserve(skb, 2 + NET_SKB_PAD);
+ skb_reset_network_header(skb);
+ skb_reserve(skb, sizeof(struct iphdr));
+ skb_reset_transport_header(skb);
+
+ /* Insert 0 session_id */
+ *((__be32 *) skb_put(skb, 4)) = 0;
+
+ /* Copy user data into skb */
+ rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+ if (rc < 0) {
+ kfree_skb(skb);
+ goto error;
+ }
+
+ if (connected)
+ rt = (struct rtable *) __sk_dst_check(sk, 0);
+
+ if (rt == NULL) {
+ /* Use correct destination address if we have options. */
+ if (opt && opt->srr)
+ daddr = opt->faddr;
+
+ {
+ struct flowi fl = { .oif = sk->sk_bound_dev_if,
+ .nl_u = { .ip4_u = {
+ .daddr = daddr,
+ .saddr = inet->inet_saddr,
+ .tos = RT_CONN_FLAGS(sk) } },
+ .proto = sk->sk_protocol,
+ .flags = inet_sk_flowi_flags(sk),
+ .uli_u = { .ports = {
+ .sport = inet->inet_sport,
+ .dport = inet->inet_dport } } };
+
+ /* If this fails, retransmit mechanism of transport layer will
+ * keep trying until route appears or the connection times
+ * itself out.
+ */
+ security_sk_classify_flow(sk, &fl);
+ if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0))
+ goto no_route;
+ }
+ sk_setup_caps(sk, &rt->u.dst);
+ }
+ skb_dst_set(skb, dst_clone(&rt->u.dst));
+
+ /* Queue the packet to IP for output */
+ rc = ip_queue_xmit(skb, 0);
+
+error:
+ /* Update stats */
+ if (rc >= 0) {
+ lsa->tx_packets++;
+ lsa->tx_bytes += len;
+ rc = len;
+ } else {
+ lsa->tx_errors++;
+ }
+
+ return rc;
+
+no_route:
+ IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
+ kfree_skb(skb);
+ return -EHOSTUNREACH;
+}
+
+static int l2tp_ip_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len, int noblock, int flags, int *addr_len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct l2tp_ip_sock *lsk = l2tp_ip_sk(sk);
+ size_t copied = 0;
+ int err = -EOPNOTSUPP;
+ struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+ struct sk_buff *skb;
+
+ if (flags & MSG_OOB)
+ goto out;
+
+ if (addr_len)
+ *addr_len = sizeof(*sin);
+
+ skb = skb_recv_datagram(sk, flags, noblock, &err);
+ if (!skb)
+ goto out;
+
+ copied = skb->len;
+ if (len < copied) {
+ msg->msg_flags |= MSG_TRUNC;
+ copied = len;
+ }
+
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ if (err)
+ goto done;
+
+ sock_recv_timestamp(msg, sk, skb);
+
+ /* Copy the address. */
+ if (sin) {
+ sin->sin_family = AF_INET;
+ sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
+ sin->sin_port = 0;
+ memset(&sin->sin_zero, 0, sizeof(sin->sin_zero));
+ }
+ if (inet->cmsg_flags)
+ ip_cmsg_recv(msg, skb);
+ if (flags & MSG_TRUNC)
+ copied = skb->len;
+done:
+ skb_free_datagram(sk, skb);
+out:
+ if (err) {
+ lsk->rx_errors++;
+ return err;
+ }
+
+ lsk->rx_packets++;
+ lsk->rx_bytes += copied;
+
+ return copied;
+}
+
+struct proto l2tp_ip_prot = {
+ .name = "L2TP/IP",
+ .owner = THIS_MODULE,
+ .init = l2tp_ip_open,
+ .close = l2tp_ip_close,
+ .bind = l2tp_ip_bind,
+ .connect = l2tp_ip_connect,
+ .disconnect = udp_disconnect,
+ .ioctl = udp_ioctl,
+ .destroy = l2tp_ip_destroy_sock,
+ .setsockopt = ip_setsockopt,
+ .getsockopt = ip_getsockopt,
+ .sendmsg = l2tp_ip_sendmsg,
+ .recvmsg = l2tp_ip_recvmsg,
+ .backlog_rcv = l2tp_ip_backlog_recv,
+ .hash = inet_hash,
+ .unhash = inet_unhash,
+ .obj_size = sizeof(struct l2tp_ip_sock),
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_ip_setsockopt,
+ .compat_getsockopt = compat_ip_getsockopt,
+#endif
+};
+
+static const struct proto_ops l2tp_ip_ops = {
+ .family = PF_INET,
+ .owner = THIS_MODULE,
+ .release = inet_release,
+ .bind = inet_bind,
+ .connect = inet_dgram_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = l2tp_ip_getname,
+ .poll = datagram_poll,
+ .ioctl = inet_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = inet_shutdown,
+ .setsockopt = sock_common_setsockopt,
+ .getsockopt = sock_common_getsockopt,
+ .sendmsg = inet_sendmsg,
+ .recvmsg = sock_common_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_sock_common_setsockopt,
+ .compat_getsockopt = compat_sock_common_getsockopt,
+#endif
+};
+
+static struct inet_protosw l2tp_ip_protosw = {
+ .type = SOCK_DGRAM,
+ .protocol = IPPROTO_L2TP,
+ .prot = &l2tp_ip_prot,
+ .ops = &l2tp_ip_ops,
+ .no_check = 0,
+};
+
+static struct net_protocol l2tp_ip_protocol __read_mostly = {
+ .handler = l2tp_ip_recv,
+};
+
+static int __init l2tp_ip_init(void)
+{
+ int err;
+
+ printk(KERN_INFO "L2TP IP encapsulation support (L2TPv3)\n");
+
+ err = proto_register(&l2tp_ip_prot, 1);
+ if (err != 0)
+ goto out;
+
+ err = inet_add_protocol(&l2tp_ip_protocol, IPPROTO_L2TP);
+ if (err)
+ goto out1;
+
+ inet_register_protosw(&l2tp_ip_protosw);
+ return 0;
+
+out1:
+ proto_unregister(&l2tp_ip_prot);
+out:
+ return err;
+}
+
+static void __exit l2tp_ip_exit(void)
+{
+ inet_unregister_protosw(&l2tp_ip_protosw);
+ inet_del_protocol(&l2tp_ip_protocol, IPPROTO_L2TP);
+ proto_unregister(&l2tp_ip_prot);
+}
+
+module_init(l2tp_ip_init);
+module_exit(l2tp_ip_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("L2TP over IP");
+MODULE_VERSION("1.0");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, SOCK_DGRAM, IPPROTO_L2TP);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 907cfbd..1778aaf 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -305,6 +305,7 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
struct l2tp_session *session;
struct l2tp_tunnel *tunnel;
struct pppol2tp_session *ps;
+ int uhlen;
error = -ENOTCONN;
if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
@@ -321,10 +322,12 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
if (tunnel == NULL)
goto error_put_sess;
+ uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
+
/* Allocate a socket buffer */
error = -ENOMEM;
skb = sock_wmalloc(sk, NET_SKB_PAD + sizeof(struct iphdr) +
- sizeof(struct udphdr) + session->hdr_len +
+ uhlen + session->hdr_len +
sizeof(ppph) + total_len,
0, GFP_KERNEL);
if (!skb)
@@ -335,7 +338,7 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
skb_reset_network_header(skb);
skb_reserve(skb, sizeof(struct iphdr));
skb_reset_transport_header(skb);
- skb_reserve(skb, sizeof(struct udphdr));
+ skb_reserve(skb, uhlen);
/* Add PPP header */
skb->data[0] = ppph[0];
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 08/12] netlink: Export genl_lock() API for use by modules
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (6 preceding siblings ...)
2010-03-30 16:18 ` [PATCH v3 07/12] l2tp: Add L2TPv3 IP encapsulation (no UDP) support James Chapman
@ 2010-03-30 16:18 ` James Chapman
2010-03-30 16:18 ` [PATCH v3 09/12] l2tp: Add netlink control API for L2TP James Chapman
` (3 subsequent siblings)
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:18 UTC (permalink / raw)
To: netdev
This lets kernel modules which use genl netlink APIs serialize netlink
processing.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
include/linux/genetlink.h | 8 ++++++++
net/netlink/genetlink.c | 6 ++++--
2 files changed, 12 insertions(+), 2 deletions(-)
diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h
index b834ef6..61549b2 100644
--- a/include/linux/genetlink.h
+++ b/include/linux/genetlink.h
@@ -80,4 +80,12 @@ enum {
#define CTRL_ATTR_MCAST_GRP_MAX (__CTRL_ATTR_MCAST_GRP_MAX - 1)
+#ifdef __KERNEL__
+
+/* All generic netlink requests are serialized by a global lock. */
+extern void genl_lock(void);
+extern void genl_unlock(void);
+
+#endif /* __KERNEL__ */
+
#endif /* __LINUX_GENERIC_NETLINK_H */
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index a4b6e14..a28fda7 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -20,15 +20,17 @@
static DEFINE_MUTEX(genl_mutex); /* serialization of message processing */
-static inline void genl_lock(void)
+void genl_lock(void)
{
mutex_lock(&genl_mutex);
}
+EXPORT_SYMBOL(genl_lock);
-static inline void genl_unlock(void)
+void genl_unlock(void)
{
mutex_unlock(&genl_mutex);
}
+EXPORT_SYMBOL(genl_unlock);
#define GENL_FAM_TAB_SIZE 16
#define GENL_FAM_TAB_MASK (GENL_FAM_TAB_SIZE - 1)
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 09/12] l2tp: Add netlink control API for L2TP
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (7 preceding siblings ...)
2010-03-30 16:18 ` [PATCH v3 08/12] netlink: Export genl_lock() API for use by modules James Chapman
@ 2010-03-30 16:18 ` James Chapman
2010-03-31 8:59 ` Patrick McHardy
2010-03-30 16:18 ` [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support James Chapman
` (2 subsequent siblings)
11 siblings, 1 reply; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:18 UTC (permalink / raw)
To: netdev
In L2TPv3, we need to create/delete/modify/query L2TP tunnel and
session contexts. The number of parameters is significant. So let's
use netlink. Userspace uses this API to control L2TP tunnel/session
contexts in the kernel.
The previous pppol2tp driver was managed using [gs]etsockopt(). This
API is retained for backwards compatibility. Unlike L2TPv2 which
carries only PPP frames, L2TPv3 can carry raw ethernet frames or other
frame types and these do not always have an associated socket
family. Therefore, we need a way to use L2TP sessions that doesn't
require a socket type for each supported frame type. Hence netlink is
used.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
include/linux/l2tp.h | 126 +++++++
net/l2tp/Makefile | 1
net/l2tp/l2tp_core.c | 98 +++++-
net/l2tp/l2tp_core.h | 38 +-
net/l2tp/l2tp_netlink.c | 834 +++++++++++++++++++++++++++++++++++++++++++++++
net/l2tp/l2tp_ppp.c | 163 ++++++++-
6 files changed, 1214 insertions(+), 46 deletions(-)
create mode 100644 net/l2tp/l2tp_netlink.c
diff --git a/include/linux/l2tp.h b/include/linux/l2tp.h
index deff7bc..7dc5368 100644
--- a/include/linux/l2tp.h
+++ b/include/linux/l2tp.h
@@ -11,6 +11,8 @@
#ifdef __KERNEL__
#include <linux/socket.h>
#include <linux/in.h>
+#else
+#include <netinet/in.h>
#endif
#define IPPROTO_L2TP 115
@@ -21,6 +23,7 @@
* @l2tp_addr: protocol specific address information
* @l2tp_conn_id: connection id of tunnel
*/
+#define __SOCK_SIZE__ 16 /* sizeof(struct sockaddr) */
struct sockaddr_l2tpip {
/* The first fields must match struct sockaddr_in */
sa_family_t l2tp_family; /* AF_INET */
@@ -35,4 +38,127 @@ struct sockaddr_l2tpip {
sizeof(__u32)];
};
+/*****************************************************************************
+ * NETLINK_GENERIC netlink family.
+ *****************************************************************************/
+
+/*
+ * Commands.
+ * Valid TLVs of each command are:-
+ * TUNNEL_CREATE - CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum, vlanid
+ * TUNNEL_DELETE - CONN_ID
+ * TUNNEL_MODIFY - CONN_ID, udpcsum
+ * TUNNEL_GETSTATS - CONN_ID, (stats)
+ * TUNNEL_GET - CONN_ID, (...)
+ * SESSION_CREATE - SESSION_ID, PW_TYPE, offset, data_seq, cookie, peer_cookie, offset, l2spec
+ * SESSION_DELETE - SESSION_ID
+ * SESSION_MODIFY - SESSION_ID, data_seq
+ * SESSION_GET - SESSION_ID, (...)
+ * SESSION_GETSTATS - SESSION_ID, (stats)
+ *
+ */
+enum {
+ L2TP_CMD_NOOP,
+ L2TP_CMD_TUNNEL_CREATE,
+ L2TP_CMD_TUNNEL_DELETE,
+ L2TP_CMD_TUNNEL_MODIFY,
+ L2TP_CMD_TUNNEL_GET,
+ L2TP_CMD_SESSION_CREATE,
+ L2TP_CMD_SESSION_DELETE,
+ L2TP_CMD_SESSION_MODIFY,
+ L2TP_CMD_SESSION_GET,
+ __L2TP_CMD_MAX,
+};
+
+#define L2TP_CMD_MAX (__L2TP_CMD_MAX - 1)
+
+/*
+ * ATTR types defined for L2TP
+ */
+enum {
+ L2TP_ATTR_NONE, /* no data */
+ L2TP_ATTR_PW_TYPE, /* u16, enum l2tp_pwtype */
+ L2TP_ATTR_ENCAP_TYPE, /* u16, enum l2tp_encap_type */
+ L2TP_ATTR_OFFSET, /* u16 */
+ L2TP_ATTR_DATA_SEQ, /* u16 */
+ L2TP_ATTR_L2SPEC_TYPE, /* u8, enum l2tp_l2spec_type */
+ L2TP_ATTR_L2SPEC_LEN, /* u8, enum l2tp_l2spec_type */
+ L2TP_ATTR_PROTO_VERSION, /* u8 */
+ L2TP_ATTR_IFNAME, /* string */
+ L2TP_ATTR_CONN_ID, /* u32 */
+ L2TP_ATTR_PEER_CONN_ID, /* u32 */
+ L2TP_ATTR_SESSION_ID, /* u32 */
+ L2TP_ATTR_PEER_SESSION_ID, /* u32 */
+ L2TP_ATTR_UDP_CSUM, /* flag */
+ L2TP_ATTR_VLAN_ID, /* u16 */
+ L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */
+ L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */
+ L2TP_ATTR_DEBUG, /* u32 */
+ L2TP_ATTR_RECV_SEQ, /* flag */
+ L2TP_ATTR_SEND_SEQ, /* flag */
+ L2TP_ATTR_LNS_MODE, /* flag */
+ L2TP_ATTR_USING_IPSEC, /* flag */
+ L2TP_ATTR_RECV_TIMEOUT, /* msec */
+ L2TP_ATTR_FD, /* int */
+ L2TP_ATTR_IP_SADDR, /* u32 */
+ L2TP_ATTR_IP_DADDR, /* u32 */
+ L2TP_ATTR_UDP_SPORT, /* u16 */
+ L2TP_ATTR_UDP_DPORT, /* u16 */
+ L2TP_ATTR_MTU, /* u16 */
+ L2TP_ATTR_MRU, /* u16 */
+ L2TP_ATTR_STATS, /* nested */
+ __L2TP_ATTR_MAX,
+};
+
+#define L2TP_ATTR_MAX (__L2TP_ATTR_MAX - 1)
+
+/* Nested in L2TP_ATTR_STATS */
+enum {
+ L2TP_ATTR_STATS_NONE, /* no data */
+ L2TP_ATTR_TX_PACKETS, /* u64 */
+ L2TP_ATTR_TX_BYTES, /* u64 */
+ L2TP_ATTR_TX_ERRORS, /* u64 */
+ L2TP_ATTR_RX_PACKETS, /* u64 */
+ L2TP_ATTR_RX_BYTES, /* u64 */
+ L2TP_ATTR_RX_SEQ_DISCARDS, /* u64 */
+ L2TP_ATTR_RX_OOS_PACKETS, /* u64 */
+ L2TP_ATTR_RX_ERRORS, /* u64 */
+ __L2TP_ATTR_STATS_MAX,
+};
+
+#define L2TP_ATTR_STATS_MAX (__L2TP_ATTR_STATS_MAX - 1)
+
+enum l2tp_pwtype {
+ L2TP_PWTYPE_NONE = 0x0000,
+ L2TP_PWTYPE_ETH_VLAN = 0x0004,
+ L2TP_PWTYPE_ETH = 0x0005,
+ L2TP_PWTYPE_PPP = 0x0007,
+ L2TP_PWTYPE_PPP_AC = 0x0008,
+ L2TP_PWTYPE_IP = 0x000b,
+ __L2TP_PWTYPE_MAX
+};
+
+enum l2tp_l2spec_type {
+ L2TP_L2SPECTYPE_NONE,
+ L2TP_L2SPECTYPE_DEFAULT,
+};
+
+enum l2tp_encap_type {
+ L2TP_ENCAPTYPE_UDP,
+ L2TP_ENCAPTYPE_IP,
+};
+
+
+enum l2tp_seqmode {
+ L2TP_SEQ_NONE = 0,
+ L2TP_SEQ_IP = 1,
+ L2TP_SEQ_ALL = 2,
+};
+
+/*
+ * NETLINK_GENERIC related info
+ */
+#define L2TP_GENL_NAME "l2tp"
+#define L2TP_GENL_VERSION 0x1
+
#endif
diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
index ef28b16..2c4a14b 100644
--- a/net/l2tp/Makefile
+++ b/net/l2tp/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_L2TP) += l2tp_core.o
# Build l2tp as modules if L2TP is M
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o
+obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_V3)) += l2tp_netlink.o
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 2272272..1dd9dc7 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -50,6 +50,7 @@
#include <net/dst.h>
#include <net/ip.h>
#include <net/udp.h>
+#include <net/inet_common.h>
#include <net/xfrm.h>
#include <net/protocol.h>
@@ -218,6 +219,53 @@ struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth,
}
EXPORT_SYMBOL_GPL(l2tp_session_find_nth);
+/* Lookup a session by interface name.
+ * This is very inefficient but is only used by management interfaces.
+ */
+struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+ int hash;
+ struct hlist_node *walk;
+ struct l2tp_session *session;
+ struct l2tp_session *ret = NULL;
+
+ read_lock_bh(&pn->l2tp_session_hlist_lock);
+ for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
+ hlist_for_each_entry(session, walk, &pn->l2tp_session_hlist[hash], global_hlist) {
+ if (!strcmp(session->ifname, ifname)) {
+ ret = session;
+ break;
+ }
+ }
+ }
+
+ read_unlock_bh(&pn->l2tp_session_hlist_lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_find_by_ifname);
+
+/* Call a user callback for each session.
+ */
+void l2tp_session_list_walk(struct net *net, void (*func)(struct l2tp_session *session, void *arg), void *arg)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+ int hash;
+ struct hlist_node *walk;
+ struct l2tp_session *session;
+ struct hlist_node *tmp;
+
+ read_lock_bh(&pn->l2tp_session_hlist_lock);
+ for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) {
+ hlist_for_each_entry_safe(session, walk, tmp, &pn->l2tp_session_hlist[hash], global_hlist) {
+ (*func)(session, arg);
+ }
+ }
+
+ read_unlock_bh(&pn->l2tp_session_hlist_lock);
+}
+EXPORT_SYMBOL_GPL(l2tp_session_list_walk);
+
/* Lookup a tunnel by id
*/
struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id)
@@ -258,6 +306,22 @@ struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth)
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_find_nth);
+/* Call a user function for each tunnel.
+ */
+void l2tp_tunnel_list_walk(struct net *net, void (*func)(struct l2tp_tunnel *tunnel, void *arg), void *arg)
+{
+ struct l2tp_net *pn = l2tp_pernet(net);
+ struct l2tp_tunnel *tunnel = NULL;
+ struct l2tp_tunnel *tmp;
+
+ read_lock_bh(&pn->l2tp_tunnel_list_lock);
+ list_for_each_entry_safe(tunnel, tmp, &pn->l2tp_tunnel_list, list) {
+ (*func)(tunnel, arg);
+ }
+ read_unlock_bh(&pn->l2tp_tunnel_list_lock);
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_list_walk);
+
/*****************************************************************************
* Receive data handling
*****************************************************************************/
@@ -762,7 +826,7 @@ int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
/* Find the session context */
session = l2tp_session_find(tunnel->l2tp_net, tunnel, session_id);
- if (!session) {
+ if (!session || !session->recv_skb) {
/* Not found? Pass to userspace to deal with */
PRINTK(tunnel->debug, L2TP_MSG_DATA, KERN_INFO,
"%s: no session found (%u/%u). Passing up.\n",
@@ -1309,6 +1373,23 @@ err:
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
+/* This function is used by the netlink TUNNEL_DELETE command.
+ */
+int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
+{
+ int err = 0;
+
+ /* Force the tunnel socket to close. This will eventually
+ * cause the tunnel to be deleted via the normal socket close
+ * mechanisms when userspace closes the tunnel socket.
+ */
+ if ((tunnel->sock != NULL) && (tunnel->sock->sk_socket != NULL))
+ err = inet_shutdown(tunnel->sock->sk_socket, 2);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
+
/* Really kill the session.
*/
void l2tp_session_free(struct l2tp_session *session)
@@ -1353,6 +1434,21 @@ void l2tp_session_free(struct l2tp_session *session)
}
EXPORT_SYMBOL_GPL(l2tp_session_free);
+/* This function is used by the netlink SESSION_DELETE command and by
+ pseudowire modules.
+ */
+int l2tp_session_delete(struct l2tp_session *session)
+{
+ if (session->session_close != NULL)
+ (*session->session_close)(session);
+
+ l2tp_session_dec_refcount(session);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(l2tp_session_delete);
+
+
/* We come here whenever a session's send_seq, cookie_len or
* l2specific_len parameters are set.
*/
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 3002ca8..c5f2cc9 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -33,26 +33,6 @@ enum {
L2TP_MSG_DATA = (1 << 3), /* data packets */
};
-enum l2tp_pwtype {
- L2TP_PWTYPE_NONE = 0x0000,
- L2TP_PWTYPE_ETH_VLAN = 0x0004,
- L2TP_PWTYPE_ETH = 0x0005,
- L2TP_PWTYPE_PPP = 0x0007,
- L2TP_PWTYPE_PPP_AC = 0x0008,
- L2TP_PWTYPE_IP = 0x000b,
- __L2TP_PWTYPE_MAX
-};
-
-enum l2tp_l2spec_type {
- L2TP_L2SPECTYPE_NONE,
- L2TP_L2SPECTYPE_DEFAULT,
-};
-
-enum l2tp_encap_type {
- L2TP_ENCAPTYPE_UDP,
- L2TP_ENCAPTYPE_IP,
-};
-
struct sk_buff;
struct l2tp_stats {
@@ -87,6 +67,7 @@ struct l2tp_session_cfg {
* control of LNS. */
int debug; /* bitmask of debug message
* categories */
+ u16 vlan_id; /* VLAN pseudowire only */
u16 offset; /* offset to payload */
u16 l2specific_len; /* Layer 2 specific length */
u16 l2specific_type; /* Layer 2 specific type */
@@ -98,6 +79,7 @@ struct l2tp_session_cfg {
* (in jiffies) */
int mtu;
int mru;
+ char *ifname;
};
struct l2tp_session {
@@ -124,6 +106,7 @@ struct l2tp_session {
atomic_t ref_count;
char name[32]; /* for logging */
+ char ifname[IFNAMSIZ];
unsigned data_seq:2; /* data sequencing level
* 0 => none, 1 => IP only,
* 2 => all
@@ -196,6 +179,11 @@ struct l2tp_tunnel {
uint8_t priv[0]; /* private data */
};
+struct l2tp_nl_cmd_ops {
+ int (*session_create)(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg);
+ int (*session_delete)(struct l2tp_session *session);
+};
+
static inline void *l2tp_tunnel_priv(struct l2tp_tunnel *tunnel)
{
return &tunnel->priv[0];
@@ -228,11 +216,16 @@ out:
extern struct l2tp_session *l2tp_session_find(struct net *net, struct l2tp_tunnel *tunnel, u32 session_id);
extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth, int *skipped);
+extern struct l2tp_session *l2tp_session_find_by_ifname(struct net *net, char *ifname);
extern struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
-extern struct l2tp_session *l2tp_session_find_nth(struct l2tp_tunnel *tunnel, int nth, int *skipped);
+extern struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
+extern void l2tp_tunnel_list_walk(struct net *net, void (*func)(struct l2tp_tunnel *tunnel, void *arg), void *arg);
+extern void l2tp_session_list_walk(struct net *net, void (*func)(struct l2tp_session *session, void *arg), void *arg);
extern int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp);
+extern int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
extern struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg);
+extern int l2tp_session_delete(struct l2tp_session *session);
extern void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
extern void l2tp_session_free(struct l2tp_session *session);
extern void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length, int (*payload_hook)(struct sk_buff *skb));
@@ -245,6 +238,9 @@ extern void l2tp_tunnel_destruct(struct sock *sk);
extern void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
extern void l2tp_session_set_header_len(struct l2tp_session *session, int version);
+extern int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops);
+extern void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
+
/* Tunnel reference counts. Incremented per session that is added to
* the tunnel.
*/
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
new file mode 100644
index 0000000..e051c13
--- /dev/null
+++ b/net/l2tp/l2tp_netlink.c
@@ -0,0 +1,834 @@
+/*
+ * L2TP netlink layer, for management
+ *
+ * Copyright (c) 2008,2009,2010 Katalix Systems Ltd
+ *
+ * Partly based on the IrDA nelink implementation
+ * (see net/irda/irnetlink.c) which is:
+ * Copyright (c) 2007 Samuel Ortiz <samuel@sortiz.org>
+ * which is in turn partly based on the wireless netlink code:
+ * Copyright 2006 Johannes Berg <johannes@sipsolutions.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <net/sock.h>
+#include <net/genetlink.h>
+#include <net/udp.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/socket.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <net/net_namespace.h>
+
+#include <linux/l2tp.h>
+
+#include "l2tp_core.h"
+
+
+static struct genl_family l2tp_nl_family = {
+ .id = GENL_ID_GENERATE,
+ .name = L2TP_GENL_NAME,
+ .version = L2TP_GENL_VERSION,
+ .hdrsize = 0,
+ .maxattr = L2TP_ATTR_MAX,
+};
+
+/* Accessed under genl lock */
+static const struct l2tp_nl_cmd_ops *l2tp_nl_cmd_ops[__L2TP_PWTYPE_MAX];
+
+static struct l2tp_session *l2tp_nl_session_find(struct genl_info *info)
+{
+ u32 tunnel_id;
+ u32 session_id;
+ char *ifname;
+ struct l2tp_tunnel *tunnel;
+ struct l2tp_session *session = NULL;
+ struct net *net = genl_info_net(info);
+
+ if (info->attrs[L2TP_ATTR_IFNAME]) {
+ ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
+ session = l2tp_session_find_by_ifname(net, ifname);
+ } else if ((info->attrs[L2TP_ATTR_SESSION_ID]) &&
+ (info->attrs[L2TP_ATTR_CONN_ID])) {
+ tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
+ session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+ if (tunnel)
+ session = l2tp_session_find(net, tunnel, session_id);
+ }
+
+ return session;
+}
+
+static int l2tp_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
+{
+ struct sk_buff *msg;
+ void *hdr;
+ int ret = -ENOBUFS;
+
+ msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq,
+ &l2tp_nl_family, 0, L2TP_CMD_NOOP);
+ if (IS_ERR(hdr)) {
+ ret = PTR_ERR(hdr);
+ goto err_out;
+ }
+
+ genlmsg_end(msg, hdr);
+
+ return genlmsg_unicast(genl_info_net(info), msg, info->snd_pid);
+
+err_out:
+ nlmsg_free(msg);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info)
+{
+ u32 tunnel_id;
+ u32 peer_tunnel_id;
+ int proto_version;
+ int fd;
+ int ret = 0;
+ struct l2tp_tunnel_cfg cfg = { 0, };
+ struct l2tp_tunnel *tunnel;
+ struct net *net = genl_info_net(info);
+
+ if (!info->attrs[L2TP_ATTR_CONN_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
+
+ if (!info->attrs[L2TP_ATTR_PEER_CONN_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ peer_tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_PEER_CONN_ID]);
+
+ if (!info->attrs[L2TP_ATTR_PROTO_VERSION]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ proto_version = nla_get_u8(info->attrs[L2TP_ATTR_PROTO_VERSION]);
+
+ if (!info->attrs[L2TP_ATTR_ENCAP_TYPE]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ cfg.encap = nla_get_u16(info->attrs[L2TP_ATTR_ENCAP_TYPE]);
+
+ if (!info->attrs[L2TP_ATTR_FD]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ fd = nla_get_u32(info->attrs[L2TP_ATTR_FD]);
+
+ if (info->attrs[L2TP_ATTR_DEBUG])
+ cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
+
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+ if (tunnel != NULL) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ ret = -EINVAL;
+ switch (cfg.encap) {
+ case L2TP_ENCAPTYPE_UDP:
+ case L2TP_ENCAPTYPE_IP:
+ ret = l2tp_tunnel_create(net, fd, proto_version, tunnel_id,
+ peer_tunnel_id, &cfg, &tunnel);
+ break;
+ }
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info)
+{
+ struct l2tp_tunnel *tunnel;
+ u32 tunnel_id;
+ int ret = 0;
+ struct net *net = genl_info_net(info);
+
+ if (!info->attrs[L2TP_ATTR_CONN_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
+
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+ if (tunnel == NULL) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ (void) l2tp_tunnel_delete(tunnel);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info)
+{
+ struct l2tp_tunnel *tunnel;
+ u32 tunnel_id;
+ int ret = 0;
+ struct net *net = genl_info_net(info);
+
+ if (!info->attrs[L2TP_ATTR_CONN_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
+
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+ if (tunnel == NULL) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (info->attrs[L2TP_ATTR_DEBUG])
+ tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags,
+ struct l2tp_tunnel *tunnel)
+{
+ void *hdr;
+ struct nlattr *nest;
+ struct sock *sk = NULL;
+ struct inet_sock *inet;
+
+ hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags,
+ L2TP_CMD_TUNNEL_GET);
+ if (IS_ERR(hdr))
+ return PTR_ERR(hdr);
+
+ NLA_PUT_U8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version);
+ NLA_PUT_U32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id);
+ NLA_PUT_U32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id);
+ NLA_PUT_U32(skb, L2TP_ATTR_DEBUG, tunnel->debug);
+ NLA_PUT_U16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap);
+
+ nest = nla_nest_start(skb, L2TP_ATTR_STATS);
+ if (nest == NULL)
+ goto nla_put_failure;
+
+ NLA_PUT_U64(skb, L2TP_ATTR_TX_PACKETS, tunnel->stats.tx_packets);
+ NLA_PUT_U64(skb, L2TP_ATTR_TX_BYTES, tunnel->stats.tx_bytes);
+ NLA_PUT_U64(skb, L2TP_ATTR_TX_ERRORS, tunnel->stats.tx_errors);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_PACKETS, tunnel->stats.rx_packets);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_BYTES, tunnel->stats.rx_bytes);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, tunnel->stats.rx_seq_discards);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_OOS_PACKETS, tunnel->stats.rx_oos_packets);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_ERRORS, tunnel->stats.rx_errors);
+ nla_nest_end(skb, nest);
+
+ sk = tunnel->sock;
+ if (!sk)
+ goto out;
+
+ inet = inet_sk(sk);
+
+ switch (tunnel->encap) {
+ case L2TP_ENCAPTYPE_UDP:
+ NLA_PUT_U16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport));
+ NLA_PUT_U16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport));
+ if (sk->sk_no_check != UDP_CSUM_NOXMIT)
+ NLA_PUT_FLAG(skb, L2TP_ATTR_UDP_CSUM);
+ /* NOBREAK */
+ case L2TP_ENCAPTYPE_IP:
+ NLA_PUT_BE32(skb, L2TP_ATTR_IP_SADDR, inet->inet_saddr);
+ NLA_PUT_BE32(skb, L2TP_ATTR_IP_DADDR, inet->inet_daddr);
+ break;
+ }
+
+out:
+ return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+ return -1;
+}
+
+static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct l2tp_tunnel *tunnel;
+ struct sk_buff *msg;
+ u32 tunnel_id;
+ int ret = -ENOBUFS;
+ struct net *net = genl_info_net(info);
+
+ if (!info->attrs[L2TP_ATTR_CONN_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
+
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+ if (tunnel == NULL) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = l2tp_nl_tunnel_send(msg, info->snd_pid, info->snd_seq,
+ NLM_F_ACK, tunnel);
+ if (ret < 0)
+ goto err_out;
+
+ return genlmsg_unicast(net, msg, info->snd_pid);
+
+err_out:
+ nlmsg_free(msg);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ int ti = cb->args[0];
+ struct l2tp_tunnel *tunnel;
+ struct net *net = sock_net(skb->sk);
+
+ for (;;) {
+ tunnel = l2tp_tunnel_find_nth(net, ti);
+ if (tunnel == NULL)
+ goto out;
+
+ if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ tunnel) <= 0)
+ goto out;
+
+ ti++;
+ }
+
+out:
+ cb->args[0] = ti;
+
+ return skb->len;
+}
+
+static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *info)
+{
+ u32 tunnel_id = 0;
+ u32 session_id;
+ u32 peer_session_id;
+ int ret = 0;
+ struct l2tp_tunnel *tunnel;
+ struct l2tp_session *session;
+ struct l2tp_session_cfg cfg = { 0, };
+ struct net *net = genl_info_net(info);
+
+ if (!info->attrs[L2TP_ATTR_CONN_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]);
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+ if (!tunnel) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (!info->attrs[L2TP_ATTR_SESSION_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
+ session = l2tp_session_find(net, tunnel, session_id);
+ if (session) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ if (!info->attrs[L2TP_ATTR_PEER_SESSION_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ peer_session_id = nla_get_u32(info->attrs[L2TP_ATTR_PEER_SESSION_ID]);
+
+ if (!info->attrs[L2TP_ATTR_PW_TYPE]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ cfg.pw_type = nla_get_u16(info->attrs[L2TP_ATTR_PW_TYPE]);
+ if (cfg.pw_type >= __L2TP_PWTYPE_MAX) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (tunnel->version > 2) {
+ if (info->attrs[L2TP_ATTR_OFFSET])
+ cfg.offset = nla_get_u16(info->attrs[L2TP_ATTR_OFFSET]);
+
+ if (info->attrs[L2TP_ATTR_DATA_SEQ])
+ cfg.data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]);
+
+ cfg.l2specific_type = L2TP_L2SPECTYPE_DEFAULT;
+ if (info->attrs[L2TP_ATTR_L2SPEC_TYPE])
+ cfg.l2specific_type = nla_get_u8(info->attrs[L2TP_ATTR_L2SPEC_TYPE]);
+
+ cfg.l2specific_len = 4;
+ if (info->attrs[L2TP_ATTR_L2SPEC_LEN])
+ cfg.l2specific_len = nla_get_u8(info->attrs[L2TP_ATTR_L2SPEC_LEN]);
+
+ if (info->attrs[L2TP_ATTR_COOKIE]) {
+ u16 len = nla_len(info->attrs[L2TP_ATTR_COOKIE]);
+ if (len > 8) {
+ ret = -EINVAL;
+ goto out;
+ }
+ cfg.cookie_len = len;
+ memcpy(&cfg.cookie[0], nla_data(info->attrs[L2TP_ATTR_COOKIE]), len);
+ }
+ if (info->attrs[L2TP_ATTR_PEER_COOKIE]) {
+ u16 len = nla_len(info->attrs[L2TP_ATTR_PEER_COOKIE]);
+ if (len > 8) {
+ ret = -EINVAL;
+ goto out;
+ }
+ cfg.peer_cookie_len = len;
+ memcpy(&cfg.peer_cookie[0], nla_data(info->attrs[L2TP_ATTR_PEER_COOKIE]), len);
+ }
+ if (info->attrs[L2TP_ATTR_IFNAME])
+ cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
+
+ if (info->attrs[L2TP_ATTR_VLAN_ID])
+ cfg.vlan_id = nla_get_u16(info->attrs[L2TP_ATTR_VLAN_ID]);
+ }
+
+ if (info->attrs[L2TP_ATTR_DEBUG])
+ cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
+
+ if (info->attrs[L2TP_ATTR_RECV_SEQ])
+ cfg.recv_seq = nla_get_flag(info->attrs[L2TP_ATTR_RECV_SEQ]);
+
+ if (info->attrs[L2TP_ATTR_SEND_SEQ])
+ cfg.send_seq = nla_get_flag(info->attrs[L2TP_ATTR_SEND_SEQ]);
+
+ if (info->attrs[L2TP_ATTR_LNS_MODE])
+ cfg.lns_mode = nla_get_flag(info->attrs[L2TP_ATTR_LNS_MODE]);
+
+ if (info->attrs[L2TP_ATTR_RECV_TIMEOUT])
+ cfg.reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]);
+
+ if (info->attrs[L2TP_ATTR_MTU])
+ cfg.mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]);
+
+ if (info->attrs[L2TP_ATTR_MRU])
+ cfg.mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]);
+
+ if ((l2tp_nl_cmd_ops[cfg.pw_type] == NULL) ||
+ (l2tp_nl_cmd_ops[cfg.pw_type]->session_create == NULL)) {
+ ret = -EPROTONOSUPPORT;
+ goto out;
+ }
+
+ /* Check that pseudowire-specific params are present */
+ switch (cfg.pw_type) {
+ case L2TP_PWTYPE_NONE:
+ break;
+ case L2TP_PWTYPE_ETH_VLAN:
+ if (!info->attrs[L2TP_ATTR_VLAN_ID]) {
+ ret = -EINVAL;
+ goto out;
+ }
+ break;
+ case L2TP_PWTYPE_ETH:
+ break;
+ case L2TP_PWTYPE_PPP:
+ case L2TP_PWTYPE_PPP_AC:
+ break;
+ case L2TP_PWTYPE_IP:
+ default:
+ ret = -EPROTONOSUPPORT;
+ break;
+ }
+
+ ret = -EPROTONOSUPPORT;
+ if (l2tp_nl_cmd_ops[cfg.pw_type]->session_create)
+ ret = (*l2tp_nl_cmd_ops[cfg.pw_type]->session_create)(net, tunnel_id,
+ session_id, peer_session_id, &cfg);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_cmd_session_delete(struct sk_buff *skb, struct genl_info *info)
+{
+ int ret = 0;
+ struct l2tp_session *session;
+ u16 pw_type;
+
+ session = l2tp_nl_session_find(info);
+ if (session == NULL) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ pw_type = session->pwtype;
+ if (pw_type < __L2TP_PWTYPE_MAX)
+ if (l2tp_nl_cmd_ops[pw_type] && l2tp_nl_cmd_ops[pw_type]->session_delete)
+ ret = (*l2tp_nl_cmd_ops[pw_type]->session_delete)(session);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *info)
+{
+ int ret = 0;
+ struct l2tp_session *session;
+
+ session = l2tp_nl_session_find(info);
+ if (session == NULL) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (info->attrs[L2TP_ATTR_DEBUG])
+ session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
+
+ if (info->attrs[L2TP_ATTR_DATA_SEQ])
+ session->data_seq = nla_get_flag(info->attrs[L2TP_ATTR_DATA_SEQ]);
+
+ if (info->attrs[L2TP_ATTR_RECV_SEQ])
+ session->recv_seq = nla_get_flag(info->attrs[L2TP_ATTR_RECV_SEQ]);
+
+ if (info->attrs[L2TP_ATTR_SEND_SEQ])
+ session->send_seq = nla_get_flag(info->attrs[L2TP_ATTR_SEND_SEQ]);
+
+ if (info->attrs[L2TP_ATTR_LNS_MODE])
+ session->lns_mode = nla_get_flag(info->attrs[L2TP_ATTR_LNS_MODE]);
+
+ if (info->attrs[L2TP_ATTR_RECV_TIMEOUT])
+ session->reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]);
+
+ if (info->attrs[L2TP_ATTR_MTU])
+ session->mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]);
+
+ if (info->attrs[L2TP_ATTR_MRU])
+ session->mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags,
+ struct l2tp_session *session)
+{
+ void *hdr;
+ struct nlattr *nest;
+ struct l2tp_tunnel *tunnel = session->tunnel;
+ struct sock *sk = NULL;
+
+ sk = tunnel->sock;
+
+ hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags, L2TP_CMD_SESSION_GET);
+ if (IS_ERR(hdr))
+ return PTR_ERR(hdr);
+
+ NLA_PUT_U32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id);
+ NLA_PUT_U32(skb, L2TP_ATTR_SESSION_ID, session->session_id);
+ NLA_PUT_U32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id);
+ NLA_PUT_U32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id);
+ NLA_PUT_U32(skb, L2TP_ATTR_DEBUG, session->debug);
+ NLA_PUT_U16(skb, L2TP_ATTR_PW_TYPE, session->pwtype);
+ NLA_PUT_U16(skb, L2TP_ATTR_MTU, session->mtu);
+ if (session->mru)
+ NLA_PUT_U16(skb, L2TP_ATTR_MRU, session->mru);
+
+ if (session->ifname && session->ifname[0])
+ NLA_PUT_STRING(skb, L2TP_ATTR_IFNAME, session->ifname);
+ if (session->cookie_len)
+ NLA_PUT(skb, L2TP_ATTR_COOKIE, session->cookie_len, &session->cookie[0]);
+ if (session->peer_cookie_len)
+ NLA_PUT(skb, L2TP_ATTR_PEER_COOKIE, session->peer_cookie_len, &session->peer_cookie[0]);
+ if (session->recv_seq)
+ NLA_PUT_FLAG(skb, L2TP_ATTR_RECV_SEQ);
+ if (session->send_seq)
+ NLA_PUT_FLAG(skb, L2TP_ATTR_SEND_SEQ);
+ if (session->lns_mode)
+ NLA_PUT_FLAG(skb, L2TP_ATTR_LNS_MODE);
+#ifdef CONFIG_XFRM
+ if ((sk) && (sk->sk_policy[0] || sk->sk_policy[1]))
+ NLA_PUT_FLAG(skb, L2TP_ATTR_USING_IPSEC);
+#endif
+ if (session->reorder_timeout)
+ NLA_PUT_MSECS(skb, L2TP_ATTR_RECV_TIMEOUT, session->reorder_timeout);
+
+ nest = nla_nest_start(skb, L2TP_ATTR_STATS);
+ if (nest == NULL)
+ goto nla_put_failure;
+ NLA_PUT_U64(skb, L2TP_ATTR_TX_PACKETS, session->stats.tx_packets);
+ NLA_PUT_U64(skb, L2TP_ATTR_TX_BYTES, session->stats.tx_bytes);
+ NLA_PUT_U64(skb, L2TP_ATTR_TX_ERRORS, session->stats.tx_errors);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_PACKETS, session->stats.rx_packets);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_BYTES, session->stats.rx_bytes);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_SEQ_DISCARDS, session->stats.rx_seq_discards);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_OOS_PACKETS, session->stats.rx_oos_packets);
+ NLA_PUT_U64(skb, L2TP_ATTR_RX_ERRORS, session->stats.rx_errors);
+ nla_nest_end(skb, nest);
+
+ return genlmsg_end(skb, hdr);
+
+ nla_put_failure:
+ genlmsg_cancel(skb, hdr);
+ return -1;
+}
+
+static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info)
+{
+ struct l2tp_session *session;
+ struct sk_buff *msg;
+ int ret;
+
+ session = l2tp_nl_session_find(info);
+ if (session == NULL) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+ if (!msg) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = l2tp_nl_session_send(msg, info->snd_pid, info->snd_seq,
+ 0, session);
+ if (ret < 0)
+ goto err_out;
+
+ return genlmsg_unicast(genl_info_net(info), msg, info->snd_pid);
+
+err_out:
+ nlmsg_free(msg);
+
+out:
+ return ret;
+}
+
+static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct l2tp_session *session;
+ struct l2tp_tunnel *tunnel = NULL;
+ int ti = cb->args[0];
+ int si = cb->args[1];
+
+ for (;;) {
+ if (tunnel == NULL) {
+ tunnel = l2tp_tunnel_find_nth(net, ti);
+ if (tunnel == NULL)
+ goto out;
+ }
+
+ session = l2tp_session_find_nth(tunnel, si, NULL);
+ if (session == NULL) {
+ ti++;
+ tunnel = NULL;
+ si = 0;
+ continue;
+ }
+
+ if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ session) <= 0)
+ break;
+
+ si++;
+ }
+
+out:
+ cb->args[0] = ti;
+ cb->args[1] = si;
+
+ return skb->len;
+}
+
+static struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
+ [L2TP_ATTR_NONE] = { .type = NLA_UNSPEC, },
+ [L2TP_ATTR_PW_TYPE] = { .type = NLA_U16, },
+ [L2TP_ATTR_ENCAP_TYPE] = { .type = NLA_U16, },
+ [L2TP_ATTR_OFFSET] = { .type = NLA_U16, },
+ [L2TP_ATTR_DATA_SEQ] = { .type = NLA_U8, },
+ [L2TP_ATTR_L2SPEC_TYPE] = { .type = NLA_U8, },
+ [L2TP_ATTR_L2SPEC_LEN] = { .type = NLA_U8, },
+ [L2TP_ATTR_PROTO_VERSION] = { .type = NLA_U8, },
+ [L2TP_ATTR_CONN_ID] = { .type = NLA_U32, },
+ [L2TP_ATTR_PEER_CONN_ID] = { .type = NLA_U32, },
+ [L2TP_ATTR_SESSION_ID] = { .type = NLA_U32, },
+ [L2TP_ATTR_PEER_SESSION_ID] = { .type = NLA_U32, },
+ [L2TP_ATTR_UDP_CSUM] = { .type = NLA_FLAG, },
+ [L2TP_ATTR_VLAN_ID] = { .type = NLA_U16, },
+ [L2TP_ATTR_DEBUG] = { .type = NLA_U32, },
+ [L2TP_ATTR_RECV_SEQ] = { .type = NLA_FLAG, },
+ [L2TP_ATTR_SEND_SEQ] = { .type = NLA_FLAG, },
+ [L2TP_ATTR_LNS_MODE] = { .type = NLA_FLAG, },
+ [L2TP_ATTR_USING_IPSEC] = { .type = NLA_FLAG, },
+ [L2TP_ATTR_RECV_TIMEOUT] = { .type = NLA_MSECS, },
+ [L2TP_ATTR_FD] = { .type = NLA_U32, },
+ [L2TP_ATTR_IP_SADDR] = { .type = NLA_U32, },
+ [L2TP_ATTR_IP_DADDR] = { .type = NLA_U32, },
+ [L2TP_ATTR_UDP_SPORT] = { .type = NLA_U16, },
+ [L2TP_ATTR_UDP_DPORT] = { .type = NLA_U16, },
+ [L2TP_ATTR_MTU] = { .type = NLA_U16, },
+ [L2TP_ATTR_MRU] = { .type = NLA_U16, },
+ [L2TP_ATTR_STATS] = { .type = NLA_NESTED, },
+ [L2TP_ATTR_IFNAME] = {
+ .type = NLA_NUL_STRING,
+ .len = IFNAMSIZ - 1,
+ },
+ [L2TP_ATTR_COOKIE] = {
+ .type = NLA_BINARY,
+ .len = 8,
+ },
+ [L2TP_ATTR_PEER_COOKIE] = {
+ .type = NLA_BINARY,
+ .len = 8,
+ },
+};
+
+static struct genl_ops l2tp_nl_ops[] = {
+ {
+ .cmd = L2TP_CMD_NOOP,
+ .doit = l2tp_nl_cmd_noop,
+ .policy = l2tp_nl_policy,
+ /* can be retrieved by unprivileged users */
+ },
+ {
+ .cmd = L2TP_CMD_TUNNEL_CREATE,
+ .doit = l2tp_nl_cmd_tunnel_create,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = L2TP_CMD_TUNNEL_DELETE,
+ .doit = l2tp_nl_cmd_tunnel_delete,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = L2TP_CMD_TUNNEL_MODIFY,
+ .doit = l2tp_nl_cmd_tunnel_modify,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = L2TP_CMD_TUNNEL_GET,
+ .doit = l2tp_nl_cmd_tunnel_get,
+ .dumpit = l2tp_nl_cmd_tunnel_dump,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = L2TP_CMD_SESSION_CREATE,
+ .doit = l2tp_nl_cmd_session_create,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = L2TP_CMD_SESSION_DELETE,
+ .doit = l2tp_nl_cmd_session_delete,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = L2TP_CMD_SESSION_MODIFY,
+ .doit = l2tp_nl_cmd_session_modify,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = L2TP_CMD_SESSION_GET,
+ .doit = l2tp_nl_cmd_session_get,
+ .dumpit = l2tp_nl_cmd_session_dump,
+ .policy = l2tp_nl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+};
+
+int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops *ops)
+{
+ int ret;
+
+ ret = -EINVAL;
+ if (pw_type >= __L2TP_PWTYPE_MAX)
+ goto err;
+
+ genl_lock();
+ ret = -EBUSY;
+ if (l2tp_nl_cmd_ops[pw_type])
+ goto out;
+
+ l2tp_nl_cmd_ops[pw_type] = ops;
+
+out:
+ genl_unlock();
+err:
+ return 0;
+}
+EXPORT_SYMBOL_GPL(l2tp_nl_register_ops);
+
+void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type)
+{
+ if (pw_type < __L2TP_PWTYPE_MAX) {
+ genl_lock();
+ l2tp_nl_cmd_ops[pw_type] = NULL;
+ genl_unlock();
+ }
+}
+EXPORT_SYMBOL_GPL(l2tp_nl_unregister_ops);
+
+static int l2tp_nl_init(void)
+{
+ int err;
+
+ printk(KERN_INFO "L2TP netlink interface\n");
+ err = genl_register_family_with_ops(&l2tp_nl_family, l2tp_nl_ops,
+ ARRAY_SIZE(l2tp_nl_ops));
+
+ return err;
+}
+
+static void l2tp_nl_cleanup(void)
+{
+ genl_unregister_family(&l2tp_nl_family);
+}
+
+module_init(l2tp_nl_init);
+module_exit(l2tp_nl_cleanup);
+
+MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("L2TP netlink");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0");
+MODULE_ALIAS("net-pf-" __stringify(PF_NETLINK) "-proto-" \
+ __stringify(NETLINK_GENERIC) "-type-" "l2tp")
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1778aaf..1fac56d 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -87,6 +87,7 @@
#include <linux/hash.h>
#include <linux/sort.h>
#include <linux/proc_fs.h>
+#include <linux/l2tp.h>
#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
@@ -670,17 +671,23 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
if (tunnel_id == 0)
goto end;
+ tunnel = l2tp_tunnel_find(sock_net(sk), tunnel_id);
+
/* Special case: create tunnel context if session_id and
* peer_session_id is 0. Otherwise look up tunnel using supplied
* tunnel id.
*/
if ((session_id == 0) && (peer_session_id == 0)) {
- error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, NULL, &tunnel);
- if (error < 0)
- goto end;
+ if (tunnel == NULL) {
+ struct l2tp_tunnel_cfg tcfg = {
+ .encap = L2TP_ENCAPTYPE_UDP,
+ .debug = 0,
+ };
+ error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel);
+ if (error < 0)
+ goto end;
+ }
} else {
- tunnel = l2tp_tunnel_find(sock_net(sk), tunnel_id);
-
/* Error if we can't find the tunnel */
error = -ENOENT;
if (tunnel == NULL)
@@ -694,28 +701,46 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
if (tunnel->recv_payload_hook == NULL)
tunnel->recv_payload_hook = pppol2tp_recv_payload_hook;
- /* Check that this session doesn't already exist */
- error = -EEXIST;
- session = l2tp_session_find(sock_net(sk), tunnel, session_id);
- if (session != NULL)
- goto end;
-
- /* Default MTU values. */
- if (cfg.mtu == 0)
- cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
- if (cfg.mru == 0)
- cfg.mru = cfg.mtu;
- cfg.debug = tunnel->debug;
+ if (tunnel->peer_tunnel_id == 0) {
+ if (ver == 2)
+ tunnel->peer_tunnel_id = sp->pppol2tp.d_tunnel;
+ else
+ tunnel->peer_tunnel_id = sp3->pppol2tp.d_tunnel;
+ }
- /* Allocate and initialize a new session context. */
- session = l2tp_session_create(sizeof(struct pppol2tp_session),
- tunnel, session_id,
- peer_session_id, &cfg);
+ /* Create session if it doesn't already exist. We handle the
+ * case where a session was previously created by the netlink
+ * interface by checking that the session doesn't already have
+ * a socket and its tunnel socket are what we expect. If any
+ * of those checks fail, return EEXIST to the caller.
+ */
+ session = l2tp_session_find(sock_net(sk), tunnel, session_id);
if (session == NULL) {
- error = -ENOMEM;
- goto end;
+ /* Default MTU must allow space for UDP/L2TP/PPP
+ * headers.
+ */
+ cfg.mtu = cfg.mru = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+
+ /* Allocate and initialize a new session context. */
+ session = l2tp_session_create(sizeof(struct pppol2tp_session),
+ tunnel, session_id,
+ peer_session_id, &cfg);
+ if (session == NULL) {
+ error = -ENOMEM;
+ goto end;
+ }
+ } else {
+ ps = l2tp_session_priv(session);
+ error = -EEXIST;
+ if (ps->sock != NULL)
+ goto end;
+
+ /* consistency checks */
+ if (ps->tunnel_sock != tunnel->sock)
+ goto end;
}
+ /* Associate session with its PPPoL2TP socket */
ps = l2tp_session_priv(session);
ps->owner = current->pid;
ps->sock = sk;
@@ -781,6 +806,74 @@ end:
return error;
}
+#ifdef CONFIG_L2TP_V3
+
+/* Called when creating sessions via the netlink interface.
+ */
+static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
+{
+ int error;
+ struct l2tp_tunnel *tunnel;
+ struct l2tp_session *session;
+ struct pppol2tp_session *ps;
+
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+
+ /* Error if we can't find the tunnel */
+ error = -ENOENT;
+ if (tunnel == NULL)
+ goto out;
+
+ /* Error if tunnel socket is not prepped */
+ if (tunnel->sock == NULL)
+ goto out;
+
+ /* Check that this session doesn't already exist */
+ error = -EEXIST;
+ session = l2tp_session_find(net, tunnel, session_id);
+ if (session != NULL)
+ goto out;
+
+ /* Default MTU values. */
+ if (cfg->mtu == 0)
+ cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
+ if (cfg->mru == 0)
+ cfg->mru = cfg->mtu;
+
+ /* Allocate and initialize a new session context. */
+ error = -ENOMEM;
+ session = l2tp_session_create(sizeof(struct pppol2tp_session),
+ tunnel, session_id,
+ peer_session_id, cfg);
+ if (session == NULL)
+ goto out;
+
+ ps = l2tp_session_priv(session);
+ ps->tunnel_sock = tunnel->sock;
+
+ PRINTK(session->debug, PPPOL2TP_MSG_CONTROL, KERN_INFO,
+ "%s: created\n", session->name);
+
+ error = 0;
+
+out:
+ return error;
+}
+
+/* Called when deleting sessions via the netlink interface.
+ */
+static int pppol2tp_session_delete(struct l2tp_session *session)
+{
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+
+ if (ps->sock == NULL)
+ l2tp_session_dec_refcount(session);
+
+ return 0;
+}
+
+#endif /* CONFIG_L2TP_V3 */
+
/* getname() support.
*/
static int pppol2tp_getname(struct socket *sock, struct sockaddr *uaddr,
@@ -1449,6 +1542,15 @@ static struct pppox_proto pppol2tp_proto = {
.ioctl = pppol2tp_ioctl
};
+#ifdef CONFIG_L2TP_V3
+
+static const struct l2tp_nl_cmd_ops pppol2tp_nl_cmd_ops = {
+ .session_create = pppol2tp_session_create,
+ .session_delete = pppol2tp_session_delete,
+};
+
+#endif /* CONFIG_L2TP_V3 */
+
static int __init pppol2tp_init(void)
{
int err;
@@ -1460,11 +1562,22 @@ static int __init pppol2tp_init(void)
if (err)
goto out_unregister_pppol2tp_proto;
+#ifdef CONFIG_L2TP_V3
+ err = l2tp_nl_register_ops(L2TP_PWTYPE_PPP, &pppol2tp_nl_cmd_ops);
+ if (err)
+ goto out_unregister_pppox;
+#endif
+
printk(KERN_INFO "PPPoL2TP kernel driver, %s\n",
PPPOL2TP_DRV_VERSION);
out:
return err;
+
+#ifdef CONFIG_L2TP_V3
+out_unregister_pppox:
+ unregister_pppox_proto(PX_PROTO_OL2TP);
+#endif
out_unregister_pppol2tp_proto:
proto_unregister(&pppol2tp_sk_proto);
goto out;
@@ -1472,8 +1585,10 @@ out_unregister_pppol2tp_proto:
static void __exit pppol2tp_exit(void)
{
+#ifdef CONFIG_L2TP_V3
+ l2tp_nl_unregister_ops(L2TP_PWTYPE_PPP);
+#endif
unregister_pppox_proto(PX_PROTO_OL2TP);
-
proto_unregister(&pppol2tp_sk_proto);
}
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [PATCH v3 09/12] l2tp: Add netlink control API for L2TP
2010-03-30 16:18 ` [PATCH v3 09/12] l2tp: Add netlink control API for L2TP James Chapman
@ 2010-03-31 8:59 ` Patrick McHardy
0 siblings, 0 replies; 32+ messages in thread
From: Patrick McHardy @ 2010-03-31 8:59 UTC (permalink / raw)
To: James Chapman; +Cc: netdev
James Chapman wrote:
> +static struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
> + [L2TP_ATTR_NONE] = { .type = NLA_UNSPEC, },
> + [L2TP_ATTR_PW_TYPE] = { .type = NLA_U16, },
> + [L2TP_ATTR_ENCAP_TYPE] = { .type = NLA_U16, },
> + [L2TP_ATTR_OFFSET] = { .type = NLA_U16, },
> + [L2TP_ATTR_DATA_SEQ] = { .type = NLA_U8, },
> + [L2TP_ATTR_L2SPEC_TYPE] = { .type = NLA_U8, },
> + [L2TP_ATTR_L2SPEC_LEN] = { .type = NLA_U8, },
> + [L2TP_ATTR_PROTO_VERSION] = { .type = NLA_U8, },
> + [L2TP_ATTR_CONN_ID] = { .type = NLA_U32, },
> + [L2TP_ATTR_PEER_CONN_ID] = { .type = NLA_U32, },
> + [L2TP_ATTR_SESSION_ID] = { .type = NLA_U32, },
> + [L2TP_ATTR_PEER_SESSION_ID] = { .type = NLA_U32, },
> + [L2TP_ATTR_UDP_CSUM] = { .type = NLA_FLAG, },
> + [L2TP_ATTR_VLAN_ID] = { .type = NLA_U16, },
> + [L2TP_ATTR_DEBUG] = { .type = NLA_U32, },
> + [L2TP_ATTR_RECV_SEQ] = { .type = NLA_FLAG, },
> + [L2TP_ATTR_SEND_SEQ] = { .type = NLA_FLAG, },
> + [L2TP_ATTR_LNS_MODE] = { .type = NLA_FLAG, },
> + [L2TP_ATTR_USING_IPSEC] = { .type = NLA_FLAG, },
Please don't use NLA_FLAG, it diverges from the usual netlink
attribute semantics since you either can't unset the flag in
case you check for the presence of the attribute (the attribute
can only encode "flag set") or you'll have to send the current
value in every message even if you don't intend to change it.
In this case it can't be unset.
A better way is to use something like this:
struct l2tp_flags {
__u32 value;
__u32 mask;
};
and set mask to the bits you intend to change.
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (8 preceding siblings ...)
2010-03-30 16:18 ` [PATCH v3 09/12] l2tp: Add netlink control API for L2TP James Chapman
@ 2010-03-30 16:18 ` James Chapman
2010-03-30 16:30 ` Stephen Hemminger
` (2 more replies)
2010-03-30 16:18 ` [PATCH v3 11/12] l2tp: Add support for static unmanaged L2TPv3 tunnels James Chapman
2010-03-30 16:18 ` [PATCH v3 12/12] l2tp: Update documentation James Chapman
11 siblings, 3 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:18 UTC (permalink / raw)
To: netdev
This driver presents a regular net_device for each L2TP ethernet
pseudowire instance. These interfaces are named l2tpethN by default,
though userspace can specify an alternative name when the L2TP
session is created, if preferred. When the pseudowire is established,
regular Linux networking utilities may be used to configure the
interface, i.e. give it IP address info or add it to a bridge. Any
data passed over the interface is carried over an L2TP tunnel.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
net/l2tp/Kconfig | 24 +++
net/l2tp/Makefile | 1
net/l2tp/l2tp_eth.c | 371 +++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 396 insertions(+), 0 deletions(-)
create mode 100644 net/l2tp/l2tp_eth.c
diff --git a/net/l2tp/Kconfig b/net/l2tp/Kconfig
index 0a11ccf..a292270 100644
--- a/net/l2tp/Kconfig
+++ b/net/l2tp/Kconfig
@@ -68,3 +68,27 @@ config L2TP_IP
To compile this driver as a module, choose M here. The module
will be called l2tp_ip.
+
+config L2TP_ETH
+ tristate "L2TP ethernet pseudowire support for L2TPv3"
+ depends on L2TP_V3
+ help
+ Support for carrying raw ethernet frames over L2TPv3.
+
+ From RFC 4719 <http://www.ietf.org/rfc/rfc4719.txt>.
+
+ The Layer 2 Tunneling Protocol, Version 3 (L2TPv3) can be
+ used as a control protocol and for data encapsulation to set
+ up Pseudowires for transporting layer 2 Packet Data Units
+ across an IP network [RFC3931].
+
+ This driver provides an ethernet virtual interface for each
+ L2TP ethernet pseudowire instance. Standard Linux tools may
+ be used to assign an IP address to the local virtual
+ interface, or add the interface to a bridge.
+
+ If you are using L2TPv3, you will almost certainly want to
+ enable this option.
+
+ To compile this driver as a module, choose M here. The module
+ will be called l2tp_eth.
diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
index 2c4a14b..bddbf04 100644
--- a/net/l2tp/Makefile
+++ b/net/l2tp/Makefile
@@ -8,3 +8,4 @@ obj-$(CONFIG_L2TP) += l2tp_core.o
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o
obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_V3)) += l2tp_netlink.o
+obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_ETH)) += l2tp_eth.o
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
new file mode 100644
index 0000000..3c4f254
--- /dev/null
+++ b/net/l2tp/l2tp_eth.c
@@ -0,0 +1,371 @@
+/*
+ * L2TPv3 ethernet pseudowire driver
+ *
+ * Copyright (c) 2008,2009,2010 Katalix Systems Ltd
+ *
+ * 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/module.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/hash.h>
+#include <linux/l2tp.h>
+#include <linux/in.h>
+#include <linux/etherdevice.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <net/icmp.h>
+#include <net/udp.h>
+#include <net/inet_common.h>
+#include <net/inet_hashtables.h>
+#include <net/tcp_states.h>
+#include <net/protocol.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+#include "l2tp_core.h"
+
+/* Default device name. May be overridden by name specified by user */
+#define L2TP_ETH_DEV_NAME "l2tpeth%d"
+
+/* via netdev_priv() */
+struct l2tp_eth {
+ struct net_device *dev;
+ struct sock *tunnel_sock;
+ struct l2tp_session *session;
+ struct list_head list;
+};
+
+/* via l2tp_session_priv() */
+struct l2tp_eth_sess {
+ struct net_device *dev;
+};
+
+/* per-net private data for this module */
+static unsigned int l2tp_eth_net_id;
+struct l2tp_eth_net {
+ struct list_head l2tp_eth_dev_list;
+ rwlock_t l2tp_eth_lock;
+};
+
+static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
+{
+ BUG_ON(!net);
+
+ return net_generic(net, l2tp_eth_net_id);
+}
+
+static int l2tp_eth_dev_init(struct net_device *dev)
+{
+ struct l2tp_eth *priv = netdev_priv(dev);
+ struct l2tp_session *session = priv->session;
+ __be32 sid = htonl(session->session_id);
+
+ priv->dev = dev;
+
+ /* Derive a MAC address for the new interface. We use the L2TP
+ * session's session-id to guarantee a system-wide unique
+ * address. This MAC is only visible within the L2TP session.
+ */
+ dev->dev_addr[0] = 0x02; /* IEEE 802 local */
+ dev->dev_addr[1] = 'L';
+ memcpy(&dev->dev_addr[2], &sid, 4);
+ memset(&dev->broadcast[0], 0xff, 6);
+
+ return 0;
+}
+
+static void l2tp_eth_dev_uninit(struct net_device *dev)
+{
+ struct l2tp_eth *priv = netdev_priv(dev);
+ struct l2tp_eth_net *pn = l2tp_eth_pernet(dev_net(dev));
+
+ write_lock(&pn->l2tp_eth_lock);
+ list_del_init(&priv->list);
+ write_unlock(&pn->l2tp_eth_lock);
+ dev_put(dev);
+}
+
+static int l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct l2tp_eth *priv = netdev_priv(dev);
+ struct l2tp_session *session = priv->session;
+
+ l2tp_xmit_skb(session, skb, session->hdr_len);
+
+ dev->stats.tx_bytes += skb->len;
+ dev->stats.tx_packets++;
+
+ return 0;
+}
+
+static struct net_device_ops l2tp_eth_netdev_ops = {
+ .ndo_init = l2tp_eth_dev_init,
+ .ndo_uninit = l2tp_eth_dev_uninit,
+ .ndo_start_xmit = l2tp_eth_dev_xmit,
+};
+
+static void l2tp_eth_dev_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+
+ dev->netdev_ops = &l2tp_eth_netdev_ops;
+ dev->destructor = free_netdev;
+}
+
+static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb, int data_len)
+{
+ struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
+ struct net_device *dev = spriv->dev;
+
+ if (session->debug & L2TP_MSG_DATA) {
+ unsigned int length;
+ int offset;
+ u8 *ptr = skb->data;
+
+ length = min(32u, skb->len);
+ if (!pskb_may_pull(skb, length))
+ goto error;
+
+ printk(KERN_DEBUG "%s: eth recv: ", session->name);
+
+ offset = 0;
+ do {
+ printk(" %02X", ptr[offset]);
+ } while (++offset < length);
+
+ printk("\n");
+ }
+
+ if (data_len < ETH_HLEN)
+ goto error;
+
+ secpath_reset(skb);
+
+ /* checksums verified by L2TP */
+ skb->ip_summed = CHECKSUM_NONE;
+
+ skb_dst_drop(skb);
+ nf_reset(skb);
+
+ if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) {
+ dev->last_rx = jiffies;
+ dev->stats.rx_packets++;
+ dev->stats.rx_bytes += data_len;
+ } else
+ dev->stats.rx_errors++;
+
+ return;
+
+error:
+ dev->stats.rx_errors++;
+ kfree_skb(skb);
+}
+
+static void l2tp_eth_delete(struct l2tp_session *session)
+{
+ struct l2tp_eth_sess *spriv;
+ struct net_device *dev;
+
+ if (session) {
+ spriv = l2tp_session_priv(session);
+ dev = spriv->dev;
+ if (dev) {
+ unregister_netdev(dev);
+ spriv->dev = NULL;
+ }
+ }
+}
+
+#ifdef CONFIG_PROC_FS
+static void l2tp_eth_show(struct seq_file *m, void *arg)
+{
+ struct l2tp_session *session = arg;
+ struct l2tp_eth_sess *spriv = l2tp_session_priv(session);
+ struct net_device *dev = spriv->dev;
+
+ seq_printf(m, " interface %s\n", dev->name);
+}
+#endif
+
+static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
+{
+ struct net_device *dev;
+ char name[IFNAMSIZ];
+ struct l2tp_tunnel *tunnel;
+ struct l2tp_session *session;
+ struct l2tp_eth *priv;
+ struct l2tp_eth_sess *spriv;
+ int rc;
+ struct l2tp_eth_net *pn;
+
+ tunnel = l2tp_tunnel_find(net, tunnel_id);
+ if (!tunnel) {
+ rc = -ENODEV;
+ goto out;
+ }
+
+ session = l2tp_session_find(net, tunnel, session_id);
+ if (session) {
+ rc = -EEXIST;
+ goto out;
+ }
+
+ if (cfg->ifname) {
+ dev = dev_get_by_name(net, cfg->ifname);
+ if (dev) {
+ dev_put(dev);
+ rc = -EEXIST;
+ goto out;
+ }
+ strlcpy(name, cfg->ifname, IFNAMSIZ);
+ } else
+ strcpy(name, L2TP_ETH_DEV_NAME);
+
+ session = l2tp_session_create(sizeof(*spriv), tunnel, session_id,
+ peer_session_id, cfg);
+ if (!session) {
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ dev = alloc_netdev(sizeof(*priv), name, l2tp_eth_dev_setup);
+ if (!dev) {
+ rc = -ENOMEM;
+ goto out_del_session;
+ }
+
+ dev_net_set(dev, net);
+ if (session->mtu == 0)
+ session->mtu = dev->mtu - session->hdr_len;
+ dev->mtu = session->mtu;
+ dev->needed_headroom += session->hdr_len;
+
+ priv = netdev_priv(dev);
+ priv->dev = dev;
+ priv->session = session;
+ INIT_LIST_HEAD(&priv->list);
+
+ priv->tunnel_sock = tunnel->sock;
+ session->recv_skb = l2tp_eth_dev_recv;
+ session->session_close = l2tp_eth_delete;
+#ifdef CONFIG_PROC_FS
+ session->show = l2tp_eth_show;
+#endif
+
+ spriv = l2tp_session_priv(session);
+ spriv->dev = dev;
+
+ rc = register_netdev(dev);
+ if (rc < 0)
+ goto out_del_dev;
+
+ /* Must be done after register_netdev() */
+ strlcpy(session->ifname, dev->name, IFNAMSIZ);
+
+ dev_hold(dev);
+ pn = l2tp_eth_pernet(dev_net(dev));
+ write_lock(&pn->l2tp_eth_lock);
+ list_add(&priv->list, &pn->l2tp_eth_dev_list);
+ write_unlock(&pn->l2tp_eth_lock);
+
+ return 0;
+
+out_del_dev:
+ free_netdev(dev);
+out_del_session:
+ l2tp_session_delete(session);
+out:
+ return rc;
+}
+
+static __net_init int l2tp_eth_init_net(struct net *net)
+{
+ struct l2tp_eth_net *pn;
+ int err;
+
+ pn = kzalloc(sizeof(*pn), GFP_KERNEL);
+ if (!pn)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&pn->l2tp_eth_dev_list);
+ rwlock_init(&pn->l2tp_eth_lock);
+
+ err = net_assign_generic(net, l2tp_eth_net_id, pn);
+ if (err)
+ goto out;
+
+ return 0;
+
+out:
+ kfree(pn);
+ return err;
+}
+
+static __net_exit void l2tp_eth_exit_net(struct net *net)
+{
+ struct l2tp_eth_net *pn;
+
+ pn = net_generic(net, l2tp_eth_net_id);
+ /*
+ * if someone has cached our net then
+ * further net_generic call will return NULL
+ */
+ net_assign_generic(net, l2tp_eth_net_id, NULL);
+ kfree(pn);
+}
+
+static __net_initdata struct pernet_operations l2tp_eth_net_ops = {
+ .init = l2tp_eth_init_net,
+ .exit = l2tp_eth_exit_net,
+ .id = &l2tp_eth_net_id,
+ .size = sizeof(struct l2tp_eth_net),
+};
+
+
+static const struct l2tp_nl_cmd_ops l2tp_eth_nl_cmd_ops = {
+ .session_create = l2tp_eth_create,
+ .session_delete = l2tp_session_delete,
+};
+
+
+static int __init l2tp_eth_init(void)
+{
+ int err = 0;
+
+ err = l2tp_nl_register_ops(L2TP_PWTYPE_ETH, &l2tp_eth_nl_cmd_ops);
+ if (err)
+ goto out;
+
+ err = register_pernet_device(&l2tp_eth_net_ops);
+ if (err)
+ goto out_unreg;
+
+ printk(KERN_INFO "L2TP ethernet pseudowire support (L2TPv3)\n");
+
+ return 0;
+
+out_unreg:
+ l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
+out:
+ return err;
+}
+
+static void __exit l2tp_eth_exit(void)
+{
+ unregister_pernet_device(&l2tp_eth_net_ops);
+ l2tp_nl_unregister_ops(L2TP_PWTYPE_ETH);
+}
+
+module_init(l2tp_eth_init);
+module_exit(l2tp_eth_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
+MODULE_DESCRIPTION("L2TP ethernet pseudowire driver");
+MODULE_VERSION("1.0");
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-03-30 16:18 ` [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support James Chapman
@ 2010-03-30 16:30 ` Stephen Hemminger
2010-03-30 16:30 ` Stephen Hemminger
2010-03-30 16:32 ` Stephen Hemminger
2 siblings, 0 replies; 32+ messages in thread
From: Stephen Hemminger @ 2010-03-30 16:30 UTC (permalink / raw)
To: James Chapman; +Cc: netdev
On Tue, 30 Mar 2010 17:18:19 +0100
James Chapman <jchapman@katalix.com> wrote:
> static inline struct l2tp_eth_net *l2tp_eth_pernet(struct net *net)
> +{
> + BUG_ON(!net);
> +
> + return net_generic(net, l2tp_eth_net_id);
> +}
Don't test for NULL with BUG_ON. It is redundant, the null
dereference will cause the same kind of backtrace failure.
--
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-03-30 16:18 ` [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support James Chapman
2010-03-30 16:30 ` Stephen Hemminger
@ 2010-03-30 16:30 ` Stephen Hemminger
2010-03-30 16:32 ` Stephen Hemminger
2 siblings, 0 replies; 32+ messages in thread
From: Stephen Hemminger @ 2010-03-30 16:30 UTC (permalink / raw)
To: James Chapman; +Cc: netdev
On Tue, 30 Mar 2010 17:18:19 +0100
James Chapman <jchapman@katalix.com> wrote:
> +
> + /* Derive a MAC address for the new interface. We use the L2TP
> + * session's session-id to guarantee a system-wide unique
> + * address. This MAC is only visible within the L2TP session.
> + */
> + dev->dev_addr[0] = 0x02; /* IEEE 802 local */
> + dev->dev_addr[1] = 'L';
> + memcpy(&dev->dev_addr[2], &sid, 4);
Why not random ether address?
--
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-03-30 16:18 ` [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support James Chapman
2010-03-30 16:30 ` Stephen Hemminger
2010-03-30 16:30 ` Stephen Hemminger
@ 2010-03-30 16:32 ` Stephen Hemminger
2010-03-31 9:35 ` James Chapman
2 siblings, 1 reply; 32+ messages in thread
From: Stephen Hemminger @ 2010-03-30 16:32 UTC (permalink / raw)
To: James Chapman; +Cc: netdev
On Tue, 30 Mar 2010 17:18:19 +0100
James Chapman <jchapman@katalix.com> wrote:
> +struct l2tp_eth_net {
> + struct list_head l2tp_eth_dev_list;
> + rwlock_t l2tp_eth_lock;
> +};
Reader/write locks are discouraged because they are slower than
spin locks. If you have lots of readers use RCU, if reading
is infrequent just use a spin lock.
--
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-03-30 16:32 ` Stephen Hemminger
@ 2010-03-31 9:35 ` James Chapman
2010-03-31 17:38 ` Paul E. McKenney
0 siblings, 1 reply; 32+ messages in thread
From: James Chapman @ 2010-03-31 9:35 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
Stephen Hemminger wrote:
> On Tue, 30 Mar 2010 17:18:19 +0100
> James Chapman <jchapman@katalix.com> wrote:
>
>> +struct l2tp_eth_net {
>> + struct list_head l2tp_eth_dev_list;
>> + rwlock_t l2tp_eth_lock;
>> +};
>
> Reader/write locks are discouraged because they are slower than
> spin locks. If you have lots of readers use RCU, if reading
> is infrequent just use a spin lock.
Ok. In doing the conversion of the rwlocks in l2tp_core.c, I'm finding
that some list access primitives don't have rcu equivalents, namely
list_is_last(), list_for_each_entry_safe(). Is this intentional? Should
I add the missing ones in a separate patch?
--
James Chapman
Katalix Systems Ltd
http://www.katalix.com
Catalysts for your Embedded Linux software development
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-03-31 9:35 ` James Chapman
@ 2010-03-31 17:38 ` Paul E. McKenney
2010-04-02 15:24 ` Paul E. McKenney
0 siblings, 1 reply; 32+ messages in thread
From: Paul E. McKenney @ 2010-03-31 17:38 UTC (permalink / raw)
To: James Chapman; +Cc: Stephen Hemminger, netdev
On Wed, Mar 31, 2010 at 10:35:29AM +0100, James Chapman wrote:
> Stephen Hemminger wrote:
> > On Tue, 30 Mar 2010 17:18:19 +0100
> > James Chapman <jchapman@katalix.com> wrote:
> >
> >> +struct l2tp_eth_net {
> >> + struct list_head l2tp_eth_dev_list;
> >> + rwlock_t l2tp_eth_lock;
> >> +};
> >
> > Reader/write locks are discouraged because they are slower than
> > spin locks. If you have lots of readers use RCU, if reading
> > is infrequent just use a spin lock.
>
> Ok. In doing the conversion of the rwlocks in l2tp_core.c, I'm finding
> that some list access primitives don't have rcu equivalents, namely
> list_is_last(), list_for_each_entry_safe(). Is this intentional? Should
> I add the missing ones in a separate patch?
The list_is_last() is RCU-safe already, since the ->next pointer is
only compared, never dereferenced. I suggest adding a comment to its
header stating that it is RCU-safe.
Feel free to create a list_for_each_entry_safe_rcu(), and I will be
happy to review it.
Thanx, Paul
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-03-31 17:38 ` Paul E. McKenney
@ 2010-04-02 15:24 ` Paul E. McKenney
2010-04-02 15:58 ` Eric Dumazet
0 siblings, 1 reply; 32+ messages in thread
From: Paul E. McKenney @ 2010-04-02 15:24 UTC (permalink / raw)
To: James Chapman; +Cc: Stephen Hemminger, netdev
On Wed, Mar 31, 2010 at 10:38:36AM -0700, Paul E. McKenney wrote:
> On Wed, Mar 31, 2010 at 10:35:29AM +0100, James Chapman wrote:
> > Stephen Hemminger wrote:
> > > On Tue, 30 Mar 2010 17:18:19 +0100
> > > James Chapman <jchapman@katalix.com> wrote:
> > >
> > >> +struct l2tp_eth_net {
> > >> + struct list_head l2tp_eth_dev_list;
> > >> + rwlock_t l2tp_eth_lock;
> > >> +};
> > >
> > > Reader/write locks are discouraged because they are slower than
> > > spin locks. If you have lots of readers use RCU, if reading
> > > is infrequent just use a spin lock.
> >
> > Ok. In doing the conversion of the rwlocks in l2tp_core.c, I'm finding
> > that some list access primitives don't have rcu equivalents, namely
> > list_is_last(), list_for_each_entry_safe(). Is this intentional? Should
> > I add the missing ones in a separate patch?
>
> The list_is_last() is RCU-safe already, since the ->next pointer is
> only compared, never dereferenced. I suggest adding a comment to its
> header stating that it is RCU-safe.
>
> Feel free to create a list_for_each_entry_safe_rcu(), and I will be
> happy to review it.
Right. When using RCU, list_for_each_entry_safe_rcu() is not needed,
because destruction of the element you removed doesn't happen until the
end of a subsequent grace period. By which time you will be done with
your RCU read-side critical section.
So you can just use list_for_each_entry_rcu(), you do not need a new
list_for_each_entry_safe_rcu().
But you did have me going for a bit!!! ;-)
Thanx, Paul
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-04-02 15:24 ` Paul E. McKenney
@ 2010-04-02 15:58 ` Eric Dumazet
2010-04-02 16:21 ` Paul E. McKenney
0 siblings, 1 reply; 32+ messages in thread
From: Eric Dumazet @ 2010-04-02 15:58 UTC (permalink / raw)
To: paulmck; +Cc: James Chapman, Stephen Hemminger, netdev
Le vendredi 02 avril 2010 à 08:24 -0700, Paul E. McKenney a écrit :
> On Wed, Mar 31, 2010 at 10:38:36AM -0700, Paul E. McKenney wrote:
> > The list_is_last() is RCU-safe already, since the ->next pointer is
> > only compared, never dereferenced. I suggest adding a comment to its
> > header stating that it is RCU-safe.
> >
> > Feel free to create a list_for_each_entry_safe_rcu(), and I will be
> > happy to review it.
>
> Right. When using RCU, list_for_each_entry_safe_rcu() is not needed,
> because destruction of the element you removed doesn't happen until the
> end of a subsequent grace period. By which time you will be done with
> your RCU read-side critical section.
>
> So you can just use list_for_each_entry_rcu(), you do not need a new
> list_for_each_entry_safe_rcu().
>
> But you did have me going for a bit!!! ;-)
Just wondering Paul if you need to rest :)
list_for_each_entry_safe_rcu() is not needed not because of various (and
very intersting) reasons you gave !!!
But because list_for_each_entry_safe() is OK, since if we are in a
destroy phase, we are a writer, and can use regular list primitive.
Remember _rcu() versions of list iterators are for readers, and readers
are NOT supposed to delete an item from the list !
Eric
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
2010-04-02 15:58 ` Eric Dumazet
@ 2010-04-02 16:21 ` Paul E. McKenney
0 siblings, 0 replies; 32+ messages in thread
From: Paul E. McKenney @ 2010-04-02 16:21 UTC (permalink / raw)
To: Eric Dumazet; +Cc: James Chapman, Stephen Hemminger, netdev
On Fri, Apr 02, 2010 at 05:58:51PM +0200, Eric Dumazet wrote:
> Le vendredi 02 avril 2010 à 08:24 -0700, Paul E. McKenney a écrit :
> > On Wed, Mar 31, 2010 at 10:38:36AM -0700, Paul E. McKenney wrote:
>
> > > The list_is_last() is RCU-safe already, since the ->next pointer is
> > > only compared, never dereferenced. I suggest adding a comment to its
> > > header stating that it is RCU-safe.
> > >
> > > Feel free to create a list_for_each_entry_safe_rcu(), and I will be
> > > happy to review it.
> >
> > Right. When using RCU, list_for_each_entry_safe_rcu() is not needed,
> > because destruction of the element you removed doesn't happen until the
> > end of a subsequent grace period. By which time you will be done with
> > your RCU read-side critical section.
> >
> > So you can just use list_for_each_entry_rcu(), you do not need a new
> > list_for_each_entry_safe_rcu().
> >
> > But you did have me going for a bit!!! ;-)
>
> Just wondering Paul if you need to rest :)
In this case, I most certainly needed to have engaged my brain more
fully before hitting "send". :-/
> list_for_each_entry_safe_rcu() is not needed not because of various (and
> very intersting) reasons you gave !!!
>
> But because list_for_each_entry_safe() is OK, since if we are in a
> destroy phase, we are a writer, and can use regular list primitive.
>
> Remember _rcu() versions of list iterators are for readers, and readers
> are NOT supposed to delete an item from the list !
Yes, RCU readers had better have acquired the update-side lock before
modifying the list. And then there would be some debate as to whether
they were still readers. For example, while reading one list under RCU
protection, you might be modifying a subordinate list while holding the
corresponding lock.
And in the networking code, you would also need to convince the usual
suspects, including Eric, that upgrading to writer in the middle of an
RCU read-side critical section was the right thing to be doing in the
first place!
Thanx, Paul
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH v3 11/12] l2tp: Add support for static unmanaged L2TPv3 tunnels
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (9 preceding siblings ...)
2010-03-30 16:18 ` [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support James Chapman
@ 2010-03-30 16:18 ` James Chapman
2010-03-30 16:18 ` [PATCH v3 12/12] l2tp: Update documentation James Chapman
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:18 UTC (permalink / raw)
To: netdev
This patch adds support for static (unmanaged) L2TPv3 tunnels, where
the tunnel socket is created by the kernel rather than being created
by userspace. This means L2TP tunnels and sessions can be created
manually, without needing an L2TP control protocol implemented in
userspace. This might be useful where the user wants a simple ethernet
over IP tunnel.
A patch to iproute2 adds a new command set under "ip l2tp" to make use
of this feature. This will be submitted separately.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
net/l2tp/l2tp_core.c | 115 +++++++++++++++++++++++++++++++++++++++++++----
net/l2tp/l2tp_core.h | 7 +++
net/l2tp/l2tp_netlink.c | 18 ++++++-
3 files changed, 126 insertions(+), 14 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1dd9dc7..994e1d2 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1256,6 +1256,82 @@ void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
}
EXPORT_SYMBOL_GPL(l2tp_tunnel_free);
+/* Create a socket for the tunnel, if one isn't set up by
+ * userspace. This is used for static tunnels where there is no
+ * managing L2TP daemon.
+ */
+static int l2tp_tunnel_sock_create(u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp)
+{
+ int err = -EINVAL;
+ struct sockaddr_in udp_addr;
+ struct sockaddr_l2tpip ip_addr;
+ struct socket *sock;
+
+ switch (cfg->encap) {
+ case L2TP_ENCAPTYPE_UDP:
+ err = sock_create(AF_INET, SOCK_DGRAM, 0, sockp);
+ if (err < 0)
+ goto out;
+
+ sock = *sockp;
+
+ memset(&udp_addr, 0, sizeof(udp_addr));
+ udp_addr.sin_family = AF_INET;
+ udp_addr.sin_addr = cfg->local_ip;
+ udp_addr.sin_port = htons(cfg->local_udp_port);
+ err = kernel_bind(sock, (struct sockaddr *) &udp_addr, sizeof(udp_addr));
+ if (err < 0)
+ goto out;
+
+ udp_addr.sin_family = AF_INET;
+ udp_addr.sin_addr = cfg->peer_ip;
+ udp_addr.sin_port = htons(cfg->peer_udp_port);
+ err = kernel_connect(sock, (struct sockaddr *) &udp_addr, sizeof(udp_addr), 0);
+ if (err < 0)
+ goto out;
+
+ if (!cfg->use_udp_checksums)
+ sock->sk->sk_no_check = UDP_CSUM_NOXMIT;
+
+ break;
+
+ case L2TP_ENCAPTYPE_IP:
+ err = sock_create(AF_INET, SOCK_DGRAM, IPPROTO_L2TP, sockp);
+ if (err < 0)
+ goto out;
+
+ sock = *sockp;
+
+ memset(&ip_addr, 0, sizeof(ip_addr));
+ ip_addr.l2tp_family = AF_INET;
+ ip_addr.l2tp_addr = cfg->local_ip;
+ ip_addr.l2tp_conn_id = tunnel_id;
+ err = kernel_bind(sock, (struct sockaddr *) &ip_addr, sizeof(ip_addr));
+ if (err < 0)
+ goto out;
+
+ ip_addr.l2tp_family = AF_INET;
+ ip_addr.l2tp_addr = cfg->peer_ip;
+ ip_addr.l2tp_conn_id = peer_tunnel_id;
+ err = kernel_connect(sock, (struct sockaddr *) &ip_addr, sizeof(ip_addr), 0);
+ if (err < 0)
+ goto out;
+
+ break;
+
+ default:
+ goto out;
+ }
+
+out:
+ if ((err < 0) && sock) {
+ sock_release(sock);
+ *sockp = NULL;
+ }
+
+ return err;
+}
+
int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp)
{
struct l2tp_tunnel *tunnel = NULL;
@@ -1266,14 +1342,21 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP;
/* Get the tunnel socket from the fd, which was opened by
- * the userspace L2TP daemon.
+ * the userspace L2TP daemon. If not specified, create a
+ * kernel socket.
*/
- err = -EBADF;
- sock = sockfd_lookup(fd, &err);
- if (!sock) {
- printk(KERN_ERR "tunl %hu: sockfd_lookup(fd=%d) returned %d\n",
- tunnel_id, fd, err);
- goto err;
+ if (fd < 0) {
+ err = l2tp_tunnel_sock_create(tunnel_id, peer_tunnel_id, cfg, &sock);
+ if (err < 0)
+ goto err;
+ } else {
+ err = -EBADF;
+ sock = sockfd_lookup(fd, &err);
+ if (!sock) {
+ printk(KERN_ERR "tunl %hu: sockfd_lookup(fd=%d) returned %d\n",
+ tunnel_id, fd, err);
+ goto err;
+ }
}
sk = sock->sk;
@@ -1366,7 +1449,10 @@ err:
if (tunnelp)
*tunnelp = tunnel;
- if (sock)
+ /* If tunnel's socket was created by the kernel, it doesn't
+ * have a file.
+ */
+ if (sock && sock->file)
sockfd_put(sock);
return err;
@@ -1378,13 +1464,22 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
{
int err = 0;
+ struct socket *sock = tunnel->sock ? tunnel->sock->sk_socket : NULL;
/* Force the tunnel socket to close. This will eventually
* cause the tunnel to be deleted via the normal socket close
* mechanisms when userspace closes the tunnel socket.
*/
- if ((tunnel->sock != NULL) && (tunnel->sock->sk_socket != NULL))
- err = inet_shutdown(tunnel->sock->sk_socket, 2);
+ if (sock != NULL) {
+ err = inet_shutdown(sock, 2);
+
+ /* If the tunnel's socket was created by the kernel,
+ * close the socket here since the socket was not
+ * created by userspace.
+ */
+ if (sock->file == NULL)
+ err = inet_release(sock);
+ }
return err;
}
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index c5f2cc9..7e3387b 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -146,6 +146,13 @@ struct l2tp_tunnel_cfg {
int debug; /* bitmask of debug message
* categories */
enum l2tp_encap_type encap;
+
+ /* Used only for kernel-created sockets */
+ struct in_addr local_ip;
+ struct in_addr peer_ip;
+ u16 local_udp_port;
+ u16 peer_udp_port;
+ int use_udp_checksums:1;
};
struct l2tp_tunnel {
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index e051c13..115ea01 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -129,11 +129,21 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
}
cfg.encap = nla_get_u16(info->attrs[L2TP_ATTR_ENCAP_TYPE]);
- if (!info->attrs[L2TP_ATTR_FD]) {
- ret = -EINVAL;
- goto out;
+ fd = -1;
+ if (info->attrs[L2TP_ATTR_FD]) {
+ fd = nla_get_u32(info->attrs[L2TP_ATTR_FD]);
+ } else {
+ if (info->attrs[L2TP_ATTR_IP_SADDR])
+ cfg.local_ip.s_addr = nla_get_be32(info->attrs[L2TP_ATTR_IP_SADDR]);
+ if (info->attrs[L2TP_ATTR_IP_DADDR])
+ cfg.peer_ip.s_addr = nla_get_be32(info->attrs[L2TP_ATTR_IP_DADDR]);
+ if (info->attrs[L2TP_ATTR_UDP_SPORT])
+ cfg.local_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_SPORT]);
+ if (info->attrs[L2TP_ATTR_UDP_DPORT])
+ cfg.peer_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_DPORT]);
+ if (info->attrs[L2TP_ATTR_UDP_CSUM])
+ cfg.use_udp_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_CSUM]);
}
- fd = nla_get_u32(info->attrs[L2TP_ATTR_FD]);
if (info->attrs[L2TP_ATTR_DEBUG])
cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v3 12/12] l2tp: Update documentation
2010-03-30 16:17 [PATCH v3 00/12] l2tp: Introduce L2TPv3 support James Chapman
` (10 preceding siblings ...)
2010-03-30 16:18 ` [PATCH v3 11/12] l2tp: Add support for static unmanaged L2TPv3 tunnels James Chapman
@ 2010-03-30 16:18 ` James Chapman
11 siblings, 0 replies; 32+ messages in thread
From: James Chapman @ 2010-03-30 16:18 UTC (permalink / raw)
To: netdev
This patch adds documentation about the L2TPv3 functionality.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
Documentation/networking/l2tp.txt | 233 ++++++++++++++++++++++++++++++++-----
1 files changed, 199 insertions(+), 34 deletions(-)
diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt
index 63214b2..8b5a7b7 100644
--- a/Documentation/networking/l2tp.txt
+++ b/Documentation/networking/l2tp.txt
@@ -1,44 +1,95 @@
-This brief document describes how to use the kernel's PPPoL2TP driver
-to provide L2TP functionality. L2TP is a protocol that tunnels one or
-more PPP sessions over a UDP tunnel. It is commonly used for VPNs
+This document describes how to use the kernel's L2TP drivers to
+provide L2TP functionality. L2TP is a protocol that tunnels one or
+more sessions over an IP tunnel. It is commonly used for VPNs
(L2TP/IPSec) and by ISPs to tunnel subscriber PPP sessions over an IP
-network infrastructure.
+network infrastructure. With L2TPv3, it is also useful as a Layer-2
+tunneling infrastructure.
+
+Features
+========
+
+L2TPv2 (PPP over L2TP (UDP tunnels)).
+L2TPv3 ethernet pseudowires.
+L2TPv3 PPP pseudowires.
+L2TPv3 IP encapsulation.
+Netlink sockets for L2TPv3 configuration management.
+
+History
+=======
+
+The original pppol2tp driver was introduced in 2.6.23 and provided
+L2TPv2 functionality (rfc2661). L2TPv2 is used to tunnel one or more PPP
+sessions over a UDP tunnel.
+
+L2TPv3 (rfc3931) changes the protocol to allow different frame types
+to be passed over an L2TP tunnel by moving the PPP-specific parts of
+the protocol out of the core L2TP packet headers. Each frame type is
+known as a pseudowire type. Ethernet, PPP, HDLC, Frame Relay and ATM
+pseudowires for L2TP are defined in separate RFC standards. Another
+change for L2TPv3 is that it can be carried directly over IP with no
+UDP header (UDP is optional). It is also possible to create static
+unmanaged L2TPv3 tunnels manually without a control protocol
+(userspace daemon) to manage them.
+
+To support L2TPv3, the original pppol2tp driver was split up to
+separate the L2TP and PPP functionality. Existing L2TPv2 userspace
+apps should be unaffected as the original pppol2tp sockets API is
+retained. L2TPv3, however, uses netlink to manage L2TPv3 tunnels and
+sessions.
Design
======
-The PPPoL2TP driver, drivers/net/pppol2tp.c, provides a mechanism by
-which PPP frames carried through an L2TP session are passed through
-the kernel's PPP subsystem. The standard PPP daemon, pppd, handles all
-PPP interaction with the peer. PPP network interfaces are created for
-each local PPP endpoint.
-
-The L2TP protocol http://www.faqs.org/rfcs/rfc2661.html defines L2TP
-control and data frames. L2TP control frames carry messages between
-L2TP clients/servers and are used to setup / teardown tunnels and
-sessions. An L2TP client or server is implemented in userspace and
-will use a regular UDP socket per tunnel. L2TP data frames carry PPP
-frames, which may be PPP control or PPP data. The kernel's PPP
+The L2TP protocol separates control and data frames. The L2TP kernel
+drivers handle only L2TP data frames; control frames are always
+handled by userspace. L2TP control frames carry messages between L2TP
+clients/servers and are used to setup / teardown tunnels and
+sessions. An L2TP client or server is implemented in userspace.
+
+Each L2TP tunnel is implemented using a UDP or L2TPIP socket; L2TPIP
+provides L2TPv3 IP encapsulation (no UDP) and is implemented using a
+new l2tpip socket family. The tunnel socket is typically created by
+userspace, though for unmanaged L2TPv3 tunnels, the socket can also be
+created by the kernel. Each L2TP session (pseudowire) gets a network
+interface instance. In the case of PPP, these interfaces are created
+indirectly by pppd using a pppol2tp socket. In the case of ethernet,
+the netdevice is created upon a netlink request to create an L2TPv3
+ethernet pseudowire.
+
+For PPP, the PPPoL2TP driver, net/l2tp/l2tp_ppp.c, provides a
+mechanism by which PPP frames carried through an L2TP session are
+passed through the kernel's PPP subsystem. The standard PPP daemon,
+pppd, handles all PPP interaction with the peer. PPP network
+interfaces are created for each local PPP endpoint. The kernel's PPP
subsystem arranges for PPP control frames to be delivered to pppd,
while data frames are forwarded as usual.
+For ethernet, the L2TPETH driver, net/l2tp/l2tp_eth.c, implements a
+netdevice driver, managing virtual ethernet devices, one per
+pseudowire. These interfaces can be managed using standard Linux tools
+such as "ip" and "ifconfig". If only IP frames are passed over the
+tunnel, the interface can be given an IP addresses of itself and its
+peer. If non-IP frames are to be passed over the tunnel, the interface
+can be added to a bridge using brctl. All L2TP datapath protocol
+functions are handled by the L2TP core driver.
+
Each tunnel and session within a tunnel is assigned a unique tunnel_id
and session_id. These ids are carried in the L2TP header of every
-control and data packet. The pppol2tp driver uses them to lookup
-internal tunnel and/or session contexts. Zero tunnel / session ids are
-treated specially - zero ids are never assigned to tunnels or sessions
-in the network. In the driver, the tunnel context keeps a pointer to
-the tunnel UDP socket. The session context keeps a pointer to the
-PPPoL2TP socket, as well as other data that lets the driver interface
-to the kernel PPP subsystem.
-
-Note that the pppol2tp kernel driver handles only L2TP data frames;
-L2TP control frames are simply passed up to userspace in the UDP
-tunnel socket. The kernel handles all datapath aspects of the
-protocol, including data packet resequencing (if enabled).
-
-There are a number of requirements on the userspace L2TP daemon in
-order to use the pppol2tp driver.
+control and data packet. (Actually, in L2TPv3, the tunnel_id isn't
+present in data frames - it is inferred from the IP connection on
+which the packet was received.) The L2TP driver uses the ids to lookup
+internal tunnel and/or session contexts to determine how to handle the
+packet. Zero tunnel / session ids are treated specially - zero ids are
+never assigned to tunnels or sessions in the network. In the driver,
+the tunnel context keeps a reference to the tunnel UDP or L2TPIP
+socket. The session context holds data that lets the driver interface
+to the kernel's network frame type subsystems, i.e. PPP, ethernet.
+
+Userspace Programming
+=====================
+
+For L2TPv2, there are a number of requirements on the userspace L2TP
+daemon in order to use the pppol2tp driver.
1. Use a UDP socket per tunnel.
@@ -86,6 +137,35 @@ In addition to the standard PPP ioctls, a PPPIOCGL2TPSTATS is provided
to retrieve tunnel and session statistics from the kernel using the
PPPoX socket of the appropriate tunnel or session.
+For L2TPv3, userspace must use the netlink API defined in
+include/linux/l2tp.h to manage tunnel and session contexts. The
+general procedure to create a new L2TP tunnel with one session is:-
+
+1. Open a GENL socket using L2TP_GENL_NAME for configuring the kernel
+ using netlink.
+
+2. Create a UDP or L2TPIP socket for the tunnel.
+
+3. Create a new L2TP tunnel using a L2TP_CMD_TUNNEL_CREATE
+ request. Set attributes according to desired tunnel parameters,
+ referencing the UDP or L2TPIP socket created in the previous step.
+
+4. Create a new L2TP session in the tunnel using a
+ L2TP_CMD_SESSION_CREATE request.
+
+The tunnel and all of its sessions are closed when the tunnel socket
+is closed. The netlink API may also be used to delete sessions and
+tunnels. Configuration and status info may be set or read using netlink.
+
+The L2TP driver also supports static (unmanaged) L2TPv3 tunnels. These
+are where there is no L2TP control message exchange with the peer to
+setup the tunnel; the tunnel is configured manually at each end of the
+tunnel. There is no need for an L2TP userspace application in this
+case -- the tunnel socket is created by the kernel and configured
+using parameters sent in the L2TP_CMD_TUNNEL_CREATE netlink
+request. The "ip" utility of iproute2 has commands for managing static
+L2TPv3 tunnels; do "ip l2tp help" for more information.
+
Debugging
=========
@@ -102,6 +182,55 @@ PPPOL2TP_MSG_CONTROL userspace - kernel interface
PPPOL2TP_MSG_SEQ sequence numbers handling
PPPOL2TP_MSG_DATA data packets
+If enabled, /proc/net/l2tp can be used to dump kernel state about L2TP
+tunnels and sessions. However, this should not be used by applications
+to obtain L2TP state because the file format is subject to
+change. Instead, use the netlink API.
+
+Unmanaged L2TPv3 Tunnels
+========================
+
+Some commercial L2TP products support unmanaged L2TPv3 ethernet
+tunnels, where there is no L2TP control protocol; tunnels are
+configured at each side manually. New commands are available in
+iproute2's ip utility to support this.
+
+To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1
+and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the
+tunnel endpoints:-
+
+# modprobe l2tp_eth
+# modprobe l2tp_netlink
+
+# ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \
+ udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2
+# ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1
+# ifconfig -a
+# ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0
+# ifconfig l2tpeth0 up
+
+Choose IP addresses to be the address of a local IP interface and that
+of the remote system. The IP addresses of the l2tpeth0 interface can be
+anything suitable.
+
+Repeat the above at the peer, with ports, tunnel/session ids and IP
+addresses reversed. The tunnel and session IDs can be any non-zero
+32-bit number, but the values must be reversed at the peer.
+
+Host 1 Host2
+udp_sport=5000 udp_sport=5001
+udp_dport=5001 udp_dport=5000
+tunnel_id=42 tunnel_id=45
+peer_tunnel_id=45 peer_tunnel_id=42
+session_id=128 session_id=5196755
+peer_session_id=5196755 peer_session_id=128
+
+When done at both ends of the tunnel, it should be possible to send
+data over the network. e.g.
+
+# ping 10.5.1.1
+
+
Sample Userspace Code
=====================
@@ -158,12 +287,48 @@ Sample Userspace Code
}
return 0;
+Internal Implementation
+=======================
+
+The driver keeps a struct l2tp_tunnel context per L2TP tunnel and a
+struct l2tp_session context for each session. The l2tp_tunnel is
+always associated with a UDP or L2TP/IP socket and keeps a list of
+sessions in the tunnel. The l2tp_session context keeps kernel state
+about the session. It has private data which is used for data specific
+to the session type. With L2TPv2, the session always carried PPP
+traffic. With L2TPv3, the session can also carry ethernet frames
+(ethernet pseudowire) or other data types such as ATM, HDLC or Frame
+Relay.
+
+When a tunnel is first opened, the reference count on the socket is
+increased using sock_hold(). This ensures that the kernel socket
+cannot be removed while L2TP's data structures reference it.
+
+Some L2TP sessions also have a socket (PPP pseudowires) while others
+do not (ethernet pseudowires). We can't use the socket reference count
+as the reference count for session contexts. The L2TP implementation
+therefore has its own internal reference counts on the session
+contexts.
+
+To Do
+=====
+
+Add L2TP tunnel switching support. This would route tunneled traffic
+from one L2TP tunnel into another. Specified in
+http://tools.ietf.org/html/draft-ietf-l2tpext-tunnel-switching-08
+
+Add L2TPv3 VLAN pseudowire support.
+
+Add L2TPv3 IP pseudowire support.
+
+Add L2TPv3 ATM pseudowire support.
+
Miscellaneous
-============
+=============
-The PPPoL2TP driver was developed as part of the OpenL2TP project by
+The L2TP drivers were developed as part of the OpenL2TP project by
Katalix Systems Ltd. OpenL2TP is a full-featured L2TP client / server,
designed from the ground up to have the L2TP datapath in the
kernel. The project also implemented the pppol2tp plugin for pppd
which allows pppd to use the kernel driver. Details can be found at
-http://openl2tp.sourceforge.net.
+http://www.openl2tp.org.
^ permalink raw reply related [flat|nested] 32+ messages in thread