diff options
author | Russell King <rmk@dyn-67.arm.linux.org.uk> | 2006-01-07 14:40:05 +0000 |
---|---|---|
committer | Russell King <rmk+kernel@arm.linux.org.uk> | 2006-01-07 14:40:05 +0000 |
commit | 123656d4cc8c946f578ebd18c2050f5251720428 (patch) | |
tree | 3d5432eff034a3b9cfdc98b37e245abe5695342d /net/dccp | |
parent | a62c80e559809e6c7851ec04d30575e85ad6f6ed (diff) | |
parent | 0aec63e67c69545ca757a73a66f5dcf05fa484bf (diff) |
Merge with Linus' kernel.
Diffstat (limited to 'net/dccp')
-rw-r--r-- | net/dccp/Makefile | 4 | ||||
-rw-r--r-- | net/dccp/ackvec.c | 33 | ||||
-rw-r--r-- | net/dccp/ackvec.h | 12 | ||||
-rw-r--r-- | net/dccp/ccid.h | 2 | ||||
-rw-r--r-- | net/dccp/dccp.h | 24 | ||||
-rw-r--r-- | net/dccp/diag.c | 2 | ||||
-rw-r--r-- | net/dccp/input.c | 79 | ||||
-rw-r--r-- | net/dccp/ipv4.c | 305 | ||||
-rw-r--r-- | net/dccp/ipv6.c | 1261 | ||||
-rw-r--r-- | net/dccp/ipv6.h | 37 | ||||
-rw-r--r-- | net/dccp/minisocks.c | 23 | ||||
-rw-r--r-- | net/dccp/output.c | 47 | ||||
-rw-r--r-- | net/dccp/proto.c | 56 |
13 files changed, 1572 insertions, 313 deletions
diff --git a/net/dccp/Makefile b/net/dccp/Makefile index 344a8da153f..87b27fff6e3 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -1,3 +1,7 @@ +obj-$(CONFIG_IPV6) += dccp_ipv6.o + +dccp_ipv6-y := ipv6.o + obj-$(CONFIG_IP_DCCP) += dccp.o dccp-y := ccid.o input.o ipv4.o minisocks.o options.o output.o proto.o \ diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index c9a62cca22f..ce9cb77c5c2 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -55,8 +55,8 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) from = av->dccpav_buf + av->dccpav_buf_head; /* Check if buf_head wraps */ - if (av->dccpav_buf_head + len > av->dccpav_vec_len) { - const u32 tailsize = (av->dccpav_vec_len - av->dccpav_buf_head); + if ((int)av->dccpav_buf_head + len > av->dccpav_vec_len) { + const u32 tailsize = av->dccpav_vec_len - av->dccpav_buf_head; memcpy(to, from, tailsize); to += tailsize; @@ -93,8 +93,14 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) struct dccp_ackvec *dccp_ackvec_alloc(const unsigned int len, const gfp_t priority) { - struct dccp_ackvec *av = kmalloc(sizeof(*av) + len, priority); + struct dccp_ackvec *av; + BUG_ON(len == 0); + + if (len > DCCP_MAX_ACKVEC_LEN) + return NULL; + + av = kmalloc(sizeof(*av) + len, priority); if (av != NULL) { av->dccpav_buf_len = len; av->dccpav_buf_head = @@ -117,13 +123,13 @@ void dccp_ackvec_free(struct dccp_ackvec *av) } static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, - const unsigned int index) + const u8 index) { return av->dccpav_buf[index] & DCCP_ACKVEC_STATE_MASK; } static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av, - const unsigned int index) + const u8 index) { return av->dccpav_buf[index] & DCCP_ACKVEC_LEN_MASK; } @@ -135,7 +141,7 @@ static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av, */ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, const unsigned int packets, - const unsigned char state) + const unsigned char state) { unsigned int gap; signed long new_head; @@ -223,7 +229,7 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * could reduce the complexity of this scan.) */ u64 delta = dccp_delta_seqno(ackno, av->dccpav_buf_ackno); - unsigned int index = av->dccpav_buf_head; + u8 index = av->dccpav_buf_head; while (1) { const u8 len = dccp_ackvec_len(av, index); @@ -291,7 +297,7 @@ void dccp_ackvec_print(const struct dccp_ackvec *av) } #endif -static void dccp_ackvec_trow_away_ack_record(struct dccp_ackvec *av) +static void dccp_ackvec_throw_away_ack_record(struct dccp_ackvec *av) { /* * As we're keeping track of the ack vector size (dccpav_vec_len) and @@ -301,9 +307,10 @@ static void dccp_ackvec_trow_away_ack_record(struct dccp_ackvec *av) * draft-ietf-dccp-spec-11.txt Appendix A. -acme */ #if 0 - av->dccpav_buf_tail = av->dccpav_ack_ptr + 1; - if (av->dccpav_buf_tail >= av->dccpav_vec_len) - av->dccpav_buf_tail -= av->dccpav_vec_len; + u32 new_buf_tail = av->dccpav_ack_ptr + 1; + if (new_buf_tail >= av->dccpav_vec_len) + new_buf_tail -= av->dccpav_vec_len; + av->dccpav_buf_tail = new_buf_tail; #endif av->dccpav_vec_len -= av->dccpav_sent_len; } @@ -326,7 +333,7 @@ void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, debug_prefix, 1, (unsigned long long)av->dccpav_ack_seqno, (unsigned long long)av->dccpav_ack_ackno); - dccp_ackvec_trow_away_ack_record(av); + dccp_ackvec_throw_away_ack_record(av); av->dccpav_ack_seqno = DCCP_MAX_SEQNO + 1; } } @@ -389,7 +396,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, av->dccpav_ack_seqno, (unsigned long long) av->dccpav_ack_ackno); - dccp_ackvec_trow_away_ack_record(av); + dccp_ackvec_throw_away_ack_record(av); } /* * If dccpav_ack_seqno was not received, no problem diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index d0fd6c60c57..f7dfb5f67b8 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -54,16 +54,16 @@ * @dccpav_buf - circular buffer of acknowledgeable packets */ struct dccp_ackvec { - unsigned int dccpav_buf_head; - unsigned int dccpav_buf_tail; u64 dccpav_buf_ackno; u64 dccpav_ack_seqno; u64 dccpav_ack_ackno; - unsigned int dccpav_ack_ptr; - unsigned int dccpav_sent_len; - unsigned int dccpav_vec_len; - unsigned int dccpav_buf_len; struct timeval dccpav_time; + u8 dccpav_buf_head; + u8 dccpav_buf_tail; + u8 dccpav_ack_ptr; + u8 dccpav_sent_len; + u8 dccpav_vec_len; + u8 dccpav_buf_len; u8 dccpav_buf_nonce; u8 dccpav_ack_nonce; u8 dccpav_buf[0]; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index c37eeeaf5c6..de681c6ad08 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -21,6 +21,8 @@ #define CCID_MAX 255 +struct tcp_info; + struct ccid { unsigned char ccid_id; const char *ccid_name; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index f97b85d55ad..93f26dd6e6c 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -59,7 +59,7 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); #define DCCP_RTO_MAX ((unsigned)(120 * HZ)) /* FIXME: using TCP value */ -extern struct proto dccp_v4_prot; +extern struct proto dccp_prot; /* is seq1 < seq2 ? */ static inline int before48(const u64 seq1, const u64 seq2) @@ -228,6 +228,9 @@ extern int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, extern int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned len); +extern int dccp_v4_init_sock(struct sock *sk); +extern int dccp_v4_destroy_sock(struct sock *sk); + extern void dccp_close(struct sock *sk, long timeout); extern struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, @@ -238,6 +241,7 @@ extern struct sk_buff *dccp_make_reset(struct sock *sk, extern int dccp_connect(struct sock *sk); extern int dccp_disconnect(struct sock *sk, int flags); +extern void dccp_unhash(struct sock *sk); extern int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); extern int dccp_setsockopt(struct sock *sk, int level, int optname, @@ -249,6 +253,13 @@ extern int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); extern void dccp_shutdown(struct sock *sk, int how); +extern int inet_dccp_listen(struct socket *sock, int backlog); +extern unsigned int dccp_poll(struct file *file, struct socket *sock, + poll_table *wait); +extern void dccp_v4_send_check(struct sock *sk, int len, + struct sk_buff *skb); +extern int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len); extern int dccp_v4_checksum(const struct sk_buff *skb, const u32 saddr, const u32 daddr); @@ -256,6 +267,17 @@ extern int dccp_v4_checksum(const struct sk_buff *skb, extern int dccp_v4_send_reset(struct sock *sk, enum dccp_reset_codes code); extern void dccp_send_close(struct sock *sk, const int active); +extern int dccp_invalid_packet(struct sk_buff *skb); + +static inline int dccp_bad_service_code(const struct sock *sk, + const __u32 service) +{ + const struct dccp_sock *dp = dccp_sk(sk); + + if (dp->dccps_service == service) + return 0; + return !dccp_list_has_service(dp->dccps_service_list, service); +} struct dccp_skb_cb { __u8 dccpd_type:4; diff --git a/net/dccp/diag.c b/net/dccp/diag.c index f675d8e642d..3f78c00e382 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -28,7 +28,7 @@ static void dccp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; info->tcpi_backoff = icsk->icsk_backoff; - info->tcpi_pmtu = dp->dccps_pmtu_cookie; + info->tcpi_pmtu = icsk->icsk_pmtu_cookie; if (dp->dccps_options.dccpo_send_ack_vector) info->tcpi_options |= TCPI_OPT_SACK; diff --git a/net/dccp/input.c b/net/dccp/input.c index 3454d594190..b6cba72b44e 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -151,29 +151,12 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) return 0; } -int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, const unsigned len) +static inline int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, + const struct dccp_hdr *dh, + const unsigned len) { struct dccp_sock *dp = dccp_sk(sk); - if (dccp_check_seqno(sk, skb)) - goto discard; - - if (dccp_parse_options(sk, skb)) - goto discard; - - if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) - dccp_event_ack_recv(sk, skb); - - if (dp->dccps_options.dccpo_send_ack_vector && - dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) - goto discard; - - ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb); - ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb); - switch (dccp_hdr(skb)->dccph_type) { case DCCP_PKT_DATAACK: case DCCP_PKT_DATA: @@ -250,6 +233,37 @@ discard: return 0; } +int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, + const struct dccp_hdr *dh, const unsigned len) +{ + struct dccp_sock *dp = dccp_sk(sk); + + if (dccp_check_seqno(sk, skb)) + goto discard; + + if (dccp_parse_options(sk, skb)) + goto discard; + + if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) + dccp_event_ack_recv(sk, skb); + + if (dp->dccps_options.dccpo_send_ack_vector && + dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, + DCCP_SKB_CB(skb)->dccpd_seq, + DCCP_ACKVEC_STATE_RECEIVED)) + goto discard; + + ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb); + ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb); + + return __dccp_rcv_established(sk, skb, dh, len); +discard: + __kfree_skb(skb); + return 0; +} + +EXPORT_SYMBOL_GPL(dccp_rcv_established); + static int dccp_rcv_request_sent_state_process(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, @@ -286,6 +300,12 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, goto out_invalid_packet; } + if (dp->dccps_options.dccpo_send_ack_vector && + dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, + DCCP_SKB_CB(skb)->dccpd_seq, + DCCP_ACKVEC_STATE_RECEIVED)) + goto out_invalid_packet; /* FIXME: change error code */ + dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; dccp_update_gsr(sk, dp->dccps_isr); /* @@ -309,7 +329,7 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, goto out_invalid_packet; } - dccp_sync_mss(sk, dp->dccps_pmtu_cookie); + dccp_sync_mss(sk, icsk->icsk_pmtu_cookie); /* * Step 10: Process REQUEST state (second part) @@ -329,7 +349,7 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, dccp_set_state(sk, DCCP_PARTOPEN); /* Make sure socket is routed, for correct metrics. */ - inet_sk_rebuild_header(sk); + icsk->icsk_af_ops->rebuild_header(sk); if (!sock_flag(sk, SOCK_DEAD)) { sk->sk_state_change(sk); @@ -398,9 +418,9 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, if (dh->dccph_type == DCCP_PKT_DATAACK || dh->dccph_type == DCCP_PKT_DATA) { - dccp_rcv_established(sk, skb, dh, len); + __dccp_rcv_established(sk, skb, dh, len); queued = 1; /* packet was queued - (by dccp_rcv_established) */ + (by __dccp_rcv_established) */ } break; } @@ -444,7 +464,8 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, */ if (sk->sk_state == DCCP_LISTEN) { if (dh->dccph_type == DCCP_PKT_REQUEST) { - if (dccp_v4_conn_request(sk, skb) < 0) + if (inet_csk(sk)->icsk_af_ops->conn_request(sk, + skb) < 0) return 1; /* FIXME: do congestion control initialization */ @@ -471,14 +492,14 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb); - ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb); - if (dp->dccps_options.dccpo_send_ack_vector && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) goto discard; + + ccid_hc_rx_packet_recv(dp->dccps_hc_rx_ccid, sk, skb); + ccid_hc_tx_packet_recv(dp->dccps_hc_tx_ccid, sk, skb); } /* @@ -566,3 +587,5 @@ discard: } return 0; } + +EXPORT_SYMBOL_GPL(dccp_rcv_state_process); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 656e13e38cf..3f244670764 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -19,7 +19,9 @@ #include <net/icmp.h> #include <net/inet_hashtables.h> +#include <net/inet_sock.h> #include <net/sock.h> +#include <net/timewait_sock.h> #include <net/tcp_states.h> #include <net/xfrm.h> @@ -37,7 +39,8 @@ EXPORT_SYMBOL_GPL(dccp_hashinfo); static int dccp_v4_get_port(struct sock *sk, const unsigned short snum) { - return inet_csk_get_port(&dccp_hashinfo, sk, snum); + return inet_csk_get_port(&dccp_hashinfo, sk, snum, + inet_csk_bind_conflict); } static void dccp_v4_hash(struct sock *sk) @@ -45,171 +48,14 @@ static void dccp_v4_hash(struct sock *sk) inet_hash(&dccp_hashinfo, sk); } -static void dccp_v4_unhash(struct sock *sk) +void dccp_unhash(struct sock *sk) { inet_unhash(&dccp_hashinfo, sk); } -/* called with local bh disabled */ -static int __dccp_v4_check_established(struct sock *sk, const __u16 lport, - struct inet_timewait_sock **twp) -{ - struct inet_sock *inet = inet_sk(sk); - const u32 daddr = inet->rcv_saddr; - const u32 saddr = inet->daddr; - const int dif = sk->sk_bound_dev_if; - INET_ADDR_COOKIE(acookie, saddr, daddr) - const __u32 ports = INET_COMBINED_PORTS(inet->dport, lport); - unsigned int hash = inet_ehashfn(daddr, lport, saddr, inet->dport); - struct inet_ehash_bucket *head = inet_ehash_bucket(&dccp_hashinfo, hash); - const struct sock *sk2; - const struct hlist_node *node; - struct inet_timewait_sock *tw; - - prefetch(head->chain.first); - write_lock(&head->lock); - - /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &(head + dccp_hashinfo.ehash_size)->chain) { - tw = inet_twsk(sk2); - - if (INET_TW_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif)) - goto not_unique; - } - tw = NULL; - - /* And established part... */ - sk_for_each(sk2, node, &head->chain) { - if (INET_MATCH(sk2, hash, acookie, saddr, daddr, ports, dif)) - goto not_unique; - } +EXPORT_SYMBOL_GPL(dccp_unhash); - /* Must record num and sport now. Otherwise we will see - * in hash table socket with a funny identity. */ - inet->num = lport; - inet->sport = htons(lport); - sk->sk_hash = hash; - BUG_TRAP(sk_unhashed(sk)); - __sk_add_node(sk, &head->chain); - sock_prot_inc_use(sk->sk_prot); - write_unlock(&head->lock); - - if (twp != NULL) { - *twp = tw; - NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); - } else if (tw != NULL) { - /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw, &dccp_death_row); - NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED); - - inet_twsk_put(tw); - } - - return 0; - -not_unique: - write_unlock(&head->lock); - return -EADDRNOTAVAIL; -} - -/* - * Bind a port for a connect operation and hash it. - */ -static int dccp_v4_hash_connect(struct sock *sk) -{ - const unsigned short snum = inet_sk(sk)->num; - struct inet_bind_hashbucket *head; - struct inet_bind_bucket *tb; - int ret; - - if (snum == 0) { - int low = sysctl_local_port_range[0]; - int high = sysctl_local_port_range[1]; - int remaining = (high - low) + 1; - int rover = net_random() % (high - low) + low; - struct hlist_node *node; - struct inet_timewait_sock *tw = NULL; - - local_bh_disable(); - do { - head = &dccp_hashinfo.bhash[inet_bhashfn(rover, - dccp_hashinfo.bhash_size)]; - spin_lock(&head->lock); - - /* Does not bother with rcv_saddr checks, - * because the established check is already - * unique enough. - */ - inet_bind_bucket_for_each(tb, node, &head->chain) { - if (tb->port == rover) { - BUG_TRAP(!hlist_empty(&tb->owners)); - if (tb->fastreuse >= 0) - goto next_port; - if (!__dccp_v4_check_established(sk, - rover, - &tw)) - goto ok; - goto next_port; - } - } - - tb = inet_bind_bucket_create(dccp_hashinfo.bind_bucket_cachep, - head, rover); - if (tb == NULL) { - spin_unlock(&head->lock); - break; - } - tb->fastreuse = -1; - goto ok; - - next_port: - spin_unlock(&head->lock); - if (++rover > high) - rover = low; - } while (--remaining > 0); - - local_bh_enable(); - - return -EADDRNOTAVAIL; - -ok: - /* All locks still held and bhs disabled */ - inet_bind_hash(sk, tb, rover); - if (sk_unhashed(sk)) { - inet_sk(sk)->sport = htons(rover); - __inet_hash(&dccp_hashinfo, sk, 0); - } - spin_unlock(&head->lock); - - if (tw != NULL) { - inet_twsk_deschedule(tw, &dccp_death_row); - inet_twsk_put(tw); - } - - ret = 0; - goto out; - } - - head = &dccp_hashinfo.bhash[inet_bhashfn(snum, - dccp_hashinfo.bhash_size)]; - tb = inet_csk(sk)->icsk_bind_hash; - spin_lock_bh(&head->lock); - if (sk_head(&tb->owners) == sk && sk->sk_bind_node.next == NULL) { - __inet_hash(&dccp_hashinfo, sk, 0); - spin_unlock_bh(&head->lock); - return 0; - } else { - spin_unlock(&head->lock); - /* No definite answer... Walk to established hash table */ - ret = __dccp_v4_check_established(sk, snum, NULL); -out: - local_bh_enable(); - return ret; - } -} - -static int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, - int addr_len) +int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); @@ -259,9 +105,9 @@ static int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, inet->dport = usin->sin_port; inet->daddr = daddr; - dp->dccps_ext_header_len = 0; + inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet->opt != NULL) - dp->dccps_ext_header_len = inet->opt->optlen; + inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; /* * Socket identity is still unknown (sport may be zero). * However we set state to DCCP_REQUESTING and not releasing socket @@ -269,7 +115,7 @@ static int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, * complete initialization after this. */ dccp_set_state(sk, DCCP_REQUESTING); - err = dccp_v4_hash_connect(sk); + err = inet_hash_connect(&dccp_death_row, sk); if (err != 0) goto failure; @@ -287,16 +133,6 @@ static int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, usin->sin_port); dccp_update_gss(sk, dp->dccps_iss); - /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. - */ - dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss)); - inet->id = dp->dccps_iss ^ jiffies; err = dccp_connect(sk); @@ -316,6 +152,8 @@ failure: goto out; } +EXPORT_SYMBOL_GPL(dccp_v4_connect); + /* * This routine does path mtu discovery as defined in RFC1191. */ @@ -354,7 +192,7 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && - dp->dccps_pmtu_cookie > mtu) { + inet_csk(sk)->icsk_pmtu_cookie > mtu) { dccp_sync_mss(sk, mtu); /* @@ -606,6 +444,17 @@ out: sock_put(sk); } +/* This routine computes an IPv4 DCCP checksum. */ +void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) +{ + const struct inet_sock *inet = inet_sk(sk); + struct dccp_hdr *dh = dccp_hdr(skb); + + dh->dccph_checksum = dccp_v4_checksum(skb, inet->saddr, inet->daddr); +} + +EXPORT_SYMBOL_GPL(dccp_v4_send_check); + int dccp_v4_send_reset(struct sock *sk, enum dccp_reset_codes code) { struct sk_buff *skb; @@ -641,16 +490,6 @@ static inline u64 dccp_v4_init_sequence(const struct sock *sk, dccp_hdr(skb)->dccph_sport); } -static inline int dccp_bad_service_code(const struct sock *sk, - const __u32 service) -{ - const struct dccp_sock *dp = dccp_sk(sk); - - if (dp->dccps_service == service) - return 0; - return !dccp_list_has_service(dp->dccps_service_list, service); -} - int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct inet_request_sock *ireq; @@ -662,7 +501,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) const __u32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); __u8 reset_code = DCCP_RESET_CODE_TOO_BUSY; - struct dst_entry *dst = NULL; /* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */ if (((struct rtable *)skb->dst)->rt_flags & @@ -703,7 +541,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->loc_addr = daddr; ireq->rmt_addr = saddr; - /* FIXME: Merge Aristeu's option parsing code when ready */ req->rcv_wnd = 100; /* Fake, option parsing will get the right value */ ireq->opt = NULL; @@ -721,23 +558,22 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) dreq->dreq_iss = dccp_v4_init_sequence(sk, skb); dreq->dreq_service = service; - if (dccp_v4_send_response(sk, req, dst)) + if (dccp_v4_send_response(sk, req, NULL)) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); return 0; drop_and_free: - /* - * FIXME: should be reqsk_free after implementing req->rsk_ops - */ - __reqsk_free(req); + reqsk_free(req); drop: DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); dcb->dccpd_reset_code = reset_code; return -1; } +EXPORT_SYMBOL_GPL(dccp_v4_conn_request); + /* * The three way handshake has completed - we got a valid ACK or DATAACK - * now create the new socket. @@ -792,6 +628,8 @@ exit: return NULL; } +EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock); + static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); @@ -1011,7 +849,9 @@ discard: return 0; } -static inline int dccp_invalid_packet(struct sk_buff *skb) +EXPORT_SYMBOL_GPL(dccp_v4_do_rcv); + +int dccp_invalid_packet(struct sk_buff *skb) { const struct dccp_hdr *dh; @@ -1065,29 +905,30 @@ static inline int dccp_invalid_packet(struct sk_buff *skb) return 1; } - /* If the header checksum is incorrect, drop packet and return */ - if (dccp_v4_verify_checksum(skb, skb->nh.iph->saddr, - skb->nh.iph->daddr) < 0) { - LIMIT_NETDEBUG(KERN_WARNING "DCCP: header checksum is " - "incorrect\n"); - return 1; - } - return 0; } +EXPORT_SYMBOL_GPL(dccp_invalid_packet); + /* this is called when real data arrives */ int dccp_v4_rcv(struct sk_buff *skb) { const struct dccp_hdr *dh; struct sock *sk; - int rc; /* Step 1: Check header basics: */ if (dccp_invalid_packet(skb)) goto discard_it; + /* If the header checksum is incorrect, drop packet and return */ + if (dccp_v4_verify_checksum(skb, skb->nh.iph->saddr, + skb->nh.iph->daddr) < 0) { + LIMIT_NETDEBUG(KERN_WARNING "%s: incorrect header checksum\n", + __FUNCTION__); + goto discard_it; + } + dh = dccp_hdr(skb); DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(skb); @@ -1143,28 +984,10 @@ int dccp_v4_rcv(struct sk_buff *skb) goto do_time_wait; } - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { - dccp_pr_debug("xfrm4_policy_check failed\n"); + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - } - - if (sk_filter(sk, skb, 0)) { - dccp_pr_debug("sk_filter failed\n"); - goto discard_and_relse; - } - - skb->dev = NULL; - - bh_lock_sock(sk); - rc = 0; - if (!sock_owned_by_user(sk)) - rc = dccp_v4_do_rcv(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); - sock_put(sk); - return rc; + return sk_receive_skb(sk, skb); no_dccp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) @@ -1194,9 +1017,23 @@ do_time_wait: goto no_dccp_socket; } -static int dccp_v4_init_sock(struct sock *sk) +struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { + .queue_xmit = ip_queue_xmit, + .send_check = dccp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = dccp_v4_conn_request, + .syn_recv_sock = dccp_v4_request_recv_sock, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ip_setsockopt, + .getsockopt = ip_getsockopt, + .addr2sockaddr = inet_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in), +}; + +int dccp_v4_init_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); + struct inet_connection_sock *icsk = inet_csk(sk); static int dccp_ctl_socket_init = 1; dccp_options_init(&dp->dccps_options); @@ -1236,9 +1073,11 @@ static int dccp_v4_init_sock(struct sock *sk) dccp_ctl_socket_init = 0; dccp_init_xmit_timers(sk); - inet_csk(sk)->icsk_rto = DCCP_TIMEOUT_INIT; + icsk->icsk_rto = DCCP_TIMEOUT_INIT; sk->sk_state = DCCP_CLOSED; sk->sk_write_space = dccp_write_space; + icsk->icsk_af_ops = &dccp_ipv4_af_ops; + icsk->icsk_sync_mss = dccp_sync_mss; dp->dccps_mss_cache = 536; dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_INVALID_VALUE; @@ -1246,7 +1085,9 @@ static int dccp_v4_init_sock(struct sock *sk) return 0; } -static int dccp_v4_destroy_sock(struct sock *sk) +EXPORT_SYMBOL_GPL(dccp_v4_init_sock); + +int dccp_v4_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); @@ -1279,6 +1120,8 @@ static int dccp_v4_destroy_sock(struct sock *sk) return 0; } +EXPORT_SYMBOL_GPL(dccp_v4_destroy_sock); + static void dccp_v4_reqsk_destructor(struct request_sock *req) { kfree(inet_rsk(req)->opt); @@ -1293,7 +1136,11 @@ static struct request_sock_ops dccp_request_sock_ops = { .send_reset = dccp_v4_ctl_send_reset, }; -struct proto dccp_v4_prot = { +static struct timewait_sock_ops dccp_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct inet_timewait_sock), +}; + +struct proto dccp_prot = { .name = "DCCP", .owner = THIS_MODULE, .close = dccp_close, @@ -1307,7 +1154,7 @@ struct proto dccp_v4_prot = { .recvmsg = dccp_recvmsg, .backlog_rcv = dccp_v4_do_rcv, .hash = dccp_v4_hash, - .unhash = dccp_v4_unhash, + .unhash = dccp_unhash, .accept = inet_csk_accept, .get_port = dccp_v4_get_port, .shutdown = dccp_shutdown, @@ -1316,5 +1163,7 @@ struct proto dccp_v4_prot = { .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp_sock), .rsk_prot = &dccp_request_sock_ops, - .twsk_obj_size = sizeof(struct inet_timewait_sock), + .twsk_prot = &dccp_timewait_sock_ops, }; + +EXPORT_SYMBOL_GPL(dccp_prot); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c new file mode 100644 index 00000000000..c609dc78f48 --- /dev/null +++ b/net/dccp/ipv6.c @@ -0,0 +1,1261 @@ +/* + * DCCP over IPv6 + * Linux INET6 implementation + * + * Based on net/dccp6/ipv6.c + * + * Arnaldo Carvalho de Melo <acme@ghostprotocols.net> + * + * 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/config.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/xfrm.h> + +#include <net/addrconf.h> +#include <net/inet_common.h> +#include <net/inet_hashtables.h> +#include <net/inet_sock.h> +#include <net/inet6_connection_sock.h> +#include <net/inet6_hashtables.h> +#include <net/ip6_route.h> +#include <net/ipv6.h> +#include <net/protocol.h> +#include <net/transp_v6.h> +#include <net/xfrm.h> + +#include "dccp.h" +#include "ipv6.h" + +static void dccp_v6_ctl_send_reset(struct sk_buff *skb); +static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, + struct request_sock *req); +static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb); + +static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); + +static struct inet_connection_sock_af_ops dccp_ipv6_mapped; +static struct inet_connection_sock_af_ops dccp_ipv6_af_ops; + +static int dccp_v6_get_port(struct sock *sk, unsigned short snum) +{ + return inet_csk_get_port(&dccp_hashinfo, sk, snum, + inet6_csk_bind_conflict); +} + +static void dccp_v6_hash(struct sock *sk) +{ + if (sk->sk_state != DCCP_CLOSED) { + if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) { + dccp_prot.hash(sk); + return; + } + local_bh_disable(); + __inet6_hash(&dccp_hashinfo, sk); + local_bh_enable(); + } +} + +static inline u16 dccp_v6_check(struct dccp_hdr *dh, int len, + struct in6_addr *saddr, + struct in6_addr *daddr, + unsigned long base) +{ + return csum_ipv6_magic(saddr, daddr, len, IPPROTO_DCCP, base); +} + +static __u32 dccp_v6_init_sequence(struct sock *sk, struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + + if (skb->protocol == htons(ETH_P_IPV6)) + return secure_tcpv6_sequence_number(skb->nh.ipv6h->daddr.s6_addr32, + skb->nh.ipv6h->saddr.s6_addr32, + dh->dccph_dport, + dh->dccph_sport); + else + return secure_dccp_sequence_number(skb->nh.iph->daddr, + skb->nh.iph->saddr, + dh->dccph_dport, + dh->dccph_sport); +} + +static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; + struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct dccp_sock *dp = dccp_sk(sk); + struct in6_addr *saddr = NULL, *final_p = NULL, final; + struct flowi fl; + struct dst_entry *dst; + int addr_type; + int err; + + dp->dccps_role = DCCP_ROLE_CLIENT; + + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + if (usin->sin6_family != AF_INET6) + return -EAFNOSUPPORT; + + memset(&fl, 0, sizeof(fl)); + + if (np->sndflow) { + fl.fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; + IP6_ECN_flow_init(fl.fl6_flowlabel); + if (fl.fl6_flowlabel & IPV6_FLOWLABEL_MASK) { + struct ip6_flowlabel *flowlabel; + flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + if (flowlabel == NULL) + return -EINVAL; + ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + fl6_sock_release(flowlabel); + } + } + + /* + * connect() to INADDR_ANY means loopback (BSD'ism). + */ + + if (ipv6_addr_any(&usin->sin6_addr)) + usin->sin6_addr.s6_addr[15] = 0x1; + + addr_type = ipv6_addr_type(&usin->sin6_addr); + + if(addr_type & IPV6_ADDR_MULTICAST) + return -ENETUNREACH; + + if (addr_type & IPV6_ADDR_LINKLOCAL) { + if (addr_len >= sizeof(struct sockaddr_in6) && + usin->sin6_scope_id) { + /* If interface is set while binding, indices + * must coincide. + */ + if (sk->sk_bound_dev_if && + sk->sk_bound_dev_if != usin->sin6_scope_id) + return -EINVAL; + + sk->sk_bound_dev_if = usin->sin6_scope_id; + } + + /* Connect to link-local address requires an interface */ + if (!sk->sk_bound_dev_if) + return -EINVAL; + } + + ipv6_addr_copy(&np->daddr, &usin->sin6_addr); + np->flow_label = fl.fl6_flowlabel; + + /* + * DCCP over IPv4 + */ + + if (addr_type == IPV6_ADDR_MAPPED) { + u32 exthdrlen = icsk->icsk_ext_hdr_len; + struct sockaddr_in sin; + + SOCK_DEBUG(sk, "connect: ipv4 mapped\n"); + + if (__ipv6_only_sock(sk)) + return -ENETUNREACH; + + sin.sin_family = AF_INET; + sin.sin_port = usin->sin6_port; + sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3]; + + icsk->icsk_af_ops = &dccp_ipv6_mapped; + sk->sk_backlog_rcv = dccp_v4_do_rcv; + + err = dccp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); + + if (err) { + icsk->icsk_ext_hdr_len = exthdrlen; + icsk->icsk_af_ops = &dccp_ipv6_af_ops; + sk->sk_backlog_rcv = dccp_v6_do_rcv; + goto failure; + } else { + ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF), + inet->saddr); + ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF), + inet->rcv_saddr); + } + + return err; + } + + if (!ipv6_addr_any(&np->rcv_saddr)) + saddr = &np->rcv_saddr; + + fl.proto = IPPROTO_DCCP; + ipv6_addr_copy(&fl.fl6_dst, &np->daddr); + ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr); + fl.oif = sk->sk_bound_dev_if; + fl.fl_ip_dport = usin->sin6_port; + fl.fl_ip_sport = inet->sport; + + if (np->opt && np->opt->srcrt) { + struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); + ipv6_addr_copy(&fl.fl6_dst, rt0->addr); + final_p = &final; + } + + err = ip6_dst_lookup(sk, &dst, &fl); + if (err) + goto failure; + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + goto failure; + + if (saddr == NULL) { + saddr = &fl.fl6_src; + ipv6_addr_copy(&np->rcv_saddr, saddr); + } + + /* set the source address */ + ipv6_addr_copy(&np->saddr, saddr); + inet->rcv_saddr = LOOPBACK4_IPV6; + + ip6_dst_store(sk, dst, NULL); + + icsk->icsk_ext_hdr_len = 0; + if (np->opt) + icsk->icsk_ext_hdr_len = (np->opt->opt_flen + + np->opt->opt_nflen); + + inet->dport = usin->sin6_port; + + dccp_set_state(sk, DCCP_REQUESTING); + err = inet6_hash_connect(&dccp_death_row, sk); + if (err) + goto late_failure; + /* FIXME */ +#if 0 + dp->dccps_gar = secure_dccp_v6_sequence_number(np->saddr.s6_addr32, + np->daddr.s6_addr32, + inet->sport, + inet->dport); +#endif + err = dccp_connect(sk); + if (err) + goto late_failure; + + return 0; + +late_failure: + dccp_set_state(sk, DCCP_CLOSED); + __sk_dst_reset(sk); +failure: + inet->dport = 0; + sk->sk_route_caps = 0; + return err; +} + +static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + int type, int code, int offset, __u32 info) +{ + struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; + const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + struct ipv6_pinfo *np; + struct sock *sk; + int err; + __u64 seq; + + sk = inet6_lookup(&dccp_hashinfo, &hdr->daddr, dh->dccph_dport, + &hdr->saddr, dh->dccph_sport, skb->dev->ifindex); + + if (sk == NULL) { + ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + return; + } + + if (sk->sk_state == DCCP_TIME_WAIT) { + inet_twsk_put((struct inet_timewait_sock *)sk); + return; + } + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) + NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); + + if (sk->sk_state == DCCP_CLOSED) + goto out; + + np = inet6_sk(sk); + + if (type == ICMPV6_PKT_TOOBIG) { + struct dst_entry *dst = NULL; + + if (sock_owned_by_user(sk)) + goto out; + if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) + goto out; + + /* icmp should have updated the destination cache entry */ + dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst == NULL) { + struct inet_sock *inet = inet_sk(sk); + struct flowi fl; + + /* BUGGG_FUTURE: Again, it is not clear how + to handle rthdr case. Ignore this complexity + for now. + */ + memset(&fl, 0, sizeof(fl)); + fl.proto = IPPROTO_DCCP; + ipv6_addr_copy(&fl.fl6_dst, &np->daddr); + ipv6_addr_copy(&fl.fl6_src, &np->saddr); + fl.oif = sk->sk_bound_dev_if; + fl.fl_ip_dport = inet->dport; + fl.fl_ip_sport = inet->sport; + + if ((err = ip6_dst_lookup(sk, &dst, &fl))) { + sk->sk_err_soft = -err; + goto out; + } + + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) { + sk->sk_err_soft = -err; + goto out; + } + + } else + dst_hold(dst); + + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + dccp_sync_mss(sk, dst_mtu(dst)); + } /* else let the usual retransmit timer handle it */ + dst_release(dst); + goto out; + } + + icmpv6_err_convert(type, code, &err); + + seq = DCCP_SKB_CB(skb)->dccpd_seq; + /* Might be for an request_sock */ + switch (sk->sk_state) { + struct request_sock *req, **prev; + case DCCP_LISTEN: + if (sock_owned_by_user(sk)) + goto out; + + req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, + &hdr->daddr, &hdr->saddr, + inet6_iif(skb)); + if (!req) + goto out; + + /* ICMPs are not backlogged, hence we cannot get + * an established socket here. + */ + BUG_TRAP(req->sk == NULL); + + if (seq != dccp_rsk(req)->dreq_iss) { + NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + goto out; + } + + inet_csk_reqsk_queue_drop(sk, req, prev); + goto out; + + case DCCP_REQUESTING: + case DCCP_RESPOND: /* Cannot happen. + It can, it SYNs are crossed. --ANK */ + if (!sock_owned_by_user(sk)) { + DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); + sk->sk_err = err; + /* + * Wake people up to see the error + * (see connect in sock.c) + */ + sk->sk_error_report(sk); + + dccp_done(sk); + } else + sk->sk_err_soft = err; + goto out; + } + + if (!sock_owned_by_user(sk) && np->recverr) { + sk->sk_err = err; + sk->sk_error_report(sk); + } else + sk->sk_err_soft = err; + +out: + bh_unlock_sock(sk); + sock_put(sk); +} + + +static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, + struct dst_entry *dst) +{ + struct inet6_request_sock *ireq6 = inet6_rsk(req); + struct ipv6_pinfo *np = inet6_sk(sk); + struct sk_buff *skb; + struct ipv6_txoptions *opt = NULL; + struct in6_addr *final_p = NULL, final; + struct flowi fl; + int err = -1; + + memset(&fl, 0, sizeof(fl)); + fl.proto = IPPROTO_DCCP; + ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); + ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); + fl.fl6_flowlabel = 0; + fl.oif = ireq6->iif; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; + fl.fl_ip_sport = inet_sk(sk)->sport; + + if (dst == NULL) { + opt = np->opt; + if (opt == NULL && + np->rxopt.bits.osrcrt == 2 && + ireq6->pktopts) { + struct sk_buff *pktopts = ireq6->pktopts; + struct inet6_skb_parm *rxopt = IP6CB(pktopts); + if (rxopt->srcrt) + opt = ipv6_invert_rthdr(sk, + (struct ipv6_rt_hdr *)(pktopts->nh.raw + + rxopt->srcrt)); + } + + if (opt && opt->srcrt) { + struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); + ipv6_addr_copy(&fl.fl6_dst, rt0->addr); + final_p = &final; + } + + err = ip6_dst_lookup(sk, &dst, &fl); + if (err) + goto done; + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) + goto done; + } + + skb = dccp_make_response(sk, dst, req); + if (skb != NULL) { + struct dccp_hdr *dh = dccp_hdr(skb); + dh->dccph_checksum = dccp_v6_check(dh, skb->len, + &ireq6->loc_addr, + &ireq6->rmt_addr, + csum_partial((char *)dh, + skb->len, + skb->csum)); + ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); + err = ip6_xmit(sk, skb, &fl, opt, 0); + if (err == NET_XMIT_CN) + err = 0; + } + +done: + if (opt && opt != np->opt) + sock_kfree_s(sk, opt, opt->tot_len); + return err; +} + +static void dccp_v6_reqsk_destructor(struct request_sock *req) +{ + if (inet6_rsk(req)->pktopts != NULL) + kfree_skb(inet6_rsk(req)->pktopts); +} + +static struct request_sock_ops dccp6_request_sock_ops = { + .family = AF_INET6, + .obj_size = sizeof(struct dccp6_request_sock), + .rtx_syn_ack = dccp_v6_send_response, + .send_ack = dccp_v6_reqsk_send_ack, + .destructor = dccp_v6_reqsk_destructor, + .send_reset = dccp_v6_ctl_send_reset, +}; + +static struct timewait_sock_ops dccp6_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct dccp6_timewait_sock), +}; + +static void dccp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct dccp_hdr *dh = dccp_hdr(skb); + + dh->dccph_checksum = csum_ipv6_magic(&np->saddr, &np->daddr, + len, IPPROTO_DCCP, + csum_partial((char *)dh, + dh->dccph_doff << 2, + skb->csum)); +} + +static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) +{ + struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; + const int dccp_hdr_reset_len = sizeof(struct dccp_hdr) + + sizeof(struct dccp_hdr_ext) + + sizeof(struct dccp_hdr_reset); + struct sk_buff *skb; + struct flowi fl; + u64 seqno; + + if (rxdh->dccph_type == DCCP_PKT_RESET) + return; + + if (!ipv6_unicast_destination(rxskb)) + return; + + /* + * We need to grab some memory, and put together an RST, + * and then put it into the queue to be sent. + */ + + skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_reset_len, GFP_ATOMIC); + if (skb == NULL) + return; + + skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_reset_len); + + skb->h.raw = skb_push(skb, dccp_hdr_reset_len); + dh = dccp_hdr(skb); + memset(dh, 0, dccp_hdr_reset_len); + + /* Swap the send and the receive. */ + dh->dccph_type = DCCP_PKT_RESET; + dh->dccph_sport = rxdh->dccph_dport; + dh->dccph_dport = rxdh->dccph_sport; + dh->dccph_doff = dccp_hdr_reset_len / 4; + dh->dccph_x = 1; + dccp_hdr_reset(skb)->dccph_reset_code = + DCCP_SKB_CB(rxskb)->dccpd_reset_code; + + /* See "8.3.1. Abnormal Termination" in draft-ietf-dccp-spec-11 */ + seqno = 0; + if (DCCP_SKB_CB(rxskb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) + dccp_set_seqno(&seqno, DCCP_SKB_CB(rxskb)->dccpd_ack_seq + 1); + + dccp_hdr_set_seq(dh, seqno); + dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), + DCCP_SKB_CB(rxskb)->dccpd_seq); + + memset(&fl, 0, sizeof(fl)); + ipv6_addr_copy(&fl.fl6_dst, &rxskb->nh.ipv6h->saddr); + ipv6_addr_copy(&fl.fl6_src, &rxskb->nh.ipv6h->daddr); + dh->dccph_checksum = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst, + sizeof(*dh), IPPROTO_DCCP, + skb->csum); + fl.proto = IPPROTO_DCCP; + fl.oif = inet6_iif(rxskb); + fl.fl_ip_dport = dh->dccph_dport; + fl.fl_ip_sport = dh->dccph_sport; + + /* sk = NULL, but it is safe for now. RST socket required. */ + if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { + if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { + ip6_xmit(NULL, skb, &fl, NULL, 0); + DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); + DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); + return; + } + } + + kfree_skb(skb); +} + +static void dccp_v6_ctl_send_ack(struct sk_buff *rxskb) +{ + struct flowi fl; + struct dccp_hdr *rxdh = dccp_hdr(rxskb), *dh; + const int dccp_hdr_ack_len = sizeof(struct dccp_hdr) + + sizeof(struct dccp_hdr_ext) + + sizeof(struct dccp_hdr_ack_bits); + struct sk_buff *skb; + + skb = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_ack_len, GFP_ATOMIC); + if (skb == NULL) + return; + + skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr) + + dccp_hdr_ack_len); + + skb->h.raw = skb_push(skb, dccp_hdr_ack_len); + dh = dccp_hdr(skb); + memset(dh, 0, dccp_hdr_ack_len); + + /* Build DCCP header and checksum it. */ + dh->dccph_type = DCCP_PKT_ACK; + dh->dccph_sport = rxdh->dccph_dport; + dh->dccph_dport = rxdh->dccph_sport; + dh->dccph_doff = dccp_hdr_ack_len / 4; + dh->dccph_x = 1; + + dccp_hdr_set_seq(dh, DCCP_SKB_CB(rxskb)->dccpd_ack_seq); + dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), + DCCP_SKB_CB(rxskb)->dccpd_seq); + + memset(&fl, 0, sizeof(fl)); + ipv6_addr_copy(&fl.fl6_dst, &rxskb->nh.ipv6h->saddr); + ipv6_addr_copy(&fl.fl6_src, &rxskb->nh.ipv6h->daddr); + + /* FIXME: calculate checksum, IPv4 also should... */ + + fl.proto = IPPROTO_DCCP; + fl.oif = inet6_iif(rxskb); + fl.fl_ip_dport = dh->dccph_dport; + fl.fl_ip_sport = dh->dccph_sport; + + if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { + if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { + ip6_xmit(NULL, skb, &fl, NULL, 0); + DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); + return; + } + } + + kfree_skb(skb); +} + +static void dccp_v6_reqsk_send_ack(struct sk_buff *skb, + struct request_sock *req) +{ + dccp_v6_ctl_send_ack(skb); +} + +static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) +{ + const struct dccp_hdr *dh = dccp_hdr(skb); + const struct ipv6hdr *iph = skb->nh.ipv6h; + struct sock *nsk; + struct request_sock **prev; + /* Find possible connection requests. */ + struct request_sock *req = inet6_csk_search_req(sk, &prev, + dh->dccph_sport, + &iph->saddr, + &iph->daddr, + inet6_iif(skb)); + if (req != NULL) + return dccp_check_req(sk, skb, req, prev); + + nsk = __inet6_lookup_established(&dccp_hashinfo, + &iph->saddr, dh->dccph_sport, + &iph->daddr, ntohs(dh->dccph_dport), + inet6_iif(skb)); + + if (nsk != NULL) { + if (nsk->sk_state != DCCP_TIME_WAIT) { + bh_lock_sock(nsk); + return nsk; + } + inet_twsk_put((struct inet_timewait_sock *)nsk); + return NULL; + } + + return sk; +} + +static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) +{ + struct inet_request_sock *ireq; + struct dccp_sock dp; + struct request_sock *req; + struct dccp_request_sock *dreq; + struct inet6_request_sock *ireq6; + struct ipv6_pinfo *np = inet6_sk(sk); + const __u32 service = dccp_hdr_request(skb)->dccph_req_service; + struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); + __u8 reset_code = DCCP_RESET_CODE_TOO_BUSY; + + if (skb->protocol == htons(ETH_P_IP)) + return dccp_v4_conn_request(sk, skb); + + if (!ipv6_unicast_destination(skb)) + goto drop; + + if (dccp_bad_service_code(sk, service)) { + reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; + goto drop; + } + /* + * There are no SYN attacks on IPv6, yet... + */ + if (inet_csk_reqsk_queue_is_full(sk)) + goto drop; + + if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) + goto drop; + + req = inet6_reqsk_alloc(sk->sk_prot->rsk_prot); + if (req == NULL) + goto drop; + + /* FIXME: process options */ + + dccp_openreq_init(req, &dp, skb); + + ireq6 = inet6_rsk(req); + ireq = inet_rsk(req); + ipv6_addr_copy(&ireq6->rmt_addr, &skb->nh.ipv6h->saddr); + ipv6_addr_copy(&ireq6->loc_addr, &skb->nh.ipv6h->daddr); + req->rcv_wnd = 100; /* Fake, option parsing will get the + right value */ + ireq6->pktopts = NULL; + + if (ipv6_opt_accepted(sk, skb) || + np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || + np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { + atomic_inc(&skb->users); + ireq6->pktopts = skb; + } + ireq6->iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq6->iif = inet6_iif(skb); + + /* + * Step 3: Process LISTEN state + * + * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie + * + * In fact we defer setting S.GSR, S.SWL, S.SWH to + * dccp_create_openreq_child. + */ + dreq = dccp_rsk(req); + dreq->dreq_isr = dcb->dccpd_seq; + dreq->dreq_iss = dccp_v6_init_sequence(sk, skb); + dreq->dreq_service = service; + + if (dccp_v6_send_response(sk, req, NULL)) + goto drop_and_free; + + inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); + return 0; + +drop_and_free: + reqsk_free(req); +drop: + DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS); + dcb->dccpd_reset_code = reset_code; + return -1; +} + +static struct sock *dccp_v6_request_recv_sock(struct sock *sk, + struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst) +{ + struct inet6_request_sock *ireq6 = inet6_rsk(req); + struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct inet_sock *newinet; + struct dccp_sock *newdp; + struct dccp6_sock *newdp6; + struct sock *newsk; + struct ipv6_txoptions *opt; + + if (skb->protocol == htons(ETH_P_IP)) { + /* + * v6 mapped + */ + + newsk = dccp_v4_request_recv_sock(sk, skb, req, dst); + if (newsk == NULL) + return NULL; + + newdp6 = (struct dccp6_sock *)newsk; + newdp = dccp_sk(newsk); + newinet = inet_sk(newsk); + newinet->pinet6 = &newdp6->inet6; + newnp = inet6_sk(newsk); + + memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + + ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), + newinet->daddr); + + ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), + newinet->saddr); + + ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + + inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; + newsk->sk_backlog_rcv = dccp_v4_do_rcv; + newnp->pktoptions = NULL; + newnp->opt = NULL; + newnp->mcast_oif = inet6_iif(skb); + newnp->mcast_hops = skb->nh.ipv6h->hop_limit; + + /* + * No need to charge this sock to the relevant IPv6 refcnt debug socks count + * here, dccp_create_openreq_child now does this for us, see the comment in + * that function for the gory details. -acme + */ + + /* It is tricky place. Until this moment IPv4 tcp + worked with IPv6 icsk.icsk_af_ops. + Sync it now. + */ + dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie); + + return newsk; + } + + opt = np->opt; + + if (sk_acceptq_is_full(sk)) + goto out_overflow; + + if (np->rxopt.bits.osrcrt == 2 && + opt == NULL && ireq6->pktopts) { + struct inet6_skb_parm *rxopt = IP6CB(ireq6->pktopts); + if (rxopt->srcrt) + opt = ipv6_invert_rthdr(sk, + (struct ipv6_rt_hdr *)(ireq6->pktopts->nh.raw + + rxopt->srcrt)); + } + + if (dst == NULL) { + struct in6_addr *final_p = NULL, final; + struct flowi fl; + + memset(&fl, 0, sizeof(fl)); + fl.proto = IPPROTO_DCCP; + ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); + if (opt && opt->srcrt) { + struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt; + ipv6_addr_copy(&final, &fl.fl6_dst); + ipv6_addr_copy(&fl.fl6_dst, rt0->addr); + final_p = &final; + } + ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); + fl.oif = sk->sk_bound_dev_if; + fl.fl_ip_dport = inet_rsk(req)->rmt_port; + fl.fl_ip_sport = inet_sk(sk)->sport; + + if (ip6_dst_lookup(sk, &dst, &fl)) + goto out; + + if (final_p) + ipv6_addr_copy(&fl.fl6_dst, final_p); + + if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) + goto out; + } + + newsk = dccp_create_openreq_child(sk, req, skb); + if (newsk == NULL) + goto out; + + /* + * No need to charge this sock to the relevant IPv6 refcnt debug socks + * count here, dccp_create_openreq_child now does this for us, see the + * comment in that function for the gory details. -acme + */ + + ip6_dst_store(newsk, dst, NULL); + newsk->sk_route_caps = dst->dev->features & + ~(NETIF_F_IP_CSUM | NETIF_F_TSO); + + newdp6 = (struct dccp6_sock *)newsk; + newinet = inet_sk(newsk); + newinet->pinet6 = &newdp6->inet6; + newdp = dccp_sk(newsk); + newnp = inet6_sk(newsk); + + memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + + ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr); + ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr); + ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr); + newsk->sk_bound_dev_if = ireq6->iif; + + /* Now IPv6 options... + + First: no IPv4 options. + */ + newinet->opt = NULL; + + /* Clone RX bits */ + newnp->rxopt.all = np->rxopt.all; + + /* Clone pktoptions received with SYN */ + newnp->pktoptions = NULL; + if (ireq6->pktopts != NULL) { + newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC); + kfree_skb(ireq6->pktopts); + ireq6->pktopts = NULL; + if (newnp->pktoptions) + skb_set_owner_r(newnp->pktoptions, newsk); + } + newnp->opt = NULL; + newnp->mcast_oif = inet6_iif(skb); + newnp->mcast_hops = skb->nh.ipv6h->hop_limit; + + /* Clone native IPv6 options from listening socket (if any) + + Yes, keeping reference count would be much more clever, + but we make one more one thing there: reattach optmem + to newsk. + */ + if (opt) { + newnp->opt = ipv6_dup_options(newsk, opt); + if (opt != np->opt) + sock_kfree_s(sk, opt, opt->tot_len); + } + + inet_csk(newsk)->icsk_ext_hdr_len = 0; + if (newnp->opt) + inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen + + newnp->opt->opt_flen); + + dccp_sync_mss(newsk, dst_mtu(dst)); + + newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + + __inet6_hash(&dccp_hashinfo, newsk); + inet_inherit_port(&dccp_hashinfo, sk, newsk); + + return newsk; + +out_overflow: + NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); +out: + NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); + if (opt && opt != np->opt) + sock_kfree_s(sk, opt, opt->tot_len); + dst_release(dst); + return NULL; +} + +/* The socket must have it's spinlock held when we get + * here. + * + * We have a potential double-lock case here, so even when + * doing backlog processing we use the BH locking scheme. + * This is because we cannot sleep with the original spinlock + * held. + */ +static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + struct sk_buff *opt_skb = NULL; + + /* Imagine: socket is IPv6. IPv4 packet arrives, + goes to IPv4 receive handler and backlogged. + From backlog it always goes here. Kerboom... + Fortunately, dccp_rcv_established and rcv_established + handle them correctly, but it is not case with + dccp_v6_hnd_req and dccp_v6_ctl_send_reset(). --ANK + */ + + if (skb->protocol == htons(ETH_P_IP)) + return dccp_v4_do_rcv(sk, skb); + + if (sk_filter(sk, skb, 0)) + goto discard; + + /* + * socket locking is here for SMP purposes as backlog rcv + * is currently called with bh processing disabled. + */ + + /* Do Stevens' IPV6_PKTOPTIONS. + + Yes, guys, it is the only place in our code, where we + may make it not affecting IPv4. + The rest of code is protocol independent, + and I do not like idea to uglify IPv4. + + Actually, all the idea behind IPV6_PKTOPTIONS + looks not very well thought. For now we latch + options, received in the last packet, enqueued + by tcp. Feel free to propose better solution. + --ANK (980728) + */ + if (np->rxopt.all) + opt_skb = skb_clone(skb, GFP_ATOMIC); + + if (sk->sk_state == DCCP_OPEN) { /* Fast path */ + if (dccp_rcv_established(sk, skb, dccp_hdr(skb), skb->len)) + goto reset; + return 0; + } + + if (sk->sk_state == DCCP_LISTEN) { + struct sock *nsk = dccp_v6_hnd_req(sk, skb); + if (!nsk) + goto discard; + + /* + * Queue it on the new socket if the new socket is active, + * otherwise we just shortcircuit this and continue with + * the new socket.. + */ + if(nsk != sk) { + if (dccp_child_process(sk, nsk, skb)) + goto reset; + if (opt_skb) + __kfree_skb(opt_skb); + return 0; + } + } + + if (dccp_rcv_state_process(sk, skb, dccp_hdr(skb), skb->len)) + goto reset; + return 0; + +reset: + dccp_v6_ctl_send_reset(skb); +discard: + if (opt_skb) + __kfree_skb(opt_skb); + kfree_skb(skb); + return 0; +} + +static int dccp_v6_rcv(struct sk_buff **pskb, unsigned int *nhoffp) +{ + const struct dccp_hdr *dh; + struct sk_buff *skb = *pskb; + struct sock *sk; + + /* Step 1: Check header basics: */ + + if (dccp_invalid_packet(skb)) + goto discard_it; + + dh = dccp_hdr(skb); + + DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(skb); + DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; + + if (dccp_packet_without_ack(skb)) + DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ; + else + DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb); + + /* Step 2: + * Look up flow ID in table and get corresponding socket */ + sk = __inet6_lookup(&dccp_hashinfo, &skb->nh.ipv6h->saddr, + dh->dccph_sport, + &skb->nh.ipv6h->daddr, ntohs(dh->dccph_dport), + inet6_iif(skb)); + /* + * Step 2: + * If no socket ... + * Generate Reset(No Connection) unless P.type == Reset + * Drop packet and return + */ + if (sk == NULL) + goto no_dccp_socket; + + /* + * Step 2: + * ... or S.state == TIMEWAIT, + * Generate Reset(No Connection) unless P.type == Reset + * Drop packet and return + */ + + if (sk->sk_state == DCCP_TIME_WAIT) + goto do_time_wait; + + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + goto discard_and_relse; + + return sk_receive_skb(sk, skb) ? -1 : 0; + +no_dccp_socket: + if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto discard_it; + /* + * Step 2: + * Generate Reset(No Connection) unless P.type == Reset + * Drop packet and return + */ + if (dh->dccph_type != DCCP_PKT_RESET) { + DCCP_SKB_CB(skb)->dccpd_reset_code = + DCCP_RESET_CODE_NO_CONNECTION; + dccp_v6_ctl_send_reset(skb); + } +discard_it: + + /* + * Discard frame + */ + + kfree_skb(skb); + return 0; + +discard_and_relse: + sock_put(sk); + goto discard_it; + +do_time_wait: + inet_twsk_put((struct inet_timewait_sock *)sk); + goto no_dccp_socket; +} + +static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { + .queue_xmit = inet6_csk_xmit, + .send_check = dccp_v6_send_check, + .rebuild_header = inet6_sk_rebuild_header, + .conn_request = dccp_v6_conn_request, + .syn_recv_sock = dccp_v6_request_recv_sock, + .net_header_len = sizeof(struct ipv6hdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6) +}; + +/* + * DCCP over IPv4 via INET6 API + */ +static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { + .queue_xmit = ip_queue_xmit, + .send_check = dccp_v4_send_check, + .rebuild_header = inet_sk_rebuild_header, + .conn_request = dccp_v6_conn_request, + .syn_recv_sock = dccp_v6_request_recv_sock, + .net_header_len = sizeof(struct iphdr), + .setsockopt = ipv6_setsockopt, + .getsockopt = ipv6_getsockopt, + .addr2sockaddr = inet6_csk_addr2sockaddr, + .sockaddr_len = sizeof(struct sockaddr_in6) +}; + +/* NOTE: A lot of things set to zero explicitly by call to + * sk_alloc() so need not be done here. + */ +static int dccp_v6_init_sock(struct sock *sk) +{ + int err = dccp_v4_init_sock(sk); + + if (err == 0) + inet_csk(sk)->icsk_af_ops = &dccp_ipv6_af_ops; + + return err; +} + +static int dccp_v6_destroy_sock(struct sock *sk) +{ + dccp_v4_destroy_sock(sk); + return inet6_destroy_sock(sk); +} + +static struct proto dccp_v6_prot = { + .name = "DCCPv6", + .owner = THIS_MODULE, + .close = dccp_close, + .connect = dccp_v6_connect, + .disconnect = dccp_disconnect, + .ioctl = dccp_ioctl, + .init = dccp_v6_init_sock, + .setsockopt = dccp_setsockopt, + .getsockopt = dccp_getsockopt, + .sendmsg = dccp_sendmsg, + .recvmsg = dccp_recvmsg, + .backlog_rcv = dccp_v6_do_rcv, + .hash = dccp_v6_hash, + .unhash = dccp_unhash, + .accept = inet_csk_accept, + .get_port = dccp_v6_get_port, + .shutdown = dccp_shutdown, + .destroy = dccp_v6_destroy_sock, + .orphan_count = &dccp_orphan_count, + .max_header = MAX_DCCP_HEADER, + .obj_size = sizeof(struct dccp6_sock), + .rsk_prot = &dccp6_request_sock_ops, + .twsk_prot = &dccp6_timewait_sock_ops, +}; + +static struct inet6_protocol dccp_v6_protocol = { + .handler = dccp_v6_rcv, + .err_handler = dccp_v6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, +}; + +static struct proto_ops inet6_dccp_ops = { + .family = PF_INET6, + .owner = THIS_MODULE, + .release = inet6_release, + .bind = inet6_bind, + .connect = inet_stream_connect, + .socketpair = sock_no_socketpair, + .accept = inet_accept, + .getname = inet6_getname, + .poll = dccp_poll, + .ioctl = inet6_ioctl, + .listen = inet_dccp_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, +}; + +static struct inet_protosw dccp_v6_protosw = { + .type = SOCK_DCCP, + .protocol = IPPROTO_DCCP, + .prot = &dccp_v6_prot, + .ops = &inet6_dccp_ops, + .capability = -1, + .flags = INET_PROTOSW_ICSK, +}; + +static int __init dccp_v6_init(void) +{ + int err = proto_register(&dccp_v6_prot, 1); + + if (err != 0) + goto out; + + err = inet6_add_protocol(&dccp_v6_protocol, IPPROTO_DCCP); + if (err != 0) + goto out_unregister_proto; + + inet6_register_protosw(&dccp_v6_protosw); +out: + return err; +out_unregister_proto: + proto_unregister(&dccp_v6_prot); + goto out; +} + +static void __exit dccp_v6_exit(void) +{ + inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); + inet6_unregister_protosw(&dccp_v6_protosw); + proto_unregister(&dccp_v6_prot); +} + +module_init(dccp_v6_init); +module_exit(dccp_v6_exit); + +/* + * __stringify doesn't likes enums, so use SOCK_DCCP (6) and IPPROTO_DCCP (33) + * values directly, Also cover the case where the protocol is not specified, + * i.e. net-pf-PF_INET6-proto-0-type-SOCK_DCCP + */ +MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-33-type-6"); +MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-0-type-6"); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); +MODULE_DESCRIPTION("DCCPv6 - Datagram Congestion Controlled Protocol"); diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h new file mode 100644 index 00000000000..e4d4e930927 --- /dev/null +++ b/net/dccp/ipv6.h @@ -0,0 +1,37 @@ +#ifndef _DCCP_IPV6_H +#define _DCCP_IPV6_H +/* + * net/dccp/ipv6.h + * + * An implementation of the DCCP protocol + * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/config.h> +#include <linux/dccp.h> +#include <linux/ipv6.h> + +struct dccp6_sock { + struct dccp_sock dccp; + /* + * ipv6_pinfo has to be the last member of dccp6_sock, + * see inet6_sk_generic. + */ + struct ipv6_pinfo inet6; +}; + +struct dccp6_request_sock { + struct dccp_request_sock dccp; + struct inet6_request_sock inet6; +}; + +struct dccp6_timewait_sock { + struct inet_timewait_sock inet; + struct inet6_timewait_sock tw6; +}; + +#endif /* _DCCP_IPV6_H */ diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 1393461898b..29261fc198e 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -40,6 +40,8 @@ struct inet_timewait_death_row dccp_death_row = { (unsigned long)&dccp_death_row), }; +EXPORT_SYMBOL_GPL(dccp_death_row); + void dccp_time_wait(struct sock *sk, int state, int timeo) { struct inet_timewait_sock *tw = NULL; @@ -50,7 +52,18 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) if (tw != NULL) { const struct inet_connection_sock *icsk = inet_csk(sk); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); - +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + if (tw->tw_family == PF_INET6) { + const struct ipv6_pinfo *np = inet6_sk(sk); + struct inet6_timewait_sock *tw6; + + tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); + tw6 = inet6_twsk((struct sock *)tw); + ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr); + ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr); + tw->tw_ipv6only = np->ipv6only; + } +#endif /* Linkage updates. */ __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); @@ -170,6 +183,8 @@ out_free: return newsk; } +EXPORT_SYMBOL_GPL(dccp_create_openreq_child); + /* * Process an incoming packet for RESPOND sockets represented * as an request_sock. @@ -214,7 +229,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, goto drop; } - child = dccp_v4_request_recv_sock(sk, skb, req, NULL); + child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); if (child == NULL) goto listen_overflow; @@ -236,6 +251,8 @@ drop: goto out; } +EXPORT_SYMBOL_GPL(dccp_check_req); + /* * Queue segment on the new socket if the new socket is active, * otherwise we just shortcircuit this and continue with @@ -266,3 +283,5 @@ int dccp_child_process(struct sock *parent, struct sock *child, sock_put(child); return ret; } + +EXPORT_SYMBOL_GPL(dccp_child_process); diff --git a/net/dccp/output.c b/net/dccp/output.c index 74ff8702587..efd7ffb903a 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> +#include <net/inet_sock.h> #include <net/sock.h> #include "ackvec.h" @@ -43,6 +44,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) { if (likely(skb != NULL)) { const struct inet_sock *inet = inet_sk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); struct dccp_sock *dp = dccp_sk(sk); struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); struct dccp_hdr *dh; @@ -108,8 +110,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) break; } - dh->dccph_checksum = dccp_v4_checksum(skb, inet->saddr, - inet->daddr); + icsk->icsk_af_ops->send_check(sk, skb->len, skb); if (set_ack) dccp_event_ack_sent(sk); @@ -117,7 +118,7 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) DCCP_INC_STATS(DCCP_MIB_OUTSEGS); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - err = ip_queue_xmit(skb, 0); + err = icsk->icsk_af_ops->queue_xmit(skb, 0); if (err <= 0) return err; @@ -134,20 +135,13 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) { + struct inet_connection_sock *icsk = inet_csk(sk); struct dccp_sock *dp = dccp_sk(sk); - int mss_now; - - /* - * FIXME: we really should be using the af_specific thing to support - * IPv6. - * mss_now = pmtu - tp->af_specific->net_header_len - - * sizeof(struct dccp_hdr) - sizeof(struct dccp_hdr_ext); - */ - mss_now = pmtu - sizeof(struct iphdr) - sizeof(struct dccp_hdr) - - sizeof(struct dccp_hdr_ext); + int mss_now = (pmtu - icsk->icsk_af_ops->net_header_len - + sizeof(struct dccp_hdr) - sizeof(struct dccp_hdr_ext)); /* Now subtract optional transport overhead */ - mss_now -= dp->dccps_ext_header_len; + mss_now -= icsk->icsk_ext_hdr_len; /* * FIXME: this should come from the CCID infrastructure, where, say, @@ -160,12 +154,14 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) mss_now -= ((5 + 6 + 10 + 6 + 6 + 6 + 3) / 4) * 4; /* And store cached results */ - dp->dccps_pmtu_cookie = pmtu; + icsk->icsk_pmtu_cookie = pmtu; dp->dccps_mss_cache = mss_now; return mss_now; } +EXPORT_SYMBOL_GPL(dccp_sync_mss); + void dccp_write_space(struct sock *sk) { read_lock(&sk->sk_callback_lock); @@ -266,7 +262,7 @@ int dccp_write_xmit(struct sock *sk, struct sk_buff *skb, long *timeo) int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb) { - if (inet_sk_rebuild_header(sk) != 0) + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0) return -EHOSTUNREACH; /* Routing failure or similar. */ return dccp_transmit_skb(sk, (skb_cloned(skb) ? @@ -321,6 +317,8 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, return skb; } +EXPORT_SYMBOL_GPL(dccp_make_response); + struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, const enum dccp_reset_codes code) @@ -377,6 +375,7 @@ struct sk_buff *dccp_make_reset(struct sock *sk, struct dst_entry *dst, */ static inline void dccp_connect_init(struct sock *sk) { + struct dccp_sock *dp = dccp_sk(sk); struct dst_entry *dst = __sk_dst_get(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -385,10 +384,16 @@ static inline void dccp_connect_init(struct sock *sk) dccp_sync_mss(sk, dst_mtu(dst)); - /* - * FIXME: set dp->{dccps_swh,dccps_swl}, with - * something like dccp_inc_seq - */ + dccp_update_gss(sk, dp->dccps_iss); + /* + * SWL and AWL are initially adjusted so that they are not less than + * the initial Sequence Numbers received and sent, respectively: + * SWL := max(GSR + 1 - floor(W/4), ISR), + * AWL := max(GSS - W' + 1, ISS). + * These adjustments MUST be applied only at the beginning of the + * connection. + */ + dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss)); icsk->icsk_retransmits = 0; } @@ -420,6 +425,8 @@ int dccp_connect(struct sock *sk) return 0; } +EXPORT_SYMBOL_GPL(dccp_connect); + void dccp_send_ack(struct sock *sk) { /* If we have been reset, we may not send again. */ diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 8a6b2a9e458..65b11ea90d8 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -24,7 +24,7 @@ #include <net/checksum.h> #include <net/inet_common.h> -#include <net/ip.h> +#include <net/inet_sock.h> #include <net/protocol.h> #include <net/sock.h> #include <net/xfrm.h> @@ -34,15 +34,18 @@ #include <linux/timer.h> #include <linux/delay.h> #include <linux/poll.h> -#include <linux/dccp.h> #include "ccid.h" #include "dccp.h" DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; +EXPORT_SYMBOL_GPL(dccp_statistics); + atomic_t dccp_orphan_count = ATOMIC_INIT(0); +EXPORT_SYMBOL_GPL(dccp_orphan_count); + static struct net_protocol dccp_protocol = { .handler = dccp_v4_rcv, .err_handler = dccp_v4_err, @@ -149,6 +152,8 @@ int dccp_disconnect(struct sock *sk, int flags) return err; } +EXPORT_SYMBOL_GPL(dccp_disconnect); + /* * Wait for a DCCP event. * @@ -156,8 +161,8 @@ int dccp_disconnect(struct sock *sk, int flags) * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ -static unsigned int dccp_poll(struct file *file, struct socket *sock, - poll_table *wait) +unsigned int dccp_poll(struct file *file, struct socket *sock, + poll_table *wait) { unsigned int mask; struct sock *sk = sock->sk; @@ -205,12 +210,16 @@ static unsigned int dccp_poll(struct file *file, struct socket *sock, return mask; } +EXPORT_SYMBOL_GPL(dccp_poll); + int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) { dccp_pr_debug("entry\n"); return -ENOIOCTLCMD; } +EXPORT_SYMBOL_GPL(dccp_ioctl); + static int dccp_setsockopt_service(struct sock *sk, const u32 service, char __user *optval, int optlen) { @@ -254,7 +263,9 @@ int dccp_setsockopt(struct sock *sk, int level, int optname, int val; if (level != SOL_DCCP) - return ip_setsockopt(sk, level, optname, optval, optlen); + return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, + optname, optval, + optlen); if (optlen < sizeof(int)) return -EINVAL; @@ -282,6 +293,8 @@ int dccp_setsockopt(struct sock *sk, int level, int optname, return err; } +EXPORT_SYMBOL_GPL(dccp_setsockopt); + static int dccp_getsockopt_service(struct sock *sk, int len, u32 __user *optval, int __user *optlen) @@ -320,8 +333,9 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, int val, len; if (level != SOL_DCCP) - return ip_getsockopt(sk, level, optname, optval, optlen); - + return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level, + optname, optval, + optlen); if (get_user(len, optlen)) return -EFAULT; @@ -354,6 +368,8 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, return 0; } +EXPORT_SYMBOL_GPL(dccp_getsockopt); + int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { @@ -410,6 +426,8 @@ out_discard: goto out_release; } +EXPORT_SYMBOL_GPL(dccp_sendmsg); + int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len) { @@ -507,7 +525,9 @@ out: return len; } -static int inet_dccp_listen(struct socket *sock, int backlog) +EXPORT_SYMBOL_GPL(dccp_recvmsg); + +int inet_dccp_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; @@ -543,6 +563,8 @@ out: return err; } +EXPORT_SYMBOL_GPL(inet_dccp_listen); + static const unsigned char dccp_new_state[] = { /* current state: new state: action: */ [0] = DCCP_CLOSED, @@ -648,12 +670,16 @@ adjudge_to_death: sock_put(sk); } +EXPORT_SYMBOL_GPL(dccp_close); + void dccp_shutdown(struct sock *sk, int how) { dccp_pr_debug("entry\n"); } -static struct proto_ops inet_dccp_ops = { +EXPORT_SYMBOL_GPL(dccp_shutdown); + +static const struct proto_ops inet_dccp_ops = { .family = PF_INET, .owner = THIS_MODULE, .release = inet_release, @@ -681,11 +707,11 @@ extern struct net_proto_family inet_family_ops; static struct inet_protosw dccp_v4_protosw = { .type = SOCK_DCCP, .protocol = IPPROTO_DCCP, - .prot = &dccp_v4_prot, + .prot = &dccp_prot, .ops = &inet_dccp_ops, .capability = -1, .no_check = 0, - .flags = 0, + .flags = INET_PROTOSW_ICSK, }; /* @@ -760,13 +786,15 @@ MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); int dccp_debug; module_param(dccp_debug, int, 0444); MODULE_PARM_DESC(dccp_debug, "Enable debug messages"); + +EXPORT_SYMBOL_GPL(dccp_debug); #endif static int __init dccp_init(void) { unsigned long goal; int ehash_order, bhash_order, i; - int rc = proto_register(&dccp_v4_prot, 1); + int rc = proto_register(&dccp_prot, 1); if (rc) goto out; @@ -869,7 +897,7 @@ out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_hashinfo.bind_bucket_cachep = NULL; out_proto_unregister: - proto_unregister(&dccp_v4_prot); + proto_unregister(&dccp_prot); goto out; } @@ -892,7 +920,7 @@ static void __exit dccp_fini(void) get_order(dccp_hashinfo.ehash_size * sizeof(struct inet_ehash_bucket))); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); - proto_unregister(&dccp_v4_prot); + proto_unregister(&dccp_prot); } module_init(dccp_init); |