int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_SHUTDOWN,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.flags = (mode & RCV_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
(mode & SEND_SHUTDOWN ?
VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_shutdown);
int
virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
struct sockaddr_vm *remote_addr,
struct msghdr *msg,
size_t dgram_len)
{
return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue);
ssize_t
virtio_transport_stream_enqueue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RW,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.msg = msg,
.pkt_len = len,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue);
void virtio_transport_destruct(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
kfree(vvs);
}
EXPORT_SYMBOL_GPL(virtio_transport_destruct);
static int virtio_transport_reset(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.reply = !!pkt,
.vsk = vsk,
};
/* Send RST only if the original pkt is not a RST pkt */
if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
return 0;
return virtio_transport_send_pkt_info(vsk, &info);
}
/* Normally packets are associated with a socket. There may be no socket if an
* attempt was made to connect to a socket that does not exist.
*/
static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RST,
.type = le16_to_cpu(pkt->hdr.type),
.reply = true,
};
/* Send RST only if the original pkt is not a RST pkt */
if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
return 0;
pkt = virtio_transport_alloc_pkt(&info, 0,
le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port),
le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
if (!pkt)
return -ENOMEM;
return virtio_transport_get_ops()->send_pkt(pkt);
}
static void virtio_transport_wait_close(struct sock *sk, long timeout)
{
if (timeout) {
DEFINE_WAIT_FUNC(wait, woken_wake_function);
add_wait_queue(sk_sleep(sk), &wait);
do {
if (sk_wait_event(sk, &timeout,
sock_flag(sk, SOCK_DONE), &wait))
break;
} while (!signal_pending(current) && timeout);
remove_wait_queue(sk_sleep(sk), &wait);
}
}
static void virtio_transport_do_close(struct vsock_sock *vsk,
bool cancel_timeout)
{
struct sock *sk = sk_vsock(vsk);
sock_set_flag(sk, SOCK_DONE);
vsk->peer_shutdown = SHUTDOWN_MASK;
if (vsock_stream_has_data(vsk) <= 0)
sk->sk_state = SS_DISCONNECTING;
sk->sk_state_change(sk);
if (vsk->close_work_scheduled &&
(!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
vsk->close_work_scheduled = false;
vsock_remove_sock(vsk);
/* Release refcnt obtained when we scheduled the timeout */
sock_put(sk);
}
}
static void virtio_transport_close_timeout(struct work_struct *work)
{
struct vsock_sock *vsk =
container_of(work, struct vsock_sock, close_work.work);
struct sock *sk = sk_vsock(vsk);
sock_hold(sk);
lock_sock(sk);
if (!sock_flag(sk, SOCK_DONE)) {
(void)virtio_transport_reset(vsk, NULL);
virtio_transport_do_close(vsk, false);
}
vsk->close_work_scheduled = false;
release_sock(sk);
sock_put(sk);
}
/* User context, vsk->sk is locked */
static bool virtio_transport_close(struct vsock_sock *vsk)
{
struct sock *sk = &vsk->sk;
if (!(sk->sk_state == SS_CONNECTED ||
sk->sk_state == SS_DISCONNECTING))
return true;
/* Already received SHUTDOWN from peer, reply with RST */
if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) {
(void)virtio_transport_reset(vsk, NULL);
return true;
}
if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK)
(void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK);
if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING))
virtio_transport_wait_close(sk, sk->sk_lingertime);
if (sock_flag(sk, SOCK_DONE)) {
return true;
}
sock_hold(sk);
INIT_DELAYED_WORK(&vsk->close_work,
virtio_transport_close_timeout);
vsk->close_work_scheduled = true;
schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT);
return false;
}
void virtio_transport_release(struct vsock_sock *vsk)
{
struct sock *sk = &vsk->sk;
bool remove_sock = true;
lock_sock(sk);
if (sk->sk_type == SOCK_STREAM)
remove_sock = virtio_transport_close(vsk);
release_sock(sk);
if (remove_sock)
vsock_remove_sock(vsk);
}
EXPORT_SYMBOL_GPL(virtio_transport_release);
static int
virtio_transport_recv_connecting(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
int err;
int skerr;
switch (le16_to_cpu(pkt->hdr.op)) {
case VIRTIO_VSOCK_OP_RESPONSE:
sk->sk_state = SS_CONNECTED;
sk->sk_socket->state = SS_CONNECTED;
vsock_insert_connected(vsk);
sk->sk_state_change(sk);
break;
case VIRTIO_VSOCK_OP_INVALID:
break;
case VIRTIO_VSOCK_OP_RST:
skerr = ECONNRESET;
err = 0;
goto destroy;
default:
skerr = EPROTO;
err = -EINVAL;
goto destroy;
}
return 0;
destroy:
virtio_transport_reset(vsk, pkt);
sk->sk_state = SS_UNCONNECTED;
sk->sk_err = skerr;
sk->sk_error_report(sk);
return err;
}
static int
virtio_transport_recv_connected(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct virtio_vsock_sock *vvs = vsk->trans;
int err = 0;
switch (le16_to_cpu(pkt->hdr.op)) {
case VIRTIO_VSOCK_OP_RW:
pkt->len = le32_to_cpu(pkt->hdr.len);
pkt->off = 0;
spin_lock_bh(&vvs->rx_lock);
virtio_transport_inc_rx_pkt(vvs, pkt);
list_add_tail(&pkt->list, &vvs->rx_queue);
spin_unlock_bh(&vvs->rx_lock);
sk->sk_data_ready(sk);
return err;
case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
sk->sk_write_space(sk);
break;
case VIRTIO_VSOCK_OP_SHUTDOWN:
if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV)
vsk->peer_shutdown |= RCV_SHUTDOWN;
if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
vsk->peer_shutdown |= SEND_SHUTDOWN;
if (vsk->peer_shutdown == SHUTDOWN_MASK &&
vsock_stream_has_data(vsk) <= 0)
sk->sk_state = SS_DISCONNECTING;
if (le32_to_cpu(pkt->hdr.flags))
sk->sk_state_change(sk);
break;
case VIRTIO_VSOCK_OP_RST:
virtio_transport_do_close(vsk, true);
break;
default:
err = -EINVAL;
break;
}
virtio_transport_free_pkt(pkt);
return err;
}
static void
virtio_transport_recv_disconnecting(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
virtio_transport_do_close(vsk, true);
}
static int
virtio_transport_send_response(struct vsock_sock *vsk,
struct virtio_vsock_pkt *pkt)
{
struct virtio_vsock_pkt_info info = {
.op = VIRTIO_VSOCK_OP_RESPONSE,
.type = VIRTIO_VSOCK_TYPE_STREAM,
.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
.remote_port = le32_to_cpu(pkt->hdr.src_port),
.reply = true,
.vsk = vsk,
};
return virtio_transport_send_pkt_info(vsk, &info);
}
/* Handle server socket */
static int
virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct vsock_sock *vchild;
struct sock *child;
if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) {
virtio_transport_reset(vsk, pkt);
return -EINVAL;
}
if (sk_acceptq_is_full(sk)) {
virtio_transport_reset(vsk, pkt);
return -ENOMEM;
}
child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
sk->sk_type, 0);
if (!child) {
virtio_transport_reset(vsk, pkt);
return -ENOMEM;
}
sk->sk_ack_backlog++;
lock_sock_nested(child, SINGLE_DEPTH_NESTING);
child->sk_state = SS_CONNECTED;
vchild = vsock_sk(child);
vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port));
vsock_addr_init(&vchild->remote_addr, le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
vsock_insert_connected(vchild);
vsock_enqueue_accept(sk, child);
virtio_transport_send_response(vchild, pkt);
release_sock(child);
sk->sk_data_ready(sk);
return 0;
}
static bool virtio_transport_space_update(struct sock *sk,
struct virtio_vsock_pkt *pkt)
{
struct vsock_sock *vsk = vsock_sk(sk);
struct virtio_vsock_sock *vvs = vsk->trans;
bool space_available;
/* buf_alloc and fwd_cnt is always included in the hdr */
spin_lock_bh(&vvs->tx_lock);
vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
space_available = virtio_transport_has_space(vsk);
spin_unlock_bh(&vvs->tx_lock);
return space_available;
}
/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
* lock.
*/
void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
{
struct sockaddr_vm src, dst;
struct vsock_sock *vsk;
struct sock *sk;
bool space_available;
vsock_addr_init(&src, le64_to_cpu(pkt->hdr.src_cid),
le32_to_cpu(pkt->hdr.src_port));
vsock_addr_init(&dst, le64_to_cpu(pkt->hdr.dst_cid),
le32_to_cpu(pkt->hdr.dst_port));
trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port,
dst.svm_cid, dst.svm_port,
le32_to_cpu(pkt->hdr.len),
le16_to_cpu(pkt->hdr.type),
le16_to_cpu(pkt->hdr.op),
le32_to_cpu(pkt->hdr.flags),
le32_to_cpu(pkt->hdr.buf_alloc),
le32_to_cpu(pkt->hdr.fwd_cnt));
if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
(void)virtio_transport_reset_no_sock(pkt);
goto free_pkt;
}
/* The socket must be in connected or bound table
* otherwise send reset back
*/
sk = vsock_find_connected_socket(&src, &dst);
if (!sk) {
sk = vsock_find_bound_socket(&dst);
if (!sk) {
(void)virtio_transport_reset_no_sock(pkt);
goto free_pkt;
}
}
vsk = vsock_sk(sk);
space_available = virtio_transport_space_update(sk, pkt);
lock_sock(sk);
/* Update CID in case it has changed after a transport reset event */
vsk->local_addr.svm_cid = dst.svm_cid;
if (space_available)
sk->sk_write_space(sk);
switch (sk->sk_state) {
case VSOCK_SS_LISTEN:
virtio_transport_recv_listen(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
case SS_CONNECTING:
virtio_transport_recv_connecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
case SS_CONNECTED:
virtio_transport_recv_connected(sk, pkt);
break;
case SS_DISCONNECTING:
virtio_transport_recv_disconnecting(sk, pkt);
virtio_transport_free_pkt(pkt);
break;
default:
virtio_transport_free_pkt(pkt);
break;
}
release_sock(sk);
/* Release refcnt obtained when we fetched this socket out of the
* bound or connected list.
*/
sock_put(sk);
return;
free_pkt:
virtio_transport_free_pkt(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);
void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
{
kfree(pkt->buf);
kfree(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("common code for virtio vsock");
int llc_conn_state_process(struct sock *sk, struct sk_buff *skb)
{
int rc;
struct llc_sock *llc = llc_sk(skb->sk);
struct llc_conn_state_ev *ev = llc_conn_ev(skb);
skb_get(skb);
ev->ind_prim = ev->cfm_prim = 0;
rc = llc_conn_service(skb->sk, skb);
if (unlikely(rc != 0)) {
printk(KERN_ERR "%s: llc_conn_service failed\n", __func__);
goto out_kfree_skb;
}
if (unlikely(!ev->ind_prim && !ev->cfm_prim)) {
if (!skb->next)
goto out_kfree_skb;
goto out_skb_put;
}
if (unlikely(ev->ind_prim && ev->cfm_prim))
skb_get(skb);
switch (ev->ind_prim) {
case LLC_DATA_PRIM:
llc_save_primitive(sk, skb, LLC_DATA_PRIM);
if (unlikely(sock_queue_rcv_skb(sk, skb))) {
printk(KERN_ERR "%s: sock_queue_rcv_skb failed!\n",
__func__);
kfree_skb(skb);
}
break;
case LLC_CONN_PRIM:
skb_queue_tail(&sk->sk_receive_queue, skb);
sk->sk_state_change(sk);
break;
case LLC_DISC_PRIM:
sock_hold(sk);
if (sk->sk_type == SOCK_STREAM &&
sk->sk_state == TCP_ESTABLISHED) {
sk->sk_shutdown = SHUTDOWN_MASK;
sk->sk_socket->state = SS_UNCONNECTED;
sk->sk_state = TCP_CLOSE;
if (!sock_flag(sk, SOCK_DEAD)) {
sock_set_flag(sk, SOCK_DEAD);
sk->sk_state_change(sk);
}
}
kfree_skb(skb);
sock_put(sk);
break;
case LLC_RESET_PRIM:
printk(KERN_INFO "%s: received a reset ind!\n", __func__);
kfree_skb(skb);
break;
default:
if (ev->ind_prim) {
printk(KERN_INFO "%s: received unknown %d prim!\n",
__func__, ev->ind_prim);
kfree_skb(skb);
}
break;
}
switch (ev->cfm_prim) {
case LLC_DATA_PRIM:
if (!llc_data_accept_state(llc->state))
sk->sk_write_space(sk);
else
rc = llc->failed_data_req = 1;
break;
case LLC_CONN_PRIM:
if (sk->sk_type == SOCK_STREAM &&
sk->sk_state == TCP_SYN_SENT) {
if (ev->status) {
sk->sk_socket->state = SS_UNCONNECTED;
sk->sk_state = TCP_CLOSE;
} else {
sk->sk_socket->state = SS_CONNECTED;
sk->sk_state = TCP_ESTABLISHED;
}
sk->sk_state_change(sk);
}
break;
case LLC_DISC_PRIM:
sock_hold(sk);
if (sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_CLOSING) {
sk->sk_socket->state = SS_UNCONNECTED;
sk->sk_state = TCP_CLOSE;
sk->sk_state_change(sk);
}
sock_put(sk);
break;
case LLC_RESET_PRIM:
printk(KERN_INFO "%s: received a reset conf!\n", __func__);
break;
default:
if (ev->cfm_prim) {
printk(KERN_INFO "%s: received unknown %d prim!\n",
__func__, ev->cfm_prim);
break;
}
goto out_skb_put;
}
out_kfree_skb:
kfree_skb(skb);
out_skb_put:
kfree_skb(skb);
return rc;
}
int sc_capwap_send(struct sc_capwap_session *session, uint8_t* buffer, int length)
{
struct kvec vec = {
.iov_base = buffer,
.iov_len = length,
};
struct msghdr msg = {
.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL,
};
TRACEKMOD("### sc_capwap_send\n");
return kernel_sendmsg(session->socket, &msg, &vec, 1, vec.iov_len);
}
int sc_capwap_recvpacket(struct sock *sk, struct sk_buff* skb)
{
struct sc_capwap_session* session;
TRACEKMOD("### sc_capwap_recvpacket\n");
CAPWAP_SKB_CB(skb)->flags = SKB_CAPWAP_FLAG_FROM_DATA_CHANNEL;
sock_hold(sk);
/* Get session */
session = (struct sc_capwap_session *)sk->sk_user_data;
if (!session) {
TRACEKMOD("*** Session not found\n");
goto drop;
}
/* Remove UDP header */
if (!skb_pull(skb, sizeof(struct udphdr))) {
TRACEKMOD("*** Invalid packet\n");
goto drop;
}
/* Parsing packet */
if (sc_capwap_parsingpacket(session, skb)) {
TRACEKMOD("*** Parsing error\n");
goto drop;
}
sock_put(sk);
return 0;
drop:
sock_put(sk);
kfree_skb(skb);
return 0;
}
/* */
struct sc_capwap_session* sc_capwap_recvunknownkeepalive(struct sc_capwap_session* session,
const struct sc_capwap_sessionid_element* sessionid)
{
TRACEKMOD("### sc_capwap_recvunknownkeepalive\n");
return NULL;
}
void dccp_close(struct sock *sk, long timeout)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == DCCP_LISTEN) {
dccp_set_state(sk, DCCP_CLOSED);
/* Special case. */
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
sk_stop_timer(sk, &dp->dccps_xmit_timer);
/*
* We need to flush the recv. buffs. We do this only on the
* descriptor close, not protocol-sourced closes, because the
*reader process may not have drained the data yet!
*/
/* FIXME: check for unread data */
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
__kfree_skb(skb);
}
if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
} else if (dccp_close_state(sk)) {
dccp_send_close(sk, 1);
}
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
atomic_inc(sk->sk_prot->orphan_count);
/*
* It is the last release_sock in its life. It will remove backlog.
*/
release_sock(sk);
/*
* Now socket is owned by kernel and we acquire BH lock
* to finish close. No need to check for user refs.
*/
local_bh_disable();
bh_lock_sock(sk);
BUG_TRAP(!sock_owned_by_user(sk));
/* Have we already been destroyed by a softirq or backlog? */
if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
goto out;
/*
* The last release_sock may have processed the CLOSE or RESET
* packet moving sock to CLOSED state, if not we have to fire
* the CLOSE/CLOSEREQ retransmission timer, see "8.3. Termination"
* in draft-ietf-dccp-spec-11. -acme
*/
if (sk->sk_state == DCCP_CLOSING) {
/* FIXME: should start at 2 * RTT */
/* Timer for repeating the CLOSE/CLOSEREQ until an answer. */
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
inet_csk(sk)->icsk_rto,
DCCP_RTO_MAX);
#if 0
/* Yeah, we should use sk->sk_prot->orphan_count, etc */
dccp_set_state(sk, DCCP_CLOSED);
#endif
}
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
/* Otherwise, socket is reprieved until protocol close. */
out:
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
}
static int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
write_lock_bh(&udp_hash_lock);
if (snum == 0) {
int best_size_so_far, best, result, i;
if (udp_port_rover > sysctl_local_port_range[1] ||
udp_port_rover < sysctl_local_port_range[0])
udp_port_rover = sysctl_local_port_range[0];
best_size_so_far = 32767;
best = result = udp_port_rover;
for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
struct sock *sk;
int size;
sk = udp_hash[result & (UDP_HTABLE_SIZE - 1)];
if (!sk) {
if (result > sysctl_local_port_range[1])
result = sysctl_local_port_range[0] +
((result - sysctl_local_port_range[0]) &
(UDP_HTABLE_SIZE - 1));
goto gotit;
}
size = 0;
do {
if (++size >= best_size_so_far)
goto next;
} while ((sk = sk->next) != NULL);
best_size_so_far = size;
best = result;
next:;
}
result = best;
for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) {
if (result > sysctl_local_port_range[1])
result = sysctl_local_port_range[0]
+ ((result - sysctl_local_port_range[0]) &
(UDP_HTABLE_SIZE - 1));
if (!udp_lport_inuse(result))
break;
}
if (i >= (1 << 16) / UDP_HTABLE_SIZE)
goto fail;
gotit:
udp_port_rover = snum = result;
} else {
struct sock *sk2;
for (sk2 = udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
sk2 != NULL;
sk2 = sk2->next) {
if (sk2->num == snum &&
sk2 != sk &&
!ipv6_only_sock(sk2) &&
sk2->bound_dev_if == sk->bound_dev_if &&
(!sk2->rcv_saddr ||
!sk->rcv_saddr ||
sk2->rcv_saddr == sk->rcv_saddr) &&
(!sk2->reuse || !sk->reuse))
goto fail;
}
}
sk->num = snum;
if (sk->pprev == NULL) {
struct sock **skp = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
if ((sk->next = *skp) != NULL)
(*skp)->pprev = &sk->next;
*skp = sk;
sk->pprev = skp;
sock_prot_inc_use(sk->prot);
sock_hold(sk);
}
write_unlock_bh(&udp_hash_lock);
return 0;
fail:
write_unlock_bh(&udp_hash_lock);
return 1;
}
static int packet_create(struct socket *sock, int protocol)
{
struct sock *sk;
struct packet_opt *po;
int err;
if (!capable(CAP_NET_RAW))
return -EPERM;
if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW
#ifdef CONFIG_SOCK_PACKET
&& sock->type != SOCK_PACKET
#endif
)
return -ESOCKTNOSUPPORT;
sock->state = SS_UNCONNECTED;
err = -ENOBUFS;
sk = sk_alloc(PF_PACKET, GFP_KERNEL, 1, NULL);
if (sk == NULL)
goto out;
sock->ops = &packet_ops;
#ifdef CONFIG_SOCK_PACKET
if (sock->type == SOCK_PACKET)
sock->ops = &packet_ops_spkt;
#endif
sock_init_data(sock,sk);
sk_set_owner(sk, THIS_MODULE);
po = sk->sk_protinfo = kmalloc(sizeof(*po), GFP_KERNEL);
if (!po)
goto out_free;
memset(po, 0, sizeof(*po));
sk->sk_family = PF_PACKET;
po->num = protocol;
sk->sk_destruct = packet_sock_destruct;
atomic_inc(&packet_socks_nr);
/*
* Attach a protocol block
*/
spin_lock_init(&po->bind_lock);
po->prot_hook.func = packet_rcv;
#ifdef CONFIG_SOCK_PACKET
if (sock->type == SOCK_PACKET)
po->prot_hook.func = packet_rcv_spkt;
#endif
po->prot_hook.af_packet_priv = sk;
if (protocol) {
po->prot_hook.type = protocol;
dev_add_pack(&po->prot_hook);
sock_hold(sk);
po->running = 1;
}
write_lock_bh(&packet_sklist_lock);
sk_add_node(sk, &packet_sklist);
write_unlock_bh(&packet_sklist_lock);
return(0);
out_free:
sk_free(sk);
out:
return err;
}
static int packet_create(struct socket *sock, int protocol)
{
struct sock *sk;
int err;
if (!capable(CAP_NET_RAW))
return -EPERM;
if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW
#ifdef CONFIG_SOCK_PACKET
&& sock->type != SOCK_PACKET
#endif
)
return -ESOCKTNOSUPPORT;
sock->state = SS_UNCONNECTED;
MOD_INC_USE_COUNT;
err = -ENOBUFS;
sk = sk_alloc(PF_PACKET, GFP_KERNEL, 1);
if (sk == NULL)
goto out;
sock->ops = &packet_ops;
#ifdef CONFIG_SOCK_PACKET
if (sock->type == SOCK_PACKET)
sock->ops = &packet_ops_spkt;
#endif
sock_init_data(sock,sk);
sk->protinfo.af_packet = kmalloc(sizeof(struct packet_opt), GFP_KERNEL);
if (sk->protinfo.af_packet == NULL)
goto out_free;
memset(sk->protinfo.af_packet, 0, sizeof(struct packet_opt));
sk->family = PF_PACKET;
sk->num = protocol;
sk->destruct = packet_sock_destruct;
atomic_inc(&packet_socks_nr);
/*
* Attach a protocol block
*/
spin_lock_init(&sk->protinfo.af_packet->bind_lock);
sk->protinfo.af_packet->prot_hook.func = packet_rcv;
#ifdef CONFIG_SOCK_PACKET
if (sock->type == SOCK_PACKET)
sk->protinfo.af_packet->prot_hook.func = packet_rcv_spkt;
#endif
sk->protinfo.af_packet->prot_hook.data = (void *)sk;
if (protocol) {
sk->protinfo.af_packet->prot_hook.type = protocol;
dev_add_pack(&sk->protinfo.af_packet->prot_hook);
sock_hold(sk);
sk->protinfo.af_packet->running = 1;
}
write_lock_bh(&packet_sklist_lock);
sk->next = packet_sklist;
packet_sklist = sk;
sock_hold(sk);
write_unlock_bh(&packet_sklist_lock);
return(0);
out_free:
sk_free(sk);
out:
MOD_DEC_USE_COUNT;
return err;
}
static void __vsock_insert_bound(struct list_head *list,
struct vsock_sock *vsk)
{
sock_hold(&vsk->sk);
list_add(&vsk->bound_table, list);
}
static void __vsock_insert_connected(struct list_head *list,
struct vsock_sock *vsk)
{
sock_hold(&vsk->sk);
list_add(&vsk->connected_table, list);
}
static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
struct sock *sk,
gfp_t gfp)
{
struct sctp_hmac_algo_param *auth_hmacs = NULL;
struct sctp_chunks_param *auth_chunks = NULL;
struct sctp_shared_key *null_key;
int err;
ep->digest = kzalloc(SCTP_SIGNATURE_SIZE, gfp);
if (!ep->digest)
return NULL;
if (sctp_auth_enable) {
/*
*/
auth_hmacs = kzalloc(sizeof(sctp_hmac_algo_param_t) +
sizeof(__u16) * SCTP_AUTH_NUM_HMACS, gfp);
if (!auth_hmacs)
goto nomem;
auth_chunks = kzalloc(sizeof(sctp_chunks_param_t) +
SCTP_NUM_CHUNK_TYPES, gfp);
if (!auth_chunks)
goto nomem;
/*
*/
auth_hmacs->param_hdr.type = SCTP_PARAM_HMAC_ALGO;
auth_hmacs->param_hdr.length =
htons(sizeof(sctp_paramhdr_t) + 2);
auth_hmacs->hmac_ids[0] = htons(SCTP_AUTH_HMAC_ID_SHA1);
/* */
auth_chunks->param_hdr.type = SCTP_PARAM_CHUNKS;
auth_chunks->param_hdr.length = htons(sizeof(sctp_paramhdr_t));
/*
*/
if (sctp_addip_enable) {
auth_chunks->chunks[0] = SCTP_CID_ASCONF;
auth_chunks->chunks[1] = SCTP_CID_ASCONF_ACK;
auth_chunks->param_hdr.length =
htons(sizeof(sctp_paramhdr_t) + 2);
}
}
/* */
/* */
ep->base.type = SCTP_EP_TYPE_SOCKET;
/* */
atomic_set(&ep->base.refcnt, 1);
ep->base.dead = 0;
ep->base.malloced = 1;
/* */
sctp_inq_init(&ep->base.inqueue);
/* */
sctp_inq_set_th_handler(&ep->base.inqueue, sctp_endpoint_bh_rcv);
/* */
sctp_bind_addr_init(&ep->base.bind_addr, 0);
/* */
ep->base.sk = sk;
sock_hold(ep->base.sk);
/* */
INIT_LIST_HEAD(&ep->asocs);
/* */
ep->sndbuf_policy = sctp_sndbuf_policy;
sk->sk_data_ready = sctp_data_ready;
sk->sk_write_space = sctp_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
/* */
ep->rcvbuf_policy = sctp_rcvbuf_policy;
/* */
get_random_bytes(&ep->secret_key[0], SCTP_SECRET_SIZE);
ep->last_key = ep->current_key = 0;
ep->key_changed_at = jiffies;
/* */
INIT_LIST_HEAD(&ep->endpoint_shared_keys);
null_key = sctp_auth_shkey_create(0, GFP_KERNEL);
if (!null_key)
goto nomem;
list_add(&null_key->key_list, &ep->endpoint_shared_keys);
/* */
err = sctp_auth_init_hmacs(ep, gfp);
if (err)
goto nomem_hmacs;
/*
*/
ep->auth_hmacs_list = auth_hmacs;
ep->auth_chunk_list = auth_chunks;
return ep;
nomem_hmacs:
sctp_auth_destroy_keys(&ep->endpoint_shared_keys);
nomem:
/* */
kfree(auth_hmacs);
kfree(auth_chunks);
kfree(ep->digest);
return NULL;
}
/* Grrr, addr_type already calculated by caller, but I don't want
* to add some silly "cookie" argument to this method just for that.
*/
static int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
write_lock_bh(&udp_hash_lock);
if (snum == 0) {
int best_size_so_far, best, result, i;
if (udp_port_rover > sysctl_local_port_range[1] ||
udp_port_rover < sysctl_local_port_range[0])
udp_port_rover = sysctl_local_port_range[0];
best_size_so_far = 32767;
best = result = udp_port_rover;
for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
struct sock *sk;
int size;
sk = udp_hash[result & (UDP_HTABLE_SIZE - 1)];
if (!sk) {
if (result > sysctl_local_port_range[1])
result = sysctl_local_port_range[0] +
((result - sysctl_local_port_range[0]) &
(UDP_HTABLE_SIZE - 1));
goto gotit;
}
size = 0;
do {
if (++size >= best_size_so_far)
goto next;
} while ((sk = sk->next) != NULL);
best_size_so_far = size;
best = result;
next:;
}
result = best;
for(;; result += UDP_HTABLE_SIZE) {
if (result > sysctl_local_port_range[1])
result = sysctl_local_port_range[0]
+ ((result - sysctl_local_port_range[0]) &
(UDP_HTABLE_SIZE - 1));
if (!udp_lport_inuse(result))
break;
}
gotit:
udp_port_rover = snum = result;
} else {
struct sock *sk2;
int sk_reuse, sk2_reuse;
int addr_type = ipv6_addr_type(&sk->net_pinfo.af_inet6.rcv_saddr),
addr_type2;
#if defined(CONFIG_NET_RESTRICTED_REUSE) || defined(CONFIG_IPV6_RESTRICTED_DOUBLE_BIND)
uid_t sk_uid = sock_i_uid_t(sk),
sk2_uid;
#endif
sk_reuse = 0;
if (sk->reuse)
sk_reuse |= 1;
#ifdef SO_REUSEPORT
if (sk->reuseport)
sk_reuse |= 2;
#endif
if (sk_reuse &&
(addr_type != IPV6_ADDR_MAPPED ? (addr_type & IPV6_ADDR_MULTICAST) : MULTICAST(sk->rcv_saddr)))
sk_reuse |= 4;
for (sk2 = udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
sk2 != NULL;
sk2 = sk2->next) {
#if 1 /* XXX: should be recoded like 2.4.21 */
#if defined(CONFIG_NET_RESTRICTED_REUSE) || defined(CONFIG_IPV6_RESTRICTED_DOUBLE_BIND)
int uid_ok;
#endif
int both_specified = 0;
if (sk2->num != snum ||
sk2 == sk ||
(sk2->bound_dev_if && sk->bound_dev_if &&
sk2->bound_dev_if != sk->bound_dev_if))
continue;
#if 0
if (sk2->family != AF_INET6 && sk2->family != AF_INET)
continue;
#endif
addr_type2 = sk2->family == AF_INET6 ? ipv6_addr_type(&sk2->net_pinfo.af_inet6.rcv_saddr) : IPV6_ADDR_MAPPED;
#if defined(CONFIG_NET_RESTRICTED_REUSE) || defined(CONFIG_IPV6_RESTRICTED_DOUBLE_BIND)
sk2_uid = sock_i_uid_t(sk2);
#endif
if ((addr_type2 != IPV6_ADDR_MAPPED ? addr_type2 != IPV6_ADDR_ANY : sk2->rcv_saddr) &&
(addr_type != IPV6_ADDR_MAPPED ? addr_type != IPV6_ADDR_ANY : sk->rcv_saddr)) {
if (addr_type2 == IPV6_ADDR_MAPPED || addr_type == IPV6_ADDR_MAPPED) {
if (addr_type2 != addr_type ||
sk2->rcv_saddr != sk->rcv_saddr)
continue;
} else {
if (ipv6_addr_cmp(&sk2->net_pinfo.af_inet6.rcv_saddr,
&sk->net_pinfo.af_inet6.rcv_saddr))
continue;
}
both_specified = 1;
}
#if defined(CONFIG_NET_RESTRICTED_REUSE) || defined(CONFIG_IPV6_RESTRICTED_DOUBLE_BIND)
uid_ok = sk2_uid == (uid_t) -1 || sk_uid == sk2_uid;
#endif
if ((addr_type2 == IPV6_ADDR_MAPPED &&
addr_type != IPV6_ADDR_MAPPED && sk->net_pinfo.af_inet6.ipv6only) ||
(addr_type == IPV6_ADDR_MAPPED &&
addr_type2 != IPV6_ADDR_MAPPED && sk2->net_pinfo.af_inet6.ipv6only)) {
#ifdef CONFIG_IPV6_RESTRICTED_DOUBLE_BIND
if (sysctl_ipv6_bindv6only_restriction == 0 || uid_ok)
continue;
#else
continue;
#endif
}
sk2_reuse = 0;
if (sk2->reuse)
sk2_reuse |= 1;
#ifdef SO_REUSEPORT
if (sk2->reuseport)
sk2_reuse |= 2;
#endif
if (sk2_reuse &&
(addr_type2 != IPV6_ADDR_MAPPED ? (addr_type2 & IPV6_ADDR_MULTICAST) : MULTICAST(sk2->rcv_saddr)))
sk2_reuse |= 4;
if (sk2_reuse & sk_reuse & 3) { /* NOT && */
if (sk2_reuse & sk_reuse & 4)
continue;
#ifdef CONFIG_NET_RESTRICTED_REUSE
if (!uid_ok)
goto fail;
#endif
#ifdef SO_REUSEPORT
if (sk2_reuse & sk_reuse & 2)
continue;
#endif
if (both_specified) {
int addr_type2d = sk2->family == AF_INET6 ? ipv6_addr_type(&sk2->net_pinfo.af_inet6.daddr) : IPV6_ADDR_MAPPED;
if (addr_type2d != IPV6_ADDR_MAPPED ? addr_type2d != IPV6_ADDR_ANY : sk2->daddr)
continue;
} else {
if ((addr_type2 != IPV6_ADDR_MAPPED ? addr_type2 != IPV6_ADDR_ANY : sk2->rcv_saddr) ||
(addr_type != IPV6_ADDR_MAPPED ? addr_type != IPV6_ADDR_ANY : sk->rcv_saddr))
continue;
}
}
goto fail;
#else /* XXX: should be recoded like 2.4.21 */
if (sk2->num == snum &&
sk2 != sk &&
(!sk2->bound_dev_if ||
!sk->bound_dev_if ||
sk2->bound_dev_if == sk->bound_dev_if) &&
((!sk2->rcv_saddr && !ipv6_only_sock(sk)) ||
(sk2->family == AF_INET6 &&
ipv6_addr_any(&sk2->net_pinfo.af_inet6.rcv_saddr) &&
!(ipv6_only_sock(sk2) && addr_type == IPV6_ADDR_MAPPED)) ||
(addr_type == IPV6_ADDR_ANY &&
(!ipv6_only_sock(sk) ||
!(sk2->family == AF_INET6 ? (ipv6_addr_type(&sk2->net_pinfo.af_inet6.rcv_saddr) == IPV6_ADDR_MAPPED) : 1))) ||
(sk2->family == AF_INET6 &&
!ipv6_addr_cmp(&sk->net_pinfo.af_inet6.rcv_saddr,
&sk2->net_pinfo.af_inet6.rcv_saddr)) ||
(addr_type == IPV6_ADDR_MAPPED &&
!ipv6_only_sock(sk2) &&
(!sk2->rcv_saddr ||
!sk->rcv_saddr ||
sk->rcv_saddr == sk2->rcv_saddr))) &&
(!sk2->reuse || !sk->reuse))
goto fail;
#endif /* XXX: should be recoded like 2.4.21 */
}
}
sk->num = snum;
if (sk->pprev == NULL) {
struct sock **skp = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
if ((sk->next = *skp) != NULL)
(*skp)->pprev = &sk->next;
*skp = sk;
sk->pprev = skp;
sock_prot_inc_use(sk->prot);
sock_hold(sk);
}
write_unlock_bh(&udp_hash_lock);
return 0;
fail:
write_unlock_bh(&udp_hash_lock);
return 1;
}
static bool tcp_fastopen_create_child(struct sock *sk,
struct sk_buff *skb,
struct dst_entry *dst,
struct request_sock *req)
{
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
if (child == NULL)
return false;
spin_lock(&queue->fastopenq->lock);
queue->fastopenq->qlen++;
spin_unlock(&queue->fastopenq->lock);
/* Initialize the child socket. Have to fix some values to take
* into account the child is a Fast Open socket and is created
* only out of the bits carried in the SYN packet.
*/
tp = tcp_sk(child);
tp->fastopen_rsk = req;
/* Do a hold on the listner sk so that if the listener is being
* closed, the child that has been accepted can live on and still
* access listen_lock.
*/
sock_hold(sk);
tcp_rsk(req)->listener = sk;
/* RFC1323: The window in SYN & SYN/ACK segments is never
* scaled. So correct it appropriately.
*/
tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
/* Activate the retrans timer so that SYNACK can be retransmitted.
* The request socket is not added to the SYN table of the parent
* because it's been added to the accept queue directly.
*/
inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
/* Add the child socket directly into the accept queue */
inet_csk_reqsk_queue_add(sk, req, child);
/* Now finish processing the fastopen child socket. */
inet_csk(child)->icsk_af_ops->rebuild_header(child);
tcp_init_congestion_control(child);
tcp_mtup_init(child);
tcp_init_metrics(child);
tcp_init_buffer_space(child);
/* Queue the data carried in the SYN packet. We need to first
* bump skb's refcnt because the caller will attempt to free it.
*
* XXX (TFO) - we honor a zero-payload TFO request for now,
* (any reason not to?) but no need to queue the skb since
* there is no data. How about SYN+FIN?
*/
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
skb = skb_get(skb);
skb_dst_drop(skb);
__skb_pull(skb, tcp_hdr(skb)->doff * 4);
skb_set_owner_r(skb, child);
__skb_queue_tail(&child->sk_receive_queue, skb);
tp->syn_data_acked = 1;
}
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
sk->sk_data_ready(sk, 0);
bh_unlock_sock(child);
sock_put(child);
WARN_ON(req->sk == NULL);
return true;
}
void dccp_close(struct sock *sk, long timeout)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
u32 data_was_unread = 0;
int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == DCCP_LISTEN) {
dccp_set_state(sk, DCCP_CLOSED);
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
sk_stop_timer(sk, &dp->dccps_xmit_timer);
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
data_was_unread += skb->len;
__kfree_skb(skb);
}
if (data_was_unread) {
DCCP_WARN("DCCP: ABORT -- %u bytes unread\n", data_was_unread);
dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
dccp_set_state(sk, DCCP_CLOSED);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
sk->sk_prot->disconnect(sk, 0);
} else if (sk->sk_state != DCCP_CLOSED) {
dccp_terminate_connection(sk);
}
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
release_sock(sk);
local_bh_disable();
bh_lock_sock(sk);
WARN_ON(sock_owned_by_user(sk));
percpu_counter_inc(sk->sk_prot->orphan_count);
if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
goto out;
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
out:
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
}
static int serval_inet_tcp_init_sock(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
struct sock *old_sk = sk;
const struct proto_ops *old_ops = sock->ops;
struct inet_sock *inet;
int err = 0;
LOG_DBG("init sock\n");
/* First fully initialize the old sock. Otherwise, the release
function will fail. */
err = old_tcp_prot.init(sk);
if (err)
return err;
sock->ops = &serval_inet_stream_ops;
sk = serval_sk_alloc(sock_net(sk), sock,
GFP_KERNEL,
SERVAL_PROTO_TCP,
&serval_tcp_proto);
if (!sk) {
LOG_ERR("Fail alloc\n");
goto out_fail_alloc;
}
/* Initialize serval sock part of socket */
serval_sock_init(sk);
/* Initialize inet part */
inet = inet_sk(sk);
inet->uc_ttl = -1; /* Let IP decide TTL */
inet->mc_loop = 1;
inet->mc_ttl = 1;
inet->mc_index = 0;
inet->mc_list = NULL;
if (sk->sk_prot->init) {
/* Call protocol specific init */
err = sk->sk_prot->init(sk);
if (err < 0) {
LOG_ERR("Fail init\n");
goto out_fail_init;
}
}
sock_hold(old_sk);
serval_sk(sk)->old_sk = old_sk;
LOG_DBG("Successfully hijacked sock\n");
return 0;
out_fail_init:
sk_common_release(sk);
out_fail_alloc:
sock->ops = old_ops;
sock->sk = old_sk;
return 0;
}
static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct net_device *dev;
struct sk_buff *frag;
struct rt6_info *rt = (struct rt6_info*)skb->dst;
struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;
struct ipv6hdr *tmp_hdr;
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
__be32 frag_id = 0;
int ptr, offset = 0, err=0;
u8 *prevhdr, nexthdr = 0;
dev = rt->u.dst.dev;
hlen = ip6_find_1stfragopt(skb, &prevhdr);
nexthdr = *prevhdr;
mtu = ip6_skb_dst_mtu(skb);
/* We must not fragment if the socket is set to force MTU discovery
* or if the skb it not generated by a local socket. (This last
* check should be redundant, but it's free.)
*/
if (!skb->local_df) {
skb->dev = skb->dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (np && np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
mtu -= hlen + sizeof(struct frag_hdr);
if (skb_shinfo(skb)->frag_list) {
int first_len = skb_pagelen(skb);
int truesizes = 0;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
skb_cloned(skb))
goto slow_path;
for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path;
BUG_ON(frag->sk);
if (skb->sk) {
sock_hold(skb->sk);
frag->sk = skb->sk;
frag->destructor = sock_wfree;
truesizes += frag->truesize;
}
}
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_shinfo(skb)->frag_list = NULL;
/* BUILD HEADER */
*prevhdr = NEXTHDR_FRAGMENT;
tmp_hdr = kmemdup(skb_network_header(skb), hlen, GFP_ATOMIC);
if (!tmp_hdr) {
IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS);
return -ENOMEM;
}
__skb_pull(skb, hlen);
fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
__skb_push(skb, hlen);
skb_reset_network_header(skb);
memcpy(skb_network_header(skb), tmp_hdr, hlen);
ipv6_select_ident(skb, fh);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
frag_id = fh->identification;
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
skb->truesize -= truesizes;
skb->len = first_len;
ipv6_hdr(skb)->payload_len = htons(first_len -
sizeof(struct ipv6hdr));
dst_hold(&rt->u.dst);
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
skb_reset_transport_header(frag);
fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr));
__skb_push(frag, hlen);
skb_reset_network_header(frag);
memcpy(skb_network_header(frag), tmp_hdr,
hlen);
offset += skb->len - hlen - sizeof(struct frag_hdr);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(offset);
if (frag->next != NULL)
fh->frag_off |= htons(IP6_MF);
fh->identification = frag_id;
ipv6_hdr(frag)->payload_len =
htons(frag->len -
sizeof(struct ipv6hdr));
ip6_copy_metadata(frag, skb);
}
err = output(skb);
if(!err)
IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGCREATES);
if (err || !frag)
break;
skb = frag;
frag = skb->next;
skb->next = NULL;
}
kfree(tmp_hdr);
if (err == 0) {
IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGOKS);
dst_release(&rt->u.dst);
return 0;
}
while (frag) {
skb = frag->next;
kfree_skb(frag);
frag = skb;
}
IP6_INC_STATS(ip6_dst_idev(&rt->u.dst), IPSTATS_MIB_FRAGFAILS);
dst_release(&rt->u.dst);
return err;
}
slow_path:
left = skb->len - hlen; /* Space per frame */
ptr = hlen; /* Where to start from */
/*
* Fragment the datagram.
*/
*prevhdr = NEXTHDR_FRAGMENT;
/*
* Keep copying data until we run out.
*/
while(left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
len = mtu;
/* IF: we are not sending upto and including the packet end
then align the next start on an eight byte boundary */
if (len < left) {
len &= ~7;
}
/*
* Allocate buffer.
*/
if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) {
NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
IP6_INC_STATS(ip6_dst_idev(skb->dst),
IPSTATS_MIB_FRAGFAILS);
err = -ENOMEM;
goto fail;
}
/*
* Set up data on packet
*/
ip6_copy_metadata(frag, skb);
skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev));
skb_put(frag, len + hlen + sizeof(struct frag_hdr));
skb_reset_network_header(frag);
fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
frag->transport_header = (frag->network_header + hlen +
sizeof(struct frag_hdr));
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(frag, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
skb_copy_from_linear_data(skb, skb_network_header(frag), hlen);
/*
* Build fragment header.
*/
fh->nexthdr = nexthdr;
fh->reserved = 0;
if (!frag_id) {
ipv6_select_ident(skb, fh);
frag_id = fh->identification;
} else
fh->identification = frag_id;
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, ptr, skb_transport_header(frag), len))
BUG();
left -= len;
fh->frag_off = htons(offset);
if (left > 0)
fh->frag_off |= htons(IP6_MF);
ipv6_hdr(frag)->payload_len = htons(frag->len -
sizeof(struct ipv6hdr));
ptr += len;
offset += len;
/*
* Put this fragment into the sending queue.
*/
err = output(frag);
if (err)
goto fail;
IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGCREATES);
}
IP6_INC_STATS(ip6_dst_idev(skb->dst),
IPSTATS_MIB_FRAGOKS);
kfree_skb(skb);
return err;
fail:
IP6_INC_STATS(ip6_dst_idev(skb->dst),
IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return err;
}
/**
* iscsi_sw_tcp_xmit_segment - transmit segment
* @tcp_conn: the iSCSI TCP connection
* @segment: the buffer to transmnit
*
* This function transmits as much of the buffer as
* the network layer will accept, and returns the number of
* bytes transmitted.
*
* If CRC hashing is enabled, the function will compute the
* hash as it goes. When the entire segment has been transmitted,
* it will retrieve the hash value and send it as well.
*/
static int iscsi_sw_tcp_xmit_segment(struct iscsi_tcp_conn *tcp_conn,
struct iscsi_segment *segment)
{
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct socket *sk = tcp_sw_conn->sock;
unsigned int copied = 0;
int r = 0;
while (!iscsi_tcp_segment_done(tcp_conn, segment, 0, r)) {
struct scatterlist *sg;
unsigned int offset, copy;
int flags = 0;
r = 0;
offset = segment->copied;
copy = segment->size - offset;
if (segment->total_copied + segment->size < segment->total_size)
flags |= MSG_MORE;
/* Use sendpage if we can; else fall back to sendmsg */
if (!segment->data) {
sg = segment->sg;
offset += segment->sg_offset + sg->offset;
r = tcp_sw_conn->sendpage(sk, sg_page(sg), offset,
copy, flags);
} else {
struct msghdr msg = { .msg_flags = flags };
struct kvec iov = {
.iov_base = segment->data + offset,
.iov_len = copy
};
r = kernel_sendmsg(sk, &msg, &iov, 1, copy);
}
if (r < 0) {
iscsi_tcp_segment_unmap(segment);
return r;
}
copied += r;
}
return copied;
}
/**
* iscsi_sw_tcp_xmit - TCP transmit
**/
static int iscsi_sw_tcp_xmit(struct iscsi_conn *conn)
{
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct iscsi_segment *segment = &tcp_sw_conn->out.segment;
unsigned int consumed = 0;
int rc = 0;
while (1) {
rc = iscsi_sw_tcp_xmit_segment(tcp_conn, segment);
/*
* We may not have been able to send data because the conn
* is getting stopped. libiscsi will know so propagate err
* for it to do the right thing.
*/
if (rc == -EAGAIN)
return rc;
else if (rc < 0) {
rc = ISCSI_ERR_XMIT_FAILED;
goto error;
} else if (rc == 0)
break;
consumed += rc;
if (segment->total_copied >= segment->total_size) {
if (segment->done != NULL) {
rc = segment->done(tcp_conn, segment);
if (rc != 0)
goto error;
}
}
}
ISCSI_SW_TCP_DBG(conn, "xmit %d bytes\n", consumed);
conn->txdata_octets += consumed;
return consumed;
error:
/* Transmit error. We could initiate error recovery
* here. */
ISCSI_SW_TCP_DBG(conn, "Error sending PDU, errno=%d\n", rc);
iscsi_conn_failure(conn, rc);
return -EIO;
}
/**
* iscsi_tcp_xmit_qlen - return the number of bytes queued for xmit
*/
static inline int iscsi_sw_tcp_xmit_qlen(struct iscsi_conn *conn)
{
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct iscsi_segment *segment = &tcp_sw_conn->out.segment;
return segment->total_copied - segment->total_size;
}
static int iscsi_sw_tcp_pdu_xmit(struct iscsi_task *task)
{
struct iscsi_conn *conn = task->conn;
int rc;
while (iscsi_sw_tcp_xmit_qlen(conn)) {
rc = iscsi_sw_tcp_xmit(conn);
if (rc == 0)
return -EAGAIN;
if (rc < 0)
return rc;
}
return 0;
}
/*
* This is called when we're done sending the header.
* Simply copy the data_segment to the send segment, and return.
*/
static int iscsi_sw_tcp_send_hdr_done(struct iscsi_tcp_conn *tcp_conn,
struct iscsi_segment *segment)
{
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
tcp_sw_conn->out.segment = tcp_sw_conn->out.data_segment;
ISCSI_SW_TCP_DBG(tcp_conn->iscsi_conn,
"Header done. Next segment size %u total_size %u\n",
tcp_sw_conn->out.segment.size,
tcp_sw_conn->out.segment.total_size);
return 0;
}
static void iscsi_sw_tcp_send_hdr_prep(struct iscsi_conn *conn, void *hdr,
size_t hdrlen)
{
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
ISCSI_SW_TCP_DBG(conn, "%s\n", conn->hdrdgst_en ?
"digest enabled" : "digest disabled");
/* Clear the data segment - needs to be filled in by the
* caller using iscsi_tcp_send_data_prep() */
memset(&tcp_sw_conn->out.data_segment, 0,
sizeof(struct iscsi_segment));
/* If header digest is enabled, compute the CRC and
* place the digest into the same buffer. We make
* sure that both iscsi_tcp_task and mtask have
* sufficient room.
*/
if (conn->hdrdgst_en) {
iscsi_tcp_dgst_header(&tcp_sw_conn->tx_hash, hdr, hdrlen,
hdr + hdrlen);
hdrlen += ISCSI_DIGEST_SIZE;
}
/* Remember header pointer for later, when we need
* to decide whether there's a payload to go along
* with the header. */
tcp_sw_conn->out.hdr = hdr;
iscsi_segment_init_linear(&tcp_sw_conn->out.segment, hdr, hdrlen,
iscsi_sw_tcp_send_hdr_done, NULL);
}
/*
* Prepare the send buffer for the payload data.
* Padding and checksumming will all be taken care
* of by the iscsi_segment routines.
*/
static int
iscsi_sw_tcp_send_data_prep(struct iscsi_conn *conn, struct scatterlist *sg,
unsigned int count, unsigned int offset,
unsigned int len)
{
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct hash_desc *tx_hash = NULL;
unsigned int hdr_spec_len;
ISCSI_SW_TCP_DBG(conn, "offset=%d, datalen=%d %s\n", offset, len,
conn->datadgst_en ?
"digest enabled" : "digest disabled");
/* Make sure the datalen matches what the caller
said he would send. */
hdr_spec_len = ntoh24(tcp_sw_conn->out.hdr->dlength);
WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));
if (conn->datadgst_en)
tx_hash = &tcp_sw_conn->tx_hash;
return iscsi_segment_seek_sg(&tcp_sw_conn->out.data_segment,
sg, count, offset, len,
NULL, tx_hash);
}
static void
iscsi_sw_tcp_send_linear_data_prep(struct iscsi_conn *conn, void *data,
size_t len)
{
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct hash_desc *tx_hash = NULL;
unsigned int hdr_spec_len;
ISCSI_SW_TCP_DBG(conn, "datalen=%zd %s\n", len, conn->datadgst_en ?
"digest enabled" : "digest disabled");
/* Make sure the datalen matches what the caller
said he would send. */
hdr_spec_len = ntoh24(tcp_sw_conn->out.hdr->dlength);
WARN_ON(iscsi_padded(len) != iscsi_padded(hdr_spec_len));
if (conn->datadgst_en)
tx_hash = &tcp_sw_conn->tx_hash;
iscsi_segment_init_linear(&tcp_sw_conn->out.data_segment,
data, len, NULL, tx_hash);
}
static int iscsi_sw_tcp_pdu_init(struct iscsi_task *task,
unsigned int offset, unsigned int count)
{
struct iscsi_conn *conn = task->conn;
int err = 0;
iscsi_sw_tcp_send_hdr_prep(conn, task->hdr, task->hdr_len);
if (!count)
return 0;
if (!task->sc)
iscsi_sw_tcp_send_linear_data_prep(conn, task->data, count);
else {
struct scsi_data_buffer *sdb = scsi_out(task->sc);
err = iscsi_sw_tcp_send_data_prep(conn, sdb->table.sgl,
sdb->table.nents, offset,
count);
}
if (err) {
/* got invalid offset/len */
return -EIO;
}
return 0;
}
static int iscsi_sw_tcp_pdu_alloc(struct iscsi_task *task, uint8_t opcode)
{
struct iscsi_tcp_task *tcp_task = task->dd_data;
task->hdr = task->dd_data + sizeof(*tcp_task);
task->hdr_max = sizeof(struct iscsi_sw_tcp_hdrbuf) - ISCSI_DIGEST_SIZE;
return 0;
}
static struct iscsi_cls_conn *
iscsi_sw_tcp_conn_create(struct iscsi_cls_session *cls_session,
uint32_t conn_idx)
{
struct iscsi_conn *conn;
struct iscsi_cls_conn *cls_conn;
struct iscsi_tcp_conn *tcp_conn;
struct iscsi_sw_tcp_conn *tcp_sw_conn;
cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*tcp_sw_conn),
conn_idx);
if (!cls_conn)
return NULL;
conn = cls_conn->dd_data;
tcp_conn = conn->dd_data;
tcp_sw_conn = tcp_conn->dd_data;
tcp_sw_conn->tx_hash.tfm = crypto_alloc_hash("crc32c", 0,
CRYPTO_ALG_ASYNC);
tcp_sw_conn->tx_hash.flags = 0;
if (IS_ERR(tcp_sw_conn->tx_hash.tfm))
goto free_conn;
tcp_sw_conn->rx_hash.tfm = crypto_alloc_hash("crc32c", 0,
CRYPTO_ALG_ASYNC);
tcp_sw_conn->rx_hash.flags = 0;
if (IS_ERR(tcp_sw_conn->rx_hash.tfm))
goto free_tx_tfm;
tcp_conn->rx_hash = &tcp_sw_conn->rx_hash;
return cls_conn;
free_tx_tfm:
crypto_free_hash(tcp_sw_conn->tx_hash.tfm);
free_conn:
iscsi_conn_printk(KERN_ERR, conn,
"Could not create connection due to crc32c "
"loading error. Make sure the crc32c "
"module is built as a module or into the "
"kernel\n");
iscsi_tcp_conn_teardown(cls_conn);
return NULL;
}
static void iscsi_sw_tcp_release_conn(struct iscsi_conn *conn)
{
struct iscsi_session *session = conn->session;
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct socket *sock = tcp_sw_conn->sock;
if (!sock)
return;
sock_hold(sock->sk);
iscsi_sw_tcp_conn_restore_callbacks(conn);
sock_put(sock->sk);
spin_lock_bh(&session->lock);
tcp_sw_conn->sock = NULL;
spin_unlock_bh(&session->lock);
sockfd_put(sock);
}
static void iscsi_sw_tcp_conn_destroy(struct iscsi_cls_conn *cls_conn)
{
struct iscsi_conn *conn = cls_conn->dd_data;
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
iscsi_sw_tcp_release_conn(conn);
if (tcp_sw_conn->tx_hash.tfm)
crypto_free_hash(tcp_sw_conn->tx_hash.tfm);
if (tcp_sw_conn->rx_hash.tfm)
crypto_free_hash(tcp_sw_conn->rx_hash.tfm);
iscsi_tcp_conn_teardown(cls_conn);
}
static void iscsi_sw_tcp_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
{
struct iscsi_conn *conn = cls_conn->dd_data;
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct socket *sock = tcp_sw_conn->sock;
/* userspace may have goofed up and not bound us */
if (!sock)
return;
sock->sk->sk_err = EIO;
wake_up_interruptible(sk_sleep(sock->sk));
/* stop xmit side */
iscsi_suspend_tx(conn);
/* stop recv side and release socket */
iscsi_sw_tcp_release_conn(conn);
iscsi_conn_stop(cls_conn, flag);
}
static int
iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session,
struct iscsi_cls_conn *cls_conn, uint64_t transport_eph,
int is_leading)
{
struct iscsi_session *session = cls_session->dd_data;
struct iscsi_conn *conn = cls_conn->dd_data;
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct sock *sk;
struct socket *sock;
int err;
/* lookup for existing socket */
sock = sockfd_lookup((int)transport_eph, &err);
if (!sock) {
iscsi_conn_printk(KERN_ERR, conn,
"sockfd_lookup failed %d\n", err);
return -EEXIST;
}
err = iscsi_conn_bind(cls_session, cls_conn, is_leading);
if (err)
goto free_socket;
spin_lock_bh(&session->lock);
/* bind iSCSI connection and socket */
tcp_sw_conn->sock = sock;
spin_unlock_bh(&session->lock);
/* setup Socket parameters */
sk = sock->sk;
sk->sk_reuse = 1;
sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
sk->sk_allocation = GFP_ATOMIC;
iscsi_sw_tcp_conn_set_callbacks(conn);
tcp_sw_conn->sendpage = tcp_sw_conn->sock->ops->sendpage;
/*
* set receive state machine into initial state
*/
iscsi_tcp_hdr_recv_prep(tcp_conn);
return 0;
free_socket:
sockfd_put(sock);
return err;
}
static int iscsi_sw_tcp_conn_set_param(struct iscsi_cls_conn *cls_conn,
enum iscsi_param param, char *buf,
int buflen)
{
struct iscsi_conn *conn = cls_conn->dd_data;
struct iscsi_session *session = conn->session;
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
int value;
switch(param) {
case ISCSI_PARAM_HDRDGST_EN:
iscsi_set_param(cls_conn, param, buf, buflen);
break;
case ISCSI_PARAM_DATADGST_EN:
iscsi_set_param(cls_conn, param, buf, buflen);
tcp_sw_conn->sendpage = conn->datadgst_en ?
sock_no_sendpage : tcp_sw_conn->sock->ops->sendpage;
break;
case ISCSI_PARAM_MAX_R2T:
sscanf(buf, "%d", &value);
if (value <= 0 || !is_power_of_2(value))
return -EINVAL;
if (session->max_r2t == value)
break;
iscsi_tcp_r2tpool_free(session);
iscsi_set_param(cls_conn, param, buf, buflen);
if (iscsi_tcp_r2tpool_alloc(session))
return -ENOMEM;
break;
default:
return iscsi_set_param(cls_conn, param, buf, buflen);
}
return 0;
}
static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn,
enum iscsi_param param, char *buf)
{
struct iscsi_conn *conn = cls_conn->dd_data;
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
struct sockaddr_in6 addr;
int rc, len;
switch(param) {
case ISCSI_PARAM_CONN_PORT:
case ISCSI_PARAM_CONN_ADDRESS:
spin_lock_bh(&conn->session->lock);
if (!tcp_sw_conn || !tcp_sw_conn->sock) {
spin_unlock_bh(&conn->session->lock);
return -ENOTCONN;
}
rc = kernel_getpeername(tcp_sw_conn->sock,
(struct sockaddr *)&addr, &len);
spin_unlock_bh(&conn->session->lock);
if (rc)
return rc;
return iscsi_conn_get_addr_param((struct sockaddr_storage *)
&addr, param, buf);
default:
return iscsi_conn_get_param(cls_conn, param, buf);
}
return 0;
}
static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost,
enum iscsi_host_param param, char *buf)
{
struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(shost);
struct iscsi_session *session = tcp_sw_host->session;
struct iscsi_conn *conn;
struct iscsi_tcp_conn *tcp_conn;
struct iscsi_sw_tcp_conn *tcp_sw_conn;
struct sockaddr_in6 addr;
int rc, len;
switch (param) {
case ISCSI_HOST_PARAM_IPADDRESS:
spin_lock_bh(&session->lock);
conn = session->leadconn;
if (!conn) {
spin_unlock_bh(&session->lock);
return -ENOTCONN;
}
tcp_conn = conn->dd_data;
tcp_sw_conn = tcp_conn->dd_data;
if (!tcp_sw_conn->sock) {
spin_unlock_bh(&session->lock);
return -ENOTCONN;
}
rc = kernel_getsockname(tcp_sw_conn->sock,
(struct sockaddr *)&addr, &len);
spin_unlock_bh(&session->lock);
if (rc)
return rc;
return iscsi_conn_get_addr_param((struct sockaddr_storage *)
&addr, param, buf);
default:
return iscsi_host_get_param(shost, param, buf);
}
return 0;
}
static void
iscsi_sw_tcp_conn_get_stats(struct iscsi_cls_conn *cls_conn,
struct iscsi_stats *stats)
{
struct iscsi_conn *conn = cls_conn->dd_data;
struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data;
stats->custom_length = 3;
strcpy(stats->custom[0].desc, "tx_sendpage_failures");
stats->custom[0].value = tcp_sw_conn->sendpage_failures_cnt;
strcpy(stats->custom[1].desc, "rx_discontiguous_hdr");
stats->custom[1].value = tcp_sw_conn->discontiguous_hdr_cnt;
strcpy(stats->custom[2].desc, "eh_abort_cnt");
stats->custom[2].value = conn->eh_abort_cnt;
iscsi_tcp_conn_get_stats(cls_conn, stats);
}
static struct iscsi_cls_session *
iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max,
uint16_t qdepth, uint32_t initial_cmdsn)
{
struct iscsi_cls_session *cls_session;
struct iscsi_session *session;
struct iscsi_sw_tcp_host *tcp_sw_host;
struct Scsi_Host *shost;
if (ep) {
printk(KERN_ERR "iscsi_tcp: invalid ep %p.\n", ep);
return NULL;
}
shost = iscsi_host_alloc(&iscsi_sw_tcp_sht,
sizeof(struct iscsi_sw_tcp_host), 1);
if (!shost)
return NULL;
shost->transportt = iscsi_sw_tcp_scsi_transport;
shost->cmd_per_lun = qdepth;
shost->max_lun = iscsi_max_lun;
shost->max_id = 0;
shost->max_channel = 0;
shost->max_cmd_len = SCSI_MAX_VARLEN_CDB_SIZE;
if (iscsi_host_add(shost, NULL))
goto free_host;
cls_session = iscsi_session_setup(&iscsi_sw_tcp_transport, shost,
cmds_max, 0,
sizeof(struct iscsi_tcp_task) +
sizeof(struct iscsi_sw_tcp_hdrbuf),
initial_cmdsn, 0);
if (!cls_session)
goto remove_host;
session = cls_session->dd_data;
tcp_sw_host = iscsi_host_priv(shost);
tcp_sw_host->session = session;
shost->can_queue = session->scsi_cmds_max;
if (iscsi_tcp_r2tpool_alloc(session))
goto remove_session;
return cls_session;
remove_session:
iscsi_session_teardown(cls_session);
remove_host:
iscsi_host_remove(shost);
free_host:
iscsi_host_free(shost);
return NULL;
}
static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session)
{
struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
iscsi_tcp_r2tpool_free(cls_session->dd_data);
iscsi_session_teardown(cls_session);
iscsi_host_remove(shost);
iscsi_host_free(shost);
}
static int iscsi_sw_tcp_slave_alloc(struct scsi_device *sdev)
{
set_bit(QUEUE_FLAG_BIDI, &sdev->request_queue->queue_flags);
return 0;
}
static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
{
struct pep_sock *pn = pep_sk(sk), *newpn;
struct sock *newsk = NULL;
struct sk_buff *skb;
struct pnpipehdr *hdr;
struct sockaddr_pn dst, src;
int err;
u16 peer_type;
u8 pipe_handle, enabled, n_sb;
u8 aligned = 0;
skb = skb_recv_datagram(sk, 0, flags & O_NONBLOCK, errp);
if (!skb)
return NULL;
lock_sock(sk);
if (sk->sk_state != TCP_LISTEN) {
err = -EINVAL;
goto drop;
}
sk_acceptq_removed(sk);
err = -EPROTO;
if (!pskb_may_pull(skb, sizeof(*hdr) + 4))
goto drop;
hdr = pnp_hdr(skb);
pipe_handle = hdr->pipe_handle;
switch (hdr->state_after_connect) {
case PN_PIPE_DISABLE:
enabled = 0;
break;
case PN_PIPE_ENABLE:
enabled = 1;
break;
default:
pep_reject_conn(sk, skb, PN_PIPE_ERR_INVALID_PARAM,
GFP_KERNEL);
goto drop;
}
peer_type = hdr->other_pep_type << 8;
/* Parse sub-blocks (options) */
n_sb = hdr->data[4];
while (n_sb > 0) {
u8 type, buf[1], len = sizeof(buf);
const u8 *data = pep_get_sb(skb, &type, &len, buf);
if (data == NULL)
goto drop;
switch (type) {
case PN_PIPE_SB_CONNECT_REQ_PEP_SUB_TYPE:
if (len < 1)
goto drop;
peer_type = (peer_type & 0xff00) | data[0];
break;
case PN_PIPE_SB_ALIGNED_DATA:
aligned = data[0] != 0;
break;
}
n_sb--;
}
/* Check for duplicate pipe handle */
newsk = pep_find_pipe(&pn->hlist, &dst, pipe_handle);
if (unlikely(newsk)) {
__sock_put(newsk);
newsk = NULL;
pep_reject_conn(sk, skb, PN_PIPE_ERR_PEP_IN_USE, GFP_KERNEL);
goto drop;
}
/* Create a new to-be-accepted sock */
newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0);
if (!newsk) {
pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL);
err = -ENOBUFS;
goto drop;
}
sock_init_data(NULL, newsk);
newsk->sk_state = TCP_SYN_RECV;
newsk->sk_backlog_rcv = pipe_do_rcv;
newsk->sk_protocol = sk->sk_protocol;
newsk->sk_destruct = pipe_destruct;
newpn = pep_sk(newsk);
pn_skb_get_dst_sockaddr(skb, &dst);
pn_skb_get_src_sockaddr(skb, &src);
newpn->pn_sk.sobject = pn_sockaddr_get_object(&dst);
newpn->pn_sk.dobject = pn_sockaddr_get_object(&src);
newpn->pn_sk.resource = pn_sockaddr_get_resource(&dst);
sock_hold(sk);
newpn->listener = sk;
skb_queue_head_init(&newpn->ctrlreq_queue);
newpn->pipe_handle = pipe_handle;
atomic_set(&newpn->tx_credits, 0);
newpn->ifindex = 0;
newpn->peer_type = peer_type;
newpn->rx_credits = 0;
newpn->rx_fc = newpn->tx_fc = PN_LEGACY_FLOW_CONTROL;
newpn->init_enable = enabled;
newpn->aligned = aligned;
err = pep_accept_conn(newsk, skb);
if (err) {
sock_put(newsk);
newsk = NULL;
goto drop;
}
sk_add_node(newsk, &pn->hlist);
drop:
release_sock(sk);
kfree_skb(skb);
*errp = err;
return newsk;
}
/*
* Initialize the base fields of the endpoint structure.
*/
static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
struct sock *sk,
gfp_t gfp)
{
struct sctp_hmac_algo_param *auth_hmacs = NULL;
struct sctp_chunks_param *auth_chunks = NULL;
struct sctp_shared_key *null_key;
int err;
memset(ep, 0, sizeof(struct sctp_endpoint));
ep->digest = kzalloc(SCTP_SIGNATURE_SIZE, gfp);
if (!ep->digest)
return NULL;
if (sctp_auth_enable) {
/* Allocate space for HMACS and CHUNKS authentication
* variables. There are arrays that we encode directly
* into parameters to make the rest of the operations easier.
*/
auth_hmacs = kzalloc(sizeof(sctp_hmac_algo_param_t) +
sizeof(__u16) * SCTP_AUTH_NUM_HMACS, gfp);
if (!auth_hmacs)
goto nomem;
auth_chunks = kzalloc(sizeof(sctp_chunks_param_t) +
SCTP_NUM_CHUNK_TYPES, gfp);
if (!auth_chunks)
goto nomem;
/* Initialize the HMACS parameter.
* SCTP-AUTH: Section 3.3
* Every endpoint supporting SCTP chunk authentication MUST
* support the HMAC based on the SHA-1 algorithm.
*/
auth_hmacs->param_hdr.type = SCTP_PARAM_HMAC_ALGO;
auth_hmacs->param_hdr.length =
htons(sizeof(sctp_paramhdr_t) + 2);
auth_hmacs->hmac_ids[0] = htons(SCTP_AUTH_HMAC_ID_SHA1);
/* Initialize the CHUNKS parameter */
auth_chunks->param_hdr.type = SCTP_PARAM_CHUNKS;
/* If the Add-IP functionality is enabled, we must
* authenticate, ASCONF and ASCONF-ACK chunks
*/
if (sctp_addip_enable) {
auth_chunks->chunks[0] = SCTP_CID_ASCONF;
auth_chunks->chunks[1] = SCTP_CID_ASCONF_ACK;
auth_chunks->param_hdr.length =
htons(sizeof(sctp_paramhdr_t) + 2);
}
}
/* Initialize the base structure. */
/* What type of endpoint are we? */
ep->base.type = SCTP_EP_TYPE_SOCKET;
/* Initialize the basic object fields. */
atomic_set(&ep->base.refcnt, 1);
ep->base.dead = 0;
ep->base.malloced = 1;
/* Create an input queue. */
sctp_inq_init(&ep->base.inqueue);
/* Set its top-half handler */
sctp_inq_set_th_handler(&ep->base.inqueue, sctp_endpoint_bh_rcv);
/* Initialize the bind addr area */
sctp_bind_addr_init(&ep->base.bind_addr, 0);
/* Remember who we are attached to. */
ep->base.sk = sk;
sock_hold(ep->base.sk);
/* Create the lists of associations. */
INIT_LIST_HEAD(&ep->asocs);
/* Use SCTP specific send buffer space queues. */
ep->sndbuf_policy = sctp_sndbuf_policy;
sk->sk_write_space = sctp_write_space;
sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
/* Get the receive buffer policy for this endpoint */
ep->rcvbuf_policy = sctp_rcvbuf_policy;
/* Initialize the secret key used with cookie. */
get_random_bytes(&ep->secret_key[0], SCTP_SECRET_SIZE);
ep->last_key = ep->current_key = 0;
ep->key_changed_at = jiffies;
/* SCTP-AUTH extensions*/
INIT_LIST_HEAD(&ep->endpoint_shared_keys);
null_key = sctp_auth_shkey_create(0, GFP_KERNEL);
if (!null_key)
goto nomem;
list_add(&null_key->key_list, &ep->endpoint_shared_keys);
/* Allocate and initialize transorms arrays for suported HMACs. */
err = sctp_auth_init_hmacs(ep, gfp);
if (err)
goto nomem_hmacs;
/* Add the null key to the endpoint shared keys list and
* set the hmcas and chunks pointers.
*/
ep->auth_hmacs_list = auth_hmacs;
ep->auth_chunk_list = auth_chunks;
return ep;
nomem_hmacs:
sctp_auth_destroy_keys(&ep->endpoint_shared_keys);
nomem:
/* Free all allocations */
kfree(auth_hmacs);
kfree(auth_chunks);
kfree(ep->digest);
return NULL;
}
void dccp_close(struct sock *sk, long timeout)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
u32 data_was_unread = 0;
int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (sk->sk_state == DCCP_LISTEN) {
dccp_set_state(sk, DCCP_CLOSED);
/* Special case. */
inet_csk_listen_stop(sk);
goto adjudge_to_death;
}
sk_stop_timer(sk, &dp->dccps_xmit_timer);
/*
* We need to flush the recv. buffs. We do this only on the
* descriptor close, not protocol-sourced closes, because the
*reader process may not have drained the data yet!
*/
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
data_was_unread += skb->len;
__kfree_skb(skb);
}
/* If socket has been already reset kill it. */
if (sk->sk_state == DCCP_CLOSED)
goto adjudge_to_death;
if (data_was_unread) {
/* Unread data was tossed, send an appropriate Reset Code */
DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread);
dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
dccp_set_state(sk, DCCP_CLOSED);
} else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) {
/* Check zero linger _after_ checking for unread data. */
sk->sk_prot->disconnect(sk, 0);
} else if (sk->sk_state != DCCP_CLOSED) {
/*
* Normal connection termination. May need to wait if there are
* still packets in the TX queue that are delayed by the CCID.
*/
dccp_flush_write_queue(sk, &timeout);
dccp_terminate_connection(sk);
}
/*
* Flush write queue. This may be necessary in several cases:
* - we have been closed by the peer but still have application data;
* - abortive termination (unread data or zero linger time),
* - normal termination but queue could not be flushed within time limit
*/
__skb_queue_purge(&sk->sk_write_queue);
sk_stream_wait_close(sk, timeout);
adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
/*
* It is the last release_sock in its life. It will remove backlog.
*/
release_sock(sk);
/*
* Now socket is owned by kernel and we acquire BH lock
* to finish close. No need to check for user refs.
*/
local_bh_disable();
bh_lock_sock(sk);
WARN_ON(sock_owned_by_user(sk));
percpu_counter_inc(sk->sk_prot->orphan_count);
/* Have we already been destroyed by a softirq or backlog? */
if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED)
goto out;
if (sk->sk_state == DCCP_CLOSED)
inet_csk_destroy_sock(sk);
/* Otherwise, socket is reprieved until protocol close. */
out:
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
}
static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
{
struct net_device *dev;
struct sk_buff *frag;
struct rt6_info *rt = (struct rt6_info*)skb->dst;
struct ipv6hdr *tmp_hdr;
struct frag_hdr *fh;
unsigned int mtu, hlen, left, len;
u32 frag_id = 0;
int ptr, offset = 0, err=0;
u8 *prevhdr, nexthdr = 0;
dev = rt->u.dst.dev;
hlen = ip6_find_1stfragopt(skb, &prevhdr);
nexthdr = *prevhdr;
mtu = dst_mtu(&rt->u.dst) - hlen - sizeof(struct frag_hdr);
if (skb_shinfo(skb)->frag_list) {
int first_len = skb_pagelen(skb);
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
skb_cloned(skb))
goto slow_path;
for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
/* Correct geometry. */
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
goto slow_path;
/* Partially cloned skb? */
if (skb_shared(frag))
goto slow_path;
BUG_ON(frag->sk);
if (skb->sk) {
sock_hold(skb->sk);
frag->sk = skb->sk;
frag->destructor = sock_wfree;
skb->truesize -= frag->truesize;
}
}
err = 0;
offset = 0;
frag = skb_shinfo(skb)->frag_list;
skb_shinfo(skb)->frag_list = NULL;
/* BUILD HEADER */
tmp_hdr = kmalloc(hlen, GFP_ATOMIC);
if (!tmp_hdr) {
IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS);
return -ENOMEM;
}
*prevhdr = NEXTHDR_FRAGMENT;
memcpy(tmp_hdr, skb->nh.raw, hlen);
__skb_pull(skb, hlen);
fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
skb->nh.raw = __skb_push(skb, hlen);
memcpy(skb->nh.raw, tmp_hdr, hlen);
ipv6_select_ident(skb, fh);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(IP6_MF);
frag_id = fh->identification;
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
skb->len = first_len;
skb->nh.ipv6h->payload_len = htons(first_len - sizeof(struct ipv6hdr));
for (;;) {
/* Prepare header of the next frame,
* before previous one went down. */
if (frag) {
frag->ip_summed = CHECKSUM_NONE;
frag->h.raw = frag->data;
fh = (struct frag_hdr*)__skb_push(frag, sizeof(struct frag_hdr));
frag->nh.raw = __skb_push(frag, hlen);
memcpy(frag->nh.raw, tmp_hdr, hlen);
offset += skb->len - hlen - sizeof(struct frag_hdr);
fh->nexthdr = nexthdr;
fh->reserved = 0;
fh->frag_off = htons(offset);
if (frag->next != NULL)
fh->frag_off |= htons(IP6_MF);
fh->identification = frag_id;
frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr));
ip6_copy_metadata(frag, skb);
}
err = output(skb);
if (err || !frag)
break;
skb = frag;
frag = skb->next;
skb->next = NULL;
}
if (tmp_hdr)
kfree(tmp_hdr);
if (err == 0) {
IP6_INC_STATS(IPSTATS_MIB_FRAGOKS);
return 0;
}
while (frag) {
skb = frag->next;
kfree_skb(frag);
frag = skb;
}
IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS);
return err;
}
slow_path:
left = skb->len - hlen; /* Space per frame */
ptr = hlen; /* Where to start from */
/*
* Fragment the datagram.
*/
*prevhdr = NEXTHDR_FRAGMENT;
/*
* Keep copying data until we run out.
*/
while(left > 0) {
len = left;
/* IF: it doesn't fit, use 'mtu' - the data space left */
if (len > mtu)
len = mtu;
/* IF: we are not sending upto and including the packet end
then align the next start on an eight byte boundary */
if (len < left) {
len &= ~7;
}
/*
* Allocate buffer.
*/
if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_RESERVED_SPACE(rt->u.dst.dev), GFP_ATOMIC)) == NULL) {
NETDEBUG(printk(KERN_INFO "IPv6: frag: no memory for new fragment!\n"));
IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS);
err = -ENOMEM;
goto fail;
}
/*
* Set up data on packet
*/
ip6_copy_metadata(frag, skb);
skb_reserve(frag, LL_RESERVED_SPACE(rt->u.dst.dev));
skb_put(frag, len + hlen + sizeof(struct frag_hdr));
frag->nh.raw = frag->data;
fh = (struct frag_hdr*)(frag->data + hlen);
frag->h.raw = frag->data + hlen + sizeof(struct frag_hdr);
/*
* Charge the memory for the fragment to any owner
* it might possess
*/
if (skb->sk)
skb_set_owner_w(frag, skb->sk);
/*
* Copy the packet header into the new buffer.
*/
memcpy(frag->nh.raw, skb->data, hlen);
/*
* Build fragment header.
*/
fh->nexthdr = nexthdr;
fh->reserved = 0;
if (frag_id) {
ipv6_select_ident(skb, fh);
frag_id = fh->identification;
} else
fh->identification = frag_id;
/*
* Copy a block of the IP datagram.
*/
if (skb_copy_bits(skb, ptr, frag->h.raw, len))
BUG();
left -= len;
fh->frag_off = htons(offset);
if (left > 0)
fh->frag_off |= htons(IP6_MF);
frag->nh.ipv6h->payload_len = htons(frag->len - sizeof(struct ipv6hdr));
ptr += len;
offset += len;
/*
* Put this fragment into the sending queue.
*/
IP6_INC_STATS(IPSTATS_MIB_FRAGCREATES);
err = output(frag);
if (err)
goto fail;
}
kfree_skb(skb);
IP6_INC_STATS(IPSTATS_MIB_FRAGOKS);
return err;
fail:
kfree_skb(skb);
IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS);
return err;
}
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), 0, &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, dh->dccph_doff * 4,
refcounted) ? -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 open_socket(cpt_object_t *obj, struct cpt_sock_image *si,
struct cpt_context *ctx)
{
int err;
struct socket *sock;
struct socket *sock2 = NULL;
struct file *file;
cpt_object_t *fobj;
cpt_object_t *pobj = NULL;
err = sock_create(si->cpt_family, si->cpt_type, si->cpt_protocol,
&sock);
if (err)
return err;
if (si->cpt_socketpair) {
err = sock_create(si->cpt_family, si->cpt_type,
si->cpt_protocol, &sock2);
if (err)
goto err_out;
err = sock->ops->socketpair(sock, sock2);
if (err < 0)
goto err_out;
/* Socketpair with a peer outside our environment.
* So, we create real half-open pipe and do not worry
* about dead end anymore. */
if (si->cpt_peer == -1) {
sock_release(sock2);
sock2 = NULL;
}
}
cpt_obj_setobj(obj, sock->sk, ctx);
if (si->cpt_file != CPT_NULL) {
file = sock_mapfile(sock);
err = PTR_ERR(file);
if (IS_ERR(file))
goto err_out;
err = -ENOMEM;
obj->o_parent = file;
if ((fobj = cpt_object_add(CPT_OBJ_FILE, file, ctx)) == NULL)
goto err_out;
cpt_obj_setpos(fobj, si->cpt_file, ctx);
cpt_obj_setindex(fobj, si->cpt_index, ctx);
}
if (sock2) {
struct file *file2;
pobj = lookup_cpt_obj_byindex(CPT_OBJ_SOCKET, si->cpt_peer, ctx);
if (!pobj) BUG();
if (pobj->o_obj) BUG();
cpt_obj_setobj(pobj, sock2->sk, ctx);
if (pobj->o_ppos != CPT_NULL) {
file2 = sock_mapfile(sock2);
err = PTR_ERR(file2);
if (IS_ERR(file2))
goto err_out;
err = -ENOMEM;
if ((fobj = cpt_object_add(CPT_OBJ_FILE, file2, ctx)) == NULL)
goto err_out;
cpt_obj_setpos(fobj, pobj->o_ppos, ctx);
cpt_obj_setindex(fobj, si->cpt_peer, ctx);
pobj->o_parent = file2;
}
}
setup_sock_common(sock->sk, si, obj->o_pos, ctx);
if (sock->sk->sk_family == AF_INET || sock->sk->sk_family == AF_INET6) {
int saved_reuse = sock->sk->sk_reuse;
inet_sk(sock->sk)->freebind = 1;
sock->sk->sk_reuse = 2;
if (si->cpt_laddrlen) {
err = sock->ops->bind(sock, (struct sockaddr *)&si->cpt_laddr, si->cpt_laddrlen);
if (err) {
dprintk_ctx("binding failed: %d, do not worry\n", err);
}
}
sock->sk->sk_reuse = saved_reuse;
rst_socket_in(si, obj->o_pos, sock->sk, ctx);
} else if (sock->sk->sk_family == AF_NETLINK) {
struct sockaddr_nl *nl = (struct sockaddr_nl *)&si->cpt_laddr;
if (nl->nl_pid) {
err = sock->ops->bind(sock, (struct sockaddr *)&si->cpt_laddr, si->cpt_laddrlen);
if (err) {
eprintk_ctx("AF_NETLINK binding failed: %d\n", err);
}
}
if (si->cpt_raddrlen && nl->nl_pid) {
err = sock->ops->connect(sock, (struct sockaddr *)&si->cpt_raddr, si->cpt_raddrlen, O_NONBLOCK);
if (err) {
eprintk_ctx("oops, AF_NETLINK connect failed: %d\n", err);
}
}
generic_restore_queues(sock->sk, si, obj->o_pos, ctx);
} else if (sock->sk->sk_family == PF_PACKET) {
struct sockaddr_ll *ll = (struct sockaddr_ll *)&si->cpt_laddr;
if (ll->sll_protocol || ll->sll_ifindex) {
int alen = si->cpt_laddrlen;
if (alen < sizeof(struct sockaddr_ll))
alen = sizeof(struct sockaddr_ll);
err = sock->ops->bind(sock, (struct sockaddr *)&si->cpt_laddr, alen);
if (err) {
eprintk_ctx("AF_PACKET binding failed: %d\n", err);
}
}
generic_restore_queues(sock->sk, si, obj->o_pos, ctx);
}
fixup_unix_address(sock, si, ctx);
if (sock2) {
err = rst_get_object(CPT_OBJ_SOCKET, pobj->o_pos, si, ctx);
if (err)
return err;
setup_sock_common(sock2->sk, si, pobj->o_pos, ctx);
fixup_unix_address(sock2, si, ctx);
}
if ((sock->sk->sk_family == AF_INET || sock->sk->sk_family == AF_INET6)
&& (int)si->cpt_parent != -1) {
cpt_object_t *lobj = lookup_cpt_obj_byindex(CPT_OBJ_SOCKET, si->cpt_parent, ctx);
if (lobj && cpt_attach_accept(lobj->o_obj, sock->sk, ctx) == 0)
sock->sk = NULL;
}
if (si->cpt_file == CPT_NULL && sock->sk &&
sock->sk->sk_family == AF_INET) {
struct sock *sk = sock->sk;
if (sk) {
sock->sk = NULL;
local_bh_disable();
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
eprintk_ctx("oops, sock is locked by user\n");
sock_hold(sk);
sock_orphan(sk);
ub_inc_orphan_count(sk);
bh_unlock_sock(sk);
local_bh_enable();
sock_put(sk);
dprintk_ctx("orphaning socket %p\n", sk);
}
}
if (si->cpt_file == CPT_NULL && sock->sk == NULL)
sock_release(sock);
return 0;
err_out:
if (sock2)
sock_release(sock2);
sock_release(sock);
return err;
}
static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
int addr_len, int flags)
{
int err;
struct sock *sk;
struct vsock_sock *vsk;
struct sockaddr_vm *remote_addr;
long timeout;
DEFINE_WAIT(wait);
err = 0;
sk = sock->sk;
vsk = vsock_sk(sk);
lock_sock(sk);
/* XXX AF_UNSPEC should make us disconnect like AF_INET. */
switch (sock->state) {
case SS_CONNECTED:
err = -EISCONN;
goto out;
case SS_DISCONNECTING:
err = -EINVAL;
goto out;
case SS_CONNECTING:
/* This continues on so we can move sock into the SS_CONNECTED
* state once the connection has completed (at which point err
* will be set to zero also). Otherwise, we will either wait
* for the connection or return -EALREADY should this be a
* non-blocking call.
*/
err = -EALREADY;
break;
default:
if ((sk->sk_state == SS_LISTEN) ||
vsock_addr_cast(addr, addr_len, &remote_addr) != 0) {
err = -EINVAL;
goto out;
}
/* The hypervisor and well-known contexts do not have socket
* endpoints.
*/
if (!transport->stream_allow(remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -ENETUNREACH;
goto out;
}
/* Set the remote address that we are connecting to. */
memcpy(&vsk->remote_addr, remote_addr,
sizeof(vsk->remote_addr));
err = vsock_auto_bind(vsk);
if (err)
goto out;
sk->sk_state = SS_CONNECTING;
err = transport->connect(vsk);
if (err < 0)
goto out;
/* Mark sock as connecting and set the error code to in
* progress in case this is a non-blocking connect.
*/
sock->state = SS_CONNECTING;
err = -EINPROGRESS;
}
/* The receive path will handle all communication until we are able to
* enter the connected state. Here we wait for the connection to be
* completed or a notification of an error.
*/
timeout = vsk->connect_timeout;
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
while (sk->sk_state != SS_CONNECTED && sk->sk_err == 0) {
if (flags & O_NONBLOCK) {
/* If we're not going to block, we schedule a timeout
* function to generate a timeout on the connection
* attempt, in case the peer doesn't respond in a
* timely manner. We hold on to the socket until the
* timeout fires.
*/
sock_hold(sk);
INIT_DELAYED_WORK(&vsk->dwork,
vsock_connect_timeout);
schedule_delayed_work(&vsk->dwork, timeout);
/* Skip ahead to preserve error code set above. */
goto out_wait;
}
release_sock(sk);
timeout = schedule_timeout(timeout);
lock_sock(sk);
if (signal_pending(current)) {
err = sock_intr_errno(timeout);
goto out_wait_error;
} else if (timeout == 0) {
err = -ETIMEDOUT;
goto out_wait_error;
}
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
if (sk->sk_err) {
err = -sk->sk_err;
goto out_wait_error;
} else
err = 0;
out_wait:
finish_wait(sk_sleep(sk), &wait);
out:
release_sock(sk);
return err;
out_wait_error:
sk->sk_state = SS_UNCONNECTED;
sock->state = SS_UNCONNECTED;
goto out_wait;
}
/* Grrr, addr_type already calculated by caller, but I don't want
* to add some silly "cookie" argument to this method just for that.
*/
static int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
write_lock_bh(&udp_hash_lock);
if (snum == 0) {
int best_size_so_far, best, result, i;
if (udp_port_rover > sysctl_local_port_range[1] ||
udp_port_rover < sysctl_local_port_range[0])
udp_port_rover = sysctl_local_port_range[0];
best_size_so_far = 32767;
best = result = udp_port_rover;
for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
struct sock *sk;
int size;
sk = udp_hash[result & (UDP_HTABLE_SIZE - 1)];
if (!sk) {
if (result > sysctl_local_port_range[1])
result = sysctl_local_port_range[0] +
((result - sysctl_local_port_range[0]) &
(UDP_HTABLE_SIZE - 1));
goto gotit;
}
size = 0;
do {
if (++size >= best_size_so_far)
goto next;
} while ((sk = sk->next) != NULL);
best_size_so_far = size;
best = result;
next:;
}
result = best;
for(;; result += UDP_HTABLE_SIZE) {
if (result > sysctl_local_port_range[1])
result = sysctl_local_port_range[0]
+ ((result - sysctl_local_port_range[0]) &
(UDP_HTABLE_SIZE - 1));
if (!udp_lport_inuse(result))
break;
}
gotit:
udp_port_rover = snum = result;
} else {
struct sock *sk2;
int addr_type = ipv6_addr_type(&sk->net_pinfo.af_inet6.rcv_saddr);
for (sk2 = udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
sk2 != NULL;
sk2 = sk2->next) {
if (sk2->num == snum &&
sk2 != sk &&
sk2->bound_dev_if == sk->bound_dev_if &&
(!sk2->rcv_saddr ||
addr_type == IPV6_ADDR_ANY ||
!ipv6_addr_cmp(&sk->net_pinfo.af_inet6.rcv_saddr,
&sk2->net_pinfo.af_inet6.rcv_saddr) ||
(addr_type == IPV6_ADDR_MAPPED &&
sk2->family == AF_INET &&
sk->rcv_saddr == sk2->rcv_saddr)) &&
(!sk2->reuse || !sk->reuse))
goto fail;
}
}
sk->num = snum;
if (sk->pprev == NULL) {
struct sock **skp = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
if ((sk->next = *skp) != NULL)
(*skp)->pprev = &sk->next;
*skp = sk;
sk->pprev = skp;
sock_prot_inc_use(sk->prot);
sock_hold(sk);
}
write_unlock_bh(&udp_hash_lock);
return 0;
fail:
write_unlock_bh(&udp_hash_lock);
return 1;
}
