From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Tue, 20 Feb 2024 01:20:52 +0000 Subject: [PATCH] add new system file --- kernel/net/l2tp/l2tp_core.c | 676 +++++++++++++++++++++++++------------------------------- 1 files changed, 302 insertions(+), 374 deletions(-) diff --git a/kernel/net/l2tp/l2tp_core.c b/kernel/net/l2tp/l2tp_core.c index bf2a53d..a4b793d 100644 --- a/kernel/net/l2tp/l2tp_core.c +++ b/kernel/net/l2tp/l2tp_core.c @@ -1,5 +1,5 @@ -/* - * L2TP core. +// SPDX-License-Identifier: GPL-2.0-only +/* L2TP core. * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd * @@ -12,10 +12,6 @@ * 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. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -65,6 +61,10 @@ #include <linux/atomic.h> #include "l2tp_core.h" +#include "trace.h" + +#define CREATE_TRACE_POINTS +#include "trace.h" #define L2TP_DRV_VERSION "V2.0" @@ -97,16 +97,18 @@ unsigned long expires; }; -#define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *) &skb->cb[sizeof(struct inet_skb_parm)]) +#define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *)&(skb)->cb[sizeof(struct inet_skb_parm)]) static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; struct l2tp_net { - struct list_head l2tp_tunnel_list; - spinlock_t l2tp_tunnel_list_lock; + /* Lock for write access to l2tp_tunnel_idr */ + spinlock_t l2tp_tunnel_idr_lock; + struct idr l2tp_tunnel_idr; struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2]; + /* Lock for write access to l2tp_session_hlist */ spinlock_t l2tp_session_hlist_lock; }; @@ -118,15 +120,8 @@ } #endif -static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) -{ - return sk->sk_user_data; -} - static inline struct l2tp_net *l2tp_pernet(const struct net *net) { - BUG_ON(!net); - return net_generic(net, l2tp_net_id); } @@ -139,7 +134,6 @@ 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)]; - } /* Session hash list. @@ -154,12 +148,58 @@ return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } -void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) +static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { + trace_free_tunnel(tunnel); sock_put(tunnel->sock); /* the tunnel is freed in the socket destructor */ } -EXPORT_SYMBOL(l2tp_tunnel_free); + +static void l2tp_session_free(struct l2tp_session *session) +{ + trace_free_session(session); + if (session->tunnel) + l2tp_tunnel_dec_refcount(session->tunnel); + kfree(session); +} + +struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) +{ + struct l2tp_tunnel *tunnel = sk->sk_user_data; + + if (tunnel) + if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) + return NULL; + + return tunnel; +} +EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); + +void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) +{ + refcount_inc(&tunnel->ref_count); +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount); + +void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) +{ + if (refcount_dec_and_test(&tunnel->ref_count)) + l2tp_tunnel_free(tunnel); +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount); + +void l2tp_session_inc_refcount(struct l2tp_session *session) +{ + refcount_inc(&session->ref_count); +} +EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount); + +void l2tp_session_dec_refcount(struct l2tp_session *session) +{ + if (refcount_dec_and_test(&session->ref_count)) + l2tp_session_free(session); +} +EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) @@ -168,13 +208,10 @@ struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (tunnel->tunnel_id == tunnel_id && - refcount_inc_not_zero(&tunnel->ref_count)) { - rcu_read_unlock_bh(); - - return tunnel; - } + tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id); + if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) { + rcu_read_unlock_bh(); + return tunnel; } rcu_read_unlock_bh(); @@ -184,13 +221,14 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) { - const struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_net *pn = l2tp_pernet(net); + unsigned long tunnel_id, tmp; struct l2tp_tunnel *tunnel; int count = 0; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (++count > nth && + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel && ++count > nth && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; @@ -347,6 +385,8 @@ hlist_add_head(&session->hlist, head); write_unlock_bh(&tunnel->hlist_lock); + trace_register_session(session); + return 0; err_tlock_pnlock: @@ -375,10 +415,6 @@ skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%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)); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } @@ -411,13 +447,11 @@ /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; - - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated nr to %hu\n", - session->name, session->nr); + trace_session_seqnum_update(session); } /* call private receive handler */ - if (session->recv_skb != NULL) + if (session->recv_skb) (*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length); else kfree_skb(skb); @@ -438,37 +472,27 @@ start: 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)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + /* If the packet has been pending on the queue for too long, discard it */ + if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%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)); + trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } - if (L2TP_SKB_CB(skb)->has_seq) { + if (cb->has_seq) { if (session->reorder_skip) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: advancing nr to next pkt: %u -> %u", - session->name, session->nr, - L2TP_SKB_CB(skb)->ns); session->reorder_skip = 0; - session->nr = L2TP_SKB_CB(skb)->ns; + session->nr = cb->ns; + trace_session_seqnum_reset(session); } - if (L2TP_SKB_CB(skb)->ns != session->nr) { - l2tp_dbg(session, L2TP_MSG_SEQ, - "%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)); + if (cb->ns != session->nr) goto out; - } } __skb_unlink(skb, &session->reorder_q); @@ -501,14 +525,13 @@ */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { - if (!l2tp_seq_check_rx_window(session, L2TP_SKB_CB(skb)->ns)) { + struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); + + if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: pkt %u len %d discarded, outside window, nr=%u\n", - session->name, L2TP_SKB_CB(skb)->ns, - L2TP_SKB_CB(skb)->length, session->nr); + trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } @@ -525,10 +548,10 @@ * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ - if (L2TP_SKB_CB(skb)->ns == session->nr) { + if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { - u32 nr_oos = L2TP_SKB_CB(skb)->ns; + u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) @@ -539,17 +562,10 @@ session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: %d oos packets received. Resetting sequence numbers\n", - session->name, session->nr_oos_count); } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); - l2tp_dbg(session, L2TP_MSG_SEQ, - "%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)); + trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); @@ -627,15 +643,13 @@ { struct l2tp_tunnel *tunnel = session->tunnel; int offset; - u32 ns, nr; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: cookie mismatch (%u/%u). Discarding.\n", - tunnel->name, tunnel->tunnel_id, - session->session_id); + pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", + tunnel->name, tunnel->tunnel_id, + session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } @@ -649,49 +663,35 @@ * 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 (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)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; + ptr += 2; + /* Skip past nr in the header */ + ptr += 2; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%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); + 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)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; - - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: recv data ns=%u, session nr=%u\n", - session->name, ns, session->nr); } ptr += 4; } if (L2TP_SKB_CB(skb)->has_seq) { - /* Received a packet with sequence numbers. If we're the LNS, + /* Received a packet with sequence numbers. If we're the LAC, * check if we sre sending sequence numbers and if not, * configure it so. */ - if ((!session->lns_mode) && (!session->send_seq)) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to enable seq numbers by LNS\n", - session->name); + if (!session->lns_mode && !session->send_seq) { + trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version); } @@ -700,9 +700,8 @@ * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -712,16 +711,13 @@ * 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)) { - l2tp_info(session, L2TP_MSG_SEQ, - "%s: requested to disable seq numbers by LNS\n", - session->name); + if (!session->lns_mode && session->send_seq) { + trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { - l2tp_warn(session, L2TP_MSG_SEQ, - "%s: recv data has no seq numbers when required. Discarding.\n", - session->name); + pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", + session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } @@ -775,20 +771,18 @@ atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } -EXPORT_SYMBOL(l2tp_recv_common); +EXPORT_SYMBOL_GPL(l2tp_recv_common); /* Drop skbs from the session's reorder_q */ -static int l2tp_session_queue_purge(struct l2tp_session *session) +static void l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; - BUG_ON(!session); - BUG_ON(session->magic != L2TP_SESSION_MAGIC); + while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } - return 0; } /* Internal UDP receive frame. Do the real work of receiving an L2TP data frame @@ -813,47 +807,32 @@ /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv short packet (len=%d)\n", - tunnel->name, skb->len); - goto error; - } - - /* Trace packet contents, if enabled */ - if (tunnel->debug & L2TP_MSG_DATA) { - length = min(32u, skb->len); - if (!pskb_may_pull(skb, length)) - goto error; - - pr_debug("%s: recv\n", tunnel->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length); + pr_debug_ratelimited("%s: recv short packet (len=%d)\n", + tunnel->name, skb->len); + goto invalid; } /* Point to L2TP header */ - optr = ptr = skb->data; + optr = skb->data; + ptr = skb->data; /* Get L2TP header flags */ - hdrflags = ntohs(*(__be16 *) ptr); + hdrflags = ntohs(*(__be16 *)ptr); /* Check protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; if (version != tunnel->version) { - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: recv protocol version mismatch: got %d expected %d\n", - tunnel->name, version, tunnel->version); - goto error; + pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n", + tunnel->name, version, tunnel->version); + goto invalid; } /* Get length of L2TP packet */ length = skb->len; /* If type is control packet, it is handled by userspace. */ - if (hdrflags & L2TP_HDRFLAG_T) { - l2tp_dbg(tunnel, L2TP_MSG_DATA, - "%s: recv control packet, len=%d\n", - tunnel->name, length); - goto error; - } + if (hdrflags & L2TP_HDRFLAG_T) + goto pass; /* Skip flags */ ptr += 2; @@ -864,14 +843,14 @@ ptr += 2; /* Extract tunnel and session ID */ - tunnel_id = ntohs(*(__be16 *) ptr); + tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; - session_id = ntohs(*(__be16 *) ptr); + session_id = ntohs(*(__be16 *)ptr); ptr += 2; } else { ptr += 2; /* skip reserved bits */ tunnel_id = tunnel->tunnel_id; - session_id = ntohl(*(__be32 *) ptr); + session_id = ntohl(*(__be32 *)ptr); ptr += 4; } @@ -882,16 +861,15 @@ l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ - l2tp_info(tunnel, L2TP_MSG_DATA, - "%s: no session found (%u/%u). Passing up.\n", - tunnel->name, tunnel_id, session_id); - goto error; + pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n", + tunnel->name, tunnel_id, session_id); + goto pass; } if (tunnel->version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { l2tp_session_dec_refcount(session); - goto error; + goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); @@ -899,7 +877,10 @@ return 0; -error: +invalid: + atomic_long_inc(&tunnel->stats.rx_invalid); + +pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); @@ -916,12 +897,17 @@ { struct l2tp_tunnel *tunnel; + /* Note that this is called from the encap_rcv hook inside an + * RCU-protected region, but without the socket being locked. + * Hence we use rcu_dereference_sk_user_data to access the + * tunnel data structure rather the usual l2tp_sk_to_tunnel + * accessor function. + */ tunnel = rcu_dereference_sk_user_data(sk); - if (tunnel == NULL) + if (!tunnel) goto pass_up; - - l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n", - tunnel->name, skb->len); + if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) + goto pass_up; if (l2tp_udp_recv_core(tunnel, skb)) goto pass_up; @@ -960,8 +946,7 @@ *bufp++ = 0; session->ns++; session->ns &= 0xffff; - l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } return bufp - optr; @@ -978,13 +963,13 @@ */ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { u16 flags = L2TP_HDR_VER_3; - *((__be16 *) bufp) = htons(flags); + *((__be16 *)bufp) = htons(flags); bufp += 2; - *((__be16 *) bufp) = 0; + *((__be16 *)bufp) = 0; bufp += 2; } - *((__be32 *) bufp) = htonl(session->peer_session_id); + *((__be32 *)bufp) = htonl(session->peer_session_id); bufp += 4; if (session->cookie_len) { memcpy(bufp, &session->cookie[0], session->cookie_len); @@ -997,9 +982,7 @@ l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; - l2tp_dbg(session, L2TP_MSG_SEQ, - "%s: updated ns to %u\n", - session->name, session->ns); + trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); @@ -1009,89 +992,56 @@ return bufp - optr; } -static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, - struct flowi *fl, size_t data_len) +/* Queue the packet to IP for output: tunnel socket lock must be held */ +static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl) { - struct l2tp_tunnel *tunnel = session->tunnel; - unsigned int len = skb->len; - int error; + int err; - /* Debug */ - if (session->send_seq) - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes, ns=%u\n", - session->name, data_len, session->ns - 1); - else - l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes\n", - session->name, data_len); - - if (session->debug & L2TP_MSG_DATA) { - int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; - unsigned char *datap = skb->data + uhlen; - - pr_debug("%s: xmit\n", session->name); - print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, - datap, min_t(size_t, 32, len - uhlen)); - } - - /* Queue the packet to IP for output */ skb->ignore_df = 1; skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) - error = inet6_csk_xmit(tunnel->sock, skb, NULL); + err = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif - error = ip_queue_xmit(tunnel->sock, skb, fl); + err = ip_queue_xmit(tunnel->sock, skb, fl); - /* Update stats */ - if (error >= 0) { - atomic_long_inc(&tunnel->stats.tx_packets); - atomic_long_add(len, &tunnel->stats.tx_bytes); - atomic_long_inc(&session->stats.tx_packets); - atomic_long_add(len, &session->stats.tx_bytes); - } else { - atomic_long_inc(&tunnel->stats.tx_errors); - atomic_long_inc(&session->stats.tx_errors); - } + return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } -/* 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) +static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int *len) { - int data_len = skb->len; struct l2tp_tunnel *tunnel = session->tunnel; + unsigned int data_len = skb->len; struct sock *sk = tunnel->sock; - struct flowi *fl; - struct udphdr *uh; - struct inet_sock *inet; - int headroom; - int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0; - int udp_len; + int headroom, uhlen, udp_len; int ret = NET_XMIT_SUCCESS; + struct inet_sock *inet; + struct udphdr *uh; /* 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) + - uhlen + hdr_len; + uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0; + headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len; if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; } /* Setup L2TP header */ - session->build_header(session, __skb_push(skb, hdr_len)); + if (tunnel->version == L2TP_HDR_VER_2) + l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len)); + else + l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); /* 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); - nf_reset(skb); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); + nf_reset_ct(skb); - bh_lock_sock(sk); + bh_lock_sock_nested(sk); if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1107,8 +1057,12 @@ goto out_unlock; } + /* Report transmitted length before we add encap header, which keeps + * statistics consistent for both UDP and IP encap tx/rx paths. + */ + *len = skb->len; + inet = inet_sk(sk); - fl = &inet->cork.fl; switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ @@ -1117,7 +1071,7 @@ uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = inet->inet_dport; - udp_len = uhlen + hdr_len + data_len; + udp_len = uhlen + session->hdr_len + data_len; uh->len = htons(udp_len); /* Calculate UDP checksum if configured to do so */ @@ -1128,18 +1082,40 @@ &sk->sk_v6_daddr, udp_len); else #endif - udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr, - inet->inet_daddr, udp_len); + udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr, + inet->inet_daddr, udp_len); break; case L2TP_ENCAPTYPE_IP: break; } - l2tp_xmit_core(session, skb, fl, data_len); + ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); + out_unlock: bh_unlock_sock(sk); + return ret; +} + +/* 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) +{ + unsigned int len = 0; + int ret; + + ret = l2tp_xmit_core(session, skb, &len); + if (ret == NET_XMIT_SUCCESS) { + atomic_long_inc(&session->tunnel->stats.tx_packets); + atomic_long_add(len, &session->tunnel->stats.tx_bytes); + atomic_long_inc(&session->stats.tx_packets); + atomic_long_add(len, &session->stats.tx_bytes); + } else { + atomic_long_inc(&session->tunnel->stats.tx_errors); + atomic_long_inc(&session->stats.tx_errors); + } return ret; } EXPORT_SYMBOL_GPL(l2tp_xmit_skb); @@ -1154,12 +1130,10 @@ */ static void l2tp_tunnel_destruct(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); - if (tunnel == NULL) + if (!tunnel) goto end; - - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name); /* Disable udp encapsulation */ switch (tunnel->encap) { @@ -1174,8 +1148,10 @@ } /* Remove hooks into tunnel socket */ + write_lock_bh(&sk->sk_callback_lock); sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; + write_unlock_bh(&sk->sk_callback_lock); /* Call the original destructor */ if (sk->sk_destruct) @@ -1184,6 +1160,30 @@ kfree_rcu(tunnel, rcu); end: return; +} + +/* Remove an l2tp session from l2tp_core's hash lists. */ +static void l2tp_session_unhash(struct l2tp_session *session) +{ + struct l2tp_tunnel *tunnel = session->tunnel; + + /* Remove the session from core hashes */ + if (tunnel) { + /* Remove from the per-tunnel hash */ + write_lock_bh(&tunnel->hlist_lock); + hlist_del_init(&session->hlist); + write_unlock_bh(&tunnel->hlist_lock); + + /* For L2TPv3 we have a per-net hash: remove from there, too */ + if (tunnel->version != L2TP_HDR_VER_2) { + struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); + + spin_lock_bh(&pn->l2tp_session_hlist_lock); + hlist_del_init_rcu(&session->global_hlist); + spin_unlock_bh(&pn->l2tp_session_hlist_lock); + synchronize_rcu(); + } + } } /* When the tunnel is closed, all the attached sessions need to go too. @@ -1195,36 +1195,16 @@ struct hlist_node *tmp; struct l2tp_session *session; - BUG_ON(tunnel == NULL); - - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing all sessions...\n", - tunnel->name); - write_lock_bh(&tunnel->hlist_lock); tunnel->acpt_newsess = false; 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); - - l2tp_info(session, L2TP_MSG_CONTROL, - "%s: closing session\n", session->name); - hlist_del_init(&session->hlist); - if (test_and_set_bit(0, &session->dead)) - goto again; - write_unlock_bh(&tunnel->hlist_lock); - - __l2tp_session_unhash(session); - l2tp_session_queue_purge(session); - - if (session->session_close != NULL) - (*session->session_close)(session); - - l2tp_session_dec_refcount(session); - + l2tp_session_delete(session); write_lock_bh(&tunnel->hlist_lock); /* Now restart from the beginning of this hash @@ -1241,10 +1221,19 @@ /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { - struct l2tp_tunnel *tunnel = l2tp_tunnel(sk); + struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) l2tp_tunnel_delete(tunnel); +} + +static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) +{ + struct l2tp_net *pn = l2tp_pernet(net); + + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); } /* Workqueue tunnel deletion function */ @@ -1254,7 +1243,6 @@ del_work); struct sock *sk = tunnel->sock; struct socket *sock = sk->sk_socket; - struct l2tp_net *pn; l2tp_tunnel_closeall(tunnel); @@ -1268,12 +1256,7 @@ } } - /* Remove the tunnel struct from the tunnel list */ - pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - + l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ l2tp_tunnel_dec_refcount(tunnel); @@ -1291,10 +1274,10 @@ * exit hook. */ static int l2tp_tunnel_sock_create(struct net *net, - u32 tunnel_id, - u32 peer_tunnel_id, - struct l2tp_tunnel_cfg *cfg, - struct socket **sockp) + u32 tunnel_id, + u32 peer_tunnel_id, + struct l2tp_tunnel_cfg *cfg, + struct socket **sockp) { int err = -EINVAL; struct socket *sock = NULL; @@ -1312,9 +1295,9 @@ memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, sizeof(udp_conf.peer_ip6)); udp_conf.use_udp6_tx_checksums = - ! cfg->udp6_zero_tx_checksums; + !cfg->udp6_zero_tx_checksums; udp_conf.use_udp6_rx_checksums = - ! cfg->udp6_zero_rx_checksums; + !cfg->udp6_zero_rx_checksums; } else #endif { @@ -1339,7 +1322,7 @@ struct sockaddr_l2tpip6 ip6_addr = {0}; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, - IPPROTO_L2TP, &sock); + IPPROTO_L2TP, &sock); if (err < 0) goto out; @@ -1347,7 +1330,7 @@ memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = tunnel_id; - err = kernel_bind(sock, (struct sockaddr *) &ip6_addr, + err = kernel_bind(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr)); if (err < 0) goto out; @@ -1357,7 +1340,7 @@ sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, - (struct sockaddr *) &ip6_addr, + (struct sockaddr *)&ip6_addr, sizeof(ip6_addr), 0); if (err < 0) goto out; @@ -1367,14 +1350,14 @@ struct sockaddr_l2tpip ip_addr = {0}; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, - IPPROTO_L2TP, &sock); + IPPROTO_L2TP, &sock); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; - err = kernel_bind(sock, (struct sockaddr *) &ip_addr, + err = kernel_bind(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr)); if (err < 0) goto out; @@ -1382,7 +1365,7 @@ ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->peer_ip; ip_addr.l2tp_conn_id = peer_tunnel_id; - err = kernel_connect(sock, (struct sockaddr *) &ip_addr, + err = kernel_connect(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr), 0); if (err < 0) goto out; @@ -1395,7 +1378,7 @@ out: *sockp = sock; - if ((err < 0) && sock) { + if (err < 0 && sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); *sockp = NULL; @@ -1404,19 +1387,18 @@ return err; } -static struct lock_class_key l2tp_socket_class; - -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) +int l2tp_tunnel_create(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; enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP; - if (cfg != NULL) + if (cfg) encap = cfg->encap; - tunnel = kzalloc(sizeof(struct l2tp_tunnel), GFP_KERNEL); - if (tunnel == NULL) { + tunnel = kzalloc(sizeof(*tunnel), GFP_KERNEL); + if (!tunnel) { err = -ENOMEM; goto err; } @@ -1424,15 +1406,11 @@ 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); tunnel->acpt_newsess = true; - - if (cfg != NULL) - tunnel->debug = cfg->debug; tunnel->encap = encap; @@ -1478,11 +1456,18 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg) { - struct l2tp_tunnel *tunnel_walk; - struct l2tp_net *pn; + struct l2tp_net *pn = l2tp_pernet(net); + u32 tunnel_id = tunnel->tunnel_id; struct socket *sock; struct sock *sk; int ret; + + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id, + GFP_ATOMIC); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); + if (ret) + return ret == -ENOSPC ? -EEXIST : ret; if (tunnel->fd < 0) { ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id, @@ -1494,30 +1479,16 @@ sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; - - ret = l2tp_validate_socket(sock->sk, net, tunnel->encap); - if (ret < 0) - goto err_sock; } - - tunnel->l2tp_net = net; - pn = l2tp_pernet(net); - - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) { - if (tunnel_walk->tunnel_id == tunnel->tunnel_id) { - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - - ret = -EEXIST; - goto err_sock; - } - } - list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); sk = sock->sk; - sock_hold(sk); - tunnel->sock = sk; + lock_sock(sk); + write_lock_bh(&sk->sk_callback_lock); + ret = l2tp_validate_socket(sk, net, tunnel->encap); + if (ret < 0) + goto err_inval_sock; + rcu_assign_sk_user_data(sk, tunnel); + write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { @@ -1528,27 +1499,38 @@ }; setup_udp_tunnel_sock(net, sock, &udp_cfg); - } else { - sk->sk_user_data = tunnel; } tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; - lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, - "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + release_sock(sk); + + sock_hold(sk); + tunnel->sock = sk; + tunnel->l2tp_net = net; + + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); + + trace_register_tunnel(tunnel); if (tunnel->fd >= 0) sockfd_put(sock); return 0; -err_sock: +err_inval_sock: + write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); + if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); err: + l2tp_tunnel_remove(net, tunnel); return ret; } EXPORT_SYMBOL_GPL(l2tp_tunnel_register); @@ -1558,73 +1540,25 @@ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { + trace_delete_tunnel(tunnel); l2tp_tunnel_inc_refcount(tunnel); queue_work(l2tp_wq, &tunnel->del_work); } } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); -/* Really kill the session. - */ -void l2tp_session_free(struct l2tp_session *session) -{ - struct l2tp_tunnel *tunnel = session->tunnel; - - BUG_ON(refcount_read(&session->ref_count) != 0); - - if (tunnel) { - BUG_ON(tunnel->magic != L2TP_TUNNEL_MAGIC); - l2tp_tunnel_dec_refcount(tunnel); - } - - kfree(session); -} -EXPORT_SYMBOL_GPL(l2tp_session_free); - -/* Remove an l2tp session from l2tp_core's hash lists. - * Provides a tidyup interface for pseudowire code which can't just route all - * shutdown via. l2tp_session_delete and a pseudowire-specific session_close - * callback. - */ -void __l2tp_session_unhash(struct l2tp_session *session) -{ - struct l2tp_tunnel *tunnel = session->tunnel; - - /* Remove the session from core hashes */ - if (tunnel) { - /* Remove from the per-tunnel hash */ - write_lock_bh(&tunnel->hlist_lock); - hlist_del_init(&session->hlist); - write_unlock_bh(&tunnel->hlist_lock); - - /* For L2TPv3 we have a per-net hash: remove from there, too */ - if (tunnel->version != L2TP_HDR_VER_2) { - struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_session_hlist_lock); - hlist_del_init_rcu(&session->global_hlist); - spin_unlock_bh(&pn->l2tp_session_hlist_lock); - synchronize_rcu(); - } - } -} -EXPORT_SYMBOL_GPL(__l2tp_session_unhash); - -/* This function is used by the netlink SESSION_DELETE command and by - pseudowire modules. - */ -int l2tp_session_delete(struct l2tp_session *session) +void l2tp_session_delete(struct l2tp_session *session) { if (test_and_set_bit(0, &session->dead)) - return 0; + return; - __l2tp_session_unhash(session); + trace_delete_session(session); + l2tp_session_unhash(session); l2tp_session_queue_purge(session); - if (session->session_close != NULL) + if (session->session_close) (*session->session_close)(session); l2tp_session_dec_refcount(session); - - return 0; } EXPORT_SYMBOL_GPL(l2tp_session_delete); @@ -1643,16 +1577,16 @@ if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } - } 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 *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 = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); + if (session) { session->magic = L2TP_SESSION_MAGIC; session->tunnel = tunnel; @@ -1677,12 +1611,8 @@ 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->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; @@ -1693,11 +1623,6 @@ 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); @@ -1719,8 +1644,8 @@ struct l2tp_net *pn = net_generic(net, l2tp_net_id); int hash; - INIT_LIST_HEAD(&pn->l2tp_tunnel_list); - spin_lock_init(&pn->l2tp_tunnel_list_lock); + idr_init(&pn->l2tp_tunnel_idr); + spin_lock_init(&pn->l2tp_tunnel_idr_lock); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]); @@ -1734,11 +1659,13 @@ { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; + unsigned long tunnel_id, tmp; int hash; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - l2tp_tunnel_delete(tunnel); + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel) + l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); @@ -1748,6 +1675,7 @@ for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); + idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { -- Gitblit v1.6.2