* [PATCH net-next-2.6 v4 08/14] netlink: Export genl_lock() API for use by modules
From: James Chapman @ 2010-04-02 16:19 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
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
* [PATCH net-next-2.6 v4 05/14] l2tp: Add L2TPv3 protocol support
From: James Chapman @ 2010-04-02 16:18 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
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 | 532 +++++++++++++++++++++++++++++++++++++-------------
net/l2tp/l2tp_core.h | 54 ++++-
net/l2tp/l2tp_ppp.c | 21 ++
4 files changed, 484 insertions(+), 148 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 4b6da36..0eee1a6 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -65,6 +65,7 @@
#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
@@ -85,7 +86,7 @@
/* 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;
@@ -101,6 +102,8 @@ 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)
@@ -110,6 +113,40 @@ 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
@@ -124,13 +161,20 @@ 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) {
@@ -218,7 +262,7 @@ 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) {
@@ -259,6 +303,11 @@ 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);
}
@@ -291,8 +340,8 @@ 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));
@@ -306,8 +355,8 @@ 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));
@@ -352,100 +401,73 @@ 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
@@ -455,6 +477,18 @@ 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.
*
@@ -464,21 +498,40 @@ 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,
@@ -489,6 +542,7 @@ 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.
@@ -512,6 +566,7 @@ 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. "
@@ -521,11 +576,19 @@ 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))
@@ -564,8 +627,8 @@ 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));
@@ -586,7 +649,7 @@ 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++;
@@ -596,6 +659,111 @@ 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;
@@ -651,11 +819,11 @@ 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;
@@ -671,19 +839,51 @@ 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);
+ }
+
+ *((__be32 *) bufp) = htonl(l2h);
+ }
+ bufp += session->l2specific_len;
+ }
+ if (session->offset)
+ bufp += session->offset;
- BUG_ON(tunnel->version != L2TP_HDR_VER_2);
- l2tp_build_l2tpv2_header(tunnel, session, buf);
+ 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)
{
@@ -694,7 +894,7 @@ 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,
@@ -780,7 +980,7 @@ 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 */
@@ -791,7 +991,6 @@ 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));
@@ -911,6 +1110,14 @@ 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);
@@ -997,9 +1204,6 @@ 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;
@@ -1077,6 +1281,15 @@ 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);
@@ -1095,6 +1308,22 @@ 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;
@@ -1106,6 +1335,7 @@ 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);
@@ -1113,20 +1343,36 @@ 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.
*/
@@ -1142,6 +1388,16 @@ 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);
@@ -1159,6 +1415,7 @@ static __net_init int l2tp_init_net(struct net *net)
{
struct l2tp_net *pn;
int err;
+ int hash;
pn = kzalloc(sizeof(*pn), GFP_KERNEL);
if (!pn)
@@ -1167,6 +1424,11 @@ 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 2efe1a3..5c53eb2 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);
@@ -132,7 +170,6 @@ 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 */
@@ -178,7 +215,7 @@ 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);
extern struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
extern struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
@@ -187,14 +224,15 @@ 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 3ad290d..bee5b14 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -670,7 +670,7 @@ 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;
@@ -678,7 +678,6 @@ 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. */
@@ -999,7 +998,7 @@ 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
@@ -1375,6 +1374,8 @@ end:
/*****************************************************************************
* /proc filesystem for debug
+ * Since the original pppol2tp driver provided /proc/net/pppol2tp for
+ * L2TPv2, we dump only L2TPv2 tunnels and sessions here.
*****************************************************************************/
static unsigned int pppol2tp_net_id;
@@ -1391,14 +1392,24 @@ struct pppol2tp_seq_data {
static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
{
- pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx);
- pd->tunnel_idx++;
+ for (;;) {
+ pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx);
+ pd->tunnel_idx++;
+
+ if (pd->tunnel == NULL)
+ break;
+
+ /* Ignore L2TPv3 tunnels */
+ if (pd->tunnel->version < 3)
+ break;
+ }
}
static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
{
pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
pd->session_idx++;
+
if (pd->session == NULL) {
pd->session_idx = 0;
pppol2tp_next_tunnel(net, pd);
^ permalink raw reply related
* [PATCH net-next-2.6 v4 07/14] l2tp: Add L2TPv3 IP encapsulation (no UDP) support
From: James Chapman @ 2010-04-02 16:19 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
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 | 163 ++++++++----
net/l2tp/l2tp_core.h | 7 +
net/l2tp/l2tp_ip.c | 679 ++++++++++++++++++++++++++++++++++++++++++++++++++
net/l2tp/l2tp_ppp.c | 7 -
7 files changed, 850 insertions(+), 62 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 0eee1a6..1739d04 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -36,8 +36,10 @@
#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/l2tp.h>
#include <linux/hash.h>
#include <linux/sort.h>
#include <linux/file.h>
@@ -48,6 +50,7 @@
#include <net/ip.h>
#include <net/udp.h>
#include <net/xfrm.h>
+#include <net/protocol.h>
#include <asm/byteorder.h>
#include <asm/atomic.h>
@@ -849,15 +852,21 @@ 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) {
@@ -902,10 +911,11 @@ 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(" ...");
@@ -956,21 +966,23 @@ 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;
@@ -981,18 +993,8 @@ 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);
@@ -1001,29 +1003,48 @@ 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:
@@ -1053,9 +1074,15 @@ 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;
@@ -1168,6 +1195,7 @@ 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.
@@ -1182,18 +1210,27 @@ 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 */
@@ -1223,12 +1260,16 @@ 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;
@@ -1318,7 +1359,9 @@ 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;
}
}
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 5c53eb2..d239598 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 {
@@ -155,6 +160,7 @@ struct l2tp_session {
struct l2tp_tunnel_cfg {
int debug; /* bitmask of debug message
* categories */
+ enum l2tp_encap_type encap;
};
struct l2tp_tunnel {
@@ -170,6 +176,7 @@ 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 e5b5312..63fc62b 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
* [PATCH net-next-2.6 v4 06/14] l2tp: Update PPP-over-L2TP driver to work over L2TPv3
From: James Chapman @ 2010-04-02 16:18 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
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 bee5b14..e5b5312 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);
@@ -615,6 +600,7 @@ 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;
@@ -622,6 +608,10 @@ 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);
@@ -639,21 +629,40 @@ 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;
@@ -670,20 +679,21 @@ 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;
@@ -756,8 +766,7 @@ 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;
@@ -783,21 +792,40 @@ 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
* [PATCH net-next-2.6 v4 04/14] l2tp: Add ppp device name to L2TP ppp session data
From: James Chapman @ 2010-04-02 16:18 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
When dumping L2TP PPP sessions using /proc/net/pppol2tp, 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 | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index baac072..3ad290d 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1465,6 +1465,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
struct l2tp_session *session = v;
struct l2tp_tunnel *tunnel = session->tunnel;
struct pppol2tp_session *ps = l2tp_session_priv(session);
+ struct pppox_sock *po = pppox_sk(ps->sock);
u32 ip = 0;
u16 port = 0;
@@ -1499,6 +1500,9 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
(unsigned long long)session->stats.rx_packets,
(unsigned long long)session->stats.rx_bytes,
(unsigned long long)session->stats.rx_errors);
+
+ if (po)
+ seq_printf(m, " interface %s\n", ppp_dev_name(&po->chan));
}
static int pppol2tp_seq_show(struct seq_file *m, void *v)
^ permalink raw reply related
* [PATCH net-next-2.6 v4 03/14] ppp: Add ppp_dev_name() exported function
From: James Chapman @ 2010-04-02 16:18 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
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
* [PATCH net-next-2.6 v4 02/14] l2tp: Split pppol2tp patch into separate l2tp and ppp parts
From: James Chapman @ 2010-04-02 16:18 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
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 | 1227 ++++++++++++++++++++
net/l2tp/l2tp_core.h | 254 ++++
net/l2tp/l2tp_ppp.c | 1658 +++++++++++++++++++++++++++
net/l2tp/pppol2tp.c | 2680 -------------------------------------------
10 files changed, 3175 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 2cffcb8..a55bff2 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -3158,17 +3158,12 @@ 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 e10d55c..0d68b40 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 13ca77e..cb7bdc1 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..4b6da36
--- /dev/null
+++ b/net/l2tp/l2tp_core.c
@@ -0,0 +1,1227 @@
+/*
+ * 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/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 hash;
+ struct hlist_node *walk;
+ struct l2tp_session *session;
+ 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) {
+ read_unlock_bh(&tunnel->hlist_lock);
+ return session;
+ }
+ }
+ }
+
+ read_unlock_bh(&tunnel->hlist_lock);
+
+ return NULL;
+}
+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;
+ int count = 0;
+
+ read_lock_bh(&pn->l2tp_tunnel_list_lock);
+ list_for_each_entry(tunnel, &pn->l2tp_tunnel_list, list) {
+ if (++count > nth) {
+ 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_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);
+
+/*****************************************************************************
+ * Init and cleanup
+ *****************************************************************************/
+
+static __net_init int l2tp_init_net(struct net *net)
+{
+ struct l2tp_net *pn;
+ 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;
+
+ return 0;
+
+out:
+ kfree(pn);
+ return err;
+}
+
+static __net_exit void l2tp_exit_net(struct net *net)
+{
+ struct l2tp_net *pn;
+
+ 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),
+};
+
+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..2efe1a3
--- /dev/null
+++ b/net/l2tp/l2tp_core.h
@@ -0,0 +1,254 @@
+/*
+ * 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);
+
+ 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;
+
+ 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);
+extern struct l2tp_tunnel *l2tp_tunnel_find(struct net *net, u32 tunnel_id);
+extern struct l2tp_tunnel *l2tp_tunnel_find_nth(struct net *net, int nth);
+
+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..baac072
--- /dev/null
+++ b/net/l2tp/l2tp_ppp.c
@@ -0,0 +1,1658 @@
+/*****************************************************************************
+ * 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;
+}
+
+/*****************************************************************************
+ * /proc filesystem for debug
+ *****************************************************************************/
+
+static unsigned int pppol2tp_net_id;
+
+#ifdef CONFIG_PROC_FS
+
+struct pppol2tp_seq_data {
+ struct seq_net_private p;
+ int tunnel_idx; /* current tunnel */
+ int session_idx; /* index of session within current tunnel */
+ struct l2tp_tunnel *tunnel;
+ struct l2tp_session *session; /* NULL means get next tunnel */
+};
+
+static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd)
+{
+ pd->tunnel = l2tp_tunnel_find_nth(net, pd->tunnel_idx);
+ pd->tunnel_idx++;
+}
+
+static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd)
+{
+ pd->session = l2tp_session_find_nth(pd->tunnel, pd->session_idx);
+ pd->session_idx++;
+ if (pd->session == NULL) {
+ pd->session_idx = 0;
+ pppol2tp_next_tunnel(net, pd);
+ }
+}
+
+static void *pppol2tp_seq_start(struct seq_file *m, loff_t *offs)
+{
+ struct pppol2tp_seq_data *pd = SEQ_START_TOKEN;
+ loff_t pos = *offs;
+ struct net *net;
+
+ if (!pos)
+ goto out;
+
+ BUG_ON(m->private == NULL);
+ pd = m->private;
+ net = seq_file_net(m);
+
+ if (pd->tunnel == NULL)
+ pppol2tp_next_tunnel(net, pd);
+ else
+ pppol2tp_next_session(net, pd);
+
+ /* 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 l2tp_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 l2tp_session *session = v;
+ struct l2tp_tunnel *tunnel = session->tunnel;
+ struct pppol2tp_session *ps = l2tp_session_priv(session);
+ u32 ip = 0;
+ u16 port = 0;
+
+ if (tunnel->sock) {
+ struct inet_sock *inet = inet_sk(tunnel->sock);
+ ip = ntohl(inet->inet_saddr);
+ port = ntohs(inet->inet_sport);
+ }
+
+ seq_printf(m, " SESSION '%s' %08X/%d %04X/%04X -> "
+ "%04X/%04X %d %c\n",
+ session->name, ip, port,
+ tunnel->tunnel_id,
+ session->session_id,
+ tunnel->peer_tunnel_id,
+ session->peer_session_id,
+ ps->sock->sk_state,
+ (session == ps->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 */
+
+/*****************************************************************************
+ * Network namespace
+ *****************************************************************************/
+
+static __net_init int pppol2tp_init_net(struct net *net)
+{
+ struct proc_dir_entry *pde;
+ int err = 0;
+
+ pde = proc_net_fops_create(net, "pppol2tp", S_IRUGO, &pppol2tp_proc_fops);
+ if (!pde) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+out:
+ return err;
+}
+
+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,
+};
+
+/*****************************************************************************
+ * 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 = register_pernet_device(&pppol2tp_net_ops);
+ if (err)
+ goto out;
+
+ err = proto_register(&pppol2tp_sk_proto, 0);
+ if (err)
+ goto out_unregister_pppol2tp_pernet;
+
+ 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);
+out_unregister_pppol2tp_pernet:
+ unregister_pernet_device(&pppol2tp_net_ops);
+ goto out;
+}
+
+static void __exit pppol2tp_exit(void)
+{
+ unregister_pppox_proto(PX_PROTO_OL2TP);
+ proto_unregister(&pppol2tp_sk_proto);
+ unregister_pernet_device(&pppol2tp_net_ops);
+}
+
+module_init(pppol2tp_init);
+module_exit(pppol2tp_exit);
+
+MODULE_AUTHOR("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
* [PATCH net-next-2.6 v4 01/14] l2tp: Relocate pppol2tp driver to new net/l2tp directory
From: James Chapman @ 2010-04-02 16:18 UTC (permalink / raw)
To: netdev
In-Reply-To: <20100402161822.11367.70454.stgit@bert.katalix.com>
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 ba06c1c..f8444f4 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 a5eae27..13ca77e 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
* [PATCH net-next-2.6 v4 00/14] l2tp: Introduce L2TPv3 support
From: James Chapman @ 2010-04-02 16:18 UTC (permalink / raw)
To: netdev
This patch series adds L2TPv3 support. It splits the existing pppol2tp
driver to separate its L2TP and PPP parts, then adds new L2TPv3
functionality. The patches implement a new socket family for L2TPv3 IP
encapsulation, expose virtual netdevices for each L2TPv3 ethernet
pseudowire and add a netlink interface.
The following drivers are provided:-
l2tp_core - L2TP driver core. Always required.
l2tp_ppp - L2TP PPP (PPPoL2TP). L2TPv2 and L2TPv3.
l2tp_eth - L2TPv3 ethernet pseudowire.
l2tp_ip - L2TPv3 IP encapsulation.
l2tp_netlink - L2TPv3 netlink API.
l2tp_debugfs - L2TP debugfs files.
The combination of l2tp_core and l2tp_ppp provides
backwards-compatible L2TPv2 pppol2tp functionality. Userspace L2TPv2
applications using the existing pppol2tp driver should not need to
change.
The implementation is as I described in a previous posting to netdev,
archived at
http://marc.info/?l=linux-netdev&m=120845482320143&w=4. Unfortunately,
splitting the existing pppol2tp driver into l2tp_core and l2tp_ppp
makes the changes difficult to review. The split is needed to separate
PPP from L2TP, since in L2TPv3, protocols other than PPP can be
carried. I have organised the patches so that the split is done first,
with new features added in separate patches.
Relevant RFCs are:-
- http://www.ietf.org/rfc/rfc3931.txt (L2TPv3)
- http://www.ietf.org/rfc/rfc4719.txt (L2TPv3 ethernet pseudowire)
A patchset is available to iproute2 which adds a number of commands
for unmanaged L2TPv3 tunnels. This will be submitted separately.
TODO:-
- Add L2TP tunnel switching.
- Add IP pseudowires. These carry only IP frames (no L2 header).
- Add VLAN pseudowires.
- Add ATM pseudowires - RFC3355 and RFC4454.
Signed-off-by: James Chapman <jchapman@katalix.com>
Reviewed-by: Randy Dunlap <randy.dunlap@oracle.com>
---
Changelog:-
v4 (02-apr-2010, this version)
- Remove useless BUG_ON in l2tp_eth driver. (Stephen Hemminger)
- Use random_ether_addr() when deriving MAC address for virtual device
of each ethernet pseudowire instead of deriving one based on the
L2TP session id. (Stephen Hemminger)
- Convert per_net locks from rwlock to spinlock / rcu. (Stephen Hemminger)
- Rework /proc interface to move all new (L2TPv3 etc) debug info to
debugfs. Retain existing /proc file for backwards compability with
the old pppol2tp driver. Debugfs is added in a new patch. (Stephen
Hemminger, David Miller)
- Add new config option to enable the debugfs file(s) for l2tp.
- Change all flag parameters in the netlink API to u8. (Patrick McHardy)
- Update info about /proc and /debugfs in l2tp documentation.
v3 (31-mar-2010)
- Use hash_32() instead of hash_long() for better efficiency on 64-bit
archs (Eric Dumazet)
- Add missing setting of sk->sk_no_check for the case when creating
kernel socket for the unmanaged tunnel case. (Eric Dumazet)
- Fix a dev_put leak for the case when user creates an ethernet
pseudowire with a specific device name and a device with that name
already exists. (Eric Dumazet)
- Use dev_forward_skb() in receive path of l2tp_eth driver.
v2 (29-mar-2010)
- Fix compile error when CONFIG_COMPAT is defined. Since l2tp_ip is
not a UDP socket, use compat_ip_[gs]etsockopt directly instead of
config_udp_[gs]etsockopt. (David Miller)
- Fix whitespace issues found by
git apply --check --whitespace=error-all (David Miller)
James Chapman (14):
l2tp: Relocate pppol2tp driver to new net/l2tp directory
l2tp: Split pppol2tp patch into separate l2tp and ppp parts
ppp: Add ppp_dev_name() exported function
l2tp: Add ppp device name to L2TP ppp session data
l2tp: Add L2TPv3 protocol support
l2tp: Update PPP-over-L2TP driver to work over L2TPv3
l2tp: Add L2TPv3 IP encapsulation (no UDP) support
netlink: Export genl_lock() API for use by modules
l2tp: Add netlink control API for L2TP
l2tp: Convert rwlock to RCU
l2tp: Add L2TP ethernet pseudowire support
l2tp: Add debugfs files for dumping l2tp debug info
l2tp: Add support for static unmanaged L2TPv3 tunnels
l2tp: Update documentation
Documentation/networking/l2tp.txt | 247 +++
drivers/net/Kconfig | 7
drivers/net/Makefile | 2
drivers/net/ppp_generic.c | 19
drivers/net/pppol2tp.c | 2680 -------------------------------------
include/linux/genetlink.h | 8
include/linux/if_pppol2tp.h | 16
include/linux/if_pppox.h | 9
include/linux/l2tp.h | 163 ++
include/linux/ppp_channel.h | 3
net/Kconfig | 1
net/Makefile | 1
net/l2tp/Kconfig | 107 +
net/l2tp/Makefile | 12
net/l2tp/l2tp_core.c | 1692 +++++++++++++++++++++++
net/l2tp/l2tp_core.h | 304 ++++
net/l2tp/l2tp_debugfs.c | 341 +++++
net/l2tp/l2tp_eth.c | 361 +++++
net/l2tp/l2tp_ip.c | 679 +++++++++
net/l2tp/l2tp_netlink.c | 840 ++++++++++++
net/l2tp/l2tp_ppp.c | 1837 +++++++++++++++++++++++++
net/netlink/genetlink.c | 6
22 files changed, 6611 insertions(+), 2724 deletions(-)
delete mode 100644 drivers/net/pppol2tp.c
create mode 100644 include/linux/l2tp.h
create mode 100644 net/l2tp/Kconfig
create mode 100644 net/l2tp/Makefile
create mode 100644 net/l2tp/l2tp_core.c
create mode 100644 net/l2tp/l2tp_core.h
create mode 100644 net/l2tp/l2tp_debugfs.c
create mode 100644 net/l2tp/l2tp_eth.c
create mode 100644 net/l2tp/l2tp_ip.c
create mode 100644 net/l2tp/l2tp_netlink.c
create mode 100644 net/l2tp/l2tp_ppp.c
^ permalink raw reply
* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
From: Eric Dumazet @ 2010-04-02 15:58 UTC (permalink / raw)
To: paulmck; +Cc: James Chapman, Stephen Hemminger, netdev
In-Reply-To: <20100402152402.GA6017@linux.vnet.ibm.com>
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
* Re: [RFC] [PATCH v2 3/3] Let host NIC driver to DMA to guest user space.
From: Stephen Hemminger @ 2010-04-02 15:55 UTC (permalink / raw)
To: xiaohui.xin; +Cc: netdev, kvm, linux-kernel, mingo, mst, jdike, davem
In-Reply-To: <1270193410-6877-1-git-send-email-xiaohui.xin@intel.com>
On Fri, 2 Apr 2010 15:30:10 +0800
xiaohui.xin@intel.com wrote:
> From: Xin Xiaohui <xiaohui.xin@intel.com>
>
> The patch let host NIC driver to receive user space skb,
> then the driver has chance to directly DMA to guest user
> space buffers thru single ethX interface.
> We want it to be more generic as a zero copy framework.
>
> Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
> Signed-off-by: Zhao Yu <yzhao81@gmail.com>
> Sigend-off-by: Jeff Dike <jdike@c2.user-mode-linux.org>
> ---
>
> We consider 2 way to utilize the user buffres, but not sure which one
> is better. Please give any comments.
>
> One: Modify __alloc_skb() function a bit, it can only allocate a
> structure of sk_buff, and the data pointer is pointing to a
> user buffer which is coming from a page constructor API.
> Then the shinfo of the skb is also from guest.
> When packet is received from hardware, the skb->data is filled
> directly by h/w. What we have done is in this way.
>
> Pros: We can avoid any copy here.
> Cons: Guest virtio-net driver needs to allocate skb as almost
> the same method with the host NIC drivers, say the size
> of netdev_alloc_skb() and the same reserved space in the
> head of skb. Many NIC drivers are the same with guest and
> ok for this. But some lastest NIC drivers reserves special
> room in skb head. To deal with it, we suggest to provide
> a method in guest virtio-net driver to ask for parameter
> we interest from the NIC driver when we know which device
> we have bind to do zero-copy. Then we ask guest to do so.
> Is that reasonable?
>
> Two: Modify driver to get user buffer allocated from a page constructor
> API(to substitute alloc_page()), the user buffer are used as payload
> buffers and filled by h/w directly when packet is received. Driver
> should associate the pages with skb (skb_shinfo(skb)->frags). For
> the head buffer side, let host allocates skb, and h/w fills it.
> After that, the data filled in host skb header will be copied into
> guest header buffer which is submitted together with the payload buffer.
>
> Pros: We could less care the way how guest or host allocates their
> buffers.
> Cons: We still need a bit copy here for the skb header.
>
> We are not sure which way is the better here. This is the first thing we want
> to get comments from the community. We wish the modification to the network
> part will be generic which not used by vhost-net backend only, but a user
> application may use it as well when the zero-copy device may provides async
> read/write operations later.
>
>
> Thanks
> Xiaohui
How do you deal with the DoS problem of hostile user space app posting huge
number of receives and never getting anything.
^ permalink raw reply
* [PATCH] ethtool: add names of newer Marvell chips
From: Stephen Hemminger @ 2010-04-02 15:16 UTC (permalink / raw)
To: Jeff Garzik; +Cc: netdev
Fill in names of newer chips.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
diff --git a/marvell.c b/marvell.c
index 6696e0a..af38c21 100644
--- a/marvell.c
+++ b/marvell.c
@@ -184,6 +184,9 @@ static void dump_mac(const u8 *r)
case 0xb6: printf("Yukon-2 EC"); break;
case 0xb7: printf("Yukon-2 FE"); break;
case 0xb8: printf("Yukon-2 FE Plus"); break;
+ case 0xb9: printf("Yukon Supreme"); break;
+ case 0xba: printf("Yukon Ultra 2"); break;
+ case 0xbc: printf("Yukon Optima"); break;
default: printf("(Unknown)"); break;
}
--
1.6.3.3
^ permalink raw reply related
* [PATCH] ethtool: RXHASH flag support (v2)
From: Stephen Hemminger @ 2010-04-02 15:15 UTC (permalink / raw)
To: Jeff Garzik; +Cc: netdev
Add support for RXHASH flag in ethtool offload.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
---
ethtool-copy.h | 1 +
ethtool.8 | 4 ++++
ethtool.c | 39 ++++++++++++++++++++++++++++++++++-----
3 files changed, 39 insertions(+), 5 deletions(-)
diff --git a/ethtool-copy.h b/ethtool-copy.h
index a26dcbd..c5eb680 100644
--- a/ethtool-copy.h
+++ b/ethtool-copy.h
@@ -310,6 +310,7 @@ struct ethtool_perm_addr {
enum ethtool_flags {
ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */
ETH_FLAG_NTUPLE = (1 << 27), /* N-tuple filters enabled */
+ ETH_FLAG_RXHASH = (1 << 28),
};
/* The following structures are for supporting RX network flow
diff --git a/ethtool.8 b/ethtool.8
index eb6430b..a7b43d5 100644
--- a/ethtool.8
+++ b/ethtool.8
@@ -170,6 +170,7 @@ ethtool \- Display or change ethernet card settings
.B2 gso on off
.B2 gro on off
.B2 lro on off
+.B2 rxhash on off
.B ethtool \-p|\-\-identify
.I ethX
@@ -362,6 +363,9 @@ Specifies whether generic receive offload should be enabled
.A2 lro on off
Specifies whether large receive offload should be enabled
.TP
+.A2 rxhash on off
+Specifies whether receive hashing offload should be enabled
+.TP
.B \-p \-\-identify
Initiates adapter-specific action intended to enable an operator to
easily identify the adapter by sight. Typically this involves
diff --git a/ethtool.c b/ethtool.c
index 8550ba2..4226a67 100644
--- a/ethtool.c
+++ b/ethtool.c
@@ -173,6 +173,7 @@ static struct option {
" [ gro on|off ]\n"
" [ lro on|off ]\n"
" [ ntuple on|off ]\n"
+ " [ rxhash on|off ]\n"
},
{ "-i", "--driver", MODE_GDRV, "Show driver information" },
{ "-d", "--register-dump", MODE_GREGS, "Do a register dump",
@@ -257,6 +258,7 @@ static int off_gso_wanted = -1;
static int off_lro_wanted = -1;
static int off_gro_wanted = -1;
static int off_ntuple_wanted = -1;
+static int off_rxhash_wanted = -1;
static struct ethtool_pauseparam epause;
static int gpause_changed = 0;
@@ -382,6 +384,7 @@ static struct cmdline_info cmdline_offload[] = {
{ "lro", CMDL_BOOL, &off_lro_wanted, NULL },
{ "gro", CMDL_BOOL, &off_gro_wanted, NULL },
{ "ntuple", CMDL_BOOL, &off_ntuple_wanted, NULL },
+ { "rxhash", CMDL_BOOL, &off_rxhash_wanted, NULL },
};
static struct cmdline_info cmdline_pause[] = {
@@ -1526,7 +1529,7 @@ static int dump_coalesce(void)
}
static int dump_offload(int rx, int tx, int sg, int tso, int ufo, int gso,
- int gro, int lro, int ntuple)
+ int gro, int lro, int ntuple, int rxhash)
{
fprintf(stdout,
"rx-checksumming: %s\n"
@@ -1537,7 +1540,8 @@ static int dump_offload(int rx, int tx, int sg, int tso, int ufo, int gso,
"generic-segmentation-offload: %s\n"
"generic-receive-offload: %s\n"
"large-receive-offload: %s\n"
- "ntuple-filters: %s\n",
+ "ntuple-filters: %s\n"
+ "receive-hashing: %s\n",
rx ? "on" : "off",
tx ? "on" : "off",
sg ? "on" : "off",
@@ -1546,7 +1550,8 @@ static int dump_offload(int rx, int tx, int sg, int tso, int ufo, int gso,
gso ? "on" : "off",
gro ? "on" : "off",
lro ? "on" : "off",
- ntuple ? "on" : "off");
+ ntuple ? "on" : "off",
+ rxhash ? "on" : "off");
return 0;
}
@@ -1863,7 +1868,7 @@ static int do_goffload(int fd, struct ifreq *ifr)
{
struct ethtool_value eval;
int err, allfail = 1, rx = 0, tx = 0, sg = 0;
- int tso = 0, ufo = 0, gso = 0, gro = 0, lro = 0, ntuple = 0;
+ int tso = 0, ufo = 0, gso = 0, gro = 0, lro = 0, ntuple = 0, rxhash = 0;
fprintf(stdout, "Offload parameters for %s:\n", devname);
@@ -1935,6 +1940,7 @@ static int do_goffload(int fd, struct ifreq *ifr)
} else {
lro = (eval.data & ETH_FLAG_LRO) != 0;
ntuple = (eval.data & ETH_FLAG_NTUPLE) != 0;
+ rxhash = (eval.data & ETH_FLAG_RXHASH) != 0;
allfail = 0;
}
@@ -1953,7 +1959,7 @@ static int do_goffload(int fd, struct ifreq *ifr)
return 83;
}
- return dump_offload(rx, tx, sg, tso, ufo, gso, gro, lro, ntuple);
+ return dump_offload(rx, tx, sg, tso, ufo, gso, gro, lro, ntuple, rxhash);
}
static int do_soffload(int fd, struct ifreq *ifr)
@@ -2087,6 +2093,29 @@ static int do_soffload(int fd, struct ifreq *ifr)
return 93;
}
}
+ if (off_rxhash_wanted >= 0) {
+ changed = 1;
+ eval.cmd = ETHTOOL_GFLAGS;
+ eval.data = 0;
+ ifr->ifr_data = (caddr_t)&eval;
+ err = ioctl(fd, SIOCETHTOOL, ifr);
+ if (err) {
+ perror("Cannot get device flag settings");
+ return 91;
+ }
+
+ eval.cmd = ETHTOOL_SFLAGS;
+ if (off_rxhash_wanted)
+ eval.data |= ETH_FLAG_RXHASH;
+ else
+ eval.data &= ~ETH_FLAG_RXHASH;
+
+ err = ioctl(fd, SIOCETHTOOL, ifr);
+ if (err) {
+ perror("Cannot set receive hash settings");
+ return 93;
+ }
+ }
if (!changed) {
fprintf(stdout, "no offload settings changed\n");
--
1.6.3.3
^ permalink raw reply related
* Re: [PATCH 1/2] phylib: Support phy module autoloading
From: Ben Hutchings @ 2010-04-02 15:51 UTC (permalink / raw)
To: David Woodhouse; +Cc: David Miller, netdev, 553024
In-Reply-To: <1270206895.3101.2467.camel@macbook.infradead.org>
[-- Attachment #1: Type: text/plain, Size: 749 bytes --]
On Fri, 2010-04-02 at 12:14 +0100, David Woodhouse wrote:
> On Thu, 2010-04-01 at 19:38 -0700, David Miller wrote:
> > Whatever you submit
> > next I'd like to toss into net-next-2.6 so it can cook for a while
> > and maybe we'll backport it so that this bug can be fixed for good
> > upstream and then perhaps even in -stable.
>
> When backporting, note that you'll need s/PHY_ID_BCMAC131/0x0143bc70/ in
> the patch to broadcom.c, because 2.6.32 didn't have a definition for
> that.
>
> There's also trivial change in phy_device_create() which will make the
> patch fail to apply, but git-cherry-pick copes.
Thanks again, David.
Ben.
--
Ben Hutchings
Once a job is fouled up, anything done to improve it makes it worse.
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 828 bytes --]
^ permalink raw reply
* Re: [PATCH v3 10/12] l2tp: Add L2TP ethernet pseudowire support
From: Paul E. McKenney @ 2010-04-02 15:24 UTC (permalink / raw)
To: James Chapman; +Cc: Stephen Hemminger, netdev
In-Reply-To: <20100331173836.GG2461@linux.vnet.ibm.com>
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
* Re: [PATCH 0/4] caching bundles, iteration 3
From: Herbert Xu @ 2010-04-02 13:12 UTC (permalink / raw)
To: David Miller; +Cc: timo.teras, netdev
In-Reply-To: <20100401.200042.206653087.davem@davemloft.net>
On Thu, Apr 01, 2010 at 08:00:42PM -0700, David Miller wrote:
>
> I'm kind of burnt out on patch review for today, so I hope Herbert
> can take a look at this when he wakes up.
I've been busy with dash stuff today, but I should be able to
review them tomorrow.
Cheers,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH] r8169: Fix rtl8169_rx_interrupt()
From: Eric Dumazet @ 2010-04-02 13:51 UTC (permalink / raw)
To: David Miller; +Cc: sergey.senozhatsky, oleg, romieu, netdev
In-Reply-To: <20100401.184345.85529643.davem@davemloft.net>
Le jeudi 01 avril 2010 à 18:43 -0700, David Miller a écrit :
> Applied to net-next-2.6, but:
>
> > +/*
> > + * Warning : rtl8169_rx_interrupt() might be called :
> > + * 1) from NAPI (softirq) context
> > + * (polling = 1 : we should call netif_receive_skb())
> > + * 2) from process context (rtl8169_reset_task())
> > + * (polling = 0 : we must call netif_rx() instead)
> > + */
> ^^^^^^^^
>
> Trailing whitespace I had to delete.
Thanks David
^ permalink raw reply
* Re: [PATCH] rfs: Receive Flow Steering
From: Changli Gao @ 2010-04-02 13:45 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Tom Herbert, davem, netdev
In-Reply-To: <1270209708.1989.30.camel@edumazet-laptop>
On Fri, Apr 2, 2010 at 8:01 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Le vendredi 02 avril 2010 à 18:58 +0800, Changli Gao a écrit :
>
> This dispatch things in UserLand is a poor workaround even if its
> popular (because people try to code portable applications), the hard
> work is already done, this increases latencies and bus traffic.
>
> For short works, that is too expensive.
I'll write a sample program to verify it. For TCP progam, I think it
won't be too expensive.
>
> If you really want to speedup memcached/DNS_server like apps, you might
> add a generic mechanism in kernel to split queues of _individual_
> socket.
>
> Aka multiqueue capabilities at socket level. Combined to multiqueue
> devices or RPS, this can be great.
>
>
> That is, an application tells kernel in how many queues incoming UDP
> frames for a given port can be dispatched (number of worker threads)
> No more contention, and this can be done regardless of RPS/RFS.
>
> UDP frame comes in, and is stored on the appropriate sub-queue (can be a
> mapping given by current cpu number). Wakeup the thread that is likely
> running on same cpu.
>
> Same for outgoing frames (answers). You might split the sk_wmemalloc
> thing to make sure several cpus can concurrently use same UDP socket to
> send their frames.
>
Yea. It much likes my another idea: selective wakeup. Always try to
wake up the sleeping process which is likely running on the same cpu.
--
Regards，
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH] rfs: Receive Flow Steering
From: Eric Dumazet @ 2010-04-02 12:37 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, netdev
In-Reply-To: <1270197304.1936.179.camel@edumazet-laptop>
> > +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
> > + u32 hash)
> > +{
>
> Hmm, so rps_record_sock_flow() is always called from non preemptable
> contextes ?
>
> > + rps_set_sock_flow(table, hash, smp_processor_id());
> > +}
> > +
I had to change this to :
static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, u32 hash)
{
/* we only give a hint, preemption can change our cpu under us */
rps_set_sock_flow(table, hash, raw_smp_processor_id());
}
^ permalink raw reply
* Re: [PATCH] rfs: Receive Flow Steering
From: Eric Dumazet @ 2010-04-02 12:01 UTC (permalink / raw)
To: Changli Gao; +Cc: Tom Herbert, davem, netdev
In-Reply-To: <o2j412e6f7f1004020358mf9455fcbqdbb2d762d94a7aa2@mail.gmail.com>
Le vendredi 02 avril 2010 à 18:58 +0800, Changli Gao a écrit :
> Yes, it is more complex. Some high performance server use the
> event-driven model, such as memcached, nginx and lighttpd. This model
> has high performance on UP with no doubt, and on SMP they usually use
> one individual epoll fd for each Core/CPU, and the acceptor dispatches
> works among these epoll fds. This program model is popular, and it
> bypass the system scheduler. I think the socket option SO_RPSCPU can
> help this kind of applications work better, why not do that?
> Compatility with other Unixes isn't a good cause, for high performance
> applications, there are always lots of OS special features used. For
> example: epoll vs kqueue, tcp defer accept vs accept filter.
>
>
This dispatch things in UserLand is a poor workaround even if its
popular (because people try to code portable applications), the hard
work is already done, this increases latencies and bus traffic.
For short works, that is too expensive.
If you really want to speedup memcached/DNS_server like apps, you might
add a generic mechanism in kernel to split queues of _individual_
socket.
Aka multiqueue capabilities at socket level. Combined to multiqueue
devices or RPS, this can be great.
That is, an application tells kernel in how many queues incoming UDP
frames for a given port can be dispatched (number of worker threads)
No more contention, and this can be done regardless of RPS/RFS.
UDP frame comes in, and is stored on the appropriate sub-queue (can be a
mapping given by current cpu number). Wakeup the thread that is likely
running on same cpu.
Same for outgoing frames (answers). You might split the sk_wmemalloc
thing to make sure several cpus can concurrently use same UDP socket to
send their frames.
^ permalink raw reply
* Re: [PATCH 1/2] phylib: Support phy module autoloading
From: David Woodhouse @ 2010-04-02 11:14 UTC (permalink / raw)
To: David Miller; +Cc: ben, netdev, 553024
In-Reply-To: <20100401.193810.172601735.davem@davemloft.net>
On Thu, 2010-04-01 at 19:38 -0700, David Miller wrote:
> Whatever you submit
> next I'd like to toss into net-next-2.6 so it can cook for a while
> and maybe we'll backport it so that this bug can be fixed for good
> upstream and then perhaps even in -stable.
When backporting, note that you'll need s/PHY_ID_BCMAC131/0x0143bc70/ in
the patch to broadcom.c, because 2.6.32 didn't have a definition for
that.
There's also trivial change in phy_device_create() which will make the
patch fail to apply, but git-cherry-pick copes.
--
David Woodhouse Open Source Technology Centre
David.Woodhouse@intel.com Intel Corporation
^ permalink raw reply
* [PATCH 2/2] phylib: Add module table to all existing phy drivers
From: David Woodhouse @ 2010-04-02 11:05 UTC (permalink / raw)
To: davem; +Cc: netdev, ben
In-Reply-To: <20100401.193810.172601735.davem@davemloft.net>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
s/phy/mdio/
drivers/net/phy/bcm63xx.c | 8 ++++++++
drivers/net/phy/broadcom.c | 16 ++++++++++++++++
drivers/net/phy/cicada.c | 8 ++++++++
drivers/net/phy/davicom.c | 9 +++++++++
drivers/net/phy/et1011c.c | 7 +++++++
drivers/net/phy/icplus.c | 7 +++++++
drivers/net/phy/lxt.c | 8 ++++++++
drivers/net/phy/marvell.c | 13 +++++++++++++
drivers/net/phy/national.c | 7 +++++++
drivers/net/phy/qsemi.c | 7 +++++++
drivers/net/phy/realtek.c | 7 +++++++
drivers/net/phy/smsc.c | 11 +++++++++++
drivers/net/phy/ste10Xp.c | 8 ++++++++
drivers/net/phy/vitesse.c | 8 ++++++++
14 files changed, 124 insertions(+), 0 deletions(-)
diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index 4fed95e..ac5e498 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -130,3 +130,11 @@ static void __exit bcm63xx_phy_exit(void)
module_init(bcm63xx_phy_init);
module_exit(bcm63xx_phy_exit);
+
+static struct mdio_device_id bcm63xx_tbl[] = {
+ { 0x00406000, 0xfffffc00 },
+ { 0x002bdc00, 0xfffffc00 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, bcm64xx_tbl);
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index f482fc4..cecdbbd 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -908,3 +908,19 @@ static void __exit broadcom_exit(void)
module_init(broadcom_init);
module_exit(broadcom_exit);
+
+static struct mdio_device_id broadcom_tbl[] = {
+ { 0x00206070, 0xfffffff0 },
+ { 0x002060e0, 0xfffffff0 },
+ { 0x002060c0, 0xfffffff0 },
+ { 0x002060b0, 0xfffffff0 },
+ { 0x0143bca0, 0xfffffff0 },
+ { 0x0143bcb0, 0xfffffff0 },
+ { PHY_ID_BCM50610, 0xfffffff0 },
+ { PHY_ID_BCM50610M, 0xfffffff0 },
+ { PHY_ID_BCM57780, 0xfffffff0 },
+ { PHY_ID_BCMAC131, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, broadcom_tbl);
diff --git a/drivers/net/phy/cicada.c b/drivers/net/phy/cicada.c
index a1bd599..efc608f 100644
--- a/drivers/net/phy/cicada.c
+++ b/drivers/net/phy/cicada.c
@@ -159,3 +159,11 @@ static void __exit cicada_exit(void)
module_init(cicada_init);
module_exit(cicada_exit);
+
+static struct mdio_device_id cicada_tbl[] = {
+ { 0x000fc410, 0x000ffff0 },
+ { 0x000fc440, 0x000fffc0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, cicada_tbl);
diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c
index d926168..e02b18c 100644
--- a/drivers/net/phy/davicom.c
+++ b/drivers/net/phy/davicom.c
@@ -219,3 +219,12 @@ static void __exit davicom_exit(void)
module_init(davicom_init);
module_exit(davicom_exit);
+
+static struct mdio_device_id davicom_tbl[] = {
+ { 0x0181b880, 0x0ffffff0 },
+ { 0x0181b8a0, 0x0ffffff0 },
+ { 0x00181b80, 0x0ffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, davicom_tbl);
diff --git a/drivers/net/phy/et1011c.c b/drivers/net/phy/et1011c.c
index b031fa2..500f0fd 100644
--- a/drivers/net/phy/et1011c.c
+++ b/drivers/net/phy/et1011c.c
@@ -111,3 +111,10 @@ static void __exit et1011c_exit(void)
module_init(et1011c_init);
module_exit(et1011c_exit);
+
+static struct mdio_device_id et1011c_tbl[] = {
+ { 0x0282f014, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, et1011c_tbl);
diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c
index af3f1f2..e661e90 100644
--- a/drivers/net/phy/icplus.c
+++ b/drivers/net/phy/icplus.c
@@ -132,3 +132,10 @@ static void __exit ip175c_exit(void)
module_init(ip175c_init);
module_exit(ip175c_exit);
+
+static struct mdio_device_id icplus_tbl[] = {
+ { 0x02430d80, 0x0ffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, icplus_tbl);
diff --git a/drivers/net/phy/lxt.c b/drivers/net/phy/lxt.c
index 4cf3324..1d94f1d 100644
--- a/drivers/net/phy/lxt.c
+++ b/drivers/net/phy/lxt.c
@@ -174,3 +174,11 @@ static void __exit lxt_exit(void)
module_init(lxt_init);
module_exit(lxt_exit);
+
+static struct mdio_device_id lxt_tbl[] = {
+ { 0x78100000, 0xfffffff0 },
+ { 0x001378e0, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, lxt_tbl);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 65ed385..c7e5b9f 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -649,3 +649,16 @@ static void __exit marvell_exit(void)
module_init(marvell_init);
module_exit(marvell_exit);
+
+static struct mdio_device_id marvell_tbl[] = {
+ { 0x01410c60, 0xfffffff0 },
+ { 0x01410c90, 0xfffffff0 },
+ { 0x01410cc0, 0xfffffff0 },
+ { 0x01410e10, 0xfffffff0 },
+ { 0x01410cb0, 0xfffffff0 },
+ { 0x01410cd0, 0xfffffff0 },
+ { 0x01410e30, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, marvell_tbl);
diff --git a/drivers/net/phy/national.c b/drivers/net/phy/national.c
index 6c636eb..729ab29 100644
--- a/drivers/net/phy/national.c
+++ b/drivers/net/phy/national.c
@@ -153,3 +153,10 @@ MODULE_LICENSE("GPL");
module_init(ns_init);
module_exit(ns_exit);
+
+static struct mdio_device_id ns_tbl[] = {
+ { DP83865_PHY_ID, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, ns_tbl);
diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c
index 23062d0..3ec9610 100644
--- a/drivers/net/phy/qsemi.c
+++ b/drivers/net/phy/qsemi.c
@@ -138,3 +138,10 @@ static void __exit qs6612_exit(void)
module_init(qs6612_init);
module_exit(qs6612_exit);
+
+static struct mdio_device_id qs6612_tbl[] = {
+ { 0x00181440, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, qs6612_tbl);
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index a052a67..f567c0e 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -78,3 +78,10 @@ static void __exit realtek_exit(void)
module_init(realtek_init);
module_exit(realtek_exit);
+
+static struct mdio_device_id realtek_tbl[] = {
+ { 0x001cc912, 0x001fffff },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, realtek_tbl);
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index ed2644a..78fa988 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -253,3 +253,14 @@ MODULE_LICENSE("GPL");
module_init(smsc_init);
module_exit(smsc_exit);
+
+static struct mdio_device_id smsc_tbl[] = {
+ { 0x0007c0a0, 0xfffffff0 },
+ { 0x0007c0b0, 0xfffffff0 },
+ { 0x0007c0c0, 0xfffffff0 },
+ { 0x0007c0d0, 0xfffffff0 },
+ { 0x0007c0f0, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, smsc_tbl);
diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c
index 6bdb0d5..7229009 100644
--- a/drivers/net/phy/ste10Xp.c
+++ b/drivers/net/phy/ste10Xp.c
@@ -132,6 +132,14 @@ static void __exit ste10Xp_exit(void)
module_init(ste10Xp_init);
module_exit(ste10Xp_exit);
+static struct mdio_device_id ste10Xp_tbl[] = {
+ { STE101P_PHY_ID, 0xfffffff0 },
+ { STE100P_PHY_ID, 0xffffffff },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, ste10Xp_tbl);
+
MODULE_DESCRIPTION("STMicroelectronics STe10Xp PHY driver");
MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index dd3b244..45cce50 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -191,3 +191,11 @@ static void __exit vsc82xx_exit(void)
module_init(vsc82xx_init);
module_exit(vsc82xx_exit);
+
+static struct mdio_device_id vitesse_tbl[] = {
+ { PHY_ID_VSC8244, 0x000fffc0 },
+ { PHY_ID_VSC8221, 0x000ffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, vitesse_tbl);
--
1.6.6.1
--
David Woodhouse Open Source Technology Centre
David.Woodhouse@intel.com Intel Corporation
^ permalink raw reply related
* [PATCH 1/2] phylib: Support phy module autoloading
From: David Woodhouse @ 2010-04-02 11:05 UTC (permalink / raw)
To: davem; +Cc: netdev, ben
In-Reply-To: <20100401.193810.172601735.davem@davemloft.net>
We don't use the normal hotplug mechanism because it doesn't work. It will
load the module some time after the device appears, but that's not good
enough for us -- we need the driver loaded _immediately_ because otherwise
the NIC driver may just abort and then the phy 'device' goes away.
[bwh: s/phy/mdio/ in module alias, kerneldoc for struct mdio_device_id]
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
I redid the bit in file2alias.c too, so it generates the string directly
in place instead of in a temporary buffer.
drivers/net/phy/phy_device.c | 12 ++++++++++++
include/linux/mod_devicetable.h | 26 ++++++++++++++++++++++++++
include/linux/phy.h | 1 +
scripts/mod/file2alias.c | 26 ++++++++++++++++++++++++++
4 files changed, 65 insertions(+), 0 deletions(-)
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index db17945..1a99bb2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -149,6 +149,7 @@ EXPORT_SYMBOL(phy_scan_fixups);
struct phy_device* phy_device_create(struct mii_bus *bus, int addr, int phy_id)
{
struct phy_device *dev;
+
/* We allocate the device, and initialize the
* default values */
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
@@ -179,6 +180,17 @@ struct phy_device* phy_device_create(struct mii_bus *bus, int addr, int phy_id)
mutex_init(&dev->lock);
INIT_DELAYED_WORK(&dev->state_queue, phy_state_machine);
+ /* Request the appropriate module unconditionally; don't
+ bother trying to do so only if it isn't already loaded,
+ because that gets complicated. A hotplug event would have
+ done an unconditional modprobe anyway.
+ We don't do normal hotplug because it won't work for MDIO
+ -- because it relies on the device staying around for long
+ enough for the driver to get loaded. With MDIO, the NIC
+ driver will get bored and give up as soon as it finds that
+ there's no driver _already_ loaded. */
+ request_module(MDIO_MODULE_PREFIX MDIO_ID_FMT, MDIO_ID_ARGS(phy_id));
+
return dev;
}
EXPORT_SYMBOL(phy_device_create);
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index f58e9d8..55f1f9c 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -474,4 +474,30 @@ struct platform_device_id {
__attribute__((aligned(sizeof(kernel_ulong_t))));
};
+#define MDIO_MODULE_PREFIX "mdio:"
+
+#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d"
+#define MDIO_ID_ARGS(_id) \
+ (_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \
+ ((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \
+ ((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \
+ ((_id)>>19) & 1, ((_id)>>18) & 1, ((_id)>>17) & 1, ((_id)>>16) & 1, \
+ ((_id)>>15) & 1, ((_id)>>14) & 1, ((_id)>>13) & 1, ((_id)>>12) & 1, \
+ ((_id)>>11) & 1, ((_id)>>10) & 1, ((_id)>>9) & 1, ((_id)>>8) & 1, \
+ ((_id)>>7) & 1, ((_id)>>6) & 1, ((_id)>>5) & 1, ((_id)>>4) & 1, \
+ ((_id)>>3) & 1, ((_id)>>2) & 1, ((_id)>>1) & 1, (_id) & 1
+
+/**
+ * struct mdio_device_id - identifies PHY devices on an MDIO/MII bus
+ * @phy_id: The result of
+ * (mdio_read(&MII_PHYSID1) << 16 | mdio_read(&PHYSID2)) & @phy_id_mask
+ * for this PHY type
+ * @phy_id_mask: Defines the significant bits of @phy_id. A value of 0
+ * is used to terminate an array of struct mdio_device_id.
+ */
+struct mdio_device_id {
+ __u32 phy_id;
+ __u32 phy_id_mask;
+};
+
#endif /* LINUX_MOD_DEVICETABLE_H */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 14d7fdf..f269f1b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -24,6 +24,7 @@
#include <linux/mii.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
+#include <linux/mod_devicetable.h>
#include <asm/atomic.h>
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 220213e..36a60a8 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -796,6 +796,28 @@ static int do_platform_entry(const char *filename,
return 1;
}
+static int do_mdio_entry(const char *filename,
+ struct mdio_device_id *id, char *alias)
+{
+ int i;
+
+ alias += sprintf(alias, MDIO_MODULE_PREFIX);
+
+ for (i = 0; i < 32; i++) {
+ if (!((id->phy_id_mask >> (31-i)) & 1))
+ *(alias++) = '?';
+ else if ((id->phy_id >> (31-i)) & 1)
+ *(alias++) = '1';
+ else
+ *(alias++) = '0';
+ }
+
+ /* Terminate the string */
+ *alias = 0;
+
+ return 1;
+}
+
/* Ignore any prefix, eg. some architectures prepend _ */
static inline int sym_is(const char *symbol, const char *name)
{
@@ -943,6 +965,10 @@ void handle_moddevtable(struct module *mod, struct elf_info *info,
do_table(symval, sym->st_size,
sizeof(struct platform_device_id), "platform",
do_platform_entry, mod);
+ else if (sym_is(symname, "__mod_mdio_device_table"))
+ do_table(symval, sym->st_size,
+ sizeof(struct mdio_device_id), "mdio",
+ do_mdio_entry, mod);
free(zeros);
}
--
1.6.6.1
--
David Woodhouse Open Source Technology Centre
David.Woodhouse@intel.com Intel Corporation
^ permalink raw reply related
* Re: [PATCH] rfs: Receive Flow Steering
From: Changli Gao @ 2010-04-02 10:58 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Tom Herbert, davem, netdev
In-Reply-To: <1270193393.1936.52.camel@edumazet-laptop>
On Fri, Apr 2, 2010 at 3:29 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Le vendredi 02 avril 2010 à 13:04 +0800, Changli Gao a écrit :
>
>
> Your claim of RPS being not good for applications is wrong, our test
> results show an improvement as is. Maybe your applications dont scale,
> because of bad habits, or collidings heuristics, I dont know.
>
I didn't mean RPS isn't good for applications. I mean that the
performance improvement of applications isn't as much as firewalls'.
In the other words, we can do much better than the current RPS, as
RFS does.
>
> Whole point of Herbert patches is you dont need to change applications
> and put complex logic in them, knowing exact machine topology.
>
> Your suggestion is very complex, because you must bind each thread on a
> particular cpu, and this is pretty bad for many reasons. We should allow
> thread migrations, because scheduler or admin know better than the
> application.
>
> Application writers should rely on standard kernel mechanisms, and
> schedulers, because an application have a limited point of view of what
> really happens on the machine.
>
Yes, it is more complex. Some high performance server use the
event-driven model, such as memcached, nginx and lighttpd. This model
has high performance on UP with no doubt, and on SMP they usually use
one individual epoll fd for each Core/CPU, and the acceptor dispatches
works among these epoll fds. This program model is popular, and it
bypass the system scheduler. I think the socket option SO_RPSCPU can
help this kind of applications work better, why not do that?
Compatility with other Unixes isn't a good cause, for high performance
applications, there are always lots of OS special features used. For
example: epoll vs kqueue, tcp defer accept vs accept filter.
--
Regards，
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH 1/2] phylib: Support phy module autoloading
From: David Woodhouse @ 2010-04-02 10:38 UTC (permalink / raw)
To: Ben Hutchings; +Cc: davem, netdev, 553024
In-Reply-To: <1270096441.12516.18.camel@localhost>
On Thu, 2010-04-01 at 05:34 +0100, Ben Hutchings wrote:
> --- a/drivers/net/phy/phy_device.c
> +++ b/drivers/net/phy/phy_device.c
> @@ -188,7 +188,7 @@ struct phy_device* phy_device_create(struct mii_bus *bus, int addr, int phy_id)
> around for long enough for the driver to get loaded. With
> MDIO, the NIC driver will get bored and give up as soon
> as it finds that there's no driver _already_ loaded. */
> - sprintf(modid, "phy:" PHYID_FMT, PHYID_ARGS(phy_id));
> + sprintf(modid, MDIO_MODULE_PREFIX MDIO_ID_FMT, MDIO_ID_ARGS(phy_id));
> request_module(modid);
You forgot to increase the size of the 'modid' storage there, and it
needed to grow by one character. But that's OK. I forgot that
request_module() takes printf-style arguments. So now I've killed the
temporary 'modid' buffer altogether, and I just call
request_module(MDIO_MODULE_PREFIX ...). I dropped the ifdef, too.
> -#define PHY_MODULE_PREFIX "phy:"
> +#define MDIO_MODULE_PREFIX "mdio:"
>
> -#define PHYID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d"
> -#define PHYID_ARGS(_id) \
> +#define MDIO_ID_FMT "%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d%d"
> +#define MDIO_ID_ARGS(_id) \
> (_id)>>31, ((_id)>>30) & 1, ((_id)>>29) & 1, ((_id)>>28) & 1, \
> ((_id)>>27) & 1, ((_id)>>26) & 1, ((_id)>>25) & 1, ((_id)>>24) & 1, \
> ((_id)>>23) & 1, ((_id)>>22) & 1, ((_id)>>21) & 1, ((_id)>>20) & 1, \
> @@ -487,11 +487,17 @@ struct platform_device_id {
> ((_id)>>7) & 1, ((_id)>>6) & 1, ((_id)>>5) & 1, ((_id)>>4) & 1, \
> ((_id)>>3) & 1, ((_id)>>2) & 1, ((_id)>>1) & 1, (_id) & 1
Still tempted to add a %b format to the kernel's printf... some runtimes
have it.
> -
> -
> -struct phy_device_id {
> - uint32_t phy_id;
> - uint32_t phy_id_mask;
> +/**
> + * struct mdio_device_id - identifies PHY devices on an MDIO/MII bus
> + * @phy_id: The result of
> + * (mdio_read(&MII_PHYSID1) << 16 | mdio_read(&PHYSID2)) & @phy_id_mask
> + * for this PHY type
> + * @phy_id_mask: Defines the significant bits of @phy_id. A value of 0
> + * is used to terminate an array of struct mdio_device_id.
That last sentence is a lie; I removed it. file2alias.c just ignores the
last entry in the array regardless of what it contains. I have no idea
why we use a 'terminator' in these arrays. Legacy, perhaps?
> static int do_phy_entry(const char *filename,
> - struct phy_device_id *id, char *alias)
> + struct mdio_device_id *id, char *alias)
I made that 'do_mdio_entry()' for cosmetic reasons.
> - sizeof(struct phy_device_id), "phy",
> + sizeof(struct mdio_device_id), "phy",
And that "mdio", not "phy", so that it works.
--
dwmw2
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox