/*
* Handle an MTU/fragmentation problem.
*/
static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
{
u32 mtu = serr->ee.ee_info;
_net("Rx ICMP Fragmentation Needed (%d)", mtu);
/* wind down the local interface MTU */
if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
peer->if_mtu = mtu;
_net("I/F MTU %u", mtu);
}
if (mtu == 0) {
/* they didn't give us a size, estimate one */
mtu = peer->if_mtu;
if (mtu > 1500) {
mtu >>= 1;
if (mtu < 1500)
mtu = 1500;
} else {
/*
* Set up an incoming connection. This is called in BH context with the RCU
* read lock held.
*/
void rxrpc_new_incoming_connection(struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
_enter("");
conn->proto.epoch = sp->hdr.epoch;
conn->proto.cid = sp->hdr.cid & RXRPC_CIDMASK;
conn->params.service_id = sp->hdr.serviceId;
conn->security_ix = sp->hdr.securityIndex;
conn->out_clientflag = 0;
if (conn->security_ix)
conn->state = RXRPC_CONN_SERVICE_UNSECURED;
else
conn->state = RXRPC_CONN_SERVICE;
/* Make the connection a target for incoming packets. */
rxrpc_publish_service_conn(conn->params.peer, conn);
_net("CONNECTION new %d {%x}", conn->debug_id, conn->proto.cid);
}
/*
* handle an error received on the local endpoint
*/
void rxrpc_UDP_error_report(struct sock *sk)
{
struct sock_exterr_skb *serr;
struct rxrpc_transport *trans;
struct rxrpc_local *local = sk->sk_user_data;
struct rxrpc_peer *peer;
struct sk_buff *skb;
__be32 addr;
__be16 port;
_enter("%p{%d}", sk, local->debug_id);
skb = skb_dequeue(&sk->sk_error_queue);
if (!skb) {
_leave("UDP socket errqueue empty");
return;
}
rxrpc_new_skb(skb);
serr = SKB_EXT_ERR(skb);
addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset);
port = serr->port;
_net("Rx UDP Error from "NIPQUAD_FMT":%hu",
NIPQUAD(addr), ntohs(port));
_debug("Msg l:%d d:%d", skb->len, skb->data_len);
peer = rxrpc_find_peer(local, addr, port);
if (IS_ERR(peer)) {
rxrpc_free_skb(skb);
_leave(" [no peer]");
return;
}
trans = rxrpc_find_transport(local, peer);
if (!trans) {
rxrpc_put_peer(peer);
rxrpc_free_skb(skb);
_leave(" [no trans]");
return;
}
if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
serr->ee.ee_type == ICMP_DEST_UNREACH &&
serr->ee.ee_code == ICMP_FRAG_NEEDED
) {
u32 mtu = serr->ee.ee_info;
_net("Rx Received ICMP Fragmentation Needed (%d)", mtu);
/* wind down the local interface MTU */
if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
peer->if_mtu = mtu;
_net("I/F MTU %u", mtu);
}
/* ip_rt_frag_needed() may have eaten the info */
if (mtu == 0)
mtu = ntohs(icmp_hdr(skb)->un.frag.mtu);
if (mtu == 0) {
/* they didn't give us a size, estimate one */
if (mtu > 1500) {
mtu >>= 1;
if (mtu < 1500)
mtu = 1500;
} else {
/*
* set up a call for the given data
* - called in process context with IRQs enabled
*/
struct rxrpc_call *rxrpc_get_client_call(struct rxrpc_sock *rx,
struct rxrpc_transport *trans,
struct rxrpc_conn_bundle *bundle,
unsigned long user_call_ID,
int create,
gfp_t gfp)
{
struct rxrpc_call *call, *candidate;
struct rb_node *p, *parent, **pp;
_enter("%p,%d,%d,%lx,%d",
rx, trans ? trans->debug_id : -1, bundle ? bundle->debug_id : -1,
user_call_ID, create);
/* search the extant calls first for one that matches the specified
* user ID */
read_lock(&rx->call_lock);
p = rx->calls.rb_node;
while (p) {
call = rb_entry(p, struct rxrpc_call, sock_node);
if (user_call_ID < call->user_call_ID)
p = p->rb_left;
else if (user_call_ID > call->user_call_ID)
p = p->rb_right;
else
goto found_extant_call;
}
read_unlock(&rx->call_lock);
if (!create || !trans)
return ERR_PTR(-EBADSLT);
/* not yet present - create a candidate for a new record and then
* redo the search */
candidate = rxrpc_alloc_client_call(rx, trans, bundle, gfp);
if (IS_ERR(candidate)) {
_leave(" = %ld", PTR_ERR(candidate));
return candidate;
}
candidate->user_call_ID = user_call_ID;
__set_bit(RXRPC_CALL_HAS_USERID, &candidate->flags);
write_lock(&rx->call_lock);
pp = &rx->calls.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
call = rb_entry(parent, struct rxrpc_call, sock_node);
if (user_call_ID < call->user_call_ID)
pp = &(*pp)->rb_left;
else if (user_call_ID > call->user_call_ID)
pp = &(*pp)->rb_right;
else
goto found_extant_second;
}
/* second search also failed; add the new call */
call = candidate;
candidate = NULL;
rxrpc_get_call(call);
rb_link_node(&call->sock_node, parent, pp);
rb_insert_color(&call->sock_node, &rx->calls);
write_unlock(&rx->call_lock);
write_lock_bh(&rxrpc_call_lock);
list_add_tail(&call->link, &rxrpc_calls);
write_unlock_bh(&rxrpc_call_lock);
_net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id);
_leave(" = %p [new]", call);
return call;
/* we found the call in the list immediately */
found_extant_call:
rxrpc_get_call(call);
read_unlock(&rx->call_lock);
_leave(" = %p [extant %d]", call, atomic_read(&call->usage));
return call;
/* we found the call on the second time through the list */
found_extant_second:
rxrpc_get_call(call);
write_unlock(&rx->call_lock);
rxrpc_put_call(candidate);
_leave(" = %p [second %d]", call, atomic_read(&call->usage));
return call;
}
/*
* get bundle of client connections that a client socket can make use of
*/
struct rxrpc_conn_bundle *rxrpc_get_bundle(struct rxrpc_sock *rx,
struct rxrpc_transport *trans,
struct key *key,
__be16 service_id,
gfp_t gfp)
{
struct rxrpc_conn_bundle *bundle, *candidate;
struct rb_node *p, *parent, **pp;
_enter("%p{%x},%x,%hx,",
rx, key_serial(key), trans->debug_id, ntohs(service_id));
if (rx->trans == trans && rx->bundle) {
atomic_inc(&rx->bundle->usage);
return rx->bundle;
}
/* search the extant bundles first for one that matches the specified
* user ID */
spin_lock(&trans->client_lock);
p = trans->bundles.rb_node;
while (p) {
bundle = rb_entry(p, struct rxrpc_conn_bundle, node);
if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
p = p->rb_left;
else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
p = p->rb_right;
else
goto found_extant_bundle;
}
spin_unlock(&trans->client_lock);
/* not yet present - create a candidate for a new record and then
* redo the search */
candidate = rxrpc_alloc_bundle(gfp);
if (!candidate) {
_leave(" = -ENOMEM");
return ERR_PTR(-ENOMEM);
}
candidate->key = key_get(key);
candidate->service_id = service_id;
spin_lock(&trans->client_lock);
pp = &trans->bundles.rb_node;
parent = NULL;
while (*pp) {
parent = *pp;
bundle = rb_entry(parent, struct rxrpc_conn_bundle, node);
if (rxrpc_cmp_bundle(bundle, key, service_id) < 0)
pp = &(*pp)->rb_left;
else if (rxrpc_cmp_bundle(bundle, key, service_id) > 0)
pp = &(*pp)->rb_right;
else
goto found_extant_second;
}
/* second search also failed; add the new bundle */
bundle = candidate;
candidate = NULL;
rb_link_node(&bundle->node, parent, pp);
rb_insert_color(&bundle->node, &trans->bundles);
spin_unlock(&trans->client_lock);
_net("BUNDLE new on trans %d", trans->debug_id);
if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
atomic_inc(&bundle->usage);
rx->bundle = bundle;
}
_leave(" = %p [new]", bundle);
return bundle;
/* we found the bundle in the list immediately */
found_extant_bundle:
atomic_inc(&bundle->usage);
spin_unlock(&trans->client_lock);
_net("BUNDLE old on trans %d", trans->debug_id);
if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
atomic_inc(&bundle->usage);
rx->bundle = bundle;
}
_leave(" = %p [extant %d]", bundle, atomic_read(&bundle->usage));
return bundle;
/* we found the bundle on the second time through the list */
found_extant_second:
atomic_inc(&bundle->usage);
spin_unlock(&trans->client_lock);
kfree(candidate);
_net("BUNDLE old2 on trans %d", trans->debug_id);
if (!rx->bundle && rx->sk.sk_state == RXRPC_CLIENT_CONNECTED) {
atomic_inc(&bundle->usage);
rx->bundle = bundle;
}
_leave(" = %p [second %d]", bundle, atomic_read(&bundle->usage));
return bundle;
}
/*
* send data through a socket
* - must be called in process context
* - caller holds the socket locked
*/
static int rxrpc_send_data(struct kiocb *iocb,
struct rxrpc_sock *rx,
struct rxrpc_call *call,
struct msghdr *msg, size_t len)
{
struct rxrpc_skb_priv *sp;
unsigned char __user *from;
struct sk_buff *skb;
struct iovec *iov;
struct sock *sk = &rx->sk;
long timeo;
bool more;
int ret, ioc, segment, copied;
_enter(",,,{%zu},%zu", msg->msg_iovlen, len);
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
/* this should be in poll */
clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
return -EPIPE;
iov = msg->msg_iov;
ioc = msg->msg_iovlen - 1;
from = iov->iov_base;
segment = iov->iov_len;
iov++;
more = msg->msg_flags & MSG_MORE;
skb = call->tx_pending;
call->tx_pending = NULL;
copied = 0;
do {
int copy;
if (segment > len)
segment = len;
_debug("SEGMENT %d @%p", segment, from);
if (!skb) {
size_t size, chunk, max, space;
_debug("alloc");
if (CIRC_SPACE(call->acks_head, call->acks_tail,
call->acks_winsz) <= 0) {
ret = -EAGAIN;
if (msg->msg_flags & MSG_DONTWAIT)
goto maybe_error;
ret = rxrpc_wait_for_tx_window(rx, call,
&timeo);
if (ret < 0)
goto maybe_error;
}
max = call->conn->trans->peer->maxdata;
max -= call->conn->security_size;
max &= ~(call->conn->size_align - 1UL);
chunk = max;
if (chunk > len && !more)
chunk = len;
space = chunk + call->conn->size_align;
space &= ~(call->conn->size_align - 1UL);
size = space + call->conn->header_size;
_debug("SIZE: %zu/%zu/%zu", chunk, space, size);
/* create a buffer that we can retain until it's ACK'd */
skb = sock_alloc_send_skb(
sk, size, msg->msg_flags & MSG_DONTWAIT, &ret);
if (!skb)
goto maybe_error;
rxrpc_new_skb(skb);
_debug("ALLOC SEND %p", skb);
ASSERTCMP(skb->mark, ==, 0);
_debug("HS: %u", call->conn->header_size);
skb_reserve(skb, call->conn->header_size);
skb->len += call->conn->header_size;
sp = rxrpc_skb(skb);
sp->remain = chunk;
if (sp->remain > skb_tailroom(skb))
sp->remain = skb_tailroom(skb);
_net("skb: hr %d, tr %d, hl %d, rm %d",
skb_headroom(skb),
skb_tailroom(skb),
skb_headlen(skb),
sp->remain);
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
_debug("append");
sp = rxrpc_skb(skb);
/* append next segment of data to the current buffer */
copy = skb_tailroom(skb);
ASSERTCMP(copy, >, 0);
if (copy > segment)
copy = segment;
if (copy > sp->remain)
copy = sp->remain;
_debug("add");
ret = skb_add_data(skb, from, copy);
_debug("added");
if (ret < 0)
goto efault;
sp->remain -= copy;
skb->mark += copy;
copied += copy;
len -= copy;
segment -= copy;
from += copy;
while (segment == 0 && ioc > 0) {
from = iov->iov_base;
segment = iov->iov_len;
iov++;
ioc--;
}
if (len == 0) {
segment = 0;
ioc = 0;
}
/* check for the far side aborting the call or a network error
* occurring */
if (call->state > RXRPC_CALL_COMPLETE)
goto call_aborted;
/* add the packet to the send queue if it's now full */
if (sp->remain <= 0 || (segment == 0 && !more)) {
struct rxrpc_connection *conn = call->conn;
size_t pad;
/* pad out if we're using security */
if (conn->security) {
pad = conn->security_size + skb->mark;
pad = conn->size_align - pad;
pad &= conn->size_align - 1;
_debug("pad %zu", pad);
if (pad)
memset(skb_put(skb, pad), 0, pad);
}
sp->hdr.epoch = conn->epoch;
sp->hdr.cid = call->cid;
sp->hdr.callNumber = call->call_id;
sp->hdr.seq =
htonl(atomic_inc_return(&call->sequence));
sp->hdr.serial =
htonl(atomic_inc_return(&conn->serial));
sp->hdr.type = RXRPC_PACKET_TYPE_DATA;
sp->hdr.userStatus = 0;
sp->hdr.securityIndex = conn->security_ix;
sp->hdr._rsvd = 0;
sp->hdr.serviceId = conn->service_id;
sp->hdr.flags = conn->out_clientflag;
if (len == 0 && !more)
sp->hdr.flags |= RXRPC_LAST_PACKET;
else if (CIRC_SPACE(call->acks_head, call->acks_tail,
call->acks_winsz) > 1)
sp->hdr.flags |= RXRPC_MORE_PACKETS;
ret = rxrpc_secure_packet(
call, skb, skb->mark,
skb->head + sizeof(struct rxrpc_header));
if (ret < 0)
goto out;
memcpy(skb->head, &sp->hdr,
sizeof(struct rxrpc_header));
rxrpc_queue_packet(call, skb, segment == 0 && !more);
skb = NULL;
}
} while (segment > 0);
/*
* queue a packet for transmission, set the resend timer and attempt
* to send the packet immediately
*/
static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb,
bool last)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
int ret;
_net("queue skb %p [%d]", skb, call->acks_head);
ASSERT(call->acks_window != NULL);
call->acks_window[call->acks_head] = (unsigned long) skb;
smp_wmb();
call->acks_head = (call->acks_head + 1) & (call->acks_winsz - 1);
if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) {
_debug("________awaiting reply/ACK__________");
write_lock_bh(&call->state_lock);
switch (call->state) {
case RXRPC_CALL_CLIENT_SEND_REQUEST:
call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY;
break;
case RXRPC_CALL_SERVER_ACK_REQUEST:
call->state = RXRPC_CALL_SERVER_SEND_REPLY;
if (!last)
break;
case RXRPC_CALL_SERVER_SEND_REPLY:
call->state = RXRPC_CALL_SERVER_AWAIT_ACK;
break;
default:
break;
}
write_unlock_bh(&call->state_lock);
}
_proto("Tx DATA %%%u { #%u }",
ntohl(sp->hdr.serial), ntohl(sp->hdr.seq));
sp->need_resend = 0;
sp->resend_at = jiffies + rxrpc_resend_timeout * HZ;
if (!test_and_set_bit(RXRPC_CALL_RUN_RTIMER, &call->flags)) {
_debug("run timer");
call->resend_timer.expires = sp->resend_at;
add_timer(&call->resend_timer);
}
/* attempt to cancel the rx-ACK timer, deferring reply transmission if
* we're ACK'ing the request phase of an incoming call */
ret = -EAGAIN;
if (try_to_del_timer_sync(&call->ack_timer) >= 0) {
/* the packet may be freed by rxrpc_process_call() before this
* returns */
ret = rxrpc_send_packet(call->conn->trans, skb);
_net("sent skb %p", skb);
} else {
_debug("failed to delete ACK timer");
}
if (ret < 0) {
_debug("need instant resend %d", ret);
sp->need_resend = 1;
rxrpc_instant_resend(call);
}
_leave("");
}
/*
* Find the peer associated with an ICMP packet.
*/
static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
const struct sk_buff *skb)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
struct sockaddr_rxrpc srx;
_enter("");
memset(&srx, 0, sizeof(srx));
srx.transport_type = local->srx.transport_type;
srx.transport_len = local->srx.transport_len;
srx.transport.family = local->srx.transport.family;
/* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice
* versa?
*/
switch (srx.transport.family) {
case AF_INET:
srx.transport.sin.sin_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP");
memcpy(&srx.transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6 on v4 sock");
memcpy(&srx.transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset + 12,
sizeof(struct in_addr));
break;
default:
memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr,
sizeof(struct in_addr));
break;
}
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
srx.transport.sin6.sin6_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6");
memcpy(&srx.transport.sin6.sin6_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in6_addr));
break;
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP on v6 sock");
srx.transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx.transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx.transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
default:
memcpy(&srx.transport.sin6.sin6_addr,
&ipv6_hdr(skb)->saddr,
sizeof(struct in6_addr));
break;
}
break;
#endif
default:
BUG();
}
return rxrpc_lookup_peer_rcu(local, &srx);
}
