void reqsk_queue_destroy(struct request_sock_queue *queue)
{
/* make all the listen_opt local to us */
struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue);
if (listen_sock_qlen(lopt) != 0) {
unsigned int i;
for (i = 0; i < lopt->nr_table_entries; i++) {
struct request_sock *req;
spin_lock_bh(&queue->syn_wait_lock);
while ((req = lopt->syn_table[i]) != NULL) {
lopt->syn_table[i] = req->dl_next;
/* Because of following del_timer_sync(),
* we must release the spinlock here
* or risk a dead lock.
*/
spin_unlock_bh(&queue->syn_wait_lock);
atomic_inc(&lopt->qlen_dec);
if (del_timer_sync(&req->rsk_timer))
reqsk_put(req);
reqsk_put(req);
spin_lock_bh(&queue->syn_wait_lock);
}
spin_unlock_bh(&queue->syn_wait_lock);
}
}
if (WARN_ON(listen_sock_qlen(lopt) != 0))
pr_err("qlen %u\n", listen_sock_qlen(lopt));
kvfree(lopt);
}
static bool tcp_fastopen_queue_check(struct sock *sk)
{
struct fastopen_queue *fastopenq;
/* Make sure the listener has enabled fastopen, and we don't
* exceed the max # of pending TFO requests allowed before trying
* to validating the cookie in order to avoid burning CPU cycles
* unnecessarily.
*
* XXX (TFO) - The implication of checking the max_qlen before
* processing a cookie request is that clients can't differentiate
* between qlen overflow causing Fast Open to be disabled
* temporarily vs a server not supporting Fast Open at all.
*/
fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
if (!fastopenq || fastopenq->max_qlen == 0)
return false;
if (fastopenq->qlen >= fastopenq->max_qlen) {
struct request_sock *req1;
spin_lock(&fastopenq->lock);
req1 = fastopenq->rskq_rst_head;
if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) {
spin_unlock(&fastopenq->lock);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
return false;
}
fastopenq->rskq_rst_head = req1->dl_next;
fastopenq->qlen--;
spin_unlock(&fastopenq->lock);
reqsk_put(req1);
}
return true;
}
static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
{
const struct dccp_hdr *dh = dccp_hdr(skb);
const struct iphdr *iph = ip_hdr(skb);
struct sock *nsk;
/* Find possible connection requests. */
struct request_sock *req = inet_csk_search_req(sk, dh->dccph_sport,
iph->saddr, iph->daddr);
if (req) {
nsk = dccp_check_req(sk, skb, req);
if (!nsk)
reqsk_put(req);
return nsk;
}
nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo,
iph->saddr, dh->dccph_sport,
iph->daddr, dh->dccph_dport,
inet_iif(skb));
if (nsk != NULL) {
if (nsk->sk_state != DCCP_TIME_WAIT) {
bh_lock_sock(nsk);
return nsk;
}
inet_twsk_put(inet_twsk(nsk));
return NULL;
}
return sk;
}
/*
* This function is called to set a Fast Open socket's "fastopen_rsk" field
* to NULL when a TFO socket no longer needs to access the request_sock.
* This happens only after 3WHS has been either completed or aborted (e.g.,
* RST is received).
*
* Before TFO, a child socket is created only after 3WHS is completed,
* hence it never needs to access the request_sock. things get a lot more
* complex with TFO. A child socket, accepted or not, has to access its
* request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts,
* until 3WHS is either completed or aborted. Afterwards the req will stay
* until either the child socket is accepted, or in the rare case when the
* listener is closed before the child is accepted.
*
* In short, a request socket is only freed after BOTH 3WHS has completed
* (or aborted) and the child socket has been accepted (or listener closed).
* When a child socket is accepted, its corresponding req->sk is set to
* NULL since it's no longer needed. More importantly, "req->sk == NULL"
* will be used by the code below to determine if a child socket has been
* accepted or not, and the check is protected by the fastopenq->lock
* described below.
*
* Note that fastopen_rsk is only accessed from the child socket's context
* with its socket lock held. But a request_sock (req) can be accessed by
* both its child socket through fastopen_rsk, and a listener socket through
* icsk_accept_queue.rskq_accept_head. To protect the access a simple spin
* lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created.
* only in the rare case when both the listener and the child locks are held,
* e.g., in inet_csk_listen_stop() do we not need to acquire the lock.
* The lock also protects other fields such as fastopenq->qlen, which is
* decremented by this function when fastopen_rsk is no longer needed.
*
* Note that another solution was to simply use the existing socket lock
* from the listener. But first socket lock is difficult to use. It is not
* a simple spin lock - one must consider sock_owned_by_user() and arrange
* to use sk_add_backlog() stuff. But what really makes it infeasible is the
* locking hierarchy violation. E.g., inet_csk_listen_stop() may try to
* acquire a child's lock while holding listener's socket lock. A corner
* case might also exist in tcp_v4_hnd_req() that will trigger this locking
* order.
*
* This function also sets "treq->tfo_listener" to false.
* treq->tfo_listener is used by the listener so it is protected by the
* fastopenq->lock in this function.
*/
void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
bool reset)
{
struct sock *lsk = req->rsk_listener;
struct fastopen_queue *fastopenq;
fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq;
tcp_sk(sk)->fastopen_rsk = NULL;
spin_lock_bh(&fastopenq->lock);
fastopenq->qlen--;
tcp_rsk(req)->tfo_listener = false;
if (req->sk) /* the child socket hasn't been accepted yet */
goto out;
if (!reset || lsk->sk_state != TCP_LISTEN) {
/* If the listener has been closed don't bother with the
* special RST handling below.
*/
spin_unlock_bh(&fastopenq->lock);
reqsk_put(req);
return;
}
/* Wait for 60secs before removing a req that has triggered RST.
* This is a simple defense against TFO spoofing attack - by
* counting the req against fastopen.max_qlen, and disabling
* TFO when the qlen exceeds max_qlen.
*
* For more details see CoNext'11 "TCP Fast Open" paper.
*/
req->rsk_timer.expires = jiffies + 60*HZ;
if (fastopenq->rskq_rst_head == NULL)
fastopenq->rskq_rst_head = req;
else
fastopenq->rskq_rst_tail->dl_next = req;
req->dl_next = NULL;
fastopenq->rskq_rst_tail = req;
fastopenq->qlen++;
out:
spin_unlock_bh(&fastopenq->lock);
}
void dccp_req_err(struct sock *sk, u64 seq)
{
struct request_sock *req = inet_reqsk(sk);
struct net *net = sock_net(sk);
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
if (!between48(seq, dccp_rsk(req)->dreq_iss, dccp_rsk(req)->dreq_gss)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
} else {
/*
* Still in RESPOND, just remove it silently.
* There is no good way to pass the error to the newly
* created socket, and POSIX does not want network
* errors returned from accept().
*/
inet_csk_reqsk_queue_drop(req->rsk_listener, req);
}
reqsk_put(req);
}
/* this is called when real data arrives */
static int dccp_v4_rcv(struct sk_buff *skb)
{
const struct dccp_hdr *dh;
const struct iphdr *iph;
struct sock *sk;
int min_cov;
/* Step 1: Check header basics */
if (dccp_invalid_packet(skb))
goto discard_it;
iph = ip_hdr(skb);
/* Step 1: If header checksum is incorrect, drop packet and return */
if (dccp_v4_csum_finish(skb, iph->saddr, iph->daddr)) {
DCCP_WARN("dropped packet with invalid checksum\n");
goto discard_it;
}
dh = dccp_hdr(skb);
DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh);
DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type;
dccp_pr_debug("%8.8s src=%pI4@%-5d dst=%pI4@%-5d seq=%llu",
dccp_packet_name(dh->dccph_type),
&iph->saddr, ntohs(dh->dccph_sport),
&iph->daddr, ntohs(dh->dccph_dport),
(unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq);
if (dccp_packet_without_ack(skb)) {
DCCP_SKB_CB(skb)->dccpd_ack_seq = DCCP_PKT_WITHOUT_ACK_SEQ;
dccp_pr_debug_cat("\n");
} else {
DCCP_SKB_CB(skb)->dccpd_ack_seq = dccp_hdr_ack_seq(skb);
dccp_pr_debug_cat(", ack=%llu\n", (unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
}
lookup:
sk = __inet_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
dh->dccph_sport, dh->dccph_dport);
if (!sk) {
dccp_pr_debug("failed to look up flow ID in table and "
"get corresponding socket\n");
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) {
dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n");
inet_twsk_put(inet_twsk(sk));
goto no_dccp_socket;
}
if (sk->sk_state == DCCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
struct sock *nsk;
sk = req->rsk_listener;
if (unlikely(sk->sk_state != DCCP_LISTEN)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
}
sock_hold(sk);
nsk = dccp_check_req(sk, skb, req);
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
} else if (dccp_child_process(sk, nsk, skb)) {
dccp_v4_ctl_send_reset(sk, skb);
goto discard_and_relse;
} else {
sock_put(sk);
return 0;
}
}
/*
* RFC 4340, sec. 9.2.1: Minimum Checksum Coverage
* o if MinCsCov = 0, only packets with CsCov = 0 are accepted
* o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov
*/
min_cov = dccp_sk(sk)->dccps_pcrlen;
if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) {
dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n",
dh->dccph_cscov, min_cov);
/* FIXME: "Such packets SHOULD be reported using Data Dropped
* options (Section 11.7) with Drop Code 0, Protocol
* Constraints." */
goto discard_and_relse;
}
if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
nf_reset(skb);
return sk_receive_skb(sk, skb, 1);
no_dccp_socket:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
/*
* Step 2:
* If no socket ...
* 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_v4_ctl_send_reset(sk, skb);
}
discard_it:
kfree_skb(skb);
return 0;
discard_and_relse:
sock_put(sk);
goto discard_it;
}
int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct inet_request_sock *ireq;
struct request_sock *req;
struct dccp_request_sock *dreq;
const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
/* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */
if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return 0; /* discard, don't send a reset here */
if (dccp_bad_service_code(sk, service)) {
dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
goto drop;
}
/*
* TW buckets are converted to open requests without
* limitations, they conserve resources and peer is
* evidently real one.
*/
dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
if (inet_csk_reqsk_queue_is_full(sk))
goto drop;
if (sk_acceptq_is_full(sk))
goto drop;
req = inet_reqsk_alloc(&dccp_request_sock_ops, sk, true);
if (req == NULL)
goto drop;
if (dccp_reqsk_init(req, dccp_sk(sk), skb))
goto drop_and_free;
dreq = dccp_rsk(req);
if (dccp_parse_options(sk, dreq, skb))
goto drop_and_free;
if (security_inet_conn_request(sk, skb, req))
goto drop_and_free;
ireq = inet_rsk(req);
sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
ireq->ir_mark = inet_request_mark(sk, skb);
ireq->ireq_family = AF_INET;
ireq->ir_iif = sk->sk_bound_dev_if;
/*
* Step 3: Process LISTEN state
*
* Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
*
* Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child().
*/
dreq->dreq_isr = dcb->dccpd_seq;
dreq->dreq_gsr = dreq->dreq_isr;
dreq->dreq_iss = dccp_v4_init_sequence(skb);
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
if (dccp_v4_send_response(sk, req))
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
reqsk_put(req);
return 0;
drop_and_free:
reqsk_free(req);
drop:
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
return -1;
}
static int dccp_v6_rcv(struct sk_buff *skb)
{
const struct dccp_hdr *dh;
bool refcounted;
struct sock *sk;
int min_cov;
/* Step 1: Check header basics */
if (dccp_invalid_packet(skb))
goto discard_it;
/* Step 1: If header checksum is incorrect, drop packet and return. */
if (dccp_v6_csum_finish(skb, &ipv6_hdr(skb)->saddr,
&ipv6_hdr(skb)->daddr)) {
DCCP_WARN("dropped packet with invalid checksum\n");
goto discard_it;
}
dh = dccp_hdr(skb);
DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh);
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);
lookup:
sk = __inet6_lookup_skb(&dccp_hashinfo, skb, __dccp_hdr_len(dh),
dh->dccph_sport, dh->dccph_dport,
inet6_iif(skb), &refcounted);
if (!sk) {
dccp_pr_debug("failed to look up flow ID in table and "
"get corresponding socket\n");
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) {
dccp_pr_debug("sk->sk_state == DCCP_TIME_WAIT: do_time_wait\n");
inet_twsk_put(inet_twsk(sk));
goto no_dccp_socket;
}
if (sk->sk_state == DCCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
struct sock *nsk;
sk = req->rsk_listener;
if (unlikely(sk->sk_state != DCCP_LISTEN)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
}
sock_hold(sk);
refcounted = true;
nsk = dccp_check_req(sk, skb, req);
if (!nsk) {
reqsk_put(req);
goto discard_and_relse;
}
if (nsk == sk) {
reqsk_put(req);
} else if (dccp_child_process(sk, nsk, skb)) {
dccp_v6_ctl_send_reset(sk, skb);
goto discard_and_relse;
} else {
sock_put(sk);
return 0;
}
}
/*
* RFC 4340, sec. 9.2.1: Minimum Checksum Coverage
* o if MinCsCov = 0, only packets with CsCov = 0 are accepted
* o if MinCsCov > 0, also accept packets with CsCov >= MinCsCov
*/
min_cov = dccp_sk(sk)->dccps_pcrlen;
if (dh->dccph_cscov && (min_cov == 0 || dh->dccph_cscov < min_cov)) {
dccp_pr_debug("Packet CsCov %d does not satisfy MinCsCov %d\n",
dh->dccph_cscov, min_cov);
/* FIXME: send Data Dropped option (see also dccp_v4_rcv) */
goto discard_and_relse;
}
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
return sk_receive_skb(sk, skb, 1) ? -1 : 0;
no_dccp_socket:
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard_it;
/*
* Step 2:
* If no socket ...
* 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(sk, skb);
}
discard_it:
kfree_skb(skb);
return 0;
discard_and_relse:
if (refcounted)
sock_put(sk);
goto discard_it;
}
static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct request_sock *req;
struct dccp_request_sock *dreq;
struct inet_request_sock *ireq;
struct ipv6_pinfo *np = inet6_sk(sk);
const __be32 service = dccp_hdr_request(skb)->dccph_req_service;
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
if (skb->protocol == htons(ETH_P_IP))
return dccp_v4_conn_request(sk, skb);
if (!ipv6_unicast_destination(skb))
return 0; /* discard, don't send a reset here */
if (dccp_bad_service_code(sk, service)) {
dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
goto drop;
}
/*
* There are no SYN attacks on IPv6, yet...
*/
dcb->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
if (inet_csk_reqsk_queue_is_full(sk))
goto drop;
if (sk_acceptq_is_full(sk))
goto drop;
req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk, true);
if (req == NULL)
goto drop;
if (dccp_reqsk_init(req, dccp_sk(sk), skb))
goto drop_and_free;
dreq = dccp_rsk(req);
if (dccp_parse_options(sk, dreq, skb))
goto drop_and_free;
if (security_inet_conn_request(sk, skb, req))
goto drop_and_free;
ireq = inet_rsk(req);
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
ireq->ireq_family = AF_INET6;
ireq->ir_mark = inet_request_mark(sk, skb);
if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
refcount_inc(&skb->users);
ireq->pktopts = skb;
}
ireq->ir_iif = sk->sk_bound_dev_if;
/* So that link locals have meaning */
if (!sk->sk_bound_dev_if &&
ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
ireq->ir_iif = inet6_iif(skb);
/*
* Step 3: Process LISTEN state
*
* Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie
*
* Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child().
*/
dreq->dreq_isr = dcb->dccpd_seq;
dreq->dreq_gsr = dreq->dreq_isr;
dreq->dreq_iss = dccp_v6_init_sequence(skb);
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
if (dccp_v6_send_response(sk, req))
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
reqsk_put(req);
return 0;
drop_and_free:
reqsk_free(req);
drop:
__DCCP_INC_STATS(DCCP_MIB_ATTEMPTFAILS);
return -1;
}
/* Similar to: tcp_v4_do_rcv
* We only process join requests here. (either the SYN or the final ACK)
*/
int mptcp_v4_do_rcv(struct sock *meta_sk, struct sk_buff *skb)
{
const struct tcphdr *th = tcp_hdr(skb);
const struct iphdr *iph = ip_hdr(skb);
struct sock *child, *rsk = NULL, *sk;
int ret;
sk = inet_lookup_established(sock_net(meta_sk), &tcp_hashinfo,
iph->saddr, th->source, iph->daddr,
th->dest, inet_iif(skb));
if (!sk)
goto new_subflow;
if (is_meta_sk(sk)) {
WARN("%s Did not find a sub-sk - did found the meta!\n", __func__);
sock_put(sk);
goto discard;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
goto discard;
}
if (sk->sk_state == TCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
bool req_stolen;
if (!mptcp_can_new_subflow(meta_sk))
goto reset_and_discard;
local_bh_disable();
child = tcp_check_req(meta_sk, skb, req, false, &req_stolen);
if (!child) {
reqsk_put(req);
local_bh_enable();
goto discard;
}
if (child != meta_sk) {
ret = mptcp_finish_handshake(child, skb);
if (ret) {
rsk = child;
local_bh_enable();
goto reset_and_discard;
}
local_bh_enable();
return 0;
}
/* tcp_check_req failed */
reqsk_put(req);
local_bh_enable();
goto discard;
}
ret = tcp_v4_do_rcv(sk, skb);
sock_put(sk);
return ret;
new_subflow:
if (!mptcp_can_new_subflow(meta_sk))
goto reset_and_discard;
child = tcp_v4_cookie_check(meta_sk, skb);
if (!child)
goto discard;
if (child != meta_sk) {
ret = mptcp_finish_handshake(child, skb);
if (ret) {
rsk = child;
goto reset_and_discard;
}
}
if (tcp_hdr(skb)->syn) {
local_bh_disable();
mptcp_v4_join_request(meta_sk, skb);
local_bh_enable();
}
discard:
kfree_skb(skb);
return 0;
reset_and_discard:
tcp_v4_send_reset(rsk, skb);
goto discard;
}