void dccp_send_sync(struct sock *sk, const u64 ackno,
const enum dccp_pkt_type pkt_type)
{
/*
* We are not putting this on the write queue, so
* dccp_transmit_skb() will set the ownership to this
* sock.
*/
struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
if (skb == NULL) {
/* FIXME: how to make sure the sync is sent? */
DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type));
return;
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
/*
* Clear the flag in case the Sync was scheduled for out-of-band data,
* such as carrying a long Ack Vector.
*/
dccp_sk(sk)->dccps_sync_scheduled = 0;
dccp_transmit_skb(sk, skb);
}
void dccp_send_sync(struct sock *sk, const u64 ackno,
const enum dccp_pkt_type pkt_type)
{
struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
if (skb == NULL) {
DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type));
return;
}
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
dccp_transmit_skb(sk, skb);
}
void dccp_send_sync(struct sock *sk, const u64 ackno,
const enum dccp_pkt_type pkt_type)
{
/*
* We are not putting this on the write queue, so
* dccp_transmit_skb() will set the ownership to this
* sock.
*/
struct sk_buff *skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC);
if (skb == NULL) {
/* FIXME: how to make sure the sync is sent? */
DCCP_CRIT("could not send %s", dccp_packet_name(pkt_type));
return;
}
/* Reserve space for headers and prepare control bits. */
skb_reserve(skb, sk->sk_prot->max_header);
DCCP_SKB_CB(skb)->dccpd_type = pkt_type;
DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno;
dccp_transmit_skb(sk, skb);
}
/* 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;
}
/**
* dccp_invalid_packet - check for malformed packets
* Implements RFC 4340, 8.5: Step 1: Check header basics
* Packets that fail these checks are ignored and do not receive Resets.
*/
int dccp_invalid_packet(struct sk_buff *skb)
{
const struct dccp_hdr *dh;
unsigned int cscov;
if (skb->pkt_type != PACKET_HOST)
return 1;
/* If the packet is shorter than 12 bytes, drop packet and return */
if (!pskb_may_pull(skb, sizeof(struct dccp_hdr))) {
DCCP_WARN("pskb_may_pull failed\n");
return 1;
}
dh = dccp_hdr(skb);
/* If P.type is not understood, drop packet and return */
if (dh->dccph_type >= DCCP_PKT_INVALID) {
DCCP_WARN("invalid packet type\n");
return 1;
}
/*
* If P.Data Offset is too small for packet type, drop packet and return
*/
if (dh->dccph_doff < dccp_hdr_len(skb) / sizeof(u32)) {
DCCP_WARN("P.Data Offset(%u) too small\n", dh->dccph_doff);
return 1;
}
/*
* If P.Data Offset is too too large for packet, drop packet and return
*/
if (!pskb_may_pull(skb, dh->dccph_doff * sizeof(u32))) {
DCCP_WARN("P.Data Offset(%u) too large\n", dh->dccph_doff);
return 1;
}
/*
* If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
* has short sequence numbers), drop packet and return
*/
if ((dh->dccph_type < DCCP_PKT_DATA ||
dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0) {
DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n",
dccp_packet_name(dh->dccph_type));
return 1;
}
/*
* If P.CsCov is too large for the packet size, drop packet and return.
* This must come _before_ checksumming (not as RFC 4340 suggests).
*/
cscov = dccp_csum_coverage(skb);
if (cscov > skb->len) {
DCCP_WARN("P.CsCov %u exceeds packet length %d\n",
dh->dccph_cscov, skb->len);
return 1;
}
/* If header checksum is incorrect, drop packet and return.
* (This step is completed in the AF-dependent functions.) */
skb->csum = skb_checksum(skb, 0, cscov, 0);
return 0;
}
static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const u16 buflen = dccp_ackvec_buflen(av);
/* Figure out how many options do we need to represent the ackvec */
const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN);
u16 len = buflen + 2 * nr_opts;
u8 i, nonce = 0;
const unsigned char *tail, *from;
unsigned char *to;
if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) {
DCCP_WARN("Lacking space for %u bytes on %s packet\n", len,
dccp_packet_name(dcb->dccpd_type));
return -1;
}
/*
* Since Ack Vectors are variable-length, we can not always predict
* their size. To catch exception cases where the space is running out
* on the skb, a separate Sync is scheduled to carry the Ack Vector.
*/
if (len > DCCPAV_MIN_OPTLEN &&
len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) {
DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), "
"MPS=%u ==> reduce payload size?\n", len, skb->len,
dcb->dccpd_opt_len, dp->dccps_mss_cache);
dp->dccps_sync_scheduled = 1;
return 0;
}
dcb->dccpd_opt_len += len;
to = skb_push(skb, len);
len = buflen;
from = av->av_buf + av->av_buf_head;
tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN;
for (i = 0; i < nr_opts; ++i) {
int copylen = len;
if (len > DCCP_SINGLE_OPT_MAXLEN)
copylen = DCCP_SINGLE_OPT_MAXLEN;
/*
* RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via
* its type; ack_nonce is the sum of all individual buf_nonce's.
*/
nonce ^= av->av_buf_nonce[i];
*to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i];
*to++ = copylen + 2;
/* Check if buf_head wraps */
if (from + copylen > tail) {
const u16 tailsize = tail - from;
memcpy(to, from, tailsize);
to += tailsize;
len -= tailsize;
copylen -= tailsize;
from = av->av_buf;
}
memcpy(to, from, copylen);
from += copylen;
to += copylen;
len -= copylen;
}
/*
* Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340.
*/
if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce))
return -ENOBUFS;
return 0;
}
int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len, int nonblock, int flags, int *addr_len)
{
const struct dccp_hdr *dh;
long timeo;
lock_sock(sk);
if (sk->sk_state == DCCP_LISTEN) {
len = -ENOTCONN;
goto out;
}
timeo = sock_rcvtimeo(sk, nonblock);
do {
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
if (skb == NULL)
goto verify_sock_status;
dh = dccp_hdr(skb);
switch (dh->dccph_type) {
case DCCP_PKT_DATA:
case DCCP_PKT_DATAACK:
goto found_ok_skb;
case DCCP_PKT_CLOSE:
case DCCP_PKT_CLOSEREQ:
if (!(flags & MSG_PEEK))
dccp_finish_passive_close(sk);
/* fall through */
case DCCP_PKT_RESET:
dccp_pr_debug("found fin (%s) ok!\n",
dccp_packet_name(dh->dccph_type));
len = 0;
goto found_fin_ok;
default:
dccp_pr_debug("packet_type=%s\n",
dccp_packet_name(dh->dccph_type));
sk_eat_skb(sk, skb, false);
}
verify_sock_status:
if (sock_flag(sk, SOCK_DONE)) {
len = 0;
break;
}
if (sk->sk_err) {
len = sock_error(sk);
break;
}
if (sk->sk_shutdown & RCV_SHUTDOWN) {
len = 0;
break;
}
if (sk->sk_state == DCCP_CLOSED) {
if (!sock_flag(sk, SOCK_DONE)) {
/* This occurs when user tries to read
* from never connected socket.
*/
len = -ENOTCONN;
break;
}
len = 0;
break;
}
if (!timeo) {
len = -EAGAIN;
break;
}
if (signal_pending(current)) {
len = sock_intr_errno(timeo);
break;
}
sk_wait_data(sk, &timeo);
continue;
found_ok_skb:
if (len > skb->len)
len = skb->len;
else if (len < skb->len)
msg->msg_flags |= MSG_TRUNC;
if (skb_copy_datagram_iovec(skb, 0, msg->msg_iov, len)) {
/* Exception. Bailout! */
len = -EFAULT;
break;
}
if (flags & MSG_TRUNC)
len = skb->len;
found_fin_ok:
if (!(flags & MSG_PEEK))
sk_eat_skb(sk, skb, false);
break;
} while (1);
out:
release_sock(sk);
return len;
}
static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
{
const struct dccp_hdr *dh = dccp_hdr(skb);
struct dccp_sock *dp = dccp_sk(sk);
u64 lswl, lawl;
/*
* Step 5: Prepare sequence numbers for Sync
* If P.type == Sync or P.type == SyncAck,
* If S.AWL <= P.ackno <= S.AWH and P.seqno >= S.SWL,
* / * P is valid, so update sequence number variables
* accordingly. After this update, P will pass the tests
* in Step 6. A SyncAck is generated if necessary in
* Step 15 * /
* Update S.GSR, S.SWL, S.SWH
* Otherwise,
* Drop packet and return
*/
if (dh->dccph_type == DCCP_PKT_SYNC ||
dh->dccph_type == DCCP_PKT_SYNCACK) {
if (between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
dp->dccps_awl, dp->dccps_awh) &&
!before48(DCCP_SKB_CB(skb)->dccpd_seq, dp->dccps_swl))
dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
else
return -1;
}
/*
* Step 6: Check sequence numbers
* Let LSWL = S.SWL and LAWL = S.AWL
* If P.type == CloseReq or P.type == Close or P.type == Reset,
* LSWL := S.GSR + 1, LAWL := S.GAR
* If LSWL <= P.seqno <= S.SWH
* and (P.ackno does not exist or LAWL <= P.ackno <= S.AWH),
* Update S.GSR, S.SWL, S.SWH
* If P.type != Sync,
* Update S.GAR
* Otherwise,
* Send Sync packet acknowledging P.seqno
* Drop packet and return
*/
lswl = dp->dccps_swl;
lawl = dp->dccps_awl;
if (dh->dccph_type == DCCP_PKT_CLOSEREQ ||
dh->dccph_type == DCCP_PKT_CLOSE ||
dh->dccph_type == DCCP_PKT_RESET) {
lswl = dp->dccps_gsr;
dccp_inc_seqno(&lswl);
lawl = dp->dccps_gar;
}
if (between48(DCCP_SKB_CB(skb)->dccpd_seq, lswl, dp->dccps_swh) &&
(DCCP_SKB_CB(skb)->dccpd_ack_seq == DCCP_PKT_WITHOUT_ACK_SEQ ||
between48(DCCP_SKB_CB(skb)->dccpd_ack_seq,
lawl, dp->dccps_awh))) {
dccp_update_gsr(sk, DCCP_SKB_CB(skb)->dccpd_seq);
if (dh->dccph_type != DCCP_PKT_SYNC &&
(DCCP_SKB_CB(skb)->dccpd_ack_seq !=
DCCP_PKT_WITHOUT_ACK_SEQ))
dp->dccps_gar = DCCP_SKB_CB(skb)->dccpd_ack_seq;
} else {
DCCP_WARN("DCCP: Step 6 failed for %s packet, "
"(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and "
"(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), "
"sending SYNC...\n", dccp_packet_name(dh->dccph_type),
(unsigned long long) lswl,
(unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq,
(unsigned long long) dp->dccps_swh,
(DCCP_SKB_CB(skb)->dccpd_ack_seq ==
DCCP_PKT_WITHOUT_ACK_SEQ) ? "doesn't exist" : "exists",
(unsigned long long) lawl,
(unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq,
(unsigned long long) dp->dccps_awh);
dccp_send_sync(sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_PKT_SYNC);
return -1;
}
return 0;
}
static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
const u16 buflen = dccp_ackvec_buflen(av);
const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN);
u16 len = buflen + 2 * nr_opts;
u8 i, nonce = 0;
const unsigned char *tail, *from;
unsigned char *to;
if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) {
DCCP_WARN("Lacking space for %u bytes on %s packet\n", len,
dccp_packet_name(dcb->dccpd_type));
return -1;
}
if (len > DCCPAV_MIN_OPTLEN &&
len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) {
DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), "
"MPS=%u ==> reduce payload size?\n", len, skb->len,
dcb->dccpd_opt_len, dp->dccps_mss_cache);
dp->dccps_sync_scheduled = 1;
return 0;
}
dcb->dccpd_opt_len += len;
to = skb_push(skb, len);
len = buflen;
from = av->av_buf + av->av_buf_head;
tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN;
for (i = 0; i < nr_opts; ++i) {
int copylen = len;
if (len > DCCP_SINGLE_OPT_MAXLEN)
copylen = DCCP_SINGLE_OPT_MAXLEN;
nonce ^= av->av_buf_nonce[i];
*to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i];
*to++ = copylen + 2;
if (from + copylen > tail) {
const u16 tailsize = tail - from;
memcpy(to, from, tailsize);
to += tailsize;
len -= tailsize;
copylen -= tailsize;
from = av->av_buf;
}
memcpy(to, from, copylen);
from += copylen;
to += copylen;
len -= copylen;
}
if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce))
return -ENOBUFS;
return 0;
}
