aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/atm/common.c30
-rw-r--r--net/atm/signaling.c2
-rw-r--r--net/atm/svc.c62
-rw-r--r--net/ax25/af_ax25.c8
-rw-r--r--net/bluetooth/af_bluetooth.c6
-rw-r--r--net/bluetooth/bnep/core.c8
-rw-r--r--net/bluetooth/bnep/netdev.c6
-rw-r--r--net/bluetooth/cmtp/cmtp.h2
-rw-r--r--net/bluetooth/cmtp/core.c4
-rw-r--r--net/bluetooth/hidp/core.c10
-rw-r--r--net/bluetooth/hidp/hidp.h4
-rw-r--r--net/bluetooth/l2cap.c9
-rw-r--r--net/bluetooth/rfcomm/sock.c8
-rw-r--r--net/bluetooth/sco.c4
-rw-r--r--net/bridge/Kconfig6
-rw-r--r--net/bridge/br_device.c62
-rw-r--r--net/bridge/br_forward.c39
-rw-r--r--net/bridge/br_if.c25
-rw-r--r--net/bridge/br_multicast.c662
-rw-r--r--net/bridge/br_private.h32
-rw-r--r--net/caif/caif_dev.c25
-rw-r--r--net/caif/caif_socket.c1795
-rw-r--r--net/caif/cfcnfg.c195
-rw-r--r--net/caif/cfctrl.c95
-rw-r--r--net/caif/cfmuxl.c7
-rw-r--r--net/caif/cfsrvl.c7
-rw-r--r--net/caif/chnl_net.c130
-rw-r--r--net/core/datagram.c21
-rw-r--r--net/core/dev.c255
-rw-r--r--net/core/fib_rules.c2
-rw-r--r--net/core/filter.c7
-rw-r--r--net/core/net_namespace.c95
-rw-r--r--net/core/netpoll.c26
-rw-r--r--net/core/rtnetlink.c19
-rw-r--r--net/core/skbuff.c29
-rw-r--r--net/core/sock.c63
-rw-r--r--net/core/stream.c22
-rw-r--r--net/dccp/output.c14
-rw-r--r--net/dccp/proto.c2
-rw-r--r--net/decnet/af_decnet.c26
-rw-r--r--net/decnet/dn_rules.c4
-rw-r--r--net/ethernet/eth.c4
-rw-r--r--net/ieee802154/af_ieee802154.c3
-rw-r--r--net/ipv4/af_inet.c22
-rw-r--r--net/ipv4/fib_rules.c4
-rw-r--r--net/ipv4/fib_trie.c4
-rw-r--r--net/ipv4/inet_connection_sock.c4
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c16
-rw-r--r--net/ipv4/ipmr.c110
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c137
-rw-r--r--net/ipv4/tcp.c19
-rw-r--r--net/ipv4/tcp_input.c1
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/ipv4/tcp_output.c9
-rw-r--r--net/ipv4/tcp_timer.c4
-rw-r--r--net/ipv4/udp.c30
-rw-r--r--net/ipv6/addrconf.c19
-rw-r--r--net/ipv6/af_inet6.c3
-rw-r--r--net/ipv6/datagram.c108
-rw-r--r--net/ipv6/fib6_rules.c4
-rw-r--r--net/ipv6/icmp.c5
-rw-r--r--net/ipv6/ip6_fib.c3
-rw-r--r--net/ipv6/ip6_flowlabel.c3
-rw-r--r--net/ipv6/ip6_output.c33
-rw-r--r--net/ipv6/ipv6_sockglue.c61
-rw-r--r--net/ipv6/mcast.c135
-rw-r--r--net/ipv6/raw.c14
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/ipv6/tcp_ipv6.c25
-rw-r--r--net/ipv6/udp.c41
-rw-r--r--net/ipv6/xfrm6_policy.c2
-rw-r--r--net/irda/af_irda.c14
-rw-r--r--net/iucv/af_iucv.c21
-rw-r--r--net/l2tp/l2tp_core.c29
-rw-r--r--net/l2tp/l2tp_eth.c29
-rw-r--r--net/llc/af_llc.c12
-rw-r--r--net/mac80211/agg-rx.c18
-rw-r--r--net/mac80211/agg-tx.c3
-rw-r--r--net/mac80211/cfg.c30
-rw-r--r--net/mac80211/debugfs_sta.c65
-rw-r--r--net/mac80211/driver-ops.h14
-rw-r--r--net/mac80211/driver-trace.h9
-rw-r--r--net/mac80211/ibss.c27
-rw-r--r--net/mac80211/ieee80211_i.h3
-rw-r--r--net/mac80211/key.c1
-rw-r--r--net/mac80211/main.c19
-rw-r--r--net/mac80211/mlme.c28
-rw-r--r--net/mac80211/rx.c2
-rw-r--r--net/mac80211/scan.c53
-rw-r--r--net/mac80211/sta_info.c30
-rw-r--r--net/mac80211/status.c7
-rw-r--r--net/mac80211/tx.c12
-rw-r--r--net/mac80211/work.c28
-rw-r--r--net/netfilter/ipvs/ip_vs_sync.c2
-rw-r--r--net/netrom/af_netrom.c8
-rw-r--r--net/packet/af_packet.c2
-rw-r--r--net/phonet/pep.c8
-rw-r--r--net/phonet/pn_dev.c23
-rw-r--r--net/phonet/socket.c2
-rw-r--r--net/rds/af_rds.c2
-rw-r--r--net/rds/rdma_transport.c2
-rw-r--r--net/rds/rds.h2
-rw-r--r--net/rds/recv.c2
-rw-r--r--net/rds/send.c2
-rw-r--r--net/rose/af_rose.c8
-rw-r--r--net/rxrpc/af_rxrpc.c12
-rw-r--r--net/rxrpc/ar-recvmsg.c6
-rw-r--r--net/sched/sch_generic.c2
-rw-r--r--net/sched/sch_sfq.c10
-rw-r--r--net/sctp/Kconfig12
-rw-r--r--net/sctp/Makefile3
-rw-r--r--net/sctp/associola.c19
-rw-r--r--net/sctp/chunk.c4
-rw-r--r--net/sctp/endpointola.c3
-rw-r--r--net/sctp/output.c27
-rw-r--r--net/sctp/outqueue.c94
-rw-r--r--net/sctp/probe.c214
-rw-r--r--net/sctp/protocol.c7
-rw-r--r--net/sctp/sm_make_chunk.c118
-rw-r--r--net/sctp/sm_sideeffect.c34
-rw-r--r--net/sctp/sm_statefuns.c8
-rw-r--r--net/sctp/socket.c44
-rw-r--r--net/sctp/transport.c61
-rw-r--r--net/socket.c116
-rw-r--r--net/sunrpc/svcsock.c24
-rw-r--r--net/sunrpc/xprt.c2
-rw-r--r--net/sunrpc/xprtrdma/svc_rdma_transport.c5
-rw-r--r--net/tipc/socket.c26
-rw-r--r--net/unix/af_unix.c25
-rw-r--r--net/unix/garbage.c13
-rw-r--r--net/wireless/core.c3
-rw-r--r--net/wireless/nl80211.c4
-rw-r--r--net/wireless/sme.c16
-rw-r--r--net/x25/af_x25.c9
-rw-r--r--net/x25/x25_dev.c36
-rw-r--r--net/xfrm/xfrm_hash.h3
-rw-r--r--net/xfrm/xfrm_policy.c2
139 files changed, 3662 insertions, 2480 deletions
diff --git a/net/atm/common.c b/net/atm/common.c
index 97ed94aa0cb..b43feb1a399 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -90,10 +90,13 @@ static void vcc_sock_destruct(struct sock *sk)
static void vcc_def_wakeup(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
- if (sk_has_sleeper(sk))
- wake_up(sk->sk_sleep);
- read_unlock(&sk->sk_callback_lock);
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up(&wq->wait);
+ rcu_read_unlock();
}
static inline int vcc_writable(struct sock *sk)
@@ -106,16 +109,19 @@ static inline int vcc_writable(struct sock *sk)
static void vcc_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ struct socket_wq *wq;
+
+ rcu_read_lock();
if (vcc_writable(sk)) {
- if (sk_has_sleeper(sk))
- wake_up_interruptible(sk->sk_sleep);
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible(&wq->wait);
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
static struct proto vcc_proto = {
@@ -549,7 +555,7 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
}
eff = (size+3) & ~3; /* align to word boundary */
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
error = 0;
while (!(skb = alloc_tx(vcc, eff))) {
if (m->msg_flags & MSG_DONTWAIT) {
@@ -568,9 +574,9 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
send_sig(SIGPIPE, current, 0);
break;
}
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (error)
goto out;
skb->dev = NULL; /* for paths shared with net_device interfaces */
@@ -595,7 +601,7 @@ unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
struct atm_vcc *vcc;
unsigned int mask;
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
mask = 0;
vcc = ATM_SD(sock);
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index 6ba6e466ee5..509c8ac02b6 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -131,7 +131,7 @@ static int sigd_send(struct atm_vcc *vcc, struct sk_buff *skb)
}
sk->sk_ack_backlog++;
skb_queue_tail(&sk->sk_receive_queue, skb);
- pr_debug("waking sk->sk_sleep 0x%p\n", sk->sk_sleep);
+ pr_debug("waking sk_sleep(sk) 0x%p\n", sk_sleep(sk));
sk->sk_state_change(sk);
as_indicate_complete:
release_sock(sk);
diff --git a/net/atm/svc.c b/net/atm/svc.c
index 3ba9a45a51a..754ee4791d9 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -49,14 +49,14 @@ static void svc_disconnect(struct atm_vcc *vcc)
pr_debug("%p\n", vcc);
if (test_bit(ATM_VF_REGIS, &vcc->flags)) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq(vcc, as_close, NULL, NULL, NULL);
while (!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) {
schedule();
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_UNINTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
}
/* beware - socket is still in use by atmsigd until the last
as_indicate has been answered */
@@ -125,13 +125,13 @@ static int svc_bind(struct socket *sock, struct sockaddr *sockaddr,
}
vcc->local = *addr;
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq(vcc, as_bind, NULL, NULL, &vcc->local);
while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
schedule();
- prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
clear_bit(ATM_VF_REGIS, &vcc->flags); /* doesn't count */
if (!sigd) {
error = -EUNATCH;
@@ -201,10 +201,10 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr,
}
vcc->remote = *addr;
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sigd_enq(vcc, as_connect, NULL, NULL, &vcc->remote);
if (flags & O_NONBLOCK) {
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
sock->state = SS_CONNECTING;
error = -EINPROGRESS;
goto out;
@@ -213,7 +213,7 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr,
while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
schedule();
if (!signal_pending(current)) {
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
continue;
}
@@ -232,14 +232,14 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr,
*/
sigd_enq(vcc, as_close, NULL, NULL, NULL);
while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
schedule();
}
if (!sk->sk_err)
while (!test_bit(ATM_VF_RELEASED, &vcc->flags) &&
sigd) {
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
schedule();
}
@@ -250,7 +250,7 @@ static int svc_connect(struct socket *sock, struct sockaddr *sockaddr,
error = -EINTR;
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (error)
goto out;
if (!sigd) {
@@ -302,13 +302,13 @@ static int svc_listen(struct socket *sock, int backlog)
goto out;
}
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq(vcc, as_listen, NULL, NULL, &vcc->local);
while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
schedule();
- prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (!sigd) {
error = -EUNATCH;
goto out;
@@ -343,7 +343,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
while (1) {
DEFINE_WAIT(wait);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
while (!(skb = skb_dequeue(&sk->sk_receive_queue)) &&
sigd) {
if (test_bit(ATM_VF_RELEASED, &old_vcc->flags))
@@ -363,10 +363,10 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
error = -ERESTARTSYS;
break;
}
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (error)
goto out;
if (!skb) {
@@ -392,17 +392,17 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
}
/* wait should be short, so we ignore the non-blocking flag */
set_bit(ATM_VF_WAITING, &new_vcc->flags);
- prepare_to_wait(sk_atm(new_vcc)->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait,
TASK_UNINTERRUPTIBLE);
sigd_enq(new_vcc, as_accept, old_vcc, NULL, NULL);
while (test_bit(ATM_VF_WAITING, &new_vcc->flags) && sigd) {
release_sock(sk);
schedule();
lock_sock(sk);
- prepare_to_wait(sk_atm(new_vcc)->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk_atm(new_vcc)), &wait,
TASK_UNINTERRUPTIBLE);
}
- finish_wait(sk_atm(new_vcc)->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk_atm(new_vcc)), &wait);
if (!sigd) {
error = -EUNATCH;
goto out;
@@ -438,14 +438,14 @@ int svc_change_qos(struct atm_vcc *vcc, struct atm_qos *qos)
DEFINE_WAIT(wait);
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
sigd_enq2(vcc, as_modify, NULL, NULL, &vcc->local, qos, 0);
while (test_bit(ATM_VF_WAITING, &vcc->flags) &&
!test_bit(ATM_VF_RELEASED, &vcc->flags) && sigd) {
schedule();
- prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_UNINTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (!sigd)
return -EUNATCH;
return -sk->sk_err;
@@ -534,20 +534,20 @@ static int svc_addparty(struct socket *sock, struct sockaddr *sockaddr,
lock_sock(sk);
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sigd_enq(vcc, as_addparty, NULL, NULL,
(struct sockaddr_atmsvc *) sockaddr);
if (flags & O_NONBLOCK) {
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
error = -EINPROGRESS;
goto out;
}
pr_debug("added wait queue\n");
while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
schedule();
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
error = xchg(&sk->sk_err_soft, 0);
out:
release_sock(sk);
@@ -563,13 +563,13 @@ static int svc_dropparty(struct socket *sock, int ep_ref)
lock_sock(sk);
set_bit(ATM_VF_WAITING, &vcc->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sigd_enq2(vcc, as_dropparty, NULL, NULL, NULL, NULL, ep_ref);
while (test_bit(ATM_VF_WAITING, &vcc->flags) && sigd) {
schedule();
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (!sigd) {
error = -EUNATCH;
goto out;
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 65c5801261f..cfdfd7e2a17 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1281,7 +1281,7 @@ static int __must_check ax25_connect(struct socket *sock,
DEFINE_WAIT(wait);
for (;;) {
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
if (sk->sk_state != TCP_SYN_SENT)
break;
@@ -1294,7 +1294,7 @@ static int __must_check ax25_connect(struct socket *sock,
err = -ERESTARTSYS;
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err)
goto out_release;
@@ -1346,7 +1346,7 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags)
* hooked into the SABM we saved
*/
for (;;) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
skb = skb_dequeue(&sk->sk_receive_queue);
if (skb)
break;
@@ -1364,7 +1364,7 @@ static int ax25_accept(struct socket *sock, struct socket *newsock, int flags)
err = -ERESTARTSYS;
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err)
goto out;
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 404a8500fd0..421c45bd1b9 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -288,7 +288,7 @@ unsigned int bt_sock_poll(struct file * file, struct socket *sock, poll_table *w
BT_DBG("sock %p, sk %p", sock, sk);
- poll_wait(file, sk->sk_sleep, wait);
+ poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == BT_LISTEN)
return bt_accept_poll(sk);
@@ -378,7 +378,7 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo)
BT_DBG("sk %p", sk);
- add_wait_queue(sk->sk_sleep, &wait);
+ add_wait_queue(sk_sleep(sk), &wait);
while (sk->sk_state != state) {
set_current_state(TASK_INTERRUPTIBLE);
@@ -401,7 +401,7 @@ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo)
break;
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return err;
}
EXPORT_SYMBOL(bt_sock_wait_state);
diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c
index 8062dad6d10..f10b41fb05a 100644
--- a/net/bluetooth/bnep/core.c
+++ b/net/bluetooth/bnep/core.c
@@ -474,7 +474,7 @@ static int bnep_session(void *arg)
set_user_nice(current, -15);
init_waitqueue_entry(&wait, current);
- add_wait_queue(sk->sk_sleep, &wait);
+ add_wait_queue(sk_sleep(sk), &wait);
while (!atomic_read(&s->killed)) {
set_current_state(TASK_INTERRUPTIBLE);
@@ -496,7 +496,7 @@ static int bnep_session(void *arg)
schedule();
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
/* Cleanup session */
down_write(&bnep_session_sem);
@@ -507,7 +507,7 @@ static int bnep_session(void *arg)
/* Wakeup user-space polling for socket errors */
s->sock->sk->sk_err = EUNATCH;
- wake_up_interruptible(s->sock->sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(s->sock->sk));
/* Release the socket */
fput(s->sock->file);
@@ -638,7 +638,7 @@ int bnep_del_connection(struct bnep_conndel_req *req)
/* Kill session thread */
atomic_inc(&s->killed);
- wake_up_interruptible(s->sock->sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(s->sock->sk));
} else
err = -ENOENT;
diff --git a/net/bluetooth/bnep/netdev.c b/net/bluetooth/bnep/netdev.c
index d48b33f4d4b..0faad5ce6dc 100644
--- a/net/bluetooth/bnep/netdev.c
+++ b/net/bluetooth/bnep/netdev.c
@@ -109,7 +109,7 @@ static void bnep_net_set_mc_list(struct net_device *dev)
}
skb_queue_tail(&sk->sk_write_queue, skb);
- wake_up_interruptible(sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(sk));
#endif
}
@@ -193,11 +193,11 @@ static netdev_tx_t bnep_net_xmit(struct sk_buff *skb,
/*
* We cannot send L2CAP packets from here as we are potentially in a bh.
* So we have to queue them and wake up session thread which is sleeping
- * on the sk->sk_sleep.
+ * on the sk_sleep(sk).
*/
dev->trans_start = jiffies;
skb_queue_tail(&sk->sk_write_queue, skb);
- wake_up_interruptible(sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(sk));
if (skb_queue_len(&sk->sk_write_queue) >= BNEP_TX_QUEUE_LEN) {
BT_DBG("tx queue is full");
diff --git a/net/bluetooth/cmtp/cmtp.h b/net/bluetooth/cmtp/cmtp.h
index e4663aa14d2..785e79e953c 100644
--- a/net/bluetooth/cmtp/cmtp.h
+++ b/net/bluetooth/cmtp/cmtp.h
@@ -125,7 +125,7 @@ static inline void cmtp_schedule(struct cmtp_session *session)
{
struct sock *sk = session->sock->sk;
- wake_up_interruptible(sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(sk));
}
/* CMTP init defines */
diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c
index 0073ec8495d..d4c6af082d4 100644
--- a/net/bluetooth/cmtp/core.c
+++ b/net/bluetooth/cmtp/core.c
@@ -284,7 +284,7 @@ static int cmtp_session(void *arg)
set_user_nice(current, -15);
init_waitqueue_entry(&wait, current);
- add_wait_queue(sk->sk_sleep, &wait);
+ add_wait_queue(sk_sleep(sk), &wait);
while (!atomic_read(&session->terminate)) {
set_current_state(TASK_INTERRUPTIBLE);
@@ -301,7 +301,7 @@ static int cmtp_session(void *arg)
schedule();
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
down_write(&cmtp_session_sem);
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 280529ad927..bfe641b7dfa 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -561,8 +561,8 @@ static int hidp_session(void *arg)
init_waitqueue_entry(&ctrl_wait, current);
init_waitqueue_entry(&intr_wait, current);
- add_wait_queue(ctrl_sk->sk_sleep, &ctrl_wait);
- add_wait_queue(intr_sk->sk_sleep, &intr_wait);
+ add_wait_queue(sk_sleep(ctrl_sk), &ctrl_wait);
+ add_wait_queue(sk_sleep(intr_sk), &intr_wait);
while (!atomic_read(&session->terminate)) {
set_current_state(TASK_INTERRUPTIBLE);
@@ -584,8 +584,8 @@ static int hidp_session(void *arg)
schedule();
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(intr_sk->sk_sleep, &intr_wait);
- remove_wait_queue(ctrl_sk->sk_sleep, &ctrl_wait);
+ remove_wait_queue(sk_sleep(intr_sk), &intr_wait);
+ remove_wait_queue(sk_sleep(ctrl_sk), &ctrl_wait);
down_write(&hidp_session_sem);
@@ -609,7 +609,7 @@ static int hidp_session(void *arg)
fput(session->intr_sock->file);
- wait_event_timeout(*(ctrl_sk->sk_sleep),
+ wait_event_timeout(*(sk_sleep(ctrl_sk)),
(ctrl_sk->sk_state == BT_CLOSED), msecs_to_jiffies(500));
fput(session->ctrl_sock->file);
diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h
index a4e215d50c1..8d934a19da0 100644
--- a/net/bluetooth/hidp/hidp.h
+++ b/net/bluetooth/hidp/hidp.h
@@ -164,8 +164,8 @@ static inline void hidp_schedule(struct hidp_session *session)
struct sock *ctrl_sk = session->ctrl_sock->sk;
struct sock *intr_sk = session->intr_sock->sk;
- wake_up_interruptible(ctrl_sk->sk_sleep);
- wake_up_interruptible(intr_sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(ctrl_sk));
+ wake_up_interruptible(sk_sleep(intr_sk));
}
/* HIDP init defines */
diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c
index 99d68c34e4f..864c76f4a67 100644
--- a/net/bluetooth/l2cap.c
+++ b/net/bluetooth/l2cap.c
@@ -1147,7 +1147,7 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int fl
BT_DBG("sk %p timeo %ld", sk, timeo);
/* Wait for an incoming connection. (wake-one). */
- add_wait_queue_exclusive(sk->sk_sleep, &wait);
+ add_wait_queue_exclusive(sk_sleep(sk), &wait);
while (!(nsk = bt_accept_dequeue(sk, newsock))) {
set_current_state(TASK_INTERRUPTIBLE);
if (!timeo) {
@@ -1170,7 +1170,7 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, int fl
}
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (err)
goto done;
@@ -1626,7 +1626,10 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms
/* Connectionless channel */
if (sk->sk_type == SOCK_DGRAM) {
skb = l2cap_create_connless_pdu(sk, msg, len);
- err = l2cap_do_send(sk, skb);
+ if (IS_ERR(skb))
+ err = PTR_ERR(skb);
+ else
+ err = l2cap_do_send(sk, skb);
goto done;
}
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index 8ed3c37684f..43fbf6b4b4b 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -503,7 +503,7 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f
BT_DBG("sk %p timeo %ld", sk, timeo);
/* Wait for an incoming connection. (wake-one). */
- add_wait_queue_exclusive(sk->sk_sleep, &wait);
+ add_wait_queue_exclusive(sk_sleep(sk), &wait);
while (!(nsk = bt_accept_dequeue(sk, newsock))) {
set_current_state(TASK_INTERRUPTIBLE);
if (!timeo) {
@@ -526,7 +526,7 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int f
}
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (err)
goto done;
@@ -621,7 +621,7 @@ static long rfcomm_sock_data_wait(struct sock *sk, long timeo)
{
DECLARE_WAITQUEUE(wait, current);
- add_wait_queue(sk->sk_sleep, &wait);
+ add_wait_queue(sk_sleep(sk), &wait);
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
@@ -640,7 +640,7 @@ static long rfcomm_sock_data_wait(struct sock *sk, long timeo)
}
__set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return timeo;
}
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index ca6b2ad1c3f..b406d3eff53 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -567,7 +567,7 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag
BT_DBG("sk %p timeo %ld", sk, timeo);
/* Wait for an incoming connection. (wake-one). */
- add_wait_queue_exclusive(sk->sk_sleep, &wait);
+ add_wait_queue_exclusive(sk_sleep(sk), &wait);
while (!(ch = bt_accept_dequeue(sk, newsock))) {
set_current_state(TASK_INTERRUPTIBLE);
if (!timeo) {
@@ -590,7 +590,7 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flag
}
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (err)
goto done;
diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig
index d115d5cea5b..9190ae462cb 100644
--- a/net/bridge/Kconfig
+++ b/net/bridge/Kconfig
@@ -33,14 +33,14 @@ config BRIDGE
If unsure, say N.
config BRIDGE_IGMP_SNOOPING
- bool "IGMP snooping"
+ bool "IGMP/MLD snooping"
depends on BRIDGE
depends on INET
default y
---help---
If you say Y here, then the Ethernet bridge will be able selectively
- forward multicast traffic based on IGMP traffic received from each
- port.
+ forward multicast traffic based on IGMP/MLD traffic received from
+ each port.
Say N to exclude this support and reduce the binary size.
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 007bde87415..f15f9c4a0dd 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -13,9 +13,12 @@
#include <linux/kernel.h>
#include <linux/netdevice.h>
+#include <linux/netpoll.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
+#include <linux/list.h>
#include <linux/netfilter_bridge.h>
+
#include <asm/uaccess.h>
#include "br_private.h"
@@ -43,7 +46,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
skb_reset_mac_header(skb);
skb_pull(skb, ETH_HLEN);
- if (dest[0] & 1) {
+ if (is_multicast_ether_addr(dest)) {
if (br_multicast_rcv(br, NULL, skb))
goto out;
@@ -195,6 +198,59 @@ static int br_set_tx_csum(struct net_device *dev, u32 data)
return 0;
}
+#ifdef CONFIG_NET_POLL_CONTROLLER
+bool br_devices_support_netpoll(struct net_bridge *br)
+{
+ struct net_bridge_port *p;
+ bool ret = true;
+ int count = 0;
+ unsigned long flags;
+
+ spin_lock_irqsave(&br->lock, flags);
+ list_for_each_entry(p, &br->port_list, list) {
+ count++;
+ if ((p->dev->priv_flags & IFF_DISABLE_NETPOLL) ||
+ !p->dev->netdev_ops->ndo_poll_controller)
+ ret = false;
+ }
+ spin_unlock_irqrestore(&br->lock, flags);
+ return count != 0 && ret;
+}
+
+static void br_poll_controller(struct net_device *br_dev)
+{
+ struct netpoll *np = br_dev->npinfo->netpoll;
+
+ if (np->real_dev != br_dev)
+ netpoll_poll_dev(np->real_dev);
+}
+
+void br_netpoll_cleanup(struct net_device *br_dev)
+{
+ struct net_bridge *br = netdev_priv(br_dev);
+ struct net_bridge_port *p, *n;
+ const struct net_device_ops *ops;
+
+ br->dev->npinfo = NULL;
+ list_for_each_entry_safe(p, n, &br->port_list, list) {
+ if (p->dev) {
+ ops = p->dev->netdev_ops;
+ if (ops->ndo_netpoll_cleanup)
+ ops->ndo_netpoll_cleanup(p->dev);
+ else
+ p->dev->npinfo = NULL;
+ }
+ }
+}
+
+#else
+
+void br_netpoll_cleanup(struct net_device *br_dev)
+{
+}
+
+#endif
+
static const struct ethtool_ops br_ethtool_ops = {
.get_drvinfo = br_getinfo,
.get_link = ethtool_op_get_link,
@@ -218,6 +274,10 @@ static const struct net_device_ops br_netdev_ops = {
.ndo_set_multicast_list = br_dev_set_multicast_list,
.ndo_change_mtu = br_change_mtu,
.ndo_do_ioctl = br_dev_ioctl,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_netpoll_cleanup = br_netpoll_cleanup,
+ .ndo_poll_controller = br_poll_controller,
+#endif
};
static void br_dev_free(struct net_device *dev)
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 92fb3293a21..a98ef139309 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -15,6 +15,7 @@
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
+#include <linux/netpoll.h>
#include <linux/skbuff.h>
#include <linux/if_vlan.h>
#include <linux/netfilter_bridge.h>
@@ -50,7 +51,13 @@ int br_dev_queue_push_xmit(struct sk_buff *skb)
else {
skb_push(skb, ETH_HLEN);
- dev_queue_xmit(skb);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ if (unlikely(skb->dev->priv_flags & IFF_IN_NETPOLL)) {
+ netpoll_send_skb(skb->dev->npinfo->netpoll, skb);
+ skb->dev->priv_flags &= ~IFF_IN_NETPOLL;
+ } else
+#endif
+ dev_queue_xmit(skb);
}
}
@@ -66,9 +73,23 @@ int br_forward_finish(struct sk_buff *skb)
static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
{
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ struct net_bridge *br = to->br;
+ if (unlikely(br->dev->priv_flags & IFF_IN_NETPOLL)) {
+ struct netpoll *np;
+ to->dev->npinfo = skb->dev->npinfo;
+ np = skb->dev->npinfo->netpoll;
+ np->real_dev = np->dev = to->dev;
+ to->dev->priv_flags |= IFF_IN_NETPOLL;
+ }
+#endif
skb->dev = to->dev;
NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev,
br_forward_finish);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ if (skb->dev->npinfo)
+ skb->dev->npinfo->netpoll->dev = br->dev;
+#endif
}
static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
@@ -208,17 +229,15 @@ static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
{
struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev;
struct net_bridge *br = netdev_priv(dev);
- struct net_bridge_port *port;
- struct net_bridge_port *lport, *rport;
- struct net_bridge_port *prev;
+ struct net_bridge_port *prev = NULL;
struct net_bridge_port_group *p;
struct hlist_node *rp;
- prev = NULL;
-
- rp = br->router_list.first;
- p = mdst ? mdst->ports : NULL;
+ rp = rcu_dereference(br->router_list.first);
+ p = mdst ? rcu_dereference(mdst->ports) : NULL;
while (p || rp) {
+ struct net_bridge_port *port, *lport, *rport;
+
lport = p ? p->port : NULL;
rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) :
NULL;
@@ -231,9 +250,9 @@ static void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
goto out;
if ((unsigned long)lport >= (unsigned long)port)
- p = p->next;
+ p = rcu_dereference(p->next);
if ((unsigned long)rport >= (unsigned long)port)
- rp = rp->next;
+ rp = rcu_dereference(rp->next);
}
if (!prev)
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 52143933331..537bdd60d9b 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -13,6 +13,7 @@
#include <linux/kernel.h>
#include <linux/netdevice.h>
+#include <linux/netpoll.h>
#include <linux/ethtool.h>
#include <linux/if_arp.h>
#include <linux/module.h>
@@ -153,6 +154,14 @@ static void del_nbp(struct net_bridge_port *p)
kobject_uevent(&p->kobj, KOBJ_REMOVE);
kobject_del(&p->kobj);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ if (br_devices_support_netpoll(br))
+ br->dev->priv_flags &= ~IFF_DISABLE_NETPOLL;
+ if (dev->netdev_ops->ndo_netpoll_cleanup)
+ dev->netdev_ops->ndo_netpoll_cleanup(dev);
+ else
+ dev->npinfo = NULL;
+#endif
call_rcu(&p->rcu, destroy_nbp_rcu);
}
@@ -165,6 +174,8 @@ static void del_br(struct net_bridge *br, struct list_head *head)
del_nbp(p);
}
+ br_netpoll_cleanup(br->dev);
+
del_timer_sync(&br->gc_timer);
br_sysfs_delbr(br->dev);
@@ -444,6 +455,20 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
kobject_uevent(&p->kobj, KOBJ_ADD);
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ if (br_devices_support_netpoll(br)) {
+ br->dev->priv_flags &= ~IFF_DISABLE_NETPOLL;
+ if (br->dev->npinfo)
+ dev->npinfo = br->dev->npinfo;
+ } else if (!(br->dev->priv_flags & IFF_DISABLE_NETPOLL)) {
+ br->dev->priv_flags |= IFF_DISABLE_NETPOLL;
+ printk(KERN_INFO "New device %s does not support netpoll\n",
+ dev->name);
+ printk(KERN_INFO "Disabling netpoll for %s\n",
+ br->dev->name);
+ }
+#endif
+
return 0;
err2:
br_fdb_delete_by_port(br, p, 1);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 8ccdb8ee392..c8419e24031 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -24,51 +24,139 @@
#include <linux/slab.h>
#include <linux/timer.h>
#include <net/ip.h>
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#include <net/ipv6.h>
+#include <net/mld.h>
+#include <net/addrconf.h>
+#include <net/ip6_checksum.h>
+#endif
#include "br_private.h"
-static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb, __be32 ip)
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static inline int ipv6_is_local_multicast(const struct in6_addr *addr)
{
- return jhash_1word(mdb->secret, (u32)ip) & (mdb->max - 1);
+ if (ipv6_addr_is_multicast(addr) &&
+ IPV6_ADDR_MC_SCOPE(addr) <= IPV6_ADDR_SCOPE_LINKLOCAL)
+ return 1;
+ return 0;
+}
+#endif
+
+static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
+{
+ if (a->proto != b->proto)
+ return 0;
+ switch (a->proto) {
+ case htons(ETH_P_IP):
+ return a->u.ip4 == b->u.ip4;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case htons(ETH_P_IPV6):
+ return ipv6_addr_equal(&a->u.ip6, &b->u.ip6);
+#endif
+ }
+ return 0;
+}
+
+static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip)
+{
+ return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1);
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb,
+ const struct in6_addr *ip)
+{
+ return jhash2((__force u32 *)ip->s6_addr32, 4, mdb->secret) & (mdb->max - 1);
+}
+#endif
+
+static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb,
+ struct br_ip *ip)
+{
+ switch (ip->proto) {
+ case htons(ETH_P_IP):
+ return __br_ip4_hash(mdb, ip->u.ip4);
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case htons(ETH_P_IPV6):
+ return __br_ip6_hash(mdb, &ip->u.ip6);
+#endif
+ }
+ return 0;
}
static struct net_bridge_mdb_entry *__br_mdb_ip_get(
- struct net_bridge_mdb_htable *mdb, __be32 dst, int hash)
+ struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash)
{
struct net_bridge_mdb_entry *mp;
struct hlist_node *p;
hlist_for_each_entry_rcu(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
- if (dst == mp->addr)
+ if (br_ip_equal(&mp->addr, dst))
return mp;
}
return NULL;
}
-static struct net_bridge_mdb_entry *br_mdb_ip_get(
+static struct net_bridge_mdb_entry *br_mdb_ip4_get(
struct net_bridge_mdb_htable *mdb, __be32 dst)
{
- if (!mdb)
- return NULL;
+ struct br_ip br_dst;
+
+ br_dst.u.ip4 = dst;
+ br_dst.proto = htons(ETH_P_IP);
+
+ return __br_mdb_ip_get(mdb, &br_dst, __br_ip4_hash(mdb, dst));
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static struct net_bridge_mdb_entry *br_mdb_ip6_get(
+ struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst)
+{
+ struct br_ip br_dst;
+ ipv6_addr_copy(&br_dst.u.ip6, dst);
+ br_dst.proto = htons(ETH_P_IPV6);
+
+ return __br_mdb_ip_get(mdb, &br_dst, __br_ip6_hash(mdb, dst));
+}
+#endif
+
+static struct net_bridge_mdb_entry *br_mdb_ip_get(
+ struct net_bridge_mdb_htable *mdb, struct br_ip *dst)
+{
return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst));
}
struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
struct sk_buff *skb)
{
- if (br->multicast_disabled)
+ struct net_bridge_mdb_htable *mdb = br->mdb;
+ struct br_ip ip;
+
+ if (!mdb || br->multicast_disabled)
+ return NULL;
+
+ if (BR_INPUT_SKB_CB(skb)->igmp)
return NULL;
+ ip.proto = skb->protocol;
+
switch (skb->protocol) {
case htons(ETH_P_IP):
- if (BR_INPUT_SKB_CB(skb)->igmp)
- break;
- return br_mdb_ip_get(br->mdb, ip_hdr(skb)->daddr);
+ ip.u.ip4 = ip_hdr(skb)->daddr;
+ break;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case htons(ETH_P_IPV6):
+ ipv6_addr_copy(&ip.u.ip6, &ipv6_hdr(skb)->daddr);
+ break;
+#endif
+ default:
+ return NULL;
}
- return NULL;
+ return br_mdb_ip_get(mdb, &ip);
}
static void br_mdb_free(struct rcu_head *head)
@@ -95,7 +183,7 @@ static int br_mdb_copy(struct net_bridge_mdb_htable *new,
for (i = 0; i < old->max; i++)
hlist_for_each_entry(mp, p, &old->mhash[i], hlist[old->ver])
hlist_add_head(&mp->hlist[new->ver],
- &new->mhash[br_ip_hash(new, mp->addr)]);
+ &new->mhash[br_ip_hash(new, &mp->addr)]);
if (!elasticity)
return 0;
@@ -163,7 +251,7 @@ static void br_multicast_del_pg(struct net_bridge *br,
struct net_bridge_port_group *p;
struct net_bridge_port_group **pp;
- mp = br_mdb_ip_get(mdb, pg->addr);
+ mp = br_mdb_ip_get(mdb, &pg->addr);
if (WARN_ON(!mp))
return;
@@ -171,7 +259,7 @@ static void br_multicast_del_pg(struct net_bridge *br,
if (p != pg)
continue;
- *pp = p->next;
+ rcu_assign_pointer(*pp, p->next);
hlist_del_init(&p->mglist);
del_timer(&p->timer);
del_timer(&p->query_timer);
@@ -249,8 +337,8 @@ out:
return 0;
}
-static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
- __be32 group)
+static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
+ __be32 group)
{
struct sk_buff *skb;
struct igmphdr *ih;
@@ -314,12 +402,104 @@ out:
return skb;
}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
+ struct in6_addr *group)
+{
+ struct sk_buff *skb;
+ struct ipv6hdr *ip6h;
+ struct mld_msg *mldq;
+ struct ethhdr *eth;
+ u8 *hopopt;
+ unsigned long interval;
+
+ skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) +
+ 8 + sizeof(*mldq));
+ if (!skb)
+ goto out;
+
+ skb->protocol = htons(ETH_P_IPV6);
+
+ /* Ethernet header */
+ skb_reset_mac_header(skb);
+ eth = eth_hdr(skb);
+
+ memcpy(eth->h_source, br->dev->dev_addr, 6);
+ ipv6_eth_mc_map(group, eth->h_dest);
+ eth->h_proto = htons(ETH_P_IPV6);
+ skb_put(skb, sizeof(*eth));
+
+ /* IPv6 header + HbH option */
+ skb_set_network_header(skb, skb->len);
+ ip6h = ipv6_hdr(skb);
+
+ *(__force __be32 *)ip6h = htonl(0x60000000);
+ ip6h->payload_len = 8 + sizeof(*mldq);
+ ip6h->nexthdr = IPPROTO_HOPOPTS;
+ ip6h->hop_limit = 1;
+ ipv6_addr_set(&ip6h->saddr, 0, 0, 0, 0);
+ ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
+
+ hopopt = (u8 *)(ip6h + 1);
+ hopopt[0] = IPPROTO_ICMPV6; /* next hdr */
+ hopopt[1] = 0; /* length of HbH */
+ hopopt[2] = IPV6_TLV_ROUTERALERT; /* Router Alert */
+ hopopt[3] = 2; /* Length of RA Option */
+ hopopt[4] = 0; /* Type = 0x0000 (MLD) */
+ hopopt[5] = 0;
+ hopopt[6] = IPV6_TLV_PAD0; /* Pad0 */
+ hopopt[7] = IPV6_TLV_PAD0; /* Pad0 */
+
+ skb_put(skb, sizeof(*ip6h) + 8);
+
+ /* ICMPv6 */
+ skb_set_transport_header(skb, skb->len);
+ mldq = (struct mld_msg *) icmp6_hdr(skb);
+
+ interval = ipv6_addr_any(group) ? br->multicast_last_member_interval :
+ br->multicast_query_response_interval;
+
+ mldq->mld_type = ICMPV6_MGM_QUERY;
+ mldq->mld_code = 0;
+ mldq->mld_cksum = 0;
+ mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
+ mldq->mld_reserved = 0;
+ ipv6_addr_copy(&mldq->mld_mca, group);
+
+ /* checksum */
+ mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+ sizeof(*mldq), IPPROTO_ICMPV6,
+ csum_partial(mldq,
+ sizeof(*mldq), 0));
+ skb_put(skb, sizeof(*mldq));
+
+ __skb_pull(skb, sizeof(*eth));
+
+out:
+ return skb;
+}
+#endif
+
+static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
+ struct br_ip *addr)
+{
+ switch (addr->proto) {
+ case htons(ETH_P_IP):
+ return br_ip4_multicast_alloc_query(br, addr->u.ip4);
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case htons(ETH_P_IPV6):
+ return br_ip6_multicast_alloc_query(br, &addr->u.ip6);
+#endif
+ }
+ return NULL;
+}
+
static void br_multicast_send_group_query(struct net_bridge_mdb_entry *mp)
{
struct net_bridge *br = mp->br;
struct sk_buff *skb;
- skb = br_multicast_alloc_query(br, mp->addr);
+ skb = br_multicast_alloc_query(br, &mp->addr);
if (!skb)
goto timer;
@@ -353,7 +533,7 @@ static void br_multicast_send_port_group_query(struct net_bridge_port_group *pg)
struct net_bridge *br = port->br;
struct sk_buff *skb;
- skb = br_multicast_alloc_query(br, pg->addr);
+ skb = br_multicast_alloc_query(br, &pg->addr);
if (!skb)
goto timer;
@@ -383,8 +563,8 @@ out:
}
static struct net_bridge_mdb_entry *br_multicast_get_group(
- struct net_bridge *br, struct net_bridge_port *port, __be32 group,
- int hash)
+ struct net_bridge *br, struct net_bridge_port *port,
+ struct br_ip *group, int hash)
{
struct net_bridge_mdb_htable *mdb = br->mdb;
struct net_bridge_mdb_entry *mp;
@@ -396,9 +576,8 @@ static struct net_bridge_mdb_entry *br_multicast_get_group(
hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) {
count++;
- if (unlikely(group == mp->addr)) {
+ if (unlikely(br_ip_equal(group, &mp->addr)))
return mp;
- }
}
elasticity = 0;
@@ -463,7 +642,8 @@ err:
}
static struct net_bridge_mdb_entry *br_multicast_new_group(
- struct net_bridge *br, struct net_bridge_port *port, __be32 group)
+ struct net_bridge *br, struct net_bridge_port *port,
+ struct br_ip *group)
{
struct net_bridge_mdb_htable *mdb = br->mdb;
struct net_bridge_mdb_entry *mp;
@@ -496,7 +676,7 @@ rehash:
goto out;
mp->br = br;
- mp->addr = group;
+ mp->addr = *group;
setup_timer(&mp->timer, br_multicast_group_expired,
(unsigned long)mp);
setup_timer(&mp->query_timer, br_multicast_group_query_expired,
@@ -510,7 +690,8 @@ out:
}
static int br_multicast_add_group(struct net_bridge *br,
- struct net_bridge_port *port, __be32 group)
+ struct net_bridge_port *port,
+ struct br_ip *group)
{
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
@@ -518,9 +699,6 @@ static int br_multicast_add_group(struct net_bridge *br,
unsigned long now = jiffies;
int err;
- if (ipv4_is_local_multicast(group))
- return 0;
-
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED))
@@ -549,7 +727,7 @@ static int br_multicast_add_group(struct net_bridge *br,
if (unlikely(!p))
goto err;
- p->addr = group;
+ p->addr = *group;
p->port = port;
p->next = *pp;
hlist_add_head(&p->mglist, &port->mglist);
@@ -570,6 +748,38 @@ err:
return err;
}
+static int br_ip4_multicast_add_group(struct net_bridge *br,
+ struct net_bridge_port *port,
+ __be32 group)
+{
+ struct br_ip br_group;
+
+ if (ipv4_is_local_multicast(group))
+ return 0;
+
+ br_group.u.ip4 = group;
+ br_group.proto = htons(ETH_P_IP);
+
+ return br_multicast_add_group(br, port, &br_group);
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int br_ip6_multicast_add_group(struct net_bridge *br,
+ struct net_bridge_port *port,
+ const struct in6_addr *group)
+{
+ struct br_ip br_group;
+
+ if (ipv6_is_local_multicast(group))
+ return 0;
+
+ ipv6_addr_copy(&br_group.u.ip6, group);
+ br_group.proto = htons(ETH_P_IP);
+
+ return br_multicast_add_group(br, port, &br_group);
+}
+#endif
+
static void br_multicast_router_expired(unsigned long data)
{
struct net_bridge_port *port = (void *)data;
@@ -591,19 +801,15 @@ static void br_multicast_local_router_expired(unsigned long data)
{
}
-static void br_multicast_send_query(struct net_bridge *br,
- struct net_bridge_port *port, u32 sent)
+static void __br_multicast_send_query(struct net_bridge *br,
+ struct net_bridge_port *port,
+ struct br_ip *ip)
{
- unsigned long time;
struct sk_buff *skb;
- if (!netif_running(br->dev) || br->multicast_disabled ||
- timer_pending(&br->multicast_querier_timer))
- return;
-
- skb = br_multicast_alloc_query(br, 0);
+ skb = br_multicast_alloc_query(br, ip);
if (!skb)
- goto timer;
+ return;
if (port) {
__skb_push(skb, sizeof(struct ethhdr));
@@ -612,8 +818,28 @@ static void br_multicast_send_query(struct net_bridge *br,
dev_queue_xmit);
} else
netif_rx(skb);
+}
+
+static void br_multicast_send_query(struct net_bridge *br,
+ struct net_bridge_port *port, u32 sent)
+{
+ unsigned long time;
+ struct br_ip br_group;
+
+ if (!netif_running(br->dev) || br->multicast_disabled ||
+ timer_pending(&br->multicast_querier_timer))
+ return;
+
+ memset(&br_group.u, 0, sizeof(br_group.u));
+
+ br_group.proto = htons(ETH_P_IP);
+ __br_multicast_send_query(br, port, &br_group);
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ br_group.proto = htons(ETH_P_IPV6);
+ __br_multicast_send_query(br, port, &br_group);
+#endif
-timer:
time = jiffies;
time += sent < br->multicast_startup_query_count ?
br->multicast_startup_query_interval :
@@ -698,9 +924,9 @@ void br_multicast_disable_port(struct net_bridge_port *port)
spin_unlock(&br->multicast_lock);
}
-static int br_multicast_igmp3_report(struct net_bridge *br,
- struct net_bridge_port *port,
- struct sk_buff *skb)
+static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
+ struct net_bridge_port *port,
+ struct sk_buff *skb)
{
struct igmpv3_report *ih;
struct igmpv3_grec *grec;
@@ -727,7 +953,7 @@ static int br_multicast_igmp3_report(struct net_bridge *br,
group = grec->grec_mca;
type = grec->grec_type;
- len += grec->grec_nsrcs * 4;
+ len += ntohs(grec->grec_nsrcs) * 4;
if (!pskb_may_pull(skb, len))
return -EINVAL;
@@ -745,7 +971,7 @@ static int br_multicast_igmp3_report(struct net_bridge *br,
continue;
}
- err = br_multicast_add_group(br, port, group);
+ err = br_ip4_multicast_add_group(br, port, group);
if (err)
break;
}
@@ -753,24 +979,87 @@ static int br_multicast_igmp3_report(struct net_bridge *br,
return err;
}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int br_ip6_multicast_mld2_report(struct net_bridge *br,
+ struct net_bridge_port *port,
+ struct sk_buff *skb)
+{
+ struct icmp6hdr *icmp6h;
+ struct mld2_grec *grec;
+ int i;
+ int len;
+ int num;
+ int err = 0;
+
+ if (!pskb_may_pull(skb, sizeof(*icmp6h)))
+ return -EINVAL;
+
+ icmp6h = icmp6_hdr(skb);
+ num = ntohs(icmp6h->icmp6_dataun.un_data16[1]);
+ len = sizeof(*icmp6h);
+
+ for (i = 0; i < num; i++) {
+ __be16 *nsrcs, _nsrcs;
+
+ nsrcs = skb_header_pointer(skb,
+ len + offsetof(struct mld2_grec,
+ grec_mca),
+ sizeof(_nsrcs), &_nsrcs);
+ if (!nsrcs)
+ return -EINVAL;
+
+ if (!pskb_may_pull(skb,
+ len + sizeof(*grec) +
+ sizeof(struct in6_addr) * (*nsrcs)))
+ return -EINVAL;
+
+ grec = (struct mld2_grec *)(skb->data + len);
+ len += sizeof(*grec) + sizeof(struct in6_addr) * (*nsrcs);
+
+ /* We treat these as MLDv1 reports for now. */
+ switch (grec->grec_type) {
+ case MLD2_MODE_IS_INCLUDE:
+ case MLD2_MODE_IS_EXCLUDE:
+ case MLD2_CHANGE_TO_INCLUDE:
+ case MLD2_CHANGE_TO_EXCLUDE:
+ case MLD2_ALLOW_NEW_SOURCES:
+ case MLD2_BLOCK_OLD_SOURCES:
+ break;
+
+ default:
+ continue;
+ }
+
+ err = br_ip6_multicast_add_group(br, port, &grec->grec_mca);
+ if (!err)
+ break;
+ }
+
+ return err;
+}
+#endif
+
+/*
+ * Add port to rotuer_list
+ * list is maintained ordered by pointer value
+ * and locked by br->multicast_lock and RCU
+ */
static void br_multicast_add_router(struct net_bridge *br,
struct net_bridge_port *port)
{
- struct hlist_node *p;
- struct hlist_node **h;
-
- for (h = &br->router_list.first;
- (p = *h) &&
- (unsigned long)container_of(p, struct net_bridge_port, rlist) >
- (unsigned long)port;
- h = &p->next)
- ;
-
- port->rlist.pprev = h;
- port->rlist.next = p;
- rcu_assign_pointer(*h, &port->rlist);
- if (p)
- p->pprev = &port->rlist.next;
+ struct net_bridge_port *p;
+ struct hlist_node *n, *slot = NULL;
+
+ hlist_for_each_entry(p, n, &br->router_list, rlist) {
+ if ((unsigned long) port >= (unsigned long) p)
+ break;
+ slot = n;
+ }
+
+ if (slot)
+ hlist_add_after_rcu(slot, &port->rlist);
+ else
+ hlist_add_head_rcu(&port->rlist, &br->router_list);
}
static void br_multicast_mark_router(struct net_bridge *br,
@@ -800,7 +1089,7 @@ timer:
static void br_multicast_query_received(struct net_bridge *br,
struct net_bridge_port *port,
- __be32 saddr)
+ int saddr)
{
if (saddr)
mod_timer(&br->multicast_querier_timer,
@@ -811,9 +1100,9 @@ static void br_multicast_query_received(struct net_bridge *br,
br_multicast_mark_router(br, port);
}
-static int br_multicast_query(struct net_bridge *br,
- struct net_bridge_port *port,
- struct sk_buff *skb)
+static int br_ip4_multicast_query(struct net_bridge *br,
+ struct net_bridge_port *port,
+ struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
struct igmphdr *ih = igmp_hdr(skb);
@@ -831,7 +1120,7 @@ static int br_multicast_query(struct net_bridge *br,
(port && port->state == BR_STATE_DISABLED))
goto out;
- br_multicast_query_received(br, port, iph->saddr);
+ br_multicast_query_received(br, port, !!iph->saddr);
group = ih->group;
@@ -859,7 +1148,7 @@ static int br_multicast_query(struct net_bridge *br,
if (!group)
goto out;
- mp = br_mdb_ip_get(br->mdb, group);
+ mp = br_mdb_ip4_get(br->mdb, group);
if (!mp)
goto out;
@@ -883,9 +1172,78 @@ out:
return err;
}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int br_ip6_multicast_query(struct net_bridge *br,
+ struct net_bridge_port *port,
+ struct sk_buff *skb)
+{
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct mld_msg *mld = (struct mld_msg *) icmp6_hdr(skb);
+ struct net_bridge_mdb_entry *mp;
+ struct mld2_query *mld2q;
+ struct net_bridge_port_group *p, **pp;
+ unsigned long max_delay;
+ unsigned long now = jiffies;
+ struct in6_addr *group = NULL;
+ int err = 0;
+
+ spin_lock(&br->multicast_lock);
+ if (!netif_running(br->dev) ||
+ (port && port->state == BR_STATE_DISABLED))
+ goto out;
+
+ br_multicast_query_received(br, port, !ipv6_addr_any(&ip6h->saddr));
+
+ if (skb->len == sizeof(*mld)) {
+ if (!pskb_may_pull(skb, sizeof(*mld))) {
+ err = -EINVAL;
+ goto out;
+ }
+ mld = (struct mld_msg *) icmp6_hdr(skb);
+ max_delay = msecs_to_jiffies(htons(mld->mld_maxdelay));
+ if (max_delay)
+ group = &mld->mld_mca;
+ } else if (skb->len >= sizeof(*mld2q)) {
+ if (!pskb_may_pull(skb, sizeof(*mld2q))) {
+ err = -EINVAL;
+ goto out;
+ }
+ mld2q = (struct mld2_query *)icmp6_hdr(skb);
+ if (!mld2q->mld2q_nsrcs)
+ group = &mld2q->mld2q_mca;
+ max_delay = mld2q->mld2q_mrc ? MLDV2_MRC(mld2q->mld2q_mrc) : 1;
+ }
+
+ if (!group)
+ goto out;
+
+ mp = br_mdb_ip6_get(br->mdb, group);
+ if (!mp)
+ goto out;
+
+ max_delay *= br->multicast_last_member_count;
+ if (!hlist_unhashed(&mp->mglist) &&
+ (timer_pending(&mp->timer) ?
+ time_after(mp->timer.expires, now + max_delay) :
+ try_to_del_timer_sync(&mp->timer) >= 0))
+ mod_timer(&mp->timer, now + max_delay);
+
+ for (pp = &mp->ports; (p = *pp); pp = &p->next) {
+ if (timer_pending(&p->timer) ?
+ time_after(p->timer.expires, now + max_delay) :
+ try_to_del_timer_sync(&p->timer) >= 0)
+ mod_timer(&mp->timer, now + max_delay);
+ }
+
+out:
+ spin_unlock(&br->multicast_lock);
+ return err;
+}
+#endif
+
static void br_multicast_leave_group(struct net_bridge *br,
struct net_bridge_port *port,
- __be32 group)
+ struct br_ip *group)
{
struct net_bridge_mdb_htable *mdb;
struct net_bridge_mdb_entry *mp;
@@ -893,9 +1251,6 @@ static void br_multicast_leave_group(struct net_bridge *br,
unsigned long now;
unsigned long time;
- if (ipv4_is_local_multicast(group))
- return;
-
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED) ||
@@ -946,6 +1301,38 @@ out:
spin_unlock(&br->multicast_lock);
}
+static void br_ip4_multicast_leave_group(struct net_bridge *br,
+ struct net_bridge_port *port,
+ __be32 group)
+{
+ struct br_ip br_group;
+
+ if (ipv4_is_local_multicast(group))
+ return;
+
+ br_group.u.ip4 = group;
+ br_group.proto = htons(ETH_P_IP);
+
+ br_multicast_leave_group(br, port, &br_group);
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static void br_ip6_multicast_leave_group(struct net_bridge *br,
+ struct net_bridge_port *port,
+ const struct in6_addr *group)
+{
+ struct br_ip br_group;
+
+ if (ipv6_is_local_multicast(group))
+ return;
+
+ ipv6_addr_copy(&br_group.u.ip6, group);
+ br_group.proto = htons(ETH_P_IPV6);
+
+ br_multicast_leave_group(br, port, &br_group);
+}
+#endif
+
static int br_multicast_ipv4_rcv(struct net_bridge *br,
struct net_bridge_port *port,
struct sk_buff *skb)
@@ -957,9 +1344,6 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
unsigned offset;
int err;
- BR_INPUT_SKB_CB(skb)->igmp = 0;
- BR_INPUT_SKB_CB(skb)->mrouters_only = 0;
-
/* We treat OOM as packet loss for now. */
if (!pskb_may_pull(skb, sizeof(*iph)))
return -EINVAL;
@@ -1023,16 +1407,16 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
case IGMP_HOST_MEMBERSHIP_REPORT:
case IGMPV2_HOST_MEMBERSHIP_REPORT:
BR_INPUT_SKB_CB(skb2)->mrouters_only = 1;
- err = br_multicast_add_group(br, port, ih->group);
+ err = br_ip4_multicast_add_group(br, port, ih->group);
break;
case IGMPV3_HOST_MEMBERSHIP_REPORT:
- err = br_multicast_igmp3_report(br, port, skb2);
+ err = br_ip4_multicast_igmp3_report(br, port, skb2);
break;
case IGMP_HOST_MEMBERSHIP_QUERY:
- err = br_multicast_query(br, port, skb2);
+ err = br_ip4_multicast_query(br, port, skb2);
break;
case IGMP_HOST_LEAVE_MESSAGE:
- br_multicast_leave_group(br, port, ih->group);
+ br_ip4_multicast_leave_group(br, port, ih->group);
break;
}
@@ -1044,15 +1428,139 @@ err_out:
return err;
}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int br_multicast_ipv6_rcv(struct net_bridge *br,
+ struct net_bridge_port *port,
+ struct sk_buff *skb)
+{
+ struct sk_buff *skb2 = skb;
+ struct ipv6hdr *ip6h;
+ struct icmp6hdr *icmp6h;
+ u8 nexthdr;
+ unsigned len;
+ unsigned offset;
+ int err;
+
+ if (!pskb_may_pull(skb, sizeof(*ip6h)))
+ return -EINVAL;
+
+ ip6h = ipv6_hdr(skb);
+
+ /*
+ * We're interested in MLD messages only.
+ * - Version is 6
+ * - MLD has always Router Alert hop-by-hop option
+ * - But we do not support jumbrograms.
+ */
+ if (ip6h->version != 6 ||
+ ip6h->nexthdr != IPPROTO_HOPOPTS ||
+ ip6h->payload_len == 0)
+ return 0;
+
+ len = ntohs(ip6h->payload_len);
+ if (skb->len < len)
+ return -EINVAL;
+
+ nexthdr = ip6h->nexthdr;
+ offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr);
+
+ if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
+ return 0;
+
+ /* Okay, we found ICMPv6 header */
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (!skb2)
+ return -ENOMEM;
+
+ len -= offset - skb_network_offset(skb2);
+
+ __skb_pull(skb2, offset);
+ skb_reset_transport_header(skb2);
+
+ err = -EINVAL;
+ if (!pskb_may_pull(skb2, sizeof(*icmp6h)))
+ goto out;
+
+ icmp6h = icmp6_hdr(skb2);
+
+ switch (icmp6h->icmp6_type) {
+ case ICMPV6_MGM_QUERY:
+ case ICMPV6_MGM_REPORT:
+ case ICMPV6_MGM_REDUCTION:
+ case ICMPV6_MLD2_REPORT:
+ break;
+ default:
+ err = 0;
+ goto out;
+ }
+
+ /* Okay, we found MLD message. Check further. */
+ if (skb2->len > len) {
+ err = pskb_trim_rcsum(skb2, len);
+ if (err)
+ goto out;
+ }
+
+ switch (skb2->ip_summed) {
+ case CHECKSUM_COMPLETE:
+ if (!csum_fold(skb2->csum))
+ break;
+ /*FALLTHROUGH*/
+ case CHECKSUM_NONE:
+ skb2->csum = 0;
+ if (skb_checksum_complete(skb2))
+ goto out;
+ }
+
+ err = 0;
+
+ BR_INPUT_SKB_CB(skb)->igmp = 1;
+
+ switch (icmp6h->icmp6_type) {
+ case ICMPV6_MGM_REPORT:
+ {
+ struct mld_msg *mld = (struct mld_msg *)icmp6h;
+ BR_INPUT_SKB_CB(skb2)->mrouters_only = 1;
+ err = br_ip6_multicast_add_group(br, port, &mld->mld_mca);
+ break;
+ }
+ case ICMPV6_MLD2_REPORT:
+ err = br_ip6_multicast_mld2_report(br, port, skb2);
+ break;
+ case ICMPV6_MGM_QUERY:
+ err = br_ip6_multicast_query(br, port, skb2);
+ break;
+ case ICMPV6_MGM_REDUCTION:
+ {
+ struct mld_msg *mld = (struct mld_msg *)icmp6h;
+ br_ip6_multicast_leave_group(br, port, &mld->mld_mca);
+ }
+ }
+
+out:
+ __skb_push(skb2, offset);
+ if (skb2 != skb)
+ kfree_skb(skb2);
+ return err;
+}
+#endif
+
int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
struct sk_buff *skb)
{
+ BR_INPUT_SKB_CB(skb)->igmp = 0;
+ BR_INPUT_SKB_CB(skb)->mrouters_only = 0;
+
if (br->multicast_disabled)
return 0;
switch (skb->protocol) {
case htons(ETH_P_IP):
return br_multicast_ipv4_rcv(br, port, skb);
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ case htons(ETH_P_IPV6):
+ return br_multicast_ipv6_rcv(br, port, skb);
+#endif
}
return 0;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 791d4ab0fd4..3d2d3fe0a97 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -45,6 +45,17 @@ struct mac_addr
unsigned char addr[6];
};
+struct br_ip
+{
+ union {
+ __be32 ip4;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct in6_addr ip6;
+#endif
+ } u;
+ __be16 proto;
+};
+
struct net_bridge_fdb_entry
{
struct hlist_node hlist;
@@ -64,7 +75,7 @@ struct net_bridge_port_group {
struct rcu_head rcu;
struct timer_list timer;
struct timer_list query_timer;
- __be32 addr;
+ struct br_ip addr;
u32 queries_sent;
};
@@ -77,7 +88,7 @@ struct net_bridge_mdb_entry
struct rcu_head rcu;
struct timer_list timer;
struct timer_list query_timer;
- __be32 addr;
+ struct br_ip addr;
u32 queries_sent;
};
@@ -130,19 +141,20 @@ struct net_bridge_port
#endif
};
+struct br_cpu_netstats {
+ unsigned long rx_packets;
+ unsigned long rx_bytes;
+ unsigned long tx_packets;
+ unsigned long tx_bytes;
+};
+
struct net_bridge
{
spinlock_t lock;
struct list_head port_list;
struct net_device *dev;
- struct br_cpu_netstats __percpu {
- unsigned long rx_packets;
- unsigned long rx_bytes;
- unsigned long tx_packets;
- unsigned long tx_bytes;
- } *stats;
-
+ struct br_cpu_netstats __percpu *stats;
spinlock_t hash_lock;
struct hlist_head hash[BR_HASH_SIZE];
unsigned long feature_mask;
@@ -241,6 +253,8 @@ static inline int br_is_root_bridge(const struct net_bridge *br)
extern void br_dev_setup(struct net_device *dev);
extern netdev_tx_t br_dev_xmit(struct sk_buff *skb,
struct net_device *dev);
+extern bool br_devices_support_netpoll(struct net_bridge *br);
+extern void br_netpoll_cleanup(struct net_device *br_dev);
/* br_fdb.c */
extern int br_fdb_init(void);
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index e84837e1bc8..024fd5bb2d3 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -247,10 +247,10 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
switch (caifdev->link_select) {
case CAIF_LINK_HIGH_BANDW:
- pref = CFPHYPREF_LOW_LAT;
+ pref = CFPHYPREF_HIGH_BW;
break;
case CAIF_LINK_LOW_LATENCY:
- pref = CFPHYPREF_HIGH_BW;
+ pref = CFPHYPREF_LOW_LAT;
break;
default:
pref = CFPHYPREF_HIGH_BW;
@@ -330,23 +330,28 @@ int caif_connect_client(struct caif_connect_request *conn_req,
struct cflayer *client_layer)
{
struct cfctrl_link_param param;
- if (connect_req_to_link_param(get_caif_conf(), conn_req, &param) == 0)
- /* Hook up the adaptation layer. */
- return cfcnfg_add_adaptation_layer(get_caif_conf(),
+ int ret;
+ ret = connect_req_to_link_param(get_caif_conf(), conn_req, &param);
+ if (ret)
+ return ret;
+ /* Hook up the adaptation layer. */
+ return cfcnfg_add_adaptation_layer(get_caif_conf(),
&param, client_layer);
-
- return -EINVAL;
-
- caif_assert(0);
}
EXPORT_SYMBOL(caif_connect_client);
int caif_disconnect_client(struct cflayer *adap_layer)
{
- return cfcnfg_del_adapt_layer(get_caif_conf(), adap_layer);
+ return cfcnfg_disconn_adapt_layer(get_caif_conf(), adap_layer);
}
EXPORT_SYMBOL(caif_disconnect_client);
+void caif_release_client(struct cflayer *adap_layer)
+{
+ cfcnfg_release_adap_layer(adap_layer);
+}
+EXPORT_SYMBOL(caif_release_client);
+
/* Per-namespace Caif devices handling */
static int caif_init_net(struct net *net)
{
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index cdf62b9fefa..c3a70c5c893 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -1,7 +1,6 @@
/*
* Copyright (C) ST-Ericsson AB 2010
* Author: Sjur Brendeland sjur.brandeland@stericsson.com
- * Per Sigmond per.sigmond@stericsson.com
* License terms: GNU General Public License (GPL) version 2
*/
@@ -16,91 +15,52 @@
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/uaccess.h>
-#include <asm/atomic.h>
-
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
#include <linux/caif/caif_socket.h>
+#include <asm/atomic.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
#include <net/caif/caif_layer.h>
#include <net/caif/caif_dev.h>
#include <net/caif/cfpkt.h>
MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(AF_CAIF);
+
+#define CAIF_DEF_SNDBUF (CAIF_MAX_PAYLOAD_SIZE*10)
+#define CAIF_DEF_RCVBUF (CAIF_MAX_PAYLOAD_SIZE*100)
+
+/*
+ * CAIF state is re-using the TCP socket states.
+ * caif_states stored in sk_state reflect the state as reported by
+ * the CAIF stack, while sk_socket->state is the state of the socket.
+ */
+enum caif_states {
+ CAIF_CONNECTED = TCP_ESTABLISHED,
+ CAIF_CONNECTING = TCP_SYN_SENT,
+ CAIF_DISCONNECTED = TCP_CLOSE
+};
+
+#define TX_FLOW_ON_BIT 1
+#define RX_FLOW_ON_BIT 2
-#define CHNL_SKT_READ_QUEUE_HIGH 200
-#define CHNL_SKT_READ_QUEUE_LOW 100
-
-static int caif_sockbuf_size = 40000;
-static atomic_t caif_nr_socks = ATOMIC_INIT(0);
-
-#define CONN_STATE_OPEN_BIT 1
-#define CONN_STATE_PENDING_BIT 2
-#define CONN_STATE_PEND_DESTROY_BIT 3
-#define CONN_REMOTE_SHUTDOWN_BIT 4
-
-#define TX_FLOW_ON_BIT 1
-#define RX_FLOW_ON_BIT 2
-
-#define STATE_IS_OPEN(cf_sk) test_bit(CONN_STATE_OPEN_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define STATE_IS_REMOTE_SHUTDOWN(cf_sk) test_bit(CONN_REMOTE_SHUTDOWN_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define STATE_IS_PENDING(cf_sk) test_bit(CONN_STATE_PENDING_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define STATE_IS_PENDING_DESTROY(cf_sk) test_bit(CONN_STATE_PEND_DESTROY_BIT,\
- (void *) &(cf_sk)->conn_state)
-
-#define SET_STATE_PENDING_DESTROY(cf_sk) set_bit(CONN_STATE_PEND_DESTROY_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define SET_STATE_OPEN(cf_sk) set_bit(CONN_STATE_OPEN_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define SET_STATE_CLOSED(cf_sk) clear_bit(CONN_STATE_OPEN_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define SET_PENDING_ON(cf_sk) set_bit(CONN_STATE_PENDING_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define SET_PENDING_OFF(cf_sk) clear_bit(CONN_STATE_PENDING_BIT,\
- (void *) &(cf_sk)->conn_state)
-#define SET_REMOTE_SHUTDOWN(cf_sk) set_bit(CONN_REMOTE_SHUTDOWN_BIT,\
- (void *) &(cf_sk)->conn_state)
-
-#define SET_REMOTE_SHUTDOWN_OFF(dev) clear_bit(CONN_REMOTE_SHUTDOWN_BIT,\
- (void *) &(dev)->conn_state)
-#define RX_FLOW_IS_ON(cf_sk) test_bit(RX_FLOW_ON_BIT,\
- (void *) &(cf_sk)->flow_state)
-#define TX_FLOW_IS_ON(cf_sk) test_bit(TX_FLOW_ON_BIT,\
- (void *) &(cf_sk)->flow_state)
-
-#define SET_RX_FLOW_OFF(cf_sk) clear_bit(RX_FLOW_ON_BIT,\
- (void *) &(cf_sk)->flow_state)
-#define SET_RX_FLOW_ON(cf_sk) set_bit(RX_FLOW_ON_BIT,\
- (void *) &(cf_sk)->flow_state)
-#define SET_TX_FLOW_OFF(cf_sk) clear_bit(TX_FLOW_ON_BIT,\
- (void *) &(cf_sk)->flow_state)
-#define SET_TX_FLOW_ON(cf_sk) set_bit(TX_FLOW_ON_BIT,\
- (void *) &(cf_sk)->flow_state)
-
-#define SKT_READ_FLAG 0x01
-#define SKT_WRITE_FLAG 0x02
static struct dentry *debugfsdir;
-#include <linux/debugfs.h>
#ifdef CONFIG_DEBUG_FS
struct debug_fs_counter {
- atomic_t num_open;
- atomic_t num_close;
- atomic_t num_init;
- atomic_t num_init_resp;
- atomic_t num_init_fail_resp;
- atomic_t num_deinit;
- atomic_t num_deinit_resp;
+ atomic_t caif_nr_socks;
+ atomic_t num_connect_req;
+ atomic_t num_connect_resp;
+ atomic_t num_connect_fail_resp;
+ atomic_t num_disconnect;
atomic_t num_remote_shutdown_ind;
atomic_t num_tx_flow_off_ind;
atomic_t num_tx_flow_on_ind;
atomic_t num_rx_flow_off;
atomic_t num_rx_flow_on;
- atomic_t skb_in_use;
- atomic_t skb_alloc;
- atomic_t skb_free;
};
-static struct debug_fs_counter cnt;
+struct debug_fs_counter cnt;
#define dbfs_atomic_inc(v) atomic_inc(v)
#define dbfs_atomic_dec(v) atomic_dec(v)
#else
@@ -108,624 +68,666 @@ static struct debug_fs_counter cnt;
#define dbfs_atomic_dec(v)
#endif
-/* The AF_CAIF socket */
struct caifsock {
- /* NOTE: sk has to be the first member */
- struct sock sk;
+ struct sock sk; /* must be first member */
struct cflayer layer;
- char name[CAIF_LAYER_NAME_SZ];
- u32 conn_state;
+ char name[CAIF_LAYER_NAME_SZ]; /* Used for debugging */
u32 flow_state;
- struct cfpktq *pktq;
- int file_mode;
struct caif_connect_request conn_req;
- int read_queue_len;
- /* protect updates of read_queue_len */
- spinlock_t read_queue_len_lock;
+ struct mutex readlock;
struct dentry *debugfs_socket_dir;
};
-static void drain_queue(struct caifsock *cf_sk);
+static int rx_flow_is_on(struct caifsock *cf_sk)
+{
+ return test_bit(RX_FLOW_ON_BIT,
+ (void *) &cf_sk->flow_state);
+}
+
+static int tx_flow_is_on(struct caifsock *cf_sk)
+{
+ return test_bit(TX_FLOW_ON_BIT,
+ (void *) &cf_sk->flow_state);
+}
-/* Packet Receive Callback function called from CAIF Stack */
-static int caif_sktrecv_cb(struct cflayer *layr, struct cfpkt *pkt)
+static void set_rx_flow_off(struct caifsock *cf_sk)
{
- struct caifsock *cf_sk;
- int read_queue_high;
- cf_sk = container_of(layr, struct caifsock, layer);
+ clear_bit(RX_FLOW_ON_BIT,
+ (void *) &cf_sk->flow_state);
+}
- if (!STATE_IS_OPEN(cf_sk)) {
- /*FIXME: This should be allowed finally!*/
- pr_debug("CAIF: %s(): called after close request\n", __func__);
- cfpkt_destroy(pkt);
- return 0;
- }
- /* NOTE: This function may be called in Tasklet context! */
+static void set_rx_flow_on(struct caifsock *cf_sk)
+{
+ set_bit(RX_FLOW_ON_BIT,
+ (void *) &cf_sk->flow_state);
+}
- /* The queue has its own lock */
- cfpkt_queue(cf_sk->pktq, pkt, 0);
+static void set_tx_flow_off(struct caifsock *cf_sk)
+{
+ clear_bit(TX_FLOW_ON_BIT,
+ (void *) &cf_sk->flow_state);
+}
- spin_lock(&cf_sk->read_queue_len_lock);
- cf_sk->read_queue_len++;
+static void set_tx_flow_on(struct caifsock *cf_sk)
+{
+ set_bit(TX_FLOW_ON_BIT,
+ (void *) &cf_sk->flow_state);
+}
- read_queue_high = (cf_sk->read_queue_len > CHNL_SKT_READ_QUEUE_HIGH);
- spin_unlock(&cf_sk->read_queue_len_lock);
+static void caif_read_lock(struct sock *sk)
+{
+ struct caifsock *cf_sk;
+ cf_sk = container_of(sk, struct caifsock, sk);
+ mutex_lock(&cf_sk->readlock);
+}
- if (RX_FLOW_IS_ON(cf_sk) && read_queue_high) {
- dbfs_atomic_inc(&cnt.num_rx_flow_off);
- SET_RX_FLOW_OFF(cf_sk);
+static void caif_read_unlock(struct sock *sk)
+{
+ struct caifsock *cf_sk;
+ cf_sk = container_of(sk, struct caifsock, sk);
+ mutex_unlock(&cf_sk->readlock);
+}
- /* Send flow off (NOTE: must not sleep) */
- pr_debug("CAIF: %s():"
- " sending flow OFF (queue len = %d)\n",
- __func__,
- cf_sk->read_queue_len);
- caif_assert(cf_sk->layer.dn);
- caif_assert(cf_sk->layer.dn->ctrlcmd);
+int sk_rcvbuf_lowwater(struct caifsock *cf_sk)
+{
+ /* A quarter of full buffer is used a low water mark */
+ return cf_sk->sk.sk_rcvbuf / 4;
+}
- (void) cf_sk->layer.dn->modemcmd(cf_sk->layer.dn,
- CAIF_MODEMCMD_FLOW_OFF_REQ);
- }
+void caif_flow_ctrl(struct sock *sk, int mode)
+{
+ struct caifsock *cf_sk;
+ cf_sk = container_of(sk, struct caifsock, sk);
+ if (cf_sk->layer.dn)
+ cf_sk->layer.dn->modemcmd(cf_sk->layer.dn, mode);
+}
- /* Signal reader that data is available. */
+/*
+ * Copied from sock.c:sock_queue_rcv_skb(), but changed so packets are
+ * not dropped, but CAIF is sending flow off instead.
+ */
+int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ int err;
+ int skb_len;
+ unsigned long flags;
+ struct sk_buff_head *list = &sk->sk_receive_queue;
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
- wake_up_interruptible(cf_sk->sk.sk_sleep);
+ if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
+ (unsigned)sk->sk_rcvbuf && rx_flow_is_on(cf_sk)) {
+ trace_printk("CAIF: %s():"
+ " sending flow OFF (queue len = %d %d)\n",
+ __func__,
+ atomic_read(&cf_sk->sk.sk_rmem_alloc),
+ sk_rcvbuf_lowwater(cf_sk));
+ set_rx_flow_off(cf_sk);
+ if (cf_sk->layer.dn)
+ cf_sk->layer.dn->modemcmd(cf_sk->layer.dn,
+ CAIF_MODEMCMD_FLOW_OFF_REQ);
+ }
+ err = sk_filter(sk, skb);
+ if (err)
+ return err;
+ if (!sk_rmem_schedule(sk, skb->truesize) && rx_flow_is_on(cf_sk)) {
+ set_rx_flow_off(cf_sk);
+ trace_printk("CAIF: %s():"
+ " sending flow OFF due to rmem_schedule\n",
+ __func__);
+ if (cf_sk->layer.dn)
+ cf_sk->layer.dn->modemcmd(cf_sk->layer.dn,
+ CAIF_MODEMCMD_FLOW_OFF_REQ);
+ }
+ skb->dev = NULL;
+ skb_set_owner_r(skb, sk);
+ /* Cache the SKB length before we tack it onto the receive
+ * queue. Once it is added it no longer belongs to us and
+ * may be freed by other threads of control pulling packets
+ * from the queue.
+ */
+ skb_len = skb->len;
+ spin_lock_irqsave(&list->lock, flags);
+ if (!sock_flag(sk, SOCK_DEAD))
+ __skb_queue_tail(list, skb);
+ spin_unlock_irqrestore(&list->lock, flags);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_data_ready(sk, skb_len);
+ else
+ kfree_skb(skb);
return 0;
}
-/* Packet Flow Control Callback function called from CAIF */
-static void caif_sktflowctrl_cb(struct cflayer *layr,
- enum caif_ctrlcmd flow,
- int phyid)
+/* Packet Receive Callback function called from CAIF Stack */
+static int caif_sktrecv_cb(struct cflayer *layr, struct cfpkt *pkt)
{
struct caifsock *cf_sk;
-
- /* NOTE: This function may be called in Tasklet context! */
- pr_debug("CAIF: %s(): flowctrl func called: %s.\n",
- __func__,
- flow == CAIF_CTRLCMD_FLOW_ON_IND ? "ON" :
- flow == CAIF_CTRLCMD_FLOW_OFF_IND ? "OFF" :
- flow == CAIF_CTRLCMD_INIT_RSP ? "INIT_RSP" :
- flow == CAIF_CTRLCMD_DEINIT_RSP ? "DEINIT_RSP" :
- flow == CAIF_CTRLCMD_INIT_FAIL_RSP ? "INIT_FAIL_RSP" :
- flow ==
- CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND ? "REMOTE_SHUTDOWN" :
- "UKNOWN CTRL COMMAND");
-
- if (layr == NULL)
- return;
+ struct sk_buff *skb;
cf_sk = container_of(layr, struct caifsock, layer);
+ skb = cfpkt_tonative(pkt);
+
+ if (unlikely(cf_sk->sk.sk_state != CAIF_CONNECTED)) {
+ cfpkt_destroy(pkt);
+ return 0;
+ }
+ caif_queue_rcv_skb(&cf_sk->sk, skb);
+ return 0;
+}
+/* Packet Control Callback function called from CAIF */
+static void caif_ctrl_cb(struct cflayer *layr,
+ enum caif_ctrlcmd flow,
+ int phyid)
+{
+ struct caifsock *cf_sk = container_of(layr, struct caifsock, layer);
switch (flow) {
case CAIF_CTRLCMD_FLOW_ON_IND:
+ /* OK from modem to start sending again */
dbfs_atomic_inc(&cnt.num_tx_flow_on_ind);
- /* Signal reader that data is available. */
- SET_TX_FLOW_ON(cf_sk);
- wake_up_interruptible(cf_sk->sk.sk_sleep);
+ set_tx_flow_on(cf_sk);
+ cf_sk->sk.sk_state_change(&cf_sk->sk);
break;
case CAIF_CTRLCMD_FLOW_OFF_IND:
+ /* Modem asks us to shut up */
dbfs_atomic_inc(&cnt.num_tx_flow_off_ind);
- SET_TX_FLOW_OFF(cf_sk);
+ set_tx_flow_off(cf_sk);
+ cf_sk->sk.sk_state_change(&cf_sk->sk);
break;
case CAIF_CTRLCMD_INIT_RSP:
- dbfs_atomic_inc(&cnt.num_init_resp);
- /* Signal reader that data is available. */
- caif_assert(STATE_IS_OPEN(cf_sk));
- SET_PENDING_OFF(cf_sk);
- SET_TX_FLOW_ON(cf_sk);
- wake_up_interruptible(cf_sk->sk.sk_sleep);
+ /* We're now connected */
+ dbfs_atomic_inc(&cnt.num_connect_resp);
+ cf_sk->sk.sk_state = CAIF_CONNECTED;
+ set_tx_flow_on(cf_sk);
+ cf_sk->sk.sk_state_change(&cf_sk->sk);
break;
case CAIF_CTRLCMD_DEINIT_RSP:
- dbfs_atomic_inc(&cnt.num_deinit_resp);
- caif_assert(!STATE_IS_OPEN(cf_sk));
- SET_PENDING_OFF(cf_sk);
- if (!STATE_IS_PENDING_DESTROY(cf_sk)) {
- if (cf_sk->sk.sk_sleep != NULL)
- wake_up_interruptible(cf_sk->sk.sk_sleep);
- }
- dbfs_atomic_inc(&cnt.num_deinit);
- sock_put(&cf_sk->sk);
+ /* We're now disconnected */
+ cf_sk->sk.sk_state = CAIF_DISCONNECTED;
+ cf_sk->sk.sk_state_change(&cf_sk->sk);
+ cfcnfg_release_adap_layer(&cf_sk->layer);
break;
case CAIF_CTRLCMD_INIT_FAIL_RSP:
- dbfs_atomic_inc(&cnt.num_init_fail_resp);
- caif_assert(STATE_IS_OPEN(cf_sk));
- SET_STATE_CLOSED(cf_sk);
- SET_PENDING_OFF(cf_sk);
- SET_TX_FLOW_OFF(cf_sk);
- wake_up_interruptible(cf_sk->sk.sk_sleep);
+ /* Connect request failed */
+ dbfs_atomic_inc(&cnt.num_connect_fail_resp);
+ cf_sk->sk.sk_err = ECONNREFUSED;
+ cf_sk->sk.sk_state = CAIF_DISCONNECTED;
+ cf_sk->sk.sk_shutdown = SHUTDOWN_MASK;
+ /*
+ * Socket "standards" seems to require POLLOUT to
+ * be set at connect failure.
+ */
+ set_tx_flow_on(cf_sk);
+ cf_sk->sk.sk_state_change(&cf_sk->sk);
break;
case CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND:
+ /* Modem has closed this connection, or device is down. */
dbfs_atomic_inc(&cnt.num_remote_shutdown_ind);
- SET_REMOTE_SHUTDOWN(cf_sk);
- /* Use sk_shutdown to indicate remote shutdown indication */
- cf_sk->sk.sk_shutdown |= RCV_SHUTDOWN;
- cf_sk->file_mode = 0;
- wake_up_interruptible(cf_sk->sk.sk_sleep);
+ cf_sk->sk.sk_shutdown = SHUTDOWN_MASK;
+ cf_sk->sk.sk_err = ECONNRESET;
+ set_rx_flow_on(cf_sk);
+ cf_sk->sk.sk_error_report(&cf_sk->sk);
break;
default:
pr_debug("CAIF: %s(): Unexpected flow command %d\n",
- __func__, flow);
+ __func__, flow);
}
}
-static void skb_destructor(struct sk_buff *skb)
+static void caif_check_flow_release(struct sock *sk)
{
- dbfs_atomic_inc(&cnt.skb_free);
- dbfs_atomic_dec(&cnt.skb_in_use);
-}
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
+ if (cf_sk->layer.dn == NULL || cf_sk->layer.dn->modemcmd == NULL)
+ return;
+ if (rx_flow_is_on(cf_sk))
+ return;
-static int caif_recvmsg(struct kiocb *iocb, struct socket *sock,
+ if (atomic_read(&sk->sk_rmem_alloc) <= sk_rcvbuf_lowwater(cf_sk)) {
+ dbfs_atomic_inc(&cnt.num_rx_flow_on);
+ set_rx_flow_on(cf_sk);
+ cf_sk->layer.dn->modemcmd(cf_sk->layer.dn,
+ CAIF_MODEMCMD_FLOW_ON_REQ);
+ }
+}
+/*
+ * Copied from sock.c:sock_queue_rcv_skb(), and added check that user buffer
+ * has sufficient size.
+ */
+
+static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t buf_len, int flags)
{
struct sock *sk = sock->sk;
- struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
- struct cfpkt *pkt = NULL;
- size_t len;
- int result;
struct sk_buff *skb;
- ssize_t ret = -EIO;
- int read_queue_low;
-
- if (cf_sk == NULL) {
- pr_debug("CAIF: %s(): private_data not set!\n",
- __func__);
- ret = -EBADFD;
- goto read_error;
- }
-
- /* Don't do multiple iovec entries yet */
- if (m->msg_iovlen != 1)
- return -EOPNOTSUPP;
+ int ret = 0;
+ int len;
if (unlikely(!buf_len))
return -EINVAL;
- lock_sock(&(cf_sk->sk));
-
- caif_assert(cf_sk->pktq);
-
- if (!STATE_IS_OPEN(cf_sk)) {
- /* Socket is closed or closing. */
- if (!STATE_IS_PENDING(cf_sk)) {
- pr_debug("CAIF: %s(): socket is closed (by remote)\n",
- __func__);
- ret = -EPIPE;
- } else {
- pr_debug("CAIF: %s(): socket is closing..\n", __func__);
- ret = -EBADF;
- }
+ skb = skb_recv_datagram(sk, flags, 0 , &ret);
+ if (!skb)
goto read_error;
- }
- /* Socket is open or opening. */
- if (STATE_IS_PENDING(cf_sk)) {
- pr_debug("CAIF: %s(): socket is opening...\n", __func__);
-
- if (flags & MSG_DONTWAIT) {
- /* We can't block. */
- pr_debug("CAIF: %s():state pending and MSG_DONTWAIT\n",
- __func__);
- ret = -EAGAIN;
- goto read_error;
- }
+ len = skb->len;
+
+ if (skb && skb->len > buf_len && !(flags & MSG_PEEK)) {
+ len = buf_len;
/*
- * Blocking mode; state is pending and we need to wait
- * for its conclusion.
+ * Push skb back on receive queue if buffer too small.
+ * This has a built-in race where multi-threaded receive
+ * may get packet in wrong order, but multiple read does
+ * not really guarantee ordered delivery anyway.
+ * Let's optimize for speed without taking locks.
*/
- release_sock(&cf_sk->sk);
-
- result =
- wait_event_interruptible(*cf_sk->sk.sk_sleep,
- !STATE_IS_PENDING(cf_sk));
- lock_sock(&(cf_sk->sk));
-
- if (result == -ERESTARTSYS) {
- pr_debug("CAIF: %s(): wait_event_interruptible"
- " woken by a signal (1)", __func__);
- ret = -ERESTARTSYS;
- goto read_error;
- }
+ skb_queue_head(&sk->sk_receive_queue, skb);
+ ret = -EMSGSIZE;
+ goto read_error;
}
- if (STATE_IS_REMOTE_SHUTDOWN(cf_sk) ||
- !STATE_IS_OPEN(cf_sk) ||
- STATE_IS_PENDING(cf_sk)) {
-
- pr_debug("CAIF: %s(): socket closed\n",
- __func__);
- ret = -ESHUTDOWN;
+ ret = skb_copy_datagram_iovec(skb, 0, m->msg_iov, len);
+ if (ret)
goto read_error;
- }
- /*
- * Block if we don't have any received buffers.
- * The queue has its own lock.
- */
- while ((pkt = cfpkt_qpeek(cf_sk->pktq)) == NULL) {
+ skb_free_datagram(sk, skb);
- if (flags & MSG_DONTWAIT) {
- pr_debug("CAIF: %s(): MSG_DONTWAIT\n", __func__);
- ret = -EAGAIN;
- goto read_error;
- }
- trace_printk("CAIF: %s() wait_event\n", __func__);
+ caif_check_flow_release(sk);
- /* Let writers in. */
- release_sock(&cf_sk->sk);
+ return len;
- /* Block reader until data arrives or socket is closed. */
- if (wait_event_interruptible(*cf_sk->sk.sk_sleep,
- cfpkt_qpeek(cf_sk->pktq)
- || STATE_IS_REMOTE_SHUTDOWN(cf_sk)
- || !STATE_IS_OPEN(cf_sk)) ==
- -ERESTARTSYS) {
- pr_debug("CAIF: %s():"
- " wait_event_interruptible woken by "
- "a signal, signal_pending(current) = %d\n",
- __func__,
- signal_pending(current));
- return -ERESTARTSYS;
- }
+read_error:
+ return ret;
+}
- trace_printk("CAIF: %s() awake\n", __func__);
- if (STATE_IS_REMOTE_SHUTDOWN(cf_sk)) {
- pr_debug("CAIF: %s(): "
- "received remote_shutdown indication\n",
- __func__);
- ret = -ESHUTDOWN;
- goto read_error_no_unlock;
- }
- /* I want to be alone on cf_sk (except status and queue). */
- lock_sock(&(cf_sk->sk));
+/* Copied from unix_stream_wait_data, identical except for lock call. */
+static long caif_stream_data_wait(struct sock *sk, long timeo)
+{
+ DEFINE_WAIT(wait);
+ lock_sock(sk);
+
+ for (;;) {
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+
+ if (!skb_queue_empty(&sk->sk_receive_queue) ||
+ sk->sk_err ||
+ sk->sk_state != CAIF_CONNECTED ||
+ sock_flag(sk, SOCK_DEAD) ||
+ (sk->sk_shutdown & RCV_SHUTDOWN) ||
+ signal_pending(current) ||
+ !timeo)
+ break;
- if (!STATE_IS_OPEN(cf_sk)) {
- /* Someone closed the link, report error. */
- pr_debug("CAIF: %s(): remote end shutdown!\n",
- __func__);
- ret = -EPIPE;
- goto read_error;
- }
+ set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
+ release_sock(sk);
+ timeo = schedule_timeout(timeo);
+ lock_sock(sk);
+ clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
}
- /* The queue has its own lock. */
- len = cfpkt_getlen(pkt);
-
- /* Check max length that can be copied. */
- if (len <= buf_len)
- pkt = cfpkt_dequeue(cf_sk->pktq);
- else {
- pr_debug("CAIF: %s(): user buffer too small (%ld,%ld)\n",
- __func__, (long) len, (long) buf_len);
- if (sock->type == SOCK_SEQPACKET) {
- ret = -EMSGSIZE;
- goto read_error;
- }
- len = buf_len;
- }
+ finish_wait(sk_sleep(sk), &wait);
+ release_sock(sk);
+ return timeo;
+}
- spin_lock(&cf_sk->read_queue_len_lock);
- cf_sk->read_queue_len--;
- read_queue_low = (cf_sk->read_queue_len < CHNL_SKT_READ_QUEUE_LOW);
- spin_unlock(&cf_sk->read_queue_len_lock);
+/*
+ * Copied from unix_stream_recvmsg, but removed credit checks,
+ * changed locking calls, changed address handling.
+ */
+static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *msg, size_t size,
+ int flags)
+{
+ struct sock *sk = sock->sk;
+ int copied = 0;
+ int target;
+ int err = 0;
+ long timeo;
- if (!RX_FLOW_IS_ON(cf_sk) && read_queue_low) {
- dbfs_atomic_inc(&cnt.num_rx_flow_on);
- SET_RX_FLOW_ON(cf_sk);
+ err = -EOPNOTSUPP;
+ if (flags&MSG_OOB)
+ goto out;
- /* Send flow on. */
- pr_debug("CAIF: %s(): sending flow ON (queue len = %d)\n",
- __func__, cf_sk->read_queue_len);
- caif_assert(cf_sk->layer.dn);
- caif_assert(cf_sk->layer.dn->ctrlcmd);
- (void) cf_sk->layer.dn->modemcmd(cf_sk->layer.dn,
- CAIF_MODEMCMD_FLOW_ON_REQ);
+ msg->msg_namelen = 0;
- caif_assert(cf_sk->read_queue_len >= 0);
- }
+ /*
+ * Lock the socket to prevent queue disordering
+ * while sleeps in memcpy_tomsg
+ */
+ err = -EAGAIN;
+ if (sk->sk_state == CAIF_CONNECTING)
+ goto out;
- skb = cfpkt_tonative(pkt);
- result = skb_copy_datagram_iovec(skb, 0, m->msg_iov, len);
- skb_pull(skb, len);
+ caif_read_lock(sk);
+ target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
+ timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);
- if (result) {
- pr_debug("CAIF: %s(): copy to_iovec failed\n", __func__);
- cfpkt_destroy(pkt);
- ret = -EFAULT;
- goto read_error;
- }
+ do {
+ int chunk;
+ struct sk_buff *skb;
- /* Free packet and remove from queue */
- if (skb->len == 0)
- skb_free_datagram(sk, skb);
+ lock_sock(sk);
+ skb = skb_dequeue(&sk->sk_receive_queue);
+ caif_check_flow_release(sk);
- /* Let the others in. */
- release_sock(&cf_sk->sk);
- return len;
+ if (skb == NULL) {
+ if (copied >= target)
+ goto unlock;
+ /*
+ * POSIX 1003.1g mandates this order.
+ */
+ err = sock_error(sk);
+ if (err)
+ goto unlock;
+ err = -ECONNRESET;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ goto unlock;
-read_error:
- release_sock(&cf_sk->sk);
-read_error_no_unlock:
- return ret;
-}
+ err = -EPIPE;
+ if (sk->sk_state != CAIF_CONNECTED)
+ goto unlock;
+ if (sock_flag(sk, SOCK_DEAD))
+ goto unlock;
-/* Send a signal as a consequence of sendmsg, sendto or caif_sendmsg. */
-static int caif_sendmsg(struct kiocb *kiocb, struct socket *sock,
- struct msghdr *msg, size_t len)
-{
+ release_sock(sk);
- struct sock *sk = sock->sk;
- struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
- size_t payload_size = msg->msg_iov->iov_len;
- struct cfpkt *pkt = NULL;
- struct caif_payload_info info;
- unsigned char *txbuf;
- ssize_t ret = -EIO;
- int result;
- struct sk_buff *skb;
- caif_assert(msg->msg_iovlen == 1);
+ err = -EAGAIN;
+ if (!timeo)
+ break;
- if (cf_sk == NULL) {
- pr_debug("CAIF: %s(): private_data not set!\n",
- __func__);
- ret = -EBADFD;
- goto write_error_no_unlock;
- }
+ caif_read_unlock(sk);
- if (unlikely(msg->msg_iov->iov_base == NULL)) {
- pr_warning("CAIF: %s(): Buffer is NULL.\n", __func__);
- ret = -EINVAL;
- goto write_error_no_unlock;
- }
+ timeo = caif_stream_data_wait(sk, timeo);
- if (payload_size > CAIF_MAX_PAYLOAD_SIZE) {
- pr_debug("CAIF: %s(): buffer too long\n", __func__);
- if (sock->type == SOCK_SEQPACKET) {
- ret = -EINVAL;
- goto write_error_no_unlock;
+ if (signal_pending(current)) {
+ err = sock_intr_errno(timeo);
+ goto out;
+ }
+ caif_read_lock(sk);
+ continue;
+unlock:
+ release_sock(sk);
+ break;
}
- payload_size = CAIF_MAX_PAYLOAD_SIZE;
- }
+ release_sock(sk);
+ chunk = min_t(unsigned int, skb->len, size);
+ if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
+ skb_queue_head(&sk->sk_receive_queue, skb);
+ if (copied == 0)
+ copied = -EFAULT;
+ break;
+ }
+ copied += chunk;
+ size -= chunk;
- /* I want to be alone on cf_sk (except status and queue) */
- lock_sock(&(cf_sk->sk));
+ /* Mark read part of skb as used */
+ if (!(flags & MSG_PEEK)) {
+ skb_pull(skb, chunk);
- caif_assert(cf_sk->pktq);
+ /* put the skb back if we didn't use it up. */
+ if (skb->len) {
+ skb_queue_head(&sk->sk_receive_queue, skb);
+ break;
+ }
+ kfree_skb(skb);
- if (!STATE_IS_OPEN(cf_sk)) {
- /* Socket is closed or closing */
- if (!STATE_IS_PENDING(cf_sk)) {
- pr_debug("CAIF: %s(): socket is closed (by remote)\n",
- __func__);
- ret = -EPIPE;
} else {
- pr_debug("CAIF: %s(): socket is closing...\n",
- __func__);
- ret = -EBADF;
- }
- goto write_error;
- }
-
- /* Socket is open or opening */
- if (STATE_IS_PENDING(cf_sk)) {
- pr_debug("CAIF: %s(): socket is opening...\n", __func__);
-
- if (msg->msg_flags & MSG_DONTWAIT) {
- /* We can't block */
- trace_printk("CAIF: %s():state pending:"
- "state=MSG_DONTWAIT\n", __func__);
- ret = -EAGAIN;
- goto write_error;
+ /*
+ * It is questionable, see note in unix_dgram_recvmsg.
+ */
+ /* put message back and return */
+ skb_queue_head(&sk->sk_receive_queue, skb);
+ break;
}
- /* Let readers in */
- release_sock(&cf_sk->sk);
-
- /*
- * Blocking mode; state is pending and we need to wait
- * for its conclusion.
- */
- result =
- wait_event_interruptible(*cf_sk->sk.sk_sleep,
- !STATE_IS_PENDING(cf_sk));
- /* I want to be alone on cf_sk (except status and queue) */
- lock_sock(&(cf_sk->sk));
+ } while (size);
+ caif_read_unlock(sk);
- if (result == -ERESTARTSYS) {
- pr_debug("CAIF: %s(): wait_event_interruptible"
- " woken by a signal (1)", __func__);
- ret = -ERESTARTSYS;
- goto write_error;
- }
- }
- if (STATE_IS_REMOTE_SHUTDOWN(cf_sk) ||
- !STATE_IS_OPEN(cf_sk) ||
- STATE_IS_PENDING(cf_sk)) {
+out:
+ return copied ? : err;
+}
- pr_debug("CAIF: %s(): socket closed\n",
- __func__);
- ret = -ESHUTDOWN;
- goto write_error;
+/*
+ * Copied from sock.c:sock_wait_for_wmem, but change to wait for
+ * CAIF flow-on and sock_writable.
+ */
+static long caif_wait_for_flow_on(struct caifsock *cf_sk,
+ int wait_writeable, long timeo, int *err)
+{
+ struct sock *sk = &cf_sk->sk;
+ DEFINE_WAIT(wait);
+ for (;;) {
+ *err = 0;
+ if (tx_flow_is_on(cf_sk) &&
+ (!wait_writeable || sock_writeable(&cf_sk->sk)))
+ break;
+ *err = -ETIMEDOUT;
+ if (!timeo)
+ break;
+ *err = -ERESTARTSYS;
+ if (signal_pending(current))
+ break;
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ *err = -ECONNRESET;
+ if (sk->sk_shutdown & SHUTDOWN_MASK)
+ break;
+ *err = -sk->sk_err;
+ if (sk->sk_err)
+ break;
+ *err = -EPIPE;
+ if (cf_sk->sk.sk_state != CAIF_CONNECTED)
+ break;
+ timeo = schedule_timeout(timeo);
}
+ finish_wait(sk_sleep(sk), &wait);
+ return timeo;
+}
- if (!TX_FLOW_IS_ON(cf_sk)) {
+/*
+ * Transmit a SKB. The device may temporarily request re-transmission
+ * by returning EAGAIN.
+ */
+static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk,
+ int noblock, long timeo)
+{
+ struct cfpkt *pkt;
+ int ret, loopcnt = 0;
- /* Flow is off. Check non-block flag */
- if (msg->msg_flags & MSG_DONTWAIT) {
- trace_printk("CAIF: %s(): MSG_DONTWAIT and tx flow off",
- __func__);
- ret = -EAGAIN;
- goto write_error;
- }
+ pkt = cfpkt_fromnative(CAIF_DIR_OUT, skb);
+ memset(cfpkt_info(pkt), 0, sizeof(struct caif_payload_info));
+ do {
- /* release lock before waiting */
- release_sock(&cf_sk->sk);
+ ret = -ETIMEDOUT;
- /* Wait until flow is on or socket is closed */
- if (wait_event_interruptible(*cf_sk->sk.sk_sleep,
- TX_FLOW_IS_ON(cf_sk)
- || !STATE_IS_OPEN(cf_sk)
- || STATE_IS_REMOTE_SHUTDOWN(cf_sk)
- ) == -ERESTARTSYS) {
- pr_debug("CAIF: %s():"
- " wait_event_interruptible woken by a signal",
- __func__);
- ret = -ERESTARTSYS;
- goto write_error_no_unlock;
+ /* Slight paranoia, probably not needed. */
+ if (unlikely(loopcnt++ > 1000)) {
+ pr_warning("CAIF: %s(): transmit retries failed,"
+ " error = %d\n", __func__, ret);
+ break;
}
- /* I want to be alone on cf_sk (except status and queue) */
- lock_sock(&(cf_sk->sk));
-
- if (!STATE_IS_OPEN(cf_sk)) {
- /* someone closed the link, report error */
- pr_debug("CAIF: %s(): remote end shutdown!\n",
- __func__);
- ret = -EPIPE;
- goto write_error;
+ if (cf_sk->layer.dn != NULL)
+ ret = cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt);
+ if (likely(ret >= 0))
+ break;
+ /* if transmit return -EAGAIN, then retry */
+ if (noblock && ret == -EAGAIN)
+ break;
+ timeo = caif_wait_for_flow_on(cf_sk, 0, timeo, &ret);
+ if (signal_pending(current)) {
+ ret = sock_intr_errno(timeo);
+ break;
}
-
- if (STATE_IS_REMOTE_SHUTDOWN(cf_sk)) {
- pr_debug("CAIF: %s(): "
- "received remote_shutdown indication\n",
- __func__);
- ret = -ESHUTDOWN;
- goto write_error;
+ if (ret)
+ break;
+ if (cf_sk->sk.sk_state != CAIF_CONNECTED ||
+ sock_flag(&cf_sk->sk, SOCK_DEAD) ||
+ (cf_sk->sk.sk_shutdown & RCV_SHUTDOWN)) {
+ ret = -EPIPE;
+ cf_sk->sk.sk_err = EPIPE;
+ break;
}
- }
+ } while (ret == -EAGAIN);
+ return ret;
+}
- pkt = cfpkt_create(payload_size);
- skb = (struct sk_buff *)pkt;
- skb->destructor = skb_destructor;
- skb->sk = sk;
- dbfs_atomic_inc(&cnt.skb_alloc);
- dbfs_atomic_inc(&cnt.skb_in_use);
- if (cfpkt_raw_append(pkt, (void **) &txbuf, payload_size) < 0) {
- pr_debug("CAIF: %s(): cfpkt_raw_append failed\n", __func__);
- cfpkt_destroy(pkt);
- ret = -EINVAL;
- goto write_error;
- }
+/* Copied from af_unix:unix_dgram_sendmsg, and adapted to CAIF */
+static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
+ struct msghdr *msg, size_t len)
+{
+ struct sock *sk = sock->sk;
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
+ int buffer_size;
+ int ret = 0;
+ struct sk_buff *skb = NULL;
+ int noblock;
+ long timeo;
+ caif_assert(cf_sk);
+ ret = sock_error(sk);
+ if (ret)
+ goto err;
+
+ ret = -EOPNOTSUPP;
+ if (msg->msg_flags&MSG_OOB)
+ goto err;
+
+ ret = -EOPNOTSUPP;
+ if (msg->msg_namelen)
+ goto err;
+
+ ret = -EINVAL;
+ if (unlikely(msg->msg_iov->iov_base == NULL))
+ goto err;
+ noblock = msg->msg_flags & MSG_DONTWAIT;
+
+ buffer_size = len + CAIF_NEEDED_HEADROOM + CAIF_NEEDED_TAILROOM;
+
+ ret = -EMSGSIZE;
+ if (buffer_size > CAIF_MAX_PAYLOAD_SIZE)
+ goto err;
+
+ timeo = sock_sndtimeo(sk, noblock);
+ timeo = caif_wait_for_flow_on(container_of(sk, struct caifsock, sk),
+ 1, timeo, &ret);
+
+ ret = -EPIPE;
+ if (cf_sk->sk.sk_state != CAIF_CONNECTED ||
+ sock_flag(sk, SOCK_DEAD) ||
+ (sk->sk_shutdown & RCV_SHUTDOWN))
+ goto err;
+
+ ret = -ENOMEM;
+ skb = sock_alloc_send_skb(sk, buffer_size, noblock, &ret);
+ if (!skb)
+ goto err;
+ skb_reserve(skb, CAIF_NEEDED_HEADROOM);
+
+ ret = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+
+ if (ret)
+ goto err;
+ ret = transmit_skb(skb, cf_sk, noblock, timeo);
+ if (ret < 0)
+ goto err;
+ return len;
+err:
+ kfree_skb(skb);
+ return ret;
+}
- /* Copy data into buffer. */
- if (copy_from_user(txbuf, msg->msg_iov->iov_base, payload_size)) {
- pr_debug("CAIF: %s(): copy_from_user returned non zero.\n",
- __func__);
- cfpkt_destroy(pkt);
- ret = -EINVAL;
- goto write_error;
- }
- memset(&info, 0, sizeof(info));
+/*
+ * Copied from unix_stream_sendmsg and adapted to CAIF:
+ * Changed removed permission handling and added waiting for flow on
+ * and other minor adaptations.
+ */
+static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
+ struct msghdr *msg, size_t len)
+{
+ struct sock *sk = sock->sk;
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
+ int err, size;
+ struct sk_buff *skb;
+ int sent = 0;
+ long timeo;
- /* Send the packet down the stack. */
- caif_assert(cf_sk->layer.dn);
- caif_assert(cf_sk->layer.dn->transmit);
+ err = -EOPNOTSUPP;
- do {
- ret = cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt);
+ if (unlikely(msg->msg_flags&MSG_OOB))
+ goto out_err;
- if (likely((ret >= 0) || (ret != -EAGAIN)))
- break;
+ if (unlikely(msg->msg_namelen))
+ goto out_err;
- /* EAGAIN - retry */
- if (msg->msg_flags & MSG_DONTWAIT) {
- pr_debug("CAIF: %s(): NONBLOCK and transmit failed,"
- " error = %ld\n", __func__, (long) ret);
- ret = -EAGAIN;
- goto write_error;
- }
+ timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+ timeo = caif_wait_for_flow_on(cf_sk, 1, timeo, &err);
- /* Let readers in */
- release_sock(&cf_sk->sk);
+ if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
+ goto pipe_err;
- /* Wait until flow is on or socket is closed */
- if (wait_event_interruptible(*cf_sk->sk.sk_sleep,
- TX_FLOW_IS_ON(cf_sk)
- || !STATE_IS_OPEN(cf_sk)
- || STATE_IS_REMOTE_SHUTDOWN(cf_sk)
- ) == -ERESTARTSYS) {
- pr_debug("CAIF: %s(): wait_event_interruptible"
- " woken by a signal", __func__);
- ret = -ERESTARTSYS;
- goto write_error_no_unlock;
- }
+ while (sent < len) {
- /* I want to be alone on cf_sk (except status and queue) */
- lock_sock(&(cf_sk->sk));
+ size = len-sent;
- } while (ret == -EAGAIN);
+ if (size > CAIF_MAX_PAYLOAD_SIZE)
+ size = CAIF_MAX_PAYLOAD_SIZE;
- if (ret < 0) {
- cfpkt_destroy(pkt);
- pr_debug("CAIF: %s(): transmit failed, error = %ld\n",
- __func__, (long) ret);
+ /* If size is more than half of sndbuf, chop up message */
+ if (size > ((sk->sk_sndbuf >> 1) - 64))
+ size = (sk->sk_sndbuf >> 1) - 64;
- goto write_error;
- }
+ if (size > SKB_MAX_ALLOC)
+ size = SKB_MAX_ALLOC;
- release_sock(&cf_sk->sk);
- return payload_size;
+ skb = sock_alloc_send_skb(sk,
+ size + CAIF_NEEDED_HEADROOM
+ + CAIF_NEEDED_TAILROOM,
+ msg->msg_flags&MSG_DONTWAIT,
+ &err);
+ if (skb == NULL)
+ goto out_err;
-write_error:
- release_sock(&cf_sk->sk);
-write_error_no_unlock:
- return ret;
-}
+ skb_reserve(skb, CAIF_NEEDED_HEADROOM);
+ /*
+ * If you pass two values to the sock_alloc_send_skb
+ * it tries to grab the large buffer with GFP_NOFS
+ * (which can fail easily), and if it fails grab the
+ * fallback size buffer which is under a page and will
+ * succeed. [Alan]
+ */
+ size = min_t(int, size, skb_tailroom(skb));
-static unsigned int caif_poll(struct file *file, struct socket *sock,
- poll_table *wait)
-{
- struct sock *sk = sock->sk;
- struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
- u32 mask = 0;
- poll_wait(file, sk->sk_sleep, wait);
- lock_sock(&(cf_sk->sk));
- if (!STATE_IS_OPEN(cf_sk)) {
- if (!STATE_IS_PENDING(cf_sk))
- mask |= POLLHUP;
- } else {
- if (cfpkt_qpeek(cf_sk->pktq) != NULL)
- mask |= (POLLIN | POLLRDNORM);
- if (TX_FLOW_IS_ON(cf_sk))
- mask |= (POLLOUT | POLLWRNORM);
+ err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
+ if (err) {
+ kfree_skb(skb);
+ goto out_err;
+ }
+ err = transmit_skb(skb, cf_sk,
+ msg->msg_flags&MSG_DONTWAIT, timeo);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto pipe_err;
+ }
+ sent += size;
}
- release_sock(&cf_sk->sk);
- trace_printk("CAIF: %s(): poll mask=0x%04x\n",
- __func__, mask);
- return mask;
-}
-
-static void drain_queue(struct caifsock *cf_sk)
-{
- struct cfpkt *pkt = NULL;
-
- /* Empty the queue */
- do {
- /* The queue has its own lock */
- if (!cf_sk->pktq)
- break;
-
- pkt = cfpkt_dequeue(cf_sk->pktq);
- if (!pkt)
- break;
- pr_debug("CAIF: %s(): freeing packet from read queue\n",
- __func__);
- cfpkt_destroy(pkt);
- } while (1);
+ return sent;
- cf_sk->read_queue_len = 0;
+pipe_err:
+ if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL))
+ send_sig(SIGPIPE, current, 0);
+ err = -EPIPE;
+out_err:
+ return sent ? : err;
}
static int setsockopt(struct socket *sock,
@@ -736,19 +738,13 @@ static int setsockopt(struct socket *sock,
int prio, linksel;
struct ifreq ifreq;
- if (STATE_IS_OPEN(cf_sk)) {
- pr_debug("CAIF: %s(): setsockopt "
- "cannot be done on a connected socket\n",
- __func__);
+ if (cf_sk->sk.sk_socket->state != SS_UNCONNECTED)
return -ENOPROTOOPT;
- }
+
switch (opt) {
case CAIFSO_LINK_SELECT:
- if (ol < sizeof(int)) {
- pr_debug("CAIF: %s(): setsockopt"
- " CAIFSO_CHANNEL_CONFIG bad size\n", __func__);
+ if (ol < sizeof(int))
return -EINVAL;
- }
if (lvl != SOL_CAIF)
goto bad_sol;
if (copy_from_user(&linksel, ov, sizeof(int)))
@@ -761,28 +757,20 @@ static int setsockopt(struct socket *sock,
case SO_PRIORITY:
if (lvl != SOL_SOCKET)
goto bad_sol;
- if (ol < sizeof(int)) {
- pr_debug("CAIF: %s(): setsockopt"
- " SO_PRIORITY bad size\n", __func__);
+ if (ol < sizeof(int))
return -EINVAL;
- }
if (copy_from_user(&prio, ov, sizeof(int)))
return -EINVAL;
lock_sock(&(cf_sk->sk));
cf_sk->conn_req.priority = prio;
- pr_debug("CAIF: %s(): Setting sockopt priority=%d\n", __func__,
- cf_sk->conn_req.priority);
release_sock(&cf_sk->sk);
return 0;
case SO_BINDTODEVICE:
if (lvl != SOL_SOCKET)
goto bad_sol;
- if (ol < sizeof(struct ifreq)) {
- pr_debug("CAIF: %s(): setsockopt"
- " SO_PRIORITY bad size\n", __func__);
+ if (ol < sizeof(struct ifreq))
return -EINVAL;
- }
if (copy_from_user(&ifreq, ov, sizeof(ifreq)))
return -EFAULT;
lock_sock(&(cf_sk->sk));
@@ -798,359 +786,275 @@ static int setsockopt(struct socket *sock,
goto bad_sol;
if (cf_sk->sk.sk_protocol != CAIFPROTO_UTIL)
return -ENOPROTOOPT;
- if (ol > sizeof(cf_sk->conn_req.param.data))
- goto req_param_bad_size;
-
lock_sock(&(cf_sk->sk));
cf_sk->conn_req.param.size = ol;
- if (copy_from_user(&cf_sk->conn_req.param.data, ov, ol)) {
+ if (ol > sizeof(cf_sk->conn_req.param.data) ||
+ copy_from_user(&cf_sk->conn_req.param.data, ov, ol)) {
release_sock(&cf_sk->sk);
-req_param_bad_size:
- pr_debug("CAIF: %s(): setsockopt"
- " CAIFSO_CHANNEL_CONFIG bad size\n", __func__);
return -EINVAL;
}
-
release_sock(&cf_sk->sk);
return 0;
default:
- pr_debug("CAIF: %s(): unhandled option %d\n", __func__, opt);
- return -EINVAL;
+ return -ENOPROTOOPT;
}
return 0;
bad_sol:
- pr_debug("CAIF: %s(): setsockopt bad level\n", __func__);
return -ENOPROTOOPT;
}
-static int caif_connect(struct socket *sock, struct sockaddr *uservaddr,
- int sockaddr_len, int flags)
+/*
+ * caif_connect() - Connect a CAIF Socket
+ * Copied and modified af_irda.c:irda_connect().
+ *
+ * Note : by consulting "errno", the user space caller may learn the cause
+ * of the failure. Most of them are visible in the function, others may come
+ * from subroutines called and are listed here :
+ * o -EAFNOSUPPORT: bad socket family or type.
+ * o -ESOCKTNOSUPPORT: bad socket type or protocol
+ * o -EINVAL: bad socket address, or CAIF link type
+ * o -ECONNREFUSED: remote end refused the connection.
+ * o -EINPROGRESS: connect request sent but timed out (or non-blocking)
+ * o -EISCONN: already connected.
+ * o -ETIMEDOUT: Connection timed out (send timeout)
+ * o -ENODEV: No link layer to send request
+ * o -ECONNRESET: Received Shutdown indication or lost link layer
+ * o -ENOMEM: Out of memory
+ *
+ * State Strategy:
+ * o sk_state: holds the CAIF_* protocol state, it's updated by
+ * caif_ctrl_cb.
+ * o sock->state: holds the SS_* socket state and is updated by connect and
+ * disconnect.
+ */
+static int caif_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags)
{
- struct caifsock *cf_sk = NULL;
- int result = -1;
- int mode = 0;
- int ret = -EIO;
struct sock *sk = sock->sk;
- BUG_ON(sk == NULL);
-
- cf_sk = container_of(sk, struct caifsock, sk);
-
- trace_printk("CAIF: %s(): cf_sk=%p OPEN=%d, TX_FLOW=%d, RX_FLOW=%d\n",
- __func__, cf_sk,
- STATE_IS_OPEN(cf_sk),
- TX_FLOW_IS_ON(cf_sk), RX_FLOW_IS_ON(cf_sk));
-
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
+ long timeo;
+ int err;
+ lock_sock(sk);
- if (sock->type == SOCK_SEQPACKET || sock->type == SOCK_STREAM)
- sock->state = SS_CONNECTING;
- else
+ err = -EAFNOSUPPORT;
+ if (uaddr->sa_family != AF_CAIF)
goto out;
- /* I want to be alone on cf_sk (except status and queue) */
- lock_sock(&(cf_sk->sk));
-
- if (sockaddr_len != sizeof(struct sockaddr_caif)) {
- pr_debug("CAIF: %s(): Bad address len (%ld,%lu)\n",
- __func__, (long) sockaddr_len,
- (long unsigned) sizeof(struct sockaddr_caif));
- ret = -EINVAL;
- goto open_error;
+ err = -ESOCKTNOSUPPORT;
+ if (unlikely(!(sk->sk_type == SOCK_STREAM &&
+ cf_sk->sk.sk_protocol == CAIFPROTO_AT) &&
+ sk->sk_type != SOCK_SEQPACKET))
+ goto out;
+ switch (sock->state) {
+ case SS_UNCONNECTED:
+ /* Normal case, a fresh connect */
+ caif_assert(sk->sk_state == CAIF_DISCONNECTED);
+ break;
+ case SS_CONNECTING:
+ switch (sk->sk_state) {
+ case CAIF_CONNECTED:
+ sock->state = SS_CONNECTED;
+ err = -EISCONN;
+ goto out;
+ case CAIF_DISCONNECTED:
+ /* Reconnect allowed */
+ break;
+ case CAIF_CONNECTING:
+ err = -EALREADY;
+ if (flags & O_NONBLOCK)
+ goto out;
+ goto wait_connect;
+ }
+ break;
+ case SS_CONNECTED:
+ caif_assert(sk->sk_state == CAIF_CONNECTED ||
+ sk->sk_state == CAIF_DISCONNECTED);
+ if (sk->sk_shutdown & SHUTDOWN_MASK) {
+ /* Allow re-connect after SHUTDOWN_IND */
+ caif_disconnect_client(&cf_sk->layer);
+ break;
+ }
+ /* No reconnect on a seqpacket socket */
+ err = -EISCONN;
+ goto out;
+ case SS_DISCONNECTING:
+ case SS_FREE:
+ caif_assert(1); /*Should never happen */
+ break;
}
+ sk->sk_state = CAIF_DISCONNECTED;
+ sock->state = SS_UNCONNECTED;
+ sk_stream_kill_queues(&cf_sk->sk);
- if (uservaddr->sa_family != AF_CAIF) {
- pr_debug("CAIF: %s(): Bad address family (%d)\n",
- __func__, uservaddr->sa_family);
- ret = -EAFNOSUPPORT;
- goto open_error;
- }
+ err = -EINVAL;
+ if (addr_len != sizeof(struct sockaddr_caif) ||
+ !uaddr)
+ goto out;
- memcpy(&cf_sk->conn_req.sockaddr, uservaddr,
+ memcpy(&cf_sk->conn_req.sockaddr, uaddr,
sizeof(struct sockaddr_caif));
- dbfs_atomic_inc(&cnt.num_open);
- mode = SKT_READ_FLAG | SKT_WRITE_FLAG;
-
- /* If socket is not open, make sure socket is in fully closed state */
- if (!STATE_IS_OPEN(cf_sk)) {
- /* Has link close response been received (if we ever sent it)?*/
- if (STATE_IS_PENDING(cf_sk)) {
- /*
- * Still waiting for close response from remote.
- * If opened non-blocking, report "would block"
- */
- if (flags & O_NONBLOCK) {
- pr_debug("CAIF: %s(): O_NONBLOCK"
- " && close pending\n", __func__);
- ret = -EAGAIN;
- goto open_error;
- }
-
- pr_debug("CAIF: %s(): Wait for close response"
- " from remote...\n", __func__);
-
- release_sock(&cf_sk->sk);
-
- /*
- * Blocking mode; close is pending and we need to wait
- * for its conclusion.
- */
- result =
- wait_event_interruptible(*cf_sk->sk.sk_sleep,
- !STATE_IS_PENDING(cf_sk));
-
- lock_sock(&(cf_sk->sk));
- if (result == -ERESTARTSYS) {
- pr_debug("CAIF: %s(): wait_event_interruptible"
- "woken by a signal (1)", __func__);
- ret = -ERESTARTSYS;
- goto open_error;
- }
- }
+ /* Move to connecting socket, start sending Connect Requests */
+ sock->state = SS_CONNECTING;
+ sk->sk_state = CAIF_CONNECTING;
+
+ dbfs_atomic_inc(&cnt.num_connect_req);
+ cf_sk->layer.receive = caif_sktrecv_cb;
+ err = caif_connect_client(&cf_sk->conn_req,
+ &cf_sk->layer);
+ if (err < 0) {
+ cf_sk->sk.sk_socket->state = SS_UNCONNECTED;
+ cf_sk->sk.sk_state = CAIF_DISCONNECTED;
+ goto out;
}
- /* socket is now either closed, pending open or open */
- if (STATE_IS_OPEN(cf_sk) && !STATE_IS_PENDING(cf_sk)) {
- /* Open */
- pr_debug("CAIF: %s(): Socket is already opened (cf_sk=%p)"
- " check access f_flags = 0x%x file_mode = 0x%x\n",
- __func__, cf_sk, mode, cf_sk->file_mode);
-
- } else {
- /* We are closed or pending open.
- * If closed: send link setup
- * If pending open: link setup already sent (we could have been
- * interrupted by a signal last time)
- */
- if (!STATE_IS_OPEN(cf_sk)) {
- /* First opening of file; connect lower layers: */
- /* Drain queue (very unlikely) */
- drain_queue(cf_sk);
-
- cf_sk->layer.receive = caif_sktrecv_cb;
- SET_STATE_OPEN(cf_sk);
- SET_PENDING_ON(cf_sk);
-
- /* Register this channel. */
- result =
- caif_connect_client(&cf_sk->conn_req,
- &cf_sk->layer);
- if (result < 0) {
- pr_debug("CAIF: %s(): can't register channel\n",
- __func__);
- ret = -EIO;
- SET_STATE_CLOSED(cf_sk);
- SET_PENDING_OFF(cf_sk);
- goto open_error;
- }
- dbfs_atomic_inc(&cnt.num_init);
- }
-
- /* If opened non-blocking, report "success".
- */
- if (flags & O_NONBLOCK) {
- pr_debug("CAIF: %s(): O_NONBLOCK success\n",
- __func__);
- ret = -EINPROGRESS;
- cf_sk->sk.sk_err = -EINPROGRESS;
- goto open_error;
- }
-
- trace_printk("CAIF: %s(): Wait for connect response\n",
- __func__);
+ err = -EINPROGRESS;
+wait_connect:
- /* release lock before waiting */
- release_sock(&cf_sk->sk);
-
- result =
- wait_event_interruptible(*cf_sk->sk.sk_sleep,
- !STATE_IS_PENDING(cf_sk));
-
- lock_sock(&(cf_sk->sk));
-
- if (result == -ERESTARTSYS) {
- pr_debug("CAIF: %s(): wait_event_interruptible"
- "woken by a signal (2)", __func__);
- ret = -ERESTARTSYS;
- goto open_error;
- }
-
- if (!STATE_IS_OPEN(cf_sk)) {
- /* Lower layers said "no" */
- pr_debug("CAIF: %s(): Closed received\n", __func__);
- ret = -EPIPE;
- goto open_error;
- }
+ if (sk->sk_state != CAIF_CONNECTED && (flags & O_NONBLOCK))
+ goto out;
- trace_printk("CAIF: %s(): Connect received\n", __func__);
+ timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);
+
+ release_sock(sk);
+ err = wait_event_interruptible_timeout(*sk_sleep(sk),
+ sk->sk_state != CAIF_CONNECTING,
+ timeo);
+ lock_sock(sk);
+ if (err < 0)
+ goto out; /* -ERESTARTSYS */
+ if (err == 0 && sk->sk_state != CAIF_CONNECTED) {
+ err = -ETIMEDOUT;
+ goto out;
}
- /* Open is ok */
- cf_sk->file_mode |= mode;
- trace_printk("CAIF: %s(): Connected - file mode = %x\n",
- __func__, cf_sk->file_mode);
-
- release_sock(&cf_sk->sk);
- return 0;
-open_error:
- sock->state = SS_UNCONNECTED;
- release_sock(&cf_sk->sk);
+ if (sk->sk_state != CAIF_CONNECTED) {
+ sock->state = SS_UNCONNECTED;
+ err = sock_error(sk);
+ if (!err)
+ err = -ECONNREFUSED;
+ goto out;
+ }
+ sock->state = SS_CONNECTED;
+ err = 0;
out:
- return ret;
+ release_sock(sk);
+ return err;
}
-static int caif_shutdown(struct socket *sock, int how)
+
+/*
+ * caif_release() - Disconnect a CAIF Socket
+ * Copied and modified af_irda.c:irda_release().
+ */
+static int caif_release(struct socket *sock)
{
- struct caifsock *cf_sk = NULL;
- int result = 0;
- int tx_flow_state_was_on;
struct sock *sk = sock->sk;
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
+ int res = 0;
- trace_printk("CAIF: %s(): enter\n", __func__);
- pr_debug("f_flags=%x\n", sock->file->f_flags);
-
- if (how != SHUT_RDWR)
- return -EOPNOTSUPP;
-
- cf_sk = container_of(sk, struct caifsock, sk);
- if (cf_sk == NULL) {
- pr_debug("CAIF: %s(): COULD NOT FIND SOCKET\n", __func__);
- return -EBADF;
- }
-
- /* I want to be alone on cf_sk (except status queue) */
- lock_sock(&(cf_sk->sk));
- sock_hold(&cf_sk->sk);
-
- /* IS_CLOSED have double meaning:
- * 1) Spontanous Remote Shutdown Request.
- * 2) Ack on a channel teardown(disconnect)
- * Must clear bit in case we previously received
- * remote shudown request.
- */
- if (STATE_IS_OPEN(cf_sk) && !STATE_IS_PENDING(cf_sk)) {
- SET_STATE_CLOSED(cf_sk);
- SET_PENDING_ON(cf_sk);
- tx_flow_state_was_on = TX_FLOW_IS_ON(cf_sk);
- SET_TX_FLOW_OFF(cf_sk);
-
- /* Hold the socket until DEINIT_RSP is received */
- sock_hold(&cf_sk->sk);
- result = caif_disconnect_client(&cf_sk->layer);
-
- if (result < 0) {
- pr_debug("CAIF: %s(): "
- "caif_disconnect_client() failed\n",
- __func__);
- SET_STATE_CLOSED(cf_sk);
- SET_PENDING_OFF(cf_sk);
- SET_TX_FLOW_OFF(cf_sk);
- release_sock(&cf_sk->sk);
- sock_put(&cf_sk->sk);
- return -EIO;
- }
+ if (!sk)
+ return 0;
- }
- if (STATE_IS_REMOTE_SHUTDOWN(cf_sk)) {
- SET_PENDING_OFF(cf_sk);
- SET_REMOTE_SHUTDOWN_OFF(cf_sk);
- }
+ set_tx_flow_off(cf_sk);
/*
- * Socket is no longer in state pending close,
- * and we can release the reference.
+ * Ensure that packets are not queued after this point in time.
+ * caif_queue_rcv_skb checks SOCK_DEAD holding the queue lock,
+ * this ensures no packets when sock is dead.
*/
+ spin_lock(&sk->sk_receive_queue.lock);
+ sock_set_flag(sk, SOCK_DEAD);
+ spin_unlock(&sk->sk_receive_queue.lock);
+ sock->sk = NULL;
- dbfs_atomic_inc(&cnt.num_close);
- drain_queue(cf_sk);
- SET_RX_FLOW_ON(cf_sk);
- cf_sk->file_mode = 0;
- sock_put(&cf_sk->sk);
- release_sock(&cf_sk->sk);
- if (!result && (sock->file->f_flags & O_NONBLOCK)) {
- pr_debug("nonblocking shutdown returing -EAGAIN\n");
- return -EAGAIN;
- } else
- return result;
-}
-
-static ssize_t caif_sock_no_sendpage(struct socket *sock,
- struct page *page,
- int offset, size_t size, int flags)
-{
- return -EOPNOTSUPP;
-}
-
-/* This function is called as part of close. */
-static int caif_release(struct socket *sock)
-{
- struct sock *sk = sock->sk;
- struct caifsock *cf_sk = NULL;
- int res;
- caif_assert(sk != NULL);
- cf_sk = container_of(sk, struct caifsock, sk);
+ dbfs_atomic_inc(&cnt.num_disconnect);
if (cf_sk->debugfs_socket_dir != NULL)
debugfs_remove_recursive(cf_sk->debugfs_socket_dir);
- res = caif_shutdown(sock, SHUT_RDWR);
- if (res && res != -EINPROGRESS)
- return res;
-
- /*
- * FIXME: Shutdown should probably be possible to do async
- * without flushing queues, allowing reception of frames while
- * waiting for DEINIT_IND.
- * Release should always block, to allow secure decoupling of
- * CAIF stack.
- */
- if (!(sock->file->f_flags & O_NONBLOCK)) {
- res = wait_event_interruptible(*cf_sk->sk.sk_sleep,
- !STATE_IS_PENDING(cf_sk));
-
- if (res == -ERESTARTSYS) {
- pr_debug("CAIF: %s(): wait_event_interruptible"
- "woken by a signal (1)", __func__);
- }
- }
lock_sock(&(cf_sk->sk));
+ sk->sk_state = CAIF_DISCONNECTED;
+ sk->sk_shutdown = SHUTDOWN_MASK;
- sock->sk = NULL;
+ if (cf_sk->sk.sk_socket->state == SS_CONNECTED ||
+ cf_sk->sk.sk_socket->state == SS_CONNECTING)
+ res = caif_disconnect_client(&cf_sk->layer);
- /* Detach the socket from its process context by making it orphan. */
- sock_orphan(sk);
+ cf_sk->sk.sk_socket->state = SS_DISCONNECTING;
+ wake_up_interruptible_poll(sk_sleep(sk), POLLERR|POLLHUP);
- /*
- * Setting SHUTDOWN_MASK means that both send and receive are shutdown
- * for the socket.
- */
- sk->sk_shutdown = SHUTDOWN_MASK;
+ sock_orphan(sk);
+ cf_sk->layer.dn = NULL;
+ sk_stream_kill_queues(&cf_sk->sk);
+ release_sock(sk);
+ sock_put(sk);
+ return res;
+}
- /*
- * Set the socket state to closed, the TCP_CLOSE macro is used when
- * closing any socket.
- */
+/* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
+static unsigned int caif_poll(struct file *file,
+ struct socket *sock, poll_table *wait)
+{
+ struct sock *sk = sock->sk;
+ unsigned int mask;
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
- /* Flush out this sockets receive queue. */
- drain_queue(cf_sk);
+ sock_poll_wait(file, sk_sleep(sk), wait);
+ mask = 0;
- /* Finally release the socket. */
- SET_STATE_PENDING_DESTROY(cf_sk);
+ /* exceptional events? */
+ if (sk->sk_err)
+ mask |= POLLERR;
+ if (sk->sk_shutdown == SHUTDOWN_MASK)
+ mask |= POLLHUP;
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ mask |= POLLRDHUP;
- release_sock(&cf_sk->sk);
+ /* readable? */
+ if (!skb_queue_empty(&sk->sk_receive_queue) ||
+ (sk->sk_shutdown & RCV_SHUTDOWN))
+ mask |= POLLIN | POLLRDNORM;
- sock_put(sk);
+ /* Connection-based need to check for termination and startup */
+ if (sk->sk_state == CAIF_DISCONNECTED)
+ mask |= POLLHUP;
/*
- * The rest of the cleanup will be handled from the
- * caif_sock_destructor
+ * we set writable also when the other side has shut down the
+ * connection. This prevents stuck sockets.
*/
- return res;
+ if (sock_writeable(sk) && tx_flow_is_on(cf_sk))
+ mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+
+ return mask;
}
-static const struct proto_ops caif_ops = {
+static const struct proto_ops caif_seqpacket_ops = {
+ .family = PF_CAIF,
+ .owner = THIS_MODULE,
+ .release = caif_release,
+ .bind = sock_no_bind,
+ .connect = caif_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = caif_poll,
+ .ioctl = sock_no_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = setsockopt,
+ .getsockopt = sock_no_getsockopt,
+ .sendmsg = caif_seqpkt_sendmsg,
+ .recvmsg = caif_seqpkt_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = sock_no_sendpage,
+};
+
+static const struct proto_ops caif_stream_ops = {
.family = PF_CAIF,
.owner = THIS_MODULE,
.release = caif_release,
@@ -1162,73 +1066,62 @@ static const struct proto_ops caif_ops = {
.poll = caif_poll,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
- .shutdown = caif_shutdown,
+ .shutdown = sock_no_shutdown,
.setsockopt = setsockopt,
.getsockopt = sock_no_getsockopt,
- .sendmsg = caif_sendmsg,
- .recvmsg = caif_recvmsg,
+ .sendmsg = caif_stream_sendmsg,
+ .recvmsg = caif_stream_recvmsg,
.mmap = sock_no_mmap,
- .sendpage = caif_sock_no_sendpage,
+ .sendpage = sock_no_sendpage,
};
/* This function is called when a socket is finally destroyed. */
static void caif_sock_destructor(struct sock *sk)
{
- struct caifsock *cf_sk = NULL;
- cf_sk = container_of(sk, struct caifsock, sk);
- /* Error checks. */
+ struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
caif_assert(!atomic_read(&sk->sk_wmem_alloc));
caif_assert(sk_unhashed(sk));
caif_assert(!sk->sk_socket);
if (!sock_flag(sk, SOCK_DEAD)) {
- pr_debug("CAIF: %s(): 0x%p", __func__, sk);
+ pr_info("Attempt to release alive CAIF socket: %p\n", sk);
return;
}
-
- if (STATE_IS_OPEN(cf_sk)) {
- pr_debug("CAIF: %s(): socket is opened (cf_sk=%p)"
- " file_mode = 0x%x\n", __func__,
- cf_sk, cf_sk->file_mode);
- return;
- }
- drain_queue(cf_sk);
- kfree(cf_sk->pktq);
-
- trace_printk("CAIF: %s(): caif_sock_destructor: Removing socket %s\n",
- __func__, cf_sk->name);
- atomic_dec(&caif_nr_socks);
+ sk_stream_kill_queues(&cf_sk->sk);
+ dbfs_atomic_dec(&cnt.caif_nr_socks);
}
static int caif_create(struct net *net, struct socket *sock, int protocol,
- int kern)
+ int kern)
{
struct sock *sk = NULL;
struct caifsock *cf_sk = NULL;
- int result = 0;
static struct proto prot = {.name = "PF_CAIF",
.owner = THIS_MODULE,
.obj_size = sizeof(struct caifsock),
};
+ if (!capable(CAP_SYS_ADMIN) && !capable(CAP_NET_ADMIN))
+ return -EPERM;
/*
* The sock->type specifies the socket type to use.
- * in SEQPACKET mode packet boundaries are enforced.
+ * The CAIF socket is a packet stream in the sense
+ * that it is packet based. CAIF trusts the reliability
+ * of the link, no resending is implemented.
*/
- if (sock->type != SOCK_SEQPACKET && sock->type != SOCK_STREAM)
+ if (sock->type == SOCK_SEQPACKET)
+ sock->ops = &caif_seqpacket_ops;
+ else if (sock->type == SOCK_STREAM)
+ sock->ops = &caif_stream_ops;
+ else
return -ESOCKTNOSUPPORT;
- if (net != &init_net)
- return -EAFNOSUPPORT;
-
if (protocol < 0 || protocol >= CAIFPROTO_MAX)
return -EPROTONOSUPPORT;
/*
- * Set the socket state to unconnected. The socket state is really
- * not used at all in the net/core or socket.c but the
+ * Set the socket state to unconnected. The socket state
+ * is really not used at all in the net/core or socket.c but the
* initialization makes sure that sock->state is not uninitialized.
*/
- sock->state = SS_UNCONNECTED;
-
sk = sk_alloc(net, PF_CAIF, GFP_KERNEL, &prot);
if (!sk)
return -ENOMEM;
@@ -1238,11 +1131,9 @@ static int caif_create(struct net *net, struct socket *sock, int protocol,
/* Store the protocol */
sk->sk_protocol = (unsigned char) protocol;
- spin_lock_init(&cf_sk->read_queue_len_lock);
-
- /* Fill in some information concerning the misc socket. */
- snprintf(cf_sk->name, sizeof(cf_sk->name), "cf_sk%d",
- atomic_read(&caif_nr_socks));
+ /* Sendbuf dictates the amount of outbound packets not yet sent */
+ sk->sk_sndbuf = CAIF_DEF_SNDBUF;
+ sk->sk_rcvbuf = CAIF_DEF_RCVBUF;
/*
* Lock in order to try to stop someone from opening the socket
@@ -1252,108 +1143,85 @@ static int caif_create(struct net *net, struct socket *sock, int protocol,
/* Initialize the nozero default sock structure data. */
sock_init_data(sock, sk);
- sock->ops = &caif_ops;
sk->sk_destruct = caif_sock_destructor;
- sk->sk_sndbuf = caif_sockbuf_size;
- sk->sk_rcvbuf = caif_sockbuf_size;
- cf_sk->pktq = cfpktq_create();
+ mutex_init(&cf_sk->readlock); /* single task reading lock */
+ cf_sk->layer.ctrlcmd = caif_ctrl_cb;
+ cf_sk->sk.sk_socket->state = SS_UNCONNECTED;
+ cf_sk->sk.sk_state = CAIF_DISCONNECTED;
- if (!cf_sk->pktq) {
- pr_err("CAIF: %s(): queue create failed.\n", __func__);
- result = -ENOMEM;
- release_sock(&cf_sk->sk);
- goto err_failed;
- }
- cf_sk->layer.ctrlcmd = caif_sktflowctrl_cb;
- SET_STATE_CLOSED(cf_sk);
- SET_PENDING_OFF(cf_sk);
- SET_TX_FLOW_OFF(cf_sk);
- SET_RX_FLOW_ON(cf_sk);
+ set_tx_flow_off(cf_sk);
+ set_rx_flow_on(cf_sk);
/* Set default options on configuration */
cf_sk->conn_req.priority = CAIF_PRIO_NORMAL;
- cf_sk->conn_req.link_selector = CAIF_LINK_HIGH_BANDW;
+ cf_sk->conn_req.link_selector = CAIF_LINK_LOW_LATENCY;
cf_sk->conn_req.protocol = protocol;
/* Increase the number of sockets created. */
- atomic_inc(&caif_nr_socks);
+ dbfs_atomic_inc(&cnt.caif_nr_socks);
+#ifdef CONFIG_DEBUG_FS
if (!IS_ERR(debugfsdir)) {
+ /* Fill in some information concerning the misc socket. */
+ snprintf(cf_sk->name, sizeof(cf_sk->name), "cfsk%d",
+ atomic_read(&cnt.caif_nr_socks));
+
cf_sk->debugfs_socket_dir =
debugfs_create_dir(cf_sk->name, debugfsdir);
- debugfs_create_u32("conn_state", S_IRUSR | S_IWUSR,
- cf_sk->debugfs_socket_dir, &cf_sk->conn_state);
+ debugfs_create_u32("sk_state", S_IRUSR | S_IWUSR,
+ cf_sk->debugfs_socket_dir,
+ (u32 *) &cf_sk->sk.sk_state);
debugfs_create_u32("flow_state", S_IRUSR | S_IWUSR,
cf_sk->debugfs_socket_dir, &cf_sk->flow_state);
- debugfs_create_u32("read_queue_len", S_IRUSR | S_IWUSR,
+ debugfs_create_u32("sk_rmem_alloc", S_IRUSR | S_IWUSR,
+ cf_sk->debugfs_socket_dir,
+ (u32 *) &cf_sk->sk.sk_rmem_alloc);
+ debugfs_create_u32("sk_wmem_alloc", S_IRUSR | S_IWUSR,
cf_sk->debugfs_socket_dir,
- (u32 *) &cf_sk->read_queue_len);
+ (u32 *) &cf_sk->sk.sk_wmem_alloc);
debugfs_create_u32("identity", S_IRUSR | S_IWUSR,
cf_sk->debugfs_socket_dir,
(u32 *) &cf_sk->layer.id);
}
+#endif
release_sock(&cf_sk->sk);
return 0;
-err_failed:
- sk_free(sk);
- return result;
}
+
static struct net_proto_family caif_family_ops = {
.family = PF_CAIF,
.create = caif_create,
.owner = THIS_MODULE,
};
-static int af_caif_init(void)
+int af_caif_init(void)
{
- int err;
- err = sock_register(&caif_family_ops);
-
+ int err = sock_register(&caif_family_ops);
if (!err)
return err;
-
return 0;
}
static int __init caif_sktinit_module(void)
{
- int stat;
#ifdef CONFIG_DEBUG_FS
- debugfsdir = debugfs_create_dir("chnl_skt", NULL);
+ debugfsdir = debugfs_create_dir("caif_sk", NULL);
if (!IS_ERR(debugfsdir)) {
- debugfs_create_u32("skb_inuse", S_IRUSR | S_IWUSR,
- debugfsdir,
- (u32 *) &cnt.skb_in_use);
- debugfs_create_u32("skb_alloc", S_IRUSR | S_IWUSR,
- debugfsdir,
- (u32 *) &cnt.skb_alloc);
- debugfs_create_u32("skb_free", S_IRUSR | S_IWUSR,
- debugfsdir,
- (u32 *) &cnt.skb_free);
debugfs_create_u32("num_sockets", S_IRUSR | S_IWUSR,
debugfsdir,
- (u32 *) &caif_nr_socks);
- debugfs_create_u32("num_open", S_IRUSR | S_IWUSR,
+ (u32 *) &cnt.caif_nr_socks);
+ debugfs_create_u32("num_connect_req", S_IRUSR | S_IWUSR,
debugfsdir,
- (u32 *) &cnt.num_open);
- debugfs_create_u32("num_close", S_IRUSR | S_IWUSR,
+ (u32 *) &cnt.num_connect_req);
+ debugfs_create_u32("num_connect_resp", S_IRUSR | S_IWUSR,
debugfsdir,
- (u32 *) &cnt.num_close);
- debugfs_create_u32("num_init", S_IRUSR | S_IWUSR,
+ (u32 *) &cnt.num_connect_resp);
+ debugfs_create_u32("num_connect_fail_resp", S_IRUSR | S_IWUSR,
debugfsdir,
- (u32 *) &cnt.num_init);
- debugfs_create_u32("num_init_resp", S_IRUSR | S_IWUSR,
+ (u32 *) &cnt.num_connect_fail_resp);
+ debugfs_create_u32("num_disconnect", S_IRUSR | S_IWUSR,
debugfsdir,
- (u32 *) &cnt.num_init_resp);
- debugfs_create_u32("num_init_fail_resp", S_IRUSR | S_IWUSR,
- debugfsdir,
- (u32 *) &cnt.num_init_fail_resp);
- debugfs_create_u32("num_deinit", S_IRUSR | S_IWUSR,
- debugfsdir,
- (u32 *) &cnt.num_deinit);
- debugfs_create_u32("num_deinit_resp", S_IRUSR | S_IWUSR,
- debugfsdir,
- (u32 *) &cnt.num_deinit_resp);
+ (u32 *) &cnt.num_disconnect);
debugfs_create_u32("num_remote_shutdown_ind",
S_IRUSR | S_IWUSR, debugfsdir,
(u32 *) &cnt.num_remote_shutdown_ind);
@@ -1371,13 +1239,7 @@ static int __init caif_sktinit_module(void)
(u32 *) &cnt.num_rx_flow_on);
}
#endif
- stat = af_caif_init();
- if (stat) {
- pr_err("CAIF: %s(): Failed to initialize CAIF socket layer.",
- __func__);
- return stat;
- }
- return 0;
+ return af_caif_init();
}
static void __exit caif_sktexit_module(void)
@@ -1386,6 +1248,5 @@ static void __exit caif_sktexit_module(void)
if (debugfsdir != NULL)
debugfs_remove_recursive(debugfsdir);
}
-
module_init(caif_sktinit_module);
module_exit(caif_sktexit_module);
diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c
index c873e3d4387..471c62939fa 100644
--- a/net/caif/cfcnfg.c
+++ b/net/caif/cfcnfg.c
@@ -51,12 +51,11 @@ struct cfcnfg {
struct cfcnfg_phyinfo phy_layers[MAX_PHY_LAYERS];
};
-static void cncfg_linkup_rsp(struct cflayer *layer, u8 linkid,
+static void cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id,
enum cfctrl_srv serv, u8 phyid,
struct cflayer *adapt_layer);
-static void cncfg_linkdestroy_rsp(struct cflayer *layer, u8 linkid,
- struct cflayer *client_layer);
-static void cncfg_reject_rsp(struct cflayer *layer, u8 linkid,
+static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id);
+static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id,
struct cflayer *adapt_layer);
static void cfctrl_resp_func(void);
static void cfctrl_enum_resp(void);
@@ -82,13 +81,13 @@ struct cfcnfg *cfcnfg_create(void)
resp = cfctrl_get_respfuncs(this->ctrl);
resp->enum_rsp = cfctrl_enum_resp;
resp->linkerror_ind = cfctrl_resp_func;
- resp->linkdestroy_rsp = cncfg_linkdestroy_rsp;
+ resp->linkdestroy_rsp = cfcnfg_linkdestroy_rsp;
resp->sleep_rsp = cfctrl_resp_func;
resp->wake_rsp = cfctrl_resp_func;
resp->restart_rsp = cfctrl_resp_func;
resp->radioset_rsp = cfctrl_resp_func;
- resp->linksetup_rsp = cncfg_linkup_rsp;
- resp->reject_rsp = cncfg_reject_rsp;
+ resp->linksetup_rsp = cfcnfg_linkup_rsp;
+ resp->reject_rsp = cfcnfg_reject_rsp;
this->last_phyid = 1;
@@ -175,142 +174,82 @@ int cfcnfg_get_named(struct cfcnfg *cnfg, char *name)
return 0;
}
-/*
- * NOTE: What happens on destroy failure:
- * 1a) No response - Too early
- * This will not happen because enumerate has already
- * completed.
- * 1b) No response - FATAL
- * Not handled, but this should be a CAIF PROTOCOL ERROR
- * Modem error, response is really expected - this
- * case is not really handled.
- * 2) O/E-bit indicate error
- * Ignored - this link is destroyed anyway.
- * 3) Not able to match on request
- * Not handled, but this should be a CAIF PROTOCOL ERROR
- * 4) Link-Error - (no response)
- * Not handled, but this should be a CAIF PROTOCOL ERROR
- */
-
-int cfcnfg_del_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer)
+int cfcnfg_disconn_adapt_layer(struct cfcnfg *cnfg, struct cflayer *adap_layer)
{
u8 channel_id = 0;
int ret = 0;
+ struct cflayer *servl = NULL;
struct cfcnfg_phyinfo *phyinfo = NULL;
u8 phyid = 0;
-
caif_assert(adap_layer != NULL);
channel_id = adap_layer->id;
- if (channel_id == 0) {
+ if (adap_layer->dn == NULL || channel_id == 0) {
pr_err("CAIF: %s():adap_layer->id is 0\n", __func__);
ret = -ENOTCONN;
goto end;
}
-
- if (adap_layer->dn == NULL) {
- pr_err("CAIF: %s():adap_layer->dn is NULL\n", __func__);
- ret = -ENODEV;
- goto end;
- }
-
- if (adap_layer->dn != NULL)
- phyid = cfsrvl_getphyid(adap_layer->dn);
-
- phyinfo = cfcnfg_get_phyinfo(cnfg, phyid);
- if (phyinfo == NULL) {
- pr_warning("CAIF: %s(): No interface to send disconnect to\n",
- __func__);
- ret = -ENODEV;
+ servl = cfmuxl_remove_uplayer(cnfg->mux, channel_id);
+ if (servl == NULL)
goto end;
- }
-
- if (phyinfo->id != phyid
- || phyinfo->phy_layer->id != phyid
- || phyinfo->frm_layer->id != phyid) {
-
- pr_err("CAIF: %s(): Inconsistency in phy registration\n",
- __func__);
+ layer_set_up(servl, NULL);
+ ret = cfctrl_linkdown_req(cnfg->ctrl, channel_id, adap_layer);
+ if (servl == NULL) {
+ pr_err("CAIF: %s(): PROTOCOL ERROR "
+ "- Error removing service_layer Channel_Id(%d)",
+ __func__, channel_id);
ret = -EINVAL;
goto end;
}
+ caif_assert(channel_id == servl->id);
+ if (adap_layer->dn != NULL) {
+ phyid = cfsrvl_getphyid(adap_layer->dn);
- ret = cfctrl_linkdown_req(cnfg->ctrl, channel_id, adap_layer);
-
-end:
+ phyinfo = cfcnfg_get_phyinfo(cnfg, phyid);
+ if (phyinfo == NULL) {
+ pr_warning("CAIF: %s(): "
+ "No interface to send disconnect to\n",
+ __func__);
+ ret = -ENODEV;
+ goto end;
+ }
+ if (phyinfo->id != phyid ||
+ phyinfo->phy_layer->id != phyid ||
+ phyinfo->frm_layer->id != phyid) {
+ pr_err("CAIF: %s(): "
+ "Inconsistency in phy registration\n",
+ __func__);
+ ret = -EINVAL;
+ goto end;
+ }
+ }
if (phyinfo != NULL && --phyinfo->phy_ref_count == 0 &&
phyinfo->phy_layer != NULL &&
phyinfo->phy_layer->modemcmd != NULL) {
phyinfo->phy_layer->modemcmd(phyinfo->phy_layer,
_CAIF_MODEMCMD_PHYIF_USELESS);
}
+end:
+ cfsrvl_put(servl);
+ cfctrl_cancel_req(cnfg->ctrl, adap_layer);
+ if (adap_layer->ctrlcmd != NULL)
+ adap_layer->ctrlcmd(adap_layer, CAIF_CTRLCMD_DEINIT_RSP, 0);
return ret;
}
-EXPORT_SYMBOL(cfcnfg_del_adapt_layer);
+EXPORT_SYMBOL(cfcnfg_disconn_adapt_layer);
-static void cncfg_linkdestroy_rsp(struct cflayer *layer, u8 linkid,
- struct cflayer *client_layer)
+void cfcnfg_release_adap_layer(struct cflayer *adap_layer)
{
- struct cfcnfg *cnfg = container_obj(layer);
- struct cflayer *servl;
-
- /*
- * 1) Remove service from the MUX layer. The MUX must
- * guarante that no more payload sent "upwards" (receive)
- */
- servl = cfmuxl_remove_uplayer(cnfg->mux, linkid);
-
- if (servl == NULL) {
- pr_err("CAIF: %s(): PROTOCOL ERROR "
- "- Error removing service_layer Linkid(%d)",
- __func__, linkid);
- return;
- }
- caif_assert(linkid == servl->id);
-
- if (servl != client_layer && servl->up != client_layer) {
- pr_err("CAIF: %s(): Error removing service_layer "
- "Linkid(%d) %p %p",
- __func__, linkid, (void *) servl,
- (void *) client_layer);
- return;
- }
-
- /*
- * 2) DEINIT_RSP must guarantee that no more packets are transmitted
- * from client (adap_layer) when it returns.
- */
-
- if (servl->ctrlcmd == NULL) {
- pr_err("CAIF: %s(): Error servl->ctrlcmd == NULL", __func__);
- return;
- }
-
- servl->ctrlcmd(servl, CAIF_CTRLCMD_DEINIT_RSP, 0);
-
- /* 3) It is now safe to destroy the service layer. */
- cfservl_destroy(servl);
+ if (adap_layer->dn)
+ cfsrvl_put(adap_layer->dn);
}
+EXPORT_SYMBOL(cfcnfg_release_adap_layer);
-/*
- * NOTE: What happens on linksetup failure:
- * 1a) No response - Too early
- * This will not happen because enumerate is secured
- * before using interface.
- * 1b) No response - FATAL
- * Not handled, but this should be a CAIF PROTOCOL ERROR
- * Modem error, response is really expected - this case is
- * not really handled.
- * 2) O/E-bit indicate error
- * Handled in cnfg_reject_rsp
- * 3) Not able to match on request
- * Not handled, but this should be a CAIF PROTOCOL ERROR
- * 4) Link-Error - (no response)
- * Not handled, but this should be a CAIF PROTOCOL ERROR
- */
+static void cfcnfg_linkdestroy_rsp(struct cflayer *layer, u8 channel_id)
+{
+}
-int
-cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg,
+int cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg,
struct cfctrl_link_param *param,
struct cflayer *adap_layer)
{
@@ -340,12 +279,11 @@ cfcnfg_add_adaptation_layer(struct cfcnfg *cnfg,
param->phyid);
/* FIXME: ENUMERATE INITIALLY WHEN ACTIVATING PHYSICAL INTERFACE */
cfctrl_enum_req(cnfg->ctrl, param->phyid);
- cfctrl_linkup_request(cnfg->ctrl, param, adap_layer);
- return 0;
+ return cfctrl_linkup_request(cnfg->ctrl, param, adap_layer);
}
EXPORT_SYMBOL(cfcnfg_add_adaptation_layer);
-static void cncfg_reject_rsp(struct cflayer *layer, u8 linkid,
+static void cfcnfg_reject_rsp(struct cflayer *layer, u8 channel_id,
struct cflayer *adapt_layer)
{
if (adapt_layer != NULL && adapt_layer->ctrlcmd != NULL)
@@ -354,15 +292,17 @@ static void cncfg_reject_rsp(struct cflayer *layer, u8 linkid,
}
static void
-cncfg_linkup_rsp(struct cflayer *layer, u8 linkid, enum cfctrl_srv serv,
+cfcnfg_linkup_rsp(struct cflayer *layer, u8 channel_id, enum cfctrl_srv serv,
u8 phyid, struct cflayer *adapt_layer)
{
struct cfcnfg *cnfg = container_obj(layer);
struct cflayer *servicel = NULL;
struct cfcnfg_phyinfo *phyinfo;
if (adapt_layer == NULL) {
- pr_err("CAIF: %s(): PROTOCOL ERROR "
- "- LinkUp Request/Response did not match\n", __func__);
+ pr_debug("CAIF: %s(): link setup response "
+ "but no client exist, send linkdown back\n",
+ __func__);
+ cfctrl_linkdown_req(cnfg->ctrl, channel_id, NULL);
return;
}
@@ -383,26 +323,26 @@ cncfg_linkup_rsp(struct cflayer *layer, u8 linkid, enum cfctrl_srv serv,
_CAIF_MODEMCMD_PHYIF_USEFULL);
}
- adapt_layer->id = linkid;
+ adapt_layer->id = channel_id;
switch (serv) {
case CFCTRL_SRV_VEI:
- servicel = cfvei_create(linkid, &phyinfo->dev_info);
+ servicel = cfvei_create(channel_id, &phyinfo->dev_info);
break;
case CFCTRL_SRV_DATAGRAM:
- servicel = cfdgml_create(linkid, &phyinfo->dev_info);
+ servicel = cfdgml_create(channel_id, &phyinfo->dev_info);
break;
case CFCTRL_SRV_RFM:
- servicel = cfrfml_create(linkid, &phyinfo->dev_info);
+ servicel = cfrfml_create(channel_id, &phyinfo->dev_info);
break;
case CFCTRL_SRV_UTIL:
- servicel = cfutill_create(linkid, &phyinfo->dev_info);
+ servicel = cfutill_create(channel_id, &phyinfo->dev_info);
break;
case CFCTRL_SRV_VIDEO:
- servicel = cfvidl_create(linkid, &phyinfo->dev_info);
+ servicel = cfvidl_create(channel_id, &phyinfo->dev_info);
break;
case CFCTRL_SRV_DBG:
- servicel = cfdbgl_create(linkid, &phyinfo->dev_info);
+ servicel = cfdbgl_create(channel_id, &phyinfo->dev_info);
break;
default:
pr_err("CAIF: %s(): Protocol error. "
@@ -415,9 +355,10 @@ cncfg_linkup_rsp(struct cflayer *layer, u8 linkid, enum cfctrl_srv serv,
return;
}
layer_set_dn(servicel, cnfg->mux);
- cfmuxl_set_uplayer(cnfg->mux, servicel, linkid);
+ cfmuxl_set_uplayer(cnfg->mux, servicel, channel_id);
layer_set_up(servicel, adapt_layer);
layer_set_dn(adapt_layer, servicel);
+ cfsrvl_get(servicel);
servicel->ctrlcmd(servicel, CAIF_CTRLCMD_INIT_RSP, 0);
}
diff --git a/net/caif/cfctrl.c b/net/caif/cfctrl.c
index 11f80140f3c..a521d32cfe5 100644
--- a/net/caif/cfctrl.c
+++ b/net/caif/cfctrl.c
@@ -32,6 +32,7 @@ static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
struct cflayer *cfctrl_create(void)
{
+ struct dev_info dev_info;
struct cfctrl *this =
kmalloc(sizeof(struct cfctrl), GFP_ATOMIC);
if (!this) {
@@ -39,12 +40,13 @@ struct cflayer *cfctrl_create(void)
return NULL;
}
caif_assert(offsetof(struct cfctrl, serv.layer) == 0);
+ memset(&dev_info, 0, sizeof(dev_info));
+ dev_info.id = 0xff;
memset(this, 0, sizeof(*this));
+ cfsrvl_init(&this->serv, 0, &dev_info);
spin_lock_init(&this->info_list_lock);
atomic_set(&this->req_seq_no, 1);
atomic_set(&this->rsp_seq_no, 1);
- this->serv.dev_info.id = 0xff;
- this->serv.layer.id = 0;
this->serv.layer.receive = cfctrl_recv;
sprintf(this->serv.layer.name, "ctrl");
this->serv.layer.ctrlcmd = cfctrl_ctrlcmd;
@@ -127,20 +129,6 @@ void cfctrl_insert_req(struct cfctrl *ctrl,
spin_unlock(&ctrl->info_list_lock);
}
-static void cfctrl_insert_req2(struct cfctrl *ctrl, enum cfctrl_cmd cmd,
- u8 linkid, struct cflayer *user_layer)
-{
- struct cfctrl_request_info *req = kmalloc(sizeof(*req), GFP_KERNEL);
- if (!req) {
- pr_warning("CAIF: %s(): Out of memory\n", __func__);
- return;
- }
- req->client_layer = user_layer;
- req->cmd = cmd;
- req->channel_id = linkid;
- cfctrl_insert_req(ctrl, req);
-}
-
/* Compare and remove request */
struct cfctrl_request_info *cfctrl_remove_req(struct cfctrl *ctrl,
struct cfctrl_request_info *req)
@@ -234,7 +222,7 @@ void cfctrl_enum_req(struct cflayer *layer, u8 physlinkid)
}
}
-void cfctrl_linkup_request(struct cflayer *layer,
+int cfctrl_linkup_request(struct cflayer *layer,
struct cfctrl_link_param *param,
struct cflayer *user_layer)
{
@@ -248,7 +236,7 @@ void cfctrl_linkup_request(struct cflayer *layer,
struct cfpkt *pkt = cfpkt_create(CFPKT_CTRL_PKT_LEN);
if (!pkt) {
pr_warning("CAIF: %s(): Out of memory\n", __func__);
- return;
+ return -ENOMEM;
}
cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_SETUP);
cfpkt_addbdy(pkt, (param->chtype << 4) + param->linktype);
@@ -294,11 +282,12 @@ void cfctrl_linkup_request(struct cflayer *layer,
default:
pr_warning("CAIF: %s():Request setup of bad link type = %d\n",
__func__, param->linktype);
+ return -EINVAL;
}
req = kmalloc(sizeof(*req), GFP_KERNEL);
if (!req) {
pr_warning("CAIF: %s(): Out of memory\n", __func__);
- return;
+ return -ENOMEM;
}
memset(req, 0, sizeof(*req));
req->client_layer = user_layer;
@@ -306,6 +295,11 @@ void cfctrl_linkup_request(struct cflayer *layer,
req->param = *param;
cfctrl_insert_req(cfctrl, req);
init_info(cfpkt_info(pkt), cfctrl);
+ /*
+ * NOTE:Always send linkup and linkdown request on the same
+ * device as the payload. Otherwise old queued up payload
+ * might arrive with the newly allocated channel ID.
+ */
cfpkt_info(pkt)->dev_info->id = param->phyid;
ret =
cfctrl->serv.layer.dn->transmit(cfctrl->serv.layer.dn, pkt);
@@ -313,7 +307,9 @@ void cfctrl_linkup_request(struct cflayer *layer,
pr_err("CAIF: %s(): Could not transmit linksetup request\n",
__func__);
cfpkt_destroy(pkt);
+ return -ENODEV;
}
+ return 0;
}
int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid,
@@ -326,7 +322,6 @@ int cfctrl_linkdown_req(struct cflayer *layer, u8 channelid,
pr_warning("CAIF: %s(): Out of memory\n", __func__);
return -ENOMEM;
}
- cfctrl_insert_req2(cfctrl, CFCTRL_CMD_LINK_DESTROY, channelid, client);
cfpkt_addbdy(pkt, CFCTRL_CMD_LINK_DESTROY);
cfpkt_addbdy(pkt, channelid);
init_info(cfpkt_info(pkt), cfctrl);
@@ -392,6 +387,38 @@ void cfctrl_getstartreason_req(struct cflayer *layer)
}
+void cfctrl_cancel_req(struct cflayer *layr, struct cflayer *adap_layer)
+{
+ struct cfctrl_request_info *p, *req;
+ struct cfctrl *ctrl = container_obj(layr);
+ spin_lock(&ctrl->info_list_lock);
+
+ if (ctrl->first_req == NULL) {
+ spin_unlock(&ctrl->info_list_lock);
+ return;
+ }
+
+ if (ctrl->first_req->client_layer == adap_layer) {
+
+ req = ctrl->first_req;
+ ctrl->first_req = ctrl->first_req->next;
+ kfree(req);
+ }
+
+ p = ctrl->first_req;
+ while (p != NULL && p->next != NULL) {
+ if (p->next->client_layer == adap_layer) {
+
+ req = p->next;
+ p->next = p->next->next;
+ kfree(p->next);
+ }
+ p = p->next;
+ }
+
+ spin_unlock(&ctrl->info_list_lock);
+}
+
static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
{
u8 cmdrsp;
@@ -409,11 +436,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
cmd = cmdrsp & CFCTRL_CMD_MASK;
if (cmd != CFCTRL_CMD_LINK_ERR
&& CFCTRL_RSP_BIT != (CFCTRL_RSP_BIT & cmdrsp)) {
- if (handle_loop(cfctrl, cmd, pkt) == CAIF_FAILURE) {
- pr_info("CAIF: %s() CAIF Protocol error:"
- "Response bit not set\n", __func__);
- goto error;
- }
+ if (handle_loop(cfctrl, cmd, pkt) == CAIF_FAILURE)
+ cmdrsp |= CFCTRL_ERR_BIT;
}
switch (cmd) {
@@ -451,12 +475,16 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
switch (serv) {
case CFCTRL_SRV_VEI:
case CFCTRL_SRV_DBG:
+ if (CFCTRL_ERR_BIT & cmdrsp)
+ break;
/* Link ID */
cfpkt_extr_head(pkt, &linkid, 1);
break;
case CFCTRL_SRV_VIDEO:
cfpkt_extr_head(pkt, &tmp, 1);
linkparam.u.video.connid = tmp;
+ if (CFCTRL_ERR_BIT & cmdrsp)
+ break;
/* Link ID */
cfpkt_extr_head(pkt, &linkid, 1);
break;
@@ -465,6 +493,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
cfpkt_extr_head(pkt, &tmp32, 4);
linkparam.u.datagram.connid =
le32_to_cpu(tmp32);
+ if (CFCTRL_ERR_BIT & cmdrsp)
+ break;
/* Link ID */
cfpkt_extr_head(pkt, &linkid, 1);
break;
@@ -483,6 +513,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
*cp++ = tmp;
*cp = '\0';
+ if (CFCTRL_ERR_BIT & cmdrsp)
+ break;
/* Link ID */
cfpkt_extr_head(pkt, &linkid, 1);
@@ -519,6 +551,8 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
cfpkt_extr_head(pkt, &tmp, 1);
*cp++ = tmp;
}
+ if (CFCTRL_ERR_BIT & cmdrsp)
+ break;
/* Link ID */
cfpkt_extr_head(pkt, &linkid, 1);
/* Length */
@@ -560,13 +594,7 @@ static int cfctrl_recv(struct cflayer *layer, struct cfpkt *pkt)
break;
case CFCTRL_CMD_LINK_DESTROY:
cfpkt_extr_head(pkt, &linkid, 1);
- rsp.cmd = cmd;
- rsp.channel_id = linkid;
- req = cfctrl_remove_req(cfctrl, &rsp);
- cfctrl->res.linkdestroy_rsp(cfctrl->serv.layer.up, linkid,
- req ? req->client_layer : NULL);
- if (req != NULL)
- kfree(req);
+ cfctrl->res.linkdestroy_rsp(cfctrl->serv.layer.up, linkid);
break;
case CFCTRL_CMD_LINK_ERR:
pr_err("CAIF: %s(): Frame Error Indication received\n",
@@ -608,7 +636,7 @@ static void cfctrl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
case CAIF_CTRLCMD_FLOW_OFF_IND:
spin_lock(&this->info_list_lock);
if (this->first_req != NULL) {
- pr_warning("CAIF: %s(): Received flow off in "
+ pr_debug("CAIF: %s(): Received flow off in "
"control layer", __func__);
}
spin_unlock(&this->info_list_lock);
@@ -633,6 +661,7 @@ static int handle_loop(struct cfctrl *ctrl, int cmd, struct cfpkt *pkt)
if (!ctrl->loop_linkused[linkid])
goto found;
spin_unlock(&ctrl->loop_linkid_lock);
+ pr_err("CAIF: %s(): Out of link-ids\n", __func__);
return -EINVAL;
found:
if (!ctrl->loop_linkused[linkid])
diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c
index 6fb9f9e96cf..7372f27f1d3 100644
--- a/net/caif/cfmuxl.c
+++ b/net/caif/cfmuxl.c
@@ -62,6 +62,7 @@ int cfmuxl_set_uplayer(struct cflayer *layr, struct cflayer *up, u8 linkid)
{
struct cfmuxl *muxl = container_obj(layr);
spin_lock(&muxl->receive_lock);
+ cfsrvl_get(up);
list_add(&up->node, &muxl->srvl_list);
spin_unlock(&muxl->receive_lock);
return 0;
@@ -172,8 +173,11 @@ struct cflayer *cfmuxl_remove_uplayer(struct cflayer *layr, u8 id)
struct cfmuxl *muxl = container_obj(layr);
spin_lock(&muxl->receive_lock);
up = get_up(muxl, id);
+ if (up == NULL)
+ return NULL;
memset(muxl->up_cache, 0, sizeof(muxl->up_cache));
list_del(&up->node);
+ cfsrvl_put(up);
spin_unlock(&muxl->receive_lock);
return up;
}
@@ -203,8 +207,9 @@ static int cfmuxl_receive(struct cflayer *layr, struct cfpkt *pkt)
*/
return /* CFGLU_EPROT; */ 0;
}
-
+ cfsrvl_get(up);
ret = up->receive(up, pkt);
+ cfsrvl_put(up);
return ret;
}
diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c
index d470c51c643..aff31f34528 100644
--- a/net/caif/cfsrvl.c
+++ b/net/caif/cfsrvl.c
@@ -158,6 +158,13 @@ void cfsrvl_init(struct cfsrvl *service,
service->layer.ctrlcmd = cfservl_ctrlcmd;
service->layer.modemcmd = cfservl_modemcmd;
service->dev_info = *dev_info;
+ kref_init(&service->ref);
+}
+
+void cfsrvl_release(struct kref *kref)
+{
+ struct cfsrvl *service = container_of(kref, struct cfsrvl, ref);
+ kfree(service);
}
bool cfsrvl_ready(struct cfsrvl *service, int *err)
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index f622ff1d39b..610966abe2d 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -22,10 +22,10 @@
#include <net/caif/cfpkt.h>
#include <net/caif/caif_dev.h>
-#define CAIF_CONNECT_TIMEOUT 30
+/* GPRS PDP connection has MTU to 1500 */
#define SIZE_MTU 1500
-#define SIZE_MTU_MAX 4080
-#define SIZE_MTU_MIN 68
+/* 5 sec. connect timeout */
+#define CONNECT_TIMEOUT (5 * HZ)
#define CAIF_NET_DEFAULT_QUEUE_LEN 500
#undef pr_debug
@@ -37,6 +37,13 @@ static LIST_HEAD(chnl_net_list);
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("caif");
+enum caif_states {
+ CAIF_CONNECTED = 1,
+ CAIF_CONNECTING,
+ CAIF_DISCONNECTED,
+ CAIF_SHUTDOWN
+};
+
struct chnl_net {
struct cflayer chnl;
struct net_device_stats stats;
@@ -47,7 +54,7 @@ struct chnl_net {
wait_queue_head_t netmgmt_wq;
/* Flow status to remember and control the transmission. */
bool flowenabled;
- bool pending_close;
+ enum caif_states state;
};
static void robust_list_del(struct list_head *delete_node)
@@ -58,15 +65,16 @@ static void robust_list_del(struct list_head *delete_node)
list_for_each_safe(list_node, n, &chnl_net_list) {
if (list_node == delete_node) {
list_del(list_node);
- break;
+ return;
}
}
+ WARN_ON(1);
}
static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt)
{
struct sk_buff *skb;
- struct chnl_net *priv = NULL;
+ struct chnl_net *priv = container_of(layr, struct chnl_net, chnl);
int pktlen;
int err = 0;
@@ -91,7 +99,6 @@ static int chnl_recv_cb(struct cflayer *layr, struct cfpkt *pkt)
else
skb->ip_summed = CHECKSUM_NONE;
- /* FIXME: Drivers should call this in tasklet context. */
if (in_interrupt())
netif_rx(skb);
else
@@ -117,23 +124,25 @@ static void close_work(struct work_struct *work)
struct chnl_net *dev = NULL;
struct list_head *list_node;
struct list_head *_tmp;
- rtnl_lock();
+ /* May be called with or without RTNL lock held */
+ int islocked = rtnl_is_locked();
+ if (!islocked)
+ rtnl_lock();
list_for_each_safe(list_node, _tmp, &chnl_net_list) {
dev = list_entry(list_node, struct chnl_net, list_field);
- if (!dev->pending_close)
- continue;
- list_del(list_node);
- delete_device(dev);
+ if (dev->state == CAIF_SHUTDOWN)
+ dev_close(dev->netdev);
}
- rtnl_unlock();
+ if (!islocked)
+ rtnl_unlock();
}
static DECLARE_WORK(close_worker, close_work);
static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow,
int phyid)
{
- struct chnl_net *priv;
- pr_debug("CAIF: %s(): NET flowctrl func called flow: %s.\n",
+ struct chnl_net *priv = container_of(layr, struct chnl_net, chnl);
+ pr_debug("CAIF: %s(): NET flowctrl func called flow: %s\n",
__func__,
flow == CAIF_CTRLCMD_FLOW_ON_IND ? "ON" :
flow == CAIF_CTRLCMD_INIT_RSP ? "INIT" :
@@ -143,21 +152,31 @@ static void chnl_flowctrl_cb(struct cflayer *layr, enum caif_ctrlcmd flow,
flow == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND ?
"REMOTE_SHUTDOWN" : "UKNOWN CTRL COMMAND");
- priv = container_of(layr, struct chnl_net, chnl);
+
switch (flow) {
case CAIF_CTRLCMD_FLOW_OFF_IND:
+ priv->flowenabled = false;
+ netif_stop_queue(priv->netdev);
+ break;
case CAIF_CTRLCMD_DEINIT_RSP:
+ priv->state = CAIF_DISCONNECTED;
+ break;
case CAIF_CTRLCMD_INIT_FAIL_RSP:
+ priv->state = CAIF_DISCONNECTED;
+ wake_up_interruptible(&priv->netmgmt_wq);
+ break;
case CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND:
- priv->flowenabled = false;
+ priv->state = CAIF_SHUTDOWN;
netif_tx_disable(priv->netdev);
- pr_warning("CAIF: %s(): done\n", __func__);
- priv->pending_close = 1;
schedule_work(&close_worker);
break;
case CAIF_CTRLCMD_FLOW_ON_IND:
+ priv->flowenabled = true;
+ netif_wake_queue(priv->netdev);
+ break;
case CAIF_CTRLCMD_INIT_RSP:
+ priv->state = CAIF_CONNECTED;
priv->flowenabled = true;
netif_wake_queue(priv->netdev);
wake_up_interruptible(&priv->netmgmt_wq);
@@ -194,9 +213,6 @@ static int chnl_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
pkt = cfpkt_fromnative(CAIF_DIR_OUT, (void *) skb);
- pr_debug("CAIF: %s(): transmit inst %s %d,%p\n",
- __func__, dev->name, priv->chnl.dn->id, &priv->chnl.dn);
-
/* Send the packet down the stack. */
result = priv->chnl.dn->transmit(priv->chnl.dn, pkt);
if (result) {
@@ -217,61 +233,59 @@ static int chnl_net_open(struct net_device *dev)
struct chnl_net *priv = NULL;
int result = -1;
ASSERT_RTNL();
-
priv = netdev_priv(dev);
- pr_debug("CAIF: %s(): dev name: %s\n", __func__, priv->name);
-
if (!priv) {
pr_debug("CAIF: %s(): chnl_net_open: no priv\n", __func__);
return -ENODEV;
}
- result = caif_connect_client(&priv->conn_req, &priv->chnl);
- if (result != 0) {
- pr_debug("CAIF: %s(): err: "
- "Unable to register and open device, Err:%d\n",
- __func__,
- result);
- return -ENODEV;
+
+ if (priv->state != CAIF_CONNECTING) {
+ priv->state = CAIF_CONNECTING;
+ result = caif_connect_client(&priv->conn_req, &priv->chnl);
+ if (result != 0) {
+ priv->state = CAIF_DISCONNECTED;
+ pr_debug("CAIF: %s(): err: "
+ "Unable to register and open device,"
+ " Err:%d\n",
+ __func__,
+ result);
+ return result;
+ }
}
- result = wait_event_interruptible(priv->netmgmt_wq, priv->flowenabled);
+
+ result = wait_event_interruptible_timeout(priv->netmgmt_wq,
+ priv->state != CAIF_CONNECTING,
+ CONNECT_TIMEOUT);
if (result == -ERESTARTSYS) {
pr_debug("CAIF: %s(): wait_event_interruptible"
" woken by a signal\n", __func__);
return -ERESTARTSYS;
- } else
- pr_debug("CAIF: %s(): Flow on recieved\n", __func__);
+ }
+ if (result == 0) {
+ pr_debug("CAIF: %s(): connect timeout\n", __func__);
+ caif_disconnect_client(&priv->chnl);
+ priv->state = CAIF_DISCONNECTED;
+ pr_debug("CAIF: %s(): state disconnected\n", __func__);
+ return -ETIMEDOUT;
+ }
+ if (priv->state != CAIF_CONNECTED) {
+ pr_debug("CAIF: %s(): connect failed\n", __func__);
+ return -ECONNREFUSED;
+ }
+ pr_debug("CAIF: %s(): CAIF Netdevice connected\n", __func__);
return 0;
}
static int chnl_net_stop(struct net_device *dev)
{
struct chnl_net *priv;
- int result = -1;
+
ASSERT_RTNL();
priv = netdev_priv(dev);
-
- result = caif_disconnect_client(&priv->chnl);
- if (result != 0) {
- pr_debug("CAIF: %s(): chnl_net_stop: err: "
- "Unable to STOP device, Err:%d\n",
- __func__, result);
- return -EBUSY;
- }
- result = wait_event_interruptible(priv->netmgmt_wq,
- !priv->flowenabled);
-
- if (result == -ERESTARTSYS) {
- pr_debug("CAIF: %s(): wait_event_interruptible woken by"
- " signal, signal_pending(current) = %d\n",
- __func__,
- signal_pending(current));
- } else {
- pr_debug("CAIF: %s(): disconnect received\n", __func__);
-
- }
-
+ priv->state = CAIF_DISCONNECTED;
+ caif_disconnect_client(&priv->chnl);
return 0;
}
@@ -377,6 +391,8 @@ static int ipcaif_newlink(struct net *src_net, struct net_device *dev,
ASSERT_RTNL();
caifdev = netdev_priv(dev);
caif_netlink_parms(data, &caifdev->conn_req);
+ dev_net_set(caifdev->netdev, src_net);
+
ret = register_netdevice(dev);
if (ret)
pr_warning("CAIF: %s(): device rtml registration failed\n",
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 2dccd4ee591..e0097531417 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -86,7 +86,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
int error;
DEFINE_WAIT_FUNC(wait, receiver_wake_function);
- prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Socket errors? */
error = sock_error(sk);
@@ -115,7 +115,7 @@ static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
error = 0;
*timeo_p = schedule_timeout(*timeo_p);
out:
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return error;
interrupted:
error = sock_intr_errno(*timeo_p);
@@ -229,9 +229,18 @@ EXPORT_SYMBOL(skb_free_datagram);
void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
{
- lock_sock(sk);
- skb_free_datagram(sk, skb);
- release_sock(sk);
+ if (likely(atomic_read(&skb->users) == 1))
+ smp_rmb();
+ else if (likely(!atomic_dec_and_test(&skb->users)))
+ return;
+
+ lock_sock_bh(sk);
+ skb_orphan(skb);
+ sk_mem_reclaim_partial(sk);
+ unlock_sock_bh(sk);
+
+ /* skb is now orphaned, can be freed outside of locked section */
+ __kfree_skb(skb);
}
EXPORT_SYMBOL(skb_free_datagram_locked);
@@ -726,7 +735,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk;
unsigned int mask;
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
mask = 0;
/* exceptional events? */
diff --git a/net/core/dev.c b/net/core/dev.c
index b31d5d69a46..32611c8f121 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1557,8 +1557,9 @@ static inline void __netif_reschedule(struct Qdisc *q)
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
- q->next_sched = sd->output_queue;
- sd->output_queue = q;
+ q->next_sched = NULL;
+ *sd->output_queue_tailp = q;
+ sd->output_queue_tailp = &q->next_sched;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
@@ -1902,13 +1903,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
- if (netif_needs_gso(dev, skb)) {
- if (unlikely(dev_gso_segment(skb)))
- goto out_kfree_skb;
- if (skb->next)
- goto gso;
- }
-
/*
* If device doesnt need skb->dst, release it right now while
* its hot in this cpu cache
@@ -1917,6 +1911,14 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
skb_dst_drop(skb);
skb_orphan_try(skb);
+
+ if (netif_needs_gso(dev, skb)) {
+ if (unlikely(dev_gso_segment(skb)))
+ goto out_kfree_skb;
+ if (skb->next)
+ goto gso;
+ }
+
rc = ops->ndo_start_xmit(skb, dev);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
@@ -1937,7 +1939,6 @@ gso:
if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
skb_dst_drop(nskb);
- skb_orphan_try(nskb);
rc = ops->ndo_start_xmit(nskb, dev);
if (unlikely(rc != NETDEV_TX_OK)) {
if (rc & ~NETDEV_TX_MASK)
@@ -2015,8 +2016,12 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev,
if (dev->real_num_tx_queues > 1)
queue_index = skb_tx_hash(dev, skb);
- if (sk && rcu_dereference_check(sk->sk_dst_cache, 1))
- sk_tx_queue_set(sk, queue_index);
+ if (sk) {
+ struct dst_entry *dst = rcu_dereference_check(sk->sk_dst_cache, 1);
+
+ if (dst && skb_dst(skb) == dst)
+ sk_tx_queue_set(sk, queue_index);
+ }
}
}
@@ -2200,7 +2205,13 @@ int netdev_max_backlog __read_mostly = 1000;
int netdev_budget __read_mostly = 300;
int weight_p __read_mostly = 64; /* old backlog weight */
-DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+/* Called with irq disabled */
+static inline void ____napi_schedule(struct softnet_data *sd,
+ struct napi_struct *napi)
+{
+ list_add_tail(&napi->poll_list, &sd->poll_list);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+}
#ifdef CONFIG_RPS
@@ -2225,7 +2236,11 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
int cpu = -1;
u8 ip_proto;
u16 tcpu;
- u32 addr1, addr2, ports, ihl;
+ u32 addr1, addr2, ihl;
+ union {
+ u32 v32;
+ u16 v16[2];
+ } ports;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
@@ -2271,7 +2286,6 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
default:
goto done;
}
- ports = 0;
switch (ip_proto) {
case IPPROTO_TCP:
case IPPROTO_UDP:
@@ -2281,25 +2295,20 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
case IPPROTO_SCTP:
case IPPROTO_UDPLITE:
if (pskb_may_pull(skb, (ihl * 4) + 4)) {
- __be16 *hports = (__be16 *) (skb->data + (ihl * 4));
- u32 sport, dport;
-
- sport = (__force u16) hports[0];
- dport = (__force u16) hports[1];
- if (dport < sport)
- swap(sport, dport);
- ports = (sport << 16) + dport;
+ ports.v32 = * (__force u32 *) (skb->data + (ihl * 4));
+ if (ports.v16[1] < ports.v16[0])
+ swap(ports.v16[0], ports.v16[1]);
+ break;
}
- break;
-
default:
+ ports.v32 = 0;
break;
}
/* get a consistent hash (same value on both flow directions) */
if (addr2 < addr1)
swap(addr1, addr2);
- skb->rxhash = jhash_3words(addr1, addr2, ports, hashrnd);
+ skb->rxhash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
if (!skb->rxhash)
skb->rxhash = 1;
@@ -2362,8 +2371,8 @@ static void rps_trigger_softirq(void *data)
{
struct softnet_data *sd = data;
- __napi_schedule(&sd->backlog);
- __get_cpu_var(netdev_rx_stat).received_rps++;
+ ____napi_schedule(sd, &sd->backlog);
+ sd->received_rps++;
}
#endif /* CONFIG_RPS */
@@ -2402,15 +2411,15 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu,
sd = &per_cpu(softnet_data, cpu);
local_irq_save(flags);
- __get_cpu_var(netdev_rx_stat).total++;
rps_lock(sd);
- if (sd->input_pkt_queue.qlen <= netdev_max_backlog) {
- if (sd->input_pkt_queue.qlen) {
+ if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
+ if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
#ifdef CONFIG_RPS
- *qtail = sd->input_queue_head + sd->input_pkt_queue.qlen;
+ *qtail = sd->input_queue_head +
+ skb_queue_len(&sd->input_pkt_queue);
#endif
rps_unlock(sd);
local_irq_restore(flags);
@@ -2420,14 +2429,14 @@ enqueue:
/* Schedule NAPI for backlog device */
if (napi_schedule_prep(&sd->backlog)) {
if (!rps_ipi_queued(sd))
- __napi_schedule(&sd->backlog);
+ ____napi_schedule(sd, &sd->backlog);
}
goto enqueue;
}
+ sd->dropped++;
rps_unlock(sd);
- __get_cpu_var(netdev_rx_stat).dropped++;
local_irq_restore(flags);
kfree_skb(skb);
@@ -2527,6 +2536,7 @@ static void net_tx_action(struct softirq_action *h)
local_irq_disable();
head = sd->output_queue;
sd->output_queue = NULL;
+ sd->output_queue_tailp = &sd->output_queue;
local_irq_enable();
while (head) {
@@ -2801,7 +2811,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
skb->dev = master;
}
- __get_cpu_var(netdev_rx_stat).total++;
+ __get_cpu_var(softnet_data).processed++;
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
@@ -2930,13 +2940,21 @@ static void flush_backlog(void *arg)
struct sk_buff *skb, *tmp;
rps_lock(sd);
- skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp)
+ skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
if (skb->dev == dev) {
__skb_unlink(skb, &sd->input_pkt_queue);
kfree_skb(skb);
- input_queue_head_incr(sd);
+ input_queue_head_add(sd, 1);
}
+ }
rps_unlock(sd);
+
+ skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &sd->process_queue);
+ kfree_skb(skb);
+ }
+ }
}
static int napi_gro_complete(struct sk_buff *skb)
@@ -3239,30 +3257,85 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_gro_frags);
+/*
+ * net_rps_action sends any pending IPI's for rps.
+ * Note: called with local irq disabled, but exits with local irq enabled.
+ */
+static void net_rps_action_and_irq_enable(struct softnet_data *sd)
+{
+#ifdef CONFIG_RPS
+ struct softnet_data *remsd = sd->rps_ipi_list;
+
+ if (remsd) {
+ sd->rps_ipi_list = NULL;
+
+ local_irq_enable();
+
+ /* Send pending IPI's to kick RPS processing on remote cpus. */
+ while (remsd) {
+ struct softnet_data *next = remsd->rps_ipi_next;
+
+ if (cpu_online(remsd->cpu))
+ __smp_call_function_single(remsd->cpu,
+ &remsd->csd, 0);
+ remsd = next;
+ }
+ } else
+#endif
+ local_irq_enable();
+}
+
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
- struct softnet_data *sd = &__get_cpu_var(softnet_data);
+ struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
+#ifdef CONFIG_RPS
+ /* Check if we have pending ipi, its better to send them now,
+ * not waiting net_rx_action() end.
+ */
+ if (sd->rps_ipi_list) {
+ local_irq_disable();
+ net_rps_action_and_irq_enable(sd);
+ }
+#endif
napi->weight = weight_p;
- do {
+ local_irq_disable();
+ while (work < quota) {
struct sk_buff *skb;
+ unsigned int qlen;
- local_irq_disable();
- rps_lock(sd);
- skb = __skb_dequeue(&sd->input_pkt_queue);
- if (!skb) {
- __napi_complete(napi);
- rps_unlock(sd);
+ while ((skb = __skb_dequeue(&sd->process_queue))) {
local_irq_enable();
- break;
+ __netif_receive_skb(skb);
+ if (++work >= quota)
+ return work;
+ local_irq_disable();
}
- input_queue_head_incr(sd);
- rps_unlock(sd);
- local_irq_enable();
- __netif_receive_skb(skb);
- } while (++work < quota);
+ rps_lock(sd);
+ qlen = skb_queue_len(&sd->input_pkt_queue);
+ if (qlen) {
+ input_queue_head_add(sd, qlen);
+ skb_queue_splice_tail_init(&sd->input_pkt_queue,
+ &sd->process_queue);
+ }
+ if (qlen < quota - work) {
+ /*
+ * Inline a custom version of __napi_complete().
+ * only current cpu owns and manipulates this napi,
+ * and NAPI_STATE_SCHED is the only possible flag set on backlog.
+ * we can use a plain write instead of clear_bit(),
+ * and we dont need an smp_mb() memory barrier.
+ */
+ list_del(&napi->poll_list);
+ napi->state = 0;
+
+ quota = work + qlen;
+ }
+ rps_unlock(sd);
+ }
+ local_irq_enable();
return work;
}
@@ -3278,8 +3351,7 @@ void __napi_schedule(struct napi_struct *n)
unsigned long flags;
local_irq_save(flags);
- list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);
- __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ ____napi_schedule(&__get_cpu_var(softnet_data), n);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__napi_schedule);
@@ -3350,45 +3422,16 @@ void netif_napi_del(struct napi_struct *napi)
}
EXPORT_SYMBOL(netif_napi_del);
-/*
- * net_rps_action sends any pending IPI's for rps.
- * Note: called with local irq disabled, but exits with local irq enabled.
- */
-static void net_rps_action_and_irq_disable(void)
-{
-#ifdef CONFIG_RPS
- struct softnet_data *sd = &__get_cpu_var(softnet_data);
- struct softnet_data *remsd = sd->rps_ipi_list;
-
- if (remsd) {
- sd->rps_ipi_list = NULL;
-
- local_irq_enable();
-
- /* Send pending IPI's to kick RPS processing on remote cpus. */
- while (remsd) {
- struct softnet_data *next = remsd->rps_ipi_next;
-
- if (cpu_online(remsd->cpu))
- __smp_call_function_single(remsd->cpu,
- &remsd->csd, 0);
- remsd = next;
- }
- } else
-#endif
- local_irq_enable();
-}
-
static void net_rx_action(struct softirq_action *h)
{
- struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
local_irq_disable();
- while (!list_empty(list)) {
+ while (!list_empty(&sd->poll_list)) {
struct napi_struct *n;
int work, weight;
@@ -3406,7 +3449,7 @@ static void net_rx_action(struct softirq_action *h)
* entries to the tail of this list, and only ->poll()
* calls can remove this head entry from the list.
*/
- n = list_first_entry(list, struct napi_struct, poll_list);
+ n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
have = netpoll_poll_lock(n);
@@ -3441,13 +3484,13 @@ static void net_rx_action(struct softirq_action *h)
napi_complete(n);
local_irq_disable();
} else
- list_move_tail(&n->poll_list, list);
+ list_move_tail(&n->poll_list, &sd->poll_list);
}
netpoll_poll_unlock(have);
}
out:
- net_rps_action_and_irq_disable();
+ net_rps_action_and_irq_enable(sd);
#ifdef CONFIG_NET_DMA
/*
@@ -3460,7 +3503,7 @@ out:
return;
softnet_break:
- __get_cpu_var(netdev_rx_stat).time_squeeze++;
+ sd->time_squeeze++;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
@@ -3661,17 +3704,17 @@ static int dev_seq_show(struct seq_file *seq, void *v)
return 0;
}
-static struct netif_rx_stats *softnet_get_online(loff_t *pos)
+static struct softnet_data *softnet_get_online(loff_t *pos)
{
- struct netif_rx_stats *rc = NULL;
+ struct softnet_data *sd = NULL;
while (*pos < nr_cpu_ids)
if (cpu_online(*pos)) {
- rc = &per_cpu(netdev_rx_stat, *pos);
+ sd = &per_cpu(softnet_data, *pos);
break;
} else
++*pos;
- return rc;
+ return sd;
}
static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
@@ -3691,12 +3734,12 @@ static void softnet_seq_stop(struct seq_file *seq, void *v)
static int softnet_seq_show(struct seq_file *seq, void *v)
{
- struct netif_rx_stats *s = v;
+ struct softnet_data *sd = v;
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
- s->total, s->dropped, s->time_squeeze, 0,
+ sd->processed, sd->dropped, sd->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision, s->received_rps);
+ sd->cpu_collision, sd->received_rps);
return 0;
}
@@ -5584,7 +5627,6 @@ static int dev_cpu_callback(struct notifier_block *nfb,
void *ocpu)
{
struct sk_buff **list_skb;
- struct Qdisc **list_net;
struct sk_buff *skb;
unsigned int cpu, oldcpu = (unsigned long)ocpu;
struct softnet_data *sd, *oldsd;
@@ -5605,13 +5647,13 @@ static int dev_cpu_callback(struct notifier_block *nfb,
*list_skb = oldsd->completion_queue;
oldsd->completion_queue = NULL;
- /* Find end of our output_queue. */
- list_net = &sd->output_queue;
- while (*list_net)
- list_net = &(*list_net)->next_sched;
/* Append output queue from offline CPU. */
- *list_net = oldsd->output_queue;
- oldsd->output_queue = NULL;
+ if (oldsd->output_queue) {
+ *sd->output_queue_tailp = oldsd->output_queue;
+ sd->output_queue_tailp = oldsd->output_queue_tailp;
+ oldsd->output_queue = NULL;
+ oldsd->output_queue_tailp = &oldsd->output_queue;
+ }
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_enable();
@@ -5619,8 +5661,10 @@ static int dev_cpu_callback(struct notifier_block *nfb,
/* Process offline CPU's input_pkt_queue */
while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
- input_queue_head_incr(oldsd);
+ input_queue_head_add(oldsd, 1);
}
+ while ((skb = __skb_dequeue(&oldsd->process_queue)))
+ netif_rx(skb);
return NOTIFY_OK;
}
@@ -5838,10 +5882,13 @@ static int __init net_dev_init(void)
for_each_possible_cpu(i) {
struct softnet_data *sd = &per_cpu(softnet_data, i);
+ memset(sd, 0, sizeof(*sd));
skb_queue_head_init(&sd->input_pkt_queue);
+ skb_queue_head_init(&sd->process_queue);
sd->completion_queue = NULL;
INIT_LIST_HEAD(&sd->poll_list);
-
+ sd->output_queue = NULL;
+ sd->output_queue_tailp = &sd->output_queue;
#ifdef CONFIG_RPS
sd->csd.func = rps_trigger_softirq;
sd->csd.info = sd;
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 1bc66592453..42e84e08a1b 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -122,7 +122,7 @@ errout:
}
struct fib_rules_ops *
-fib_rules_register(struct fib_rules_ops *tmpl, struct net *net)
+fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net)
{
struct fib_rules_ops *ops;
int err;
diff --git a/net/core/filter.c b/net/core/filter.c
index ff943bed21a..da69fb728d3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -302,6 +302,8 @@ load_b:
A = skb->pkt_type;
continue;
case SKF_AD_IFINDEX:
+ if (!skb->dev)
+ return 0;
A = skb->dev->ifindex;
continue;
case SKF_AD_MARK:
@@ -310,6 +312,11 @@ load_b:
case SKF_AD_QUEUE:
A = skb->queue_mapping;
continue;
+ case SKF_AD_HATYPE:
+ if (!skb->dev)
+ return 0;
+ A = skb->dev->type;
+ continue;
case SKF_AD_NLATTR: {
struct nlattr *nla;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index bd8c4712ea2..c988e685433 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -27,6 +27,51 @@ EXPORT_SYMBOL(init_net);
#define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */
+static void net_generic_release(struct rcu_head *rcu)
+{
+ struct net_generic *ng;
+
+ ng = container_of(rcu, struct net_generic, rcu);
+ kfree(ng);
+}
+
+static int net_assign_generic(struct net *net, int id, void *data)
+{
+ struct net_generic *ng, *old_ng;
+
+ BUG_ON(!mutex_is_locked(&net_mutex));
+ BUG_ON(id == 0);
+
+ ng = old_ng = net->gen;
+ if (old_ng->len >= id)
+ goto assign;
+
+ ng = kzalloc(sizeof(struct net_generic) +
+ id * sizeof(void *), GFP_KERNEL);
+ if (ng == NULL)
+ return -ENOMEM;
+
+ /*
+ * Some synchronisation notes:
+ *
+ * The net_generic explores the net->gen array inside rcu
+ * read section. Besides once set the net->gen->ptr[x]
+ * pointer never changes (see rules in netns/generic.h).
+ *
+ * That said, we simply duplicate this array and schedule
+ * the old copy for kfree after a grace period.
+ */
+
+ ng->len = id;
+ memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*));
+
+ rcu_assign_pointer(net->gen, ng);
+ call_rcu(&old_ng->rcu, net_generic_release);
+assign:
+ ng->ptr[id - 1] = data;
+ return 0;
+}
+
static int ops_init(const struct pernet_operations *ops, struct net *net)
{
int err;
@@ -469,10 +514,10 @@ EXPORT_SYMBOL_GPL(register_pernet_subsys);
* addition run the exit method for all existing network
* namespaces.
*/
-void unregister_pernet_subsys(struct pernet_operations *module)
+void unregister_pernet_subsys(struct pernet_operations *ops)
{
mutex_lock(&net_mutex);
- unregister_pernet_operations(module);
+ unregister_pernet_operations(ops);
mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(unregister_pernet_subsys);
@@ -526,49 +571,3 @@ void unregister_pernet_device(struct pernet_operations *ops)
mutex_unlock(&net_mutex);
}
EXPORT_SYMBOL_GPL(unregister_pernet_device);
-
-static void net_generic_release(struct rcu_head *rcu)
-{
- struct net_generic *ng;
-
- ng = container_of(rcu, struct net_generic, rcu);
- kfree(ng);
-}
-
-int net_assign_generic(struct net *net, int id, void *data)
-{
- struct net_generic *ng, *old_ng;
-
- BUG_ON(!mutex_is_locked(&net_mutex));
- BUG_ON(id == 0);
-
- ng = old_ng = net->gen;
- if (old_ng->len >= id)
- goto assign;
-
- ng = kzalloc(sizeof(struct net_generic) +
- id * sizeof(void *), GFP_KERNEL);
- if (ng == NULL)
- return -ENOMEM;
-
- /*
- * Some synchronisation notes:
- *
- * The net_generic explores the net->gen array inside rcu
- * read section. Besides once set the net->gen->ptr[x]
- * pointer never changes (see rules in netns/generic.h).
- *
- * That said, we simply duplicate this array and schedule
- * the old copy for kfree after a grace period.
- */
-
- ng->len = id;
- memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*));
-
- rcu_assign_pointer(net->gen, ng);
- call_rcu(&old_ng->rcu, net_generic_release);
-assign:
- ng->ptr[id - 1] = data;
- return 0;
-}
-EXPORT_SYMBOL_GPL(net_assign_generic);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a58f59b9759..94825b10955 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -179,9 +179,8 @@ static void service_arp_queue(struct netpoll_info *npi)
}
}
-void netpoll_poll(struct netpoll *np)
+void netpoll_poll_dev(struct net_device *dev)
{
- struct net_device *dev = np->dev;
const struct net_device_ops *ops;
if (!dev || !netif_running(dev))
@@ -201,6 +200,11 @@ void netpoll_poll(struct netpoll *np)
zap_completion_queue();
}
+void netpoll_poll(struct netpoll *np)
+{
+ netpoll_poll_dev(np->dev);
+}
+
static void refill_skbs(void)
{
struct sk_buff *skb;
@@ -282,7 +286,7 @@ static int netpoll_owner_active(struct net_device *dev)
return 0;
}
-static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
+void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
{
int status = NETDEV_TX_BUSY;
unsigned long tries;
@@ -308,7 +312,9 @@ static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
tries > 0; --tries) {
if (__netif_tx_trylock(txq)) {
if (!netif_tx_queue_stopped(txq)) {
+ dev->priv_flags |= IFF_IN_NETPOLL;
status = ops->ndo_start_xmit(skb, dev);
+ dev->priv_flags &= ~IFF_IN_NETPOLL;
if (status == NETDEV_TX_OK)
txq_trans_update(txq);
}
@@ -756,7 +762,10 @@ int netpoll_setup(struct netpoll *np)
atomic_inc(&npinfo->refcnt);
}
- if (!ndev->netdev_ops->ndo_poll_controller) {
+ npinfo->netpoll = np;
+
+ if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) ||
+ !ndev->netdev_ops->ndo_poll_controller) {
printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n",
np->name, np->dev_name);
err = -ENOTSUPP;
@@ -878,6 +887,7 @@ void netpoll_cleanup(struct netpoll *np)
}
if (atomic_dec_and_test(&npinfo->refcnt)) {
+ const struct net_device_ops *ops;
skb_queue_purge(&npinfo->arp_tx);
skb_queue_purge(&npinfo->txq);
cancel_rearming_delayed_work(&npinfo->tx_work);
@@ -885,7 +895,11 @@ void netpoll_cleanup(struct netpoll *np)
/* clean after last, unfinished work */
__skb_queue_purge(&npinfo->txq);
kfree(npinfo);
- np->dev->npinfo = NULL;
+ ops = np->dev->netdev_ops;
+ if (ops->ndo_netpoll_cleanup)
+ ops->ndo_netpoll_cleanup(np->dev);
+ else
+ np->dev->npinfo = NULL;
}
}
@@ -908,6 +922,7 @@ void netpoll_set_trap(int trap)
atomic_dec(&trapped);
}
+EXPORT_SYMBOL(netpoll_send_skb);
EXPORT_SYMBOL(netpoll_set_trap);
EXPORT_SYMBOL(netpoll_trap);
EXPORT_SYMBOL(netpoll_print_options);
@@ -915,4 +930,5 @@ EXPORT_SYMBOL(netpoll_parse_options);
EXPORT_SYMBOL(netpoll_setup);
EXPORT_SYMBOL(netpoll_cleanup);
EXPORT_SYMBOL(netpoll_send_udp);
+EXPORT_SYMBOL(netpoll_poll_dev);
EXPORT_SYMBOL(netpoll_poll);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 78c85985cb3..23a71cb2127 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -98,7 +98,7 @@ int lockdep_rtnl_is_held(void)
EXPORT_SYMBOL(lockdep_rtnl_is_held);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
-static struct rtnl_link *rtnl_msg_handlers[NPROTO];
+static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
static inline int rtm_msgindex(int msgtype)
{
@@ -118,7 +118,7 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex)
{
struct rtnl_link *tab;
- if (protocol < NPROTO)
+ if (protocol <= RTNL_FAMILY_MAX)
tab = rtnl_msg_handlers[protocol];
else
tab = NULL;
@@ -133,7 +133,7 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex)
{
struct rtnl_link *tab;
- if (protocol < NPROTO)
+ if (protocol <= RTNL_FAMILY_MAX)
tab = rtnl_msg_handlers[protocol];
else
tab = NULL;
@@ -167,7 +167,7 @@ int __rtnl_register(int protocol, int msgtype,
struct rtnl_link *tab;
int msgindex;
- BUG_ON(protocol < 0 || protocol >= NPROTO);
+ BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
msgindex = rtm_msgindex(msgtype);
tab = rtnl_msg_handlers[protocol];
@@ -219,7 +219,7 @@ int rtnl_unregister(int protocol, int msgtype)
{
int msgindex;
- BUG_ON(protocol < 0 || protocol >= NPROTO);
+ BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
msgindex = rtm_msgindex(msgtype);
if (rtnl_msg_handlers[protocol] == NULL)
@@ -241,7 +241,7 @@ EXPORT_SYMBOL_GPL(rtnl_unregister);
*/
void rtnl_unregister_all(int protocol)
{
- BUG_ON(protocol < 0 || protocol >= NPROTO);
+ BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
kfree(rtnl_msg_handlers[protocol]);
rtnl_msg_handlers[protocol] = NULL;
@@ -1319,10 +1319,11 @@ replay:
err = ops->newlink(net, dev, tb, data);
else
err = register_netdevice(dev);
- if (err < 0 && !IS_ERR(dev)) {
+
+ if (err < 0 && !IS_ERR(dev))
free_netdev(dev);
+ if (err < 0)
goto out;
- }
err = rtnl_configure_link(dev, ifm);
if (err < 0)
@@ -1384,7 +1385,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
if (s_idx == 0)
s_idx = 1;
- for (idx = 1; idx < NPROTO; idx++) {
+ for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) {
int type = cb->nlh->nlmsg_type-RTM_BASE;
if (idx < s_idx || idx == PF_PACKET)
continue;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index bdea0efdf8c..a9b0e1f7780 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -117,7 +117,7 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = {
*
* Out of line support code for skb_put(). Not user callable.
*/
-void skb_over_panic(struct sk_buff *skb, int sz, void *here)
+static void skb_over_panic(struct sk_buff *skb, int sz, void *here)
{
printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p "
"data:%p tail:%#lx end:%#lx dev:%s\n",
@@ -126,7 +126,6 @@ void skb_over_panic(struct sk_buff *skb, int sz, void *here)
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
-EXPORT_SYMBOL(skb_over_panic);
/**
* skb_under_panic - private function
@@ -137,7 +136,7 @@ EXPORT_SYMBOL(skb_over_panic);
* Out of line support code for skb_push(). Not user callable.
*/
-void skb_under_panic(struct sk_buff *skb, int sz, void *here)
+static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
{
printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p "
"data:%p tail:%#lx end:%#lx dev:%s\n",
@@ -146,7 +145,6 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here)
skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
-EXPORT_SYMBOL(skb_under_panic);
/* Allocate a new skbuff. We do this ourselves so we can fill in a few
* 'private' fields and also do memory statistics to find all the
@@ -183,12 +181,14 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
skb = kmem_cache_alloc_node(cache, gfp_mask & ~__GFP_DMA, node);
if (!skb)
goto out;
+ prefetchw(skb);
size = SKB_DATA_ALIGN(size);
data = kmalloc_node_track_caller(size + sizeof(struct skb_shared_info),
gfp_mask, node);
if (!data)
goto nodata;
+ prefetchw(data + size);
/*
* Only clear those fields we need to clear, not those that we will
@@ -210,15 +210,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
/* make sure we initialize shinfo sequentially */
shinfo = skb_shinfo(skb);
+ memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
- shinfo->nr_frags = 0;
- shinfo->gso_size = 0;
- shinfo->gso_segs = 0;
- shinfo->gso_type = 0;
- shinfo->ip6_frag_id = 0;
- shinfo->tx_flags.flags = 0;
- skb_frag_list_init(skb);
- memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps));
if (fclone) {
struct sk_buff *child = skb + 1;
@@ -507,16 +500,10 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size)
return 0;
skb_release_head_state(skb);
+
shinfo = skb_shinfo(skb);
+ memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
atomic_set(&shinfo->dataref, 1);
- shinfo->nr_frags = 0;
- shinfo->gso_size = 0;
- shinfo->gso_segs = 0;
- shinfo->gso_type = 0;
- shinfo->ip6_frag_id = 0;
- shinfo->tx_flags.flags = 0;
- skb_frag_list_init(skb);
- memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps));
memset(skb, 0, offsetof(struct sk_buff, tail));
skb->data = skb->head + NET_SKB_PAD;
@@ -1053,7 +1040,7 @@ EXPORT_SYMBOL(skb_push);
*/
unsigned char *skb_pull(struct sk_buff *skb, unsigned int len)
{
- return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len);
+ return skb_pull_inline(skb, len);
}
EXPORT_SYMBOL(skb_pull);
diff --git a/net/core/sock.c b/net/core/sock.c
index 7effa1e689d..94c4affdda9 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -327,6 +327,10 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
skb->dev = NULL;
+ if (sk_rcvqueues_full(sk, skb)) {
+ atomic_inc(&sk->sk_drops);
+ goto discard_and_relse;
+ }
if (nested)
bh_lock_sock_nested(sk);
else
@@ -1207,7 +1211,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
*/
sk_refcnt_debug_inc(newsk);
sk_set_socket(newsk, NULL);
- newsk->sk_sleep = NULL;
+ newsk->sk_wq = NULL;
if (newsk->sk_prot->sockets_allocated)
percpu_counter_inc(newsk->sk_prot->sockets_allocated);
@@ -1395,7 +1399,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
if (signal_pending(current))
break;
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
break;
if (sk->sk_shutdown & SEND_SHUTDOWN)
@@ -1404,7 +1408,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
break;
timeo = schedule_timeout(timeo);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return timeo;
}
@@ -1570,11 +1574,11 @@ int sk_wait_data(struct sock *sk, long *timeo)
int rc;
DEFINE_WAIT(wait);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return rc;
}
EXPORT_SYMBOL(sk_wait_data);
@@ -1796,41 +1800,53 @@ EXPORT_SYMBOL(sock_no_sendpage);
static void sock_def_wakeup(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
- if (sk_has_sleeper(sk))
- wake_up_interruptible_all(sk->sk_sleep);
- read_unlock(&sk->sk_callback_lock);
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_all(&wq->wait);
+ rcu_read_unlock();
}
static void sock_def_error_report(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
- if (sk_has_sleeper(sk))
- wake_up_interruptible_poll(sk->sk_sleep, POLLERR);
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_poll(&wq->wait, POLLERR);
sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR);
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
static void sock_def_readable(struct sock *sk, int len)
{
- read_lock(&sk->sk_callback_lock);
- if (sk_has_sleeper(sk))
- wake_up_interruptible_sync_poll(sk->sk_sleep, POLLIN |
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
POLLRDNORM | POLLRDBAND);
sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
static void sock_def_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ struct socket_wq *wq;
+
+ rcu_read_lock();
/* Do not wake up a writer until he can make "significant"
* progress. --DaveM
*/
if ((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
- if (sk_has_sleeper(sk))
- wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT |
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_sync_poll(&wq->wait, POLLOUT |
POLLWRNORM | POLLWRBAND);
/* Should agree with poll, otherwise some programs break */
@@ -1838,7 +1854,7 @@ static void sock_def_write_space(struct sock *sk)
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
static void sock_def_destruct(struct sock *sk)
@@ -1885,7 +1901,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_allocation = GFP_KERNEL;
sk->sk_rcvbuf = sysctl_rmem_default;
sk->sk_sndbuf = sysctl_wmem_default;
- sk->sk_backlog.limit = sk->sk_rcvbuf << 1;
sk->sk_state = TCP_CLOSE;
sk_set_socket(sk, sock);
@@ -1893,10 +1908,10 @@ void sock_init_data(struct socket *sock, struct sock *sk)
if (sock) {
sk->sk_type = sock->type;
- sk->sk_sleep = &sock->wait;
+ sk->sk_wq = sock->wq;
sock->sk = sk;
} else
- sk->sk_sleep = NULL;
+ sk->sk_wq = NULL;
spin_lock_init(&sk->sk_dst_lock);
rwlock_init(&sk->sk_callback_lock);
diff --git a/net/core/stream.c b/net/core/stream.c
index a37debfeb1b..cc196f42b8d 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -28,15 +28,19 @@
void sk_stream_write_space(struct sock *sk)
{
struct socket *sock = sk->sk_socket;
+ struct socket_wq *wq;
if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) {
clear_bit(SOCK_NOSPACE, &sock->flags);
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_poll(sk->sk_sleep, POLLOUT |
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_poll(&wq->wait, POLLOUT |
POLLWRNORM | POLLWRBAND);
- if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
+ if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT);
+ rcu_read_unlock();
}
}
@@ -66,13 +70,13 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
if (signal_pending(tsk))
return sock_intr_errno(*timeo_p);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sk->sk_write_pending++;
done = sk_wait_event(sk, timeo_p,
!sk->sk_err &&
!((1 << sk->sk_state) &
~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)));
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
sk->sk_write_pending--;
} while (!done);
return 0;
@@ -96,13 +100,13 @@ void sk_stream_wait_close(struct sock *sk, long timeout)
DEFINE_WAIT(wait);
do {
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk)))
break;
} while (!signal_pending(current) && timeout);
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
}
}
@@ -126,7 +130,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
while (1) {
set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto do_error;
@@ -157,7 +161,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
*timeo_p = current_timeo;
}
out:
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return err;
do_error:
diff --git a/net/dccp/output.c b/net/dccp/output.c
index e98b65e9569..aadbdb58758 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -195,15 +195,17 @@ EXPORT_SYMBOL_GPL(dccp_sync_mss);
void dccp_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ struct socket_wq *wq;
- if (sk_has_sleeper(sk))
- wake_up_interruptible(sk->sk_sleep);
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible(&wq->wait);
/* Should agree with poll, otherwise some programs break */
if (sock_writeable(sk))
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
/**
@@ -225,7 +227,7 @@ static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay)
dccp_pr_debug("delayed send by %d msec\n", delay);
jiffdelay = msecs_to_jiffies(delay);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
sk->sk_write_pending++;
release_sock(sk);
@@ -241,7 +243,7 @@ static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay)
rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
} while ((delay = rc) > 0);
out:
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return rc;
do_error:
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index a0e38d8018f..b03ecf6b2bb 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -312,7 +312,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock,
unsigned int mask;
struct sock *sk = sock->sk;
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 55e3b6b0061..d6b93d19790 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -832,7 +832,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
scp->segsize_loc = dst_metric(__sk_dst_get(sk), RTAX_ADVMSS);
dn_send_conn_conf(sk, allocation);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
for(;;) {
release_sock(sk);
if (scp->state == DN_CC)
@@ -850,9 +850,9 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
} else if (scp->state != DN_CC) {
@@ -873,7 +873,7 @@ static int dn_wait_run(struct sock *sk, long *timeo)
if (!*timeo)
return -EALREADY;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
for(;;) {
release_sock(sk);
if (scp->state == DN_CI || scp->state == DN_CC)
@@ -891,9 +891,9 @@ static int dn_wait_run(struct sock *sk, long *timeo)
err = -ETIMEDOUT;
if (!*timeo)
break;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
out:
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
@@ -1040,7 +1040,7 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
struct sk_buff *skb = NULL;
int err = 0;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
for(;;) {
release_sock(sk);
skb = skb_dequeue(&sk->sk_receive_queue);
@@ -1060,9 +1060,9 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return skb == NULL ? ERR_PTR(err) : skb;
}
@@ -1746,11 +1746,11 @@ static int dn_recvmsg(struct kiocb *iocb, struct socket *sock,
goto out;
}
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
sk_wait_event(sk, &timeo, dn_data_ready(sk, queue, flags, target));
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
}
skb_queue_walk_safe(queue, skb, n) {
@@ -2003,12 +2003,12 @@ static int dn_sendmsg(struct kiocb *iocb, struct socket *sock,
goto out;
}
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
sk_wait_event(sk, &timeo,
!dn_queue_too_long(scp, queue, flags));
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
continue;
}
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index af28dcc2184..48fdf10be7a 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -216,8 +216,8 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops)
dn_rt_cache_flush(-1);
}
-static struct fib_rules_ops dn_fib_rules_ops_template = {
- .family = FIB_RULES_DECNET,
+static const struct fib_rules_ops __net_initdata dn_fib_rules_ops_template = {
+ .family = AF_DECnet,
.rule_size = sizeof(struct dn_fib_rule),
.addr_size = sizeof(u16),
.action = dn_fib_rule_action,
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 205a1c12f3c..61ec0329316 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -136,7 +136,7 @@ int eth_rebuild_header(struct sk_buff *skb)
default:
printk(KERN_DEBUG
"%s: unable to resolve type %X addresses.\n",
- dev->name, (int)eth->h_proto);
+ dev->name, ntohs(eth->h_proto));
memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
break;
@@ -162,7 +162,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
skb->dev = dev;
skb_reset_mac_header(skb);
- skb_pull(skb, ETH_HLEN);
+ skb_pull_inline(skb, ETH_HLEN);
eth = eth_hdr(skb);
if (unlikely(is_multicast_ether_addr(eth->h_dest))) {
diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c
index c7da600750b..93c91b633a5 100644
--- a/net/ieee802154/af_ieee802154.c
+++ b/net/ieee802154/af_ieee802154.c
@@ -151,6 +151,9 @@ static int ieee802154_dev_ioctl(struct sock *sk, struct ifreq __user *arg,
dev_load(sock_net(sk), ifr.ifr_name);
dev = dev_get_by_name(sock_net(sk), ifr.ifr_name);
+ if (!dev)
+ return -ENODEV;
+
if (dev->type == ARPHRD_IEEE802154 && dev->netdev_ops->ndo_do_ioctl)
ret = dev->netdev_ops->ndo_do_ioctl(dev, &ifr, cmd);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c5376c72550..c6c43bcd1c6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -419,7 +419,7 @@ int inet_release(struct socket *sock)
if (sk) {
long timeout;
- inet_rps_reset_flow(sk);
+ sock_rps_reset_flow(sk);
/* Applications forget to leave groups before exiting */
ip_mc_drop_socket(sk);
@@ -548,7 +548,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
{
DEFINE_WAIT(wait);
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -561,9 +561,9 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
lock_sock(sk);
if (signal_pending(current) || !timeo)
break;
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return timeo;
}
@@ -722,7 +722,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
{
struct sock *sk = sock->sk;
- inet_rps_record_flow(sk);
+ sock_rps_record_flow(sk);
/* We may need to bind the socket. */
if (!inet_sk(sk)->inet_num && inet_autobind(sk))
@@ -737,7 +737,7 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
{
struct sock *sk = sock->sk;
- inet_rps_record_flow(sk);
+ sock_rps_record_flow(sk);
/* We may need to bind the socket. */
if (!inet_sk(sk)->inet_num && inet_autobind(sk))
@@ -755,7 +755,7 @@ int inet_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
int addr_len = 0;
int err;
- inet_rps_record_flow(sk);
+ sock_rps_record_flow(sk);
err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
flags & ~MSG_DONTWAIT, &addr_len);
@@ -1323,8 +1323,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
goto out_unlock;
- id = ntohl(*(u32 *)&iph->id);
- flush = (u16)((ntohl(*(u32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
+ id = ntohl(*(__be32 *)&iph->id);
+ flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
id >>= 16;
for (p = *head; p; p = p->next) {
@@ -1337,8 +1337,8 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
if ((iph->protocol ^ iph2->protocol) |
(iph->tos ^ iph2->tos) |
- (iph->saddr ^ iph2->saddr) |
- (iph->daddr ^ iph2->daddr)) {
+ ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) |
+ ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 3ec84fea5b7..76daeb5ff56 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -245,8 +245,8 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
rt_cache_flush(ops->fro_net, -1);
}
-static struct fib_rules_ops fib4_rules_ops_template = {
- .family = FIB_RULES_IPV4,
+static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
+ .family = AF_INET,
.rule_size = sizeof(struct fib4_rule),
.addr_size = sizeof(u32),
.action = fib4_rule_action,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 59a838795e3..c98f115fb0f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -209,7 +209,9 @@ static inline struct node *tnode_get_child_rcu(struct tnode *tn, unsigned int i)
{
struct node *ret = tnode_get_child(tn, i);
- return rcu_dereference(ret);
+ return rcu_dereference_check(ret,
+ rcu_read_lock_held() ||
+ lockdep_rtnl_is_held());
}
static inline int tnode_child_length(const struct tnode *tn)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 8da6429269d..e0a3e3537b1 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -234,7 +234,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
* having to remove and re-insert us on the wait queue.
*/
for (;;) {
- prepare_to_wait_exclusive(sk->sk_sleep, &wait,
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
if (reqsk_queue_empty(&icsk->icsk_accept_queue))
@@ -253,7 +253,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
if (!timeo)
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return err;
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index d979710684b..252897443ef 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -120,7 +120,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb)
newskb->pkt_type = PACKET_LOOPBACK;
newskb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(newskb));
- netif_rx(newskb);
+ netif_rx_ni(newskb);
return 0;
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index b0aa0546a3b..ce231780a2b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -954,6 +954,22 @@ e_inval:
return -EINVAL;
}
+/**
+ * ip_queue_rcv_skb - Queue an skb into sock receive queue
+ * @sk: socket
+ * @skb: buffer
+ *
+ * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option
+ * is not set, we drop skb dst entry now, while dst cache line is hot.
+ */
+int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO))
+ skb_dst_drop(skb);
+ return sock_queue_rcv_skb(sk, skb);
+}
+EXPORT_SYMBOL(ip_queue_rcv_skb);
+
int ip_setsockopt(struct sock *sk, int level,
int optname, char __user *optval, unsigned int optlen)
{
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1aa498d7a0a..f3f1c6b5c70 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -128,8 +128,8 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt,
int local);
static int ipmr_cache_report(struct mr_table *mrt,
struct sk_buff *pkt, vifi_t vifi, int assert);
-static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
- struct mfc_cache *c, struct rtmsg *rtm);
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ struct mfc_cache *c, struct rtmsg *rtm);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -216,8 +216,8 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
return 0;
}
-static struct fib_rules_ops ipmr_rules_ops_template = {
- .family = FIB_RULES_IPMR,
+static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
+ .family = RTNL_FAMILY_IPMR,
.rule_size = sizeof(struct ipmr_rule),
.addr_size = sizeof(u32),
.action = ipmr_rule_action,
@@ -831,7 +831,7 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
if (ip_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr));
- if (ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
+ if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) {
nlh->nlmsg_len = (skb_tail_pointer(skb) -
(u8 *)nlh);
} else {
@@ -1772,10 +1772,10 @@ int ip_mr_input(struct sk_buff *skb)
vif = ipmr_find_vif(mrt, skb->dev);
if (vif >= 0) {
- int err = ipmr_cache_unresolved(mrt, vif, skb);
+ int err2 = ipmr_cache_unresolved(mrt, vif, skb);
read_unlock(&mrt_lock);
- return err;
+ return err2;
}
read_unlock(&mrt_lock);
kfree_skb(skb);
@@ -1904,9 +1904,8 @@ drop:
}
#endif
-static int
-ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mfc_cache *c,
- struct rtmsg *rtm)
+static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ struct mfc_cache *c, struct rtmsg *rtm)
{
int ct;
struct rtnexthop *nhp;
@@ -1994,11 +1993,93 @@ int ipmr_get_route(struct net *net,
if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
cache->mfc_flags |= MFC_NOTIFY;
- err = ipmr_fill_mroute(mrt, skb, cache, rtm);
+ err = __ipmr_fill_mroute(mrt, skb, cache, rtm);
read_unlock(&mrt_lock);
return err;
}
+static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
+ u32 pid, u32 seq, struct mfc_cache *c)
+{
+ struct nlmsghdr *nlh;
+ struct rtmsg *rtm;
+
+ nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI);
+ if (nlh == NULL)
+ return -EMSGSIZE;
+
+ rtm = nlmsg_data(nlh);
+ rtm->rtm_family = RTNL_FAMILY_IPMR;
+ rtm->rtm_dst_len = 32;
+ rtm->rtm_src_len = 32;
+ rtm->rtm_tos = 0;
+ rtm->rtm_table = mrt->id;
+ NLA_PUT_U32(skb, RTA_TABLE, mrt->id);
+ rtm->rtm_type = RTN_MULTICAST;
+ rtm->rtm_scope = RT_SCOPE_UNIVERSE;
+ rtm->rtm_protocol = RTPROT_UNSPEC;
+ rtm->rtm_flags = 0;
+
+ NLA_PUT_BE32(skb, RTA_SRC, c->mfc_origin);
+ NLA_PUT_BE32(skb, RTA_DST, c->mfc_mcastgrp);
+
+ if (__ipmr_fill_mroute(mrt, skb, c, rtm) < 0)
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct mr_table *mrt;
+ struct mfc_cache *mfc;
+ unsigned int t = 0, s_t;
+ unsigned int h = 0, s_h;
+ unsigned int e = 0, s_e;
+
+ s_t = cb->args[0];
+ s_h = cb->args[1];
+ s_e = cb->args[2];
+
+ read_lock(&mrt_lock);
+ ipmr_for_each_table(mrt, net) {
+ if (t < s_t)
+ goto next_table;
+ if (t > s_t)
+ s_h = 0;
+ for (h = s_h; h < MFC_LINES; h++) {
+ list_for_each_entry(mfc, &mrt->mfc_cache_array[h], list) {
+ if (e < s_e)
+ goto next_entry;
+ if (ipmr_fill_mroute(mrt, skb,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq,
+ mfc) < 0)
+ goto done;
+next_entry:
+ e++;
+ }
+ e = s_e = 0;
+ }
+ s_h = 0;
+next_table:
+ t++;
+ }
+done:
+ read_unlock(&mrt_lock);
+
+ cb->args[2] = e;
+ cb->args[1] = h;
+ cb->args[0] = t;
+
+ return skb->len;
+}
+
#ifdef CONFIG_PROC_FS
/*
* The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif
@@ -2227,9 +2308,9 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
const struct ipmr_mfc_iter *it = seq->private;
const struct mr_table *mrt = it->mrt;
- seq_printf(seq, "%08lX %08lX %-3hd",
- (unsigned long) mfc->mfc_mcastgrp,
- (unsigned long) mfc->mfc_origin,
+ seq_printf(seq, "%08X %08X %-3hd",
+ (__force u32) mfc->mfc_mcastgrp,
+ (__force u32) mfc->mfc_origin,
mfc->mfc_parent);
if (it->cache != &mrt->mfc_unres_queue) {
@@ -2355,6 +2436,7 @@ int __init ip_mr_init(void)
goto add_proto_fail;
}
#endif
+ rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute);
return 0;
#ifdef CONFIG_IP_PIMSM_V2
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bbda0d5f924..2c7a1639388 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -290,7 +290,7 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
{
/* Charge it to the socket. */
- if (sock_queue_rcv_skb(sk, skb) < 0) {
+ if (ip_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index cb562fdd9b9..dea3f926425 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,7 +129,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
-static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ;
static int rt_chain_length_max __read_mostly = 20;
static struct delayed_work expires_work;
@@ -258,10 +257,9 @@ static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
(__raw_get_cpu_var(rt_cache_stat).field++)
static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
+ int genid)
{
- return jhash_3words((__force u32)(__be32)(daddr),
- (__force u32)(__be32)(saddr),
+ return jhash_3words((__force u32)daddr, (__force u32)saddr,
idx, genid)
& rt_hash_mask;
}
@@ -378,12 +376,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
struct rtable *r = v;
int len;
- seq_printf(seq, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
- "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
+ seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
+ "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
r->u.dst.dev ? r->u.dst.dev->name : "*",
- (unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
+ (__force u32)r->rt_dst,
+ (__force u32)r->rt_gateway,
r->rt_flags, atomic_read(&r->u.dst.__refcnt),
- r->u.dst.__use, 0, (unsigned long)r->rt_src,
+ r->u.dst.__use, 0, (__force u32)r->rt_src,
(dst_metric(&r->u.dst, RTAX_ADVMSS) ?
(int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
dst_metric(&r->u.dst, RTAX_WINDOW),
@@ -685,18 +684,17 @@ static inline bool rt_caching(const struct net *net)
static inline bool compare_hash_inputs(const struct flowi *fl1,
const struct flowi *fl2)
{
- return (__force u32)(((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) |
+ return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->iif ^ fl2->iif)) == 0);
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
- (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) |
+ return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) |
+ ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) |
(fl1->mark ^ fl2->mark) |
- (*(u16 *)&fl1->nl_u.ip4_u.tos ^
- *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) |
(fl1->oif ^ fl2->oif) |
(fl1->iif ^ fl2->iif)) == 0;
}
@@ -919,32 +917,11 @@ void rt_cache_flush_batch(void)
rt_do_flush(!in_softirq());
}
-/*
- * We change rt_genid and let gc do the cleanup
- */
-static void rt_secret_rebuild(unsigned long __net)
-{
- struct net *net = (struct net *)__net;
- rt_cache_invalidate(net);
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
-}
-
-static void rt_secret_rebuild_oneshot(struct net *net)
-{
- del_timer_sync(&net->ipv4.rt_secret_timer);
- rt_cache_invalidate(net);
- if (ip_rt_secret_interval)
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
-}
-
static void rt_emergency_hash_rebuild(struct net *net)
{
- if (net_ratelimit()) {
+ if (net_ratelimit())
printk(KERN_WARNING "Route hash chain too long!\n");
- printk(KERN_WARNING "Adjust your secret_interval!\n");
- }
-
- rt_secret_rebuild_oneshot(net);
+ rt_cache_invalidate(net);
}
/*
@@ -2319,8 +2296,8 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
rth = rcu_dereference(rth->u.dst.rt_next)) {
- if (((rth->fl.fl4_dst ^ daddr) |
- (rth->fl.fl4_src ^ saddr) |
+ if ((((__force u32)rth->fl.fl4_dst ^ (__force u32)daddr) |
+ ((__force u32)rth->fl.fl4_src ^ (__force u32)saddr) |
(rth->fl.iif ^ iif) |
rth->fl.oif |
(rth->fl.fl4_tos ^ tos)) == 0 &&
@@ -3102,48 +3079,6 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
return -EINVAL;
}
-static void rt_secret_reschedule(int old)
-{
- struct net *net;
- int new = ip_rt_secret_interval;
- int diff = new - old;
-
- if (!diff)
- return;
-
- rtnl_lock();
- for_each_net(net) {
- int deleted = del_timer_sync(&net->ipv4.rt_secret_timer);
- long time;
-
- if (!new)
- continue;
-
- if (deleted) {
- time = net->ipv4.rt_secret_timer.expires - jiffies;
-
- if (time <= 0 || (time += diff) <= 0)
- time = 0;
- } else
- time = new;
-
- mod_timer(&net->ipv4.rt_secret_timer, jiffies + time);
- }
- rtnl_unlock();
-}
-
-static int ipv4_sysctl_rt_secret_interval(ctl_table *ctl, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
-{
- int old = ip_rt_secret_interval;
- int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
-
- rt_secret_reschedule(old);
-
- return ret;
-}
-
static ctl_table ipv4_route_table[] = {
{
.procname = "gc_thresh",
@@ -3252,13 +3187,6 @@ static ctl_table ipv4_route_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "secret_interval",
- .data = &ip_rt_secret_interval,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = ipv4_sysctl_rt_secret_interval,
- },
{ }
};
@@ -3337,34 +3265,15 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
};
#endif
-
-static __net_init int rt_secret_timer_init(struct net *net)
+static __net_init int rt_genid_init(struct net *net)
{
- atomic_set(&net->ipv4.rt_genid,
- (int) ((num_physpages ^ (num_physpages>>8)) ^
- (jiffies ^ (jiffies >> 7))));
-
- net->ipv4.rt_secret_timer.function = rt_secret_rebuild;
- net->ipv4.rt_secret_timer.data = (unsigned long)net;
- init_timer_deferrable(&net->ipv4.rt_secret_timer);
-
- if (ip_rt_secret_interval) {
- net->ipv4.rt_secret_timer.expires =
- jiffies + net_random() % ip_rt_secret_interval +
- ip_rt_secret_interval;
- add_timer(&net->ipv4.rt_secret_timer);
- }
+ get_random_bytes(&net->ipv4.rt_genid,
+ sizeof(net->ipv4.rt_genid));
return 0;
}
-static __net_exit void rt_secret_timer_exit(struct net *net)
-{
- del_timer_sync(&net->ipv4.rt_secret_timer);
-}
-
-static __net_initdata struct pernet_operations rt_secret_timer_ops = {
- .init = rt_secret_timer_init,
- .exit = rt_secret_timer_exit,
+static __net_initdata struct pernet_operations rt_genid_ops = {
+ .init = rt_genid_init,
};
@@ -3425,9 +3334,6 @@ int __init ip_rt_init(void)
schedule_delayed_work(&expires_work,
net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
- if (register_pernet_subsys(&rt_secret_timer_ops))
- printk(KERN_ERR "Unable to setup rt_secret_timer\n");
-
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
@@ -3439,6 +3345,7 @@ int __init ip_rt_init(void)
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
#endif
+ register_pernet_subsys(&rt_genid_ops);
return rc;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0f8caf64caa..8ce29747ad9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -378,7 +378,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
struct sock *sk = sock->sk;
struct tcp_sock *tp = tcp_sk(sk);
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -2298,7 +2298,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
if (sock_flag(sk, SOCK_KEEPOPEN) &&
!((1 << sk->sk_state) &
(TCPF_CLOSE | TCPF_LISTEN))) {
- __u32 elapsed = tcp_time_stamp - tp->rcv_tstamp;
+ u32 elapsed = keepalive_time_elapsed(tp);
if (tp->keepalive_time > elapsed)
elapsed = tp->keepalive_time - elapsed;
else
@@ -2721,7 +2721,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
struct tcphdr *th2;
unsigned int len;
unsigned int thlen;
- unsigned int flags;
+ __be32 flags;
unsigned int mss = 1;
unsigned int hlen;
unsigned int off;
@@ -2771,10 +2771,10 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
found:
flush = NAPI_GRO_CB(p)->flush;
- flush |= flags & TCP_FLAG_CWR;
- flush |= (flags ^ tcp_flag_word(th2)) &
- ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH);
- flush |= th->ack_seq ^ th2->ack_seq;
+ flush |= (__force int)(flags & TCP_FLAG_CWR);
+ flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
+ ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
+ flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
for (i = sizeof(*th); i < thlen; i += 4)
flush |= *(u32 *)((u8 *)th + i) ^
*(u32 *)((u8 *)th2 + i);
@@ -2795,8 +2795,9 @@ found:
out_check_final:
flush = len < mss;
- flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST |
- TCP_FLAG_SYN | TCP_FLAG_FIN);
+ flush |= (__force int)(flags & (TCP_FLAG_URG | TCP_FLAG_PSH |
+ TCP_FLAG_RST | TCP_FLAG_SYN |
+ TCP_FLAG_FIN));
if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
pp = head;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ae3ec15fb63..e82162c211b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4367,6 +4367,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq)
goto drop;
+ skb_dst_drop(skb);
__skb_pull(skb, th->doff * 4);
TCP_ECN_accept_cwr(tp, skb);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ad08392a738..771f8146a2e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1286,8 +1286,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_release;
/* Secret recipe starts with IP addresses */
- *mess++ ^= daddr;
- *mess++ ^= saddr;
+ *mess++ ^= (__force u32)daddr;
+ *mess++ ^= (__force u32)saddr;
/* plus variable length Initiator Cookie */
c = (u8 *)mess;
@@ -1672,7 +1672,7 @@ process:
skb->dev = NULL;
- inet_rps_save_rxhash(sk, skb->rxhash);
+ sock_rps_save_rxhash(sk, skb->rxhash);
bh_lock_sock_nested(sk);
ret = 0;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2b7d71fb843..5db3a2c6cb3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -861,7 +861,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
th->urg_ptr = htons(tp->snd_up - tcb->seq);
th->urg = 1;
} else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) {
- th->urg_ptr = 0xFFFF;
+ th->urg_ptr = htons(0xFFFF);
th->urg = 1;
}
}
@@ -888,7 +888,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
tcp_event_data_sent(tp, skb, sk);
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS,
+ tcp_skb_pcount(skb));
err = icsk->icsk_af_ops->queue_xmit(skb);
if (likely(err <= 0))
@@ -2485,7 +2486,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
*tail-- ^= TCP_SKB_CB(skb)->seq + 1;
/* recommended */
- *tail-- ^= ((th->dest << 16) | th->source);
+ *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source);
*tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
sha_transform((__u32 *)&xvp->cookie_bakery[0],
@@ -2503,7 +2504,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
th->window = htons(min(req->rcv_wnd, 65535U));
tcp_options_write((__be32 *)(th + 1), tp, &opts);
th->doff = (tcp_header_size >> 2);
- TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+ TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb));
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c732be00606..440a5c6004f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -517,7 +517,7 @@ static void tcp_keepalive_timer (unsigned long data)
struct sock *sk = (struct sock *) data;
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- __u32 elapsed;
+ u32 elapsed;
/* Only process if socket is not in use. */
bh_lock_sock(sk);
@@ -554,7 +554,7 @@ static void tcp_keepalive_timer (unsigned long data)
if (tp->packets_out || tcp_send_head(sk))
goto resched;
- elapsed = tcp_time_stamp - tp->rcv_tstamp;
+ elapsed = keepalive_time_elapsed(tp);
if (elapsed >= keepalive_time_when(tp)) {
if (icsk->icsk_probes_out >= keepalive_probes(tp)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 666b963496f..4560b291180 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -307,13 +307,13 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr,
unsigned int port)
{
- return jhash_1word(saddr, net_hash_mix(net)) ^ port;
+ return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port;
}
int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
- udp4_portaddr_hash(sock_net(sk), INADDR_ANY, snum);
+ udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum);
unsigned int hash2_partial =
udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);
@@ -466,14 +466,14 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
daddr, hnum, dif,
hslot2, slot2);
if (!result) {
- hash2 = udp4_portaddr_hash(net, INADDR_ANY, hnum);
+ hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
if (hslot->count < hslot2->count)
goto begin;
result = udp4_lib_lookup2(net, saddr, sport,
- INADDR_ANY, hnum, dif,
+ htonl(INADDR_ANY), hnum, dif,
hslot2, slot2);
}
rcu_read_unlock();
@@ -1062,10 +1062,10 @@ static unsigned int first_packet_length(struct sock *sk)
spin_unlock_bh(&rcvq->lock);
if (!skb_queue_empty(&list_kill)) {
- lock_sock(sk);
+ lock_sock_bh(sk);
__skb_queue_purge(&list_kill);
sk_mem_reclaim_partial(sk);
- release_sock(sk);
+ unlock_sock_bh(sk);
}
return res;
}
@@ -1196,10 +1196,10 @@ out:
return err;
csum_copy_err:
- lock_sock(sk);
+ lock_sock_bh(sk);
if (!skb_kill_datagram(sk, skb, flags))
UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
- release_sock(sk);
+ unlock_sock_bh(sk);
if (noblock)
return -EAGAIN;
@@ -1217,7 +1217,7 @@ int udp_disconnect(struct sock *sk, int flags)
sk->sk_state = TCP_CLOSE;
inet->inet_daddr = 0;
inet->inet_dport = 0;
- inet_rps_save_rxhash(sk, 0);
+ sock_rps_save_rxhash(sk, 0);
sk->sk_bound_dev_if = 0;
if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
inet_reset_saddr(sk);
@@ -1262,9 +1262,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
int rc;
if (inet_sk(sk)->inet_daddr)
- inet_rps_save_rxhash(sk, skb->rxhash);
+ sock_rps_save_rxhash(sk, skb->rxhash);
- rc = sock_queue_rcv_skb(sk, skb);
+ rc = ip_queue_rcv_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
@@ -1372,6 +1372,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
goto drop;
}
+
+ if (sk_rcvqueues_full(sk, skb))
+ goto drop;
+
rc = 0;
bh_lock_sock(sk);
@@ -1620,9 +1624,9 @@ int udp_rcv(struct sk_buff *skb)
void udp_destroy_sock(struct sock *sk)
{
- lock_sock(sk);
+ lock_sock_bh(sk);
udp_flush_pending_frames(sk);
- release_sock(sk);
+ unlock_sock_bh(sk);
}
/*
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 7cba8845242..3984f52181f 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -588,7 +588,8 @@ static u32 ipv6_addr_hash(const struct in6_addr *addr)
* We perform the hash function over the last 64 bits of the address
* This will include the IEEE address token on links that support it.
*/
- return jhash_2words(addr->s6_addr32[2], addr->s6_addr32[3], 0)
+ return jhash_2words((__force u32)addr->s6_addr32[2],
+ (__force u32)addr->s6_addr32[3], 0)
& (IN6_ADDR_HSIZE - 1);
}
@@ -1345,7 +1346,7 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
struct hlist_node *node;
rcu_read_lock_bh();
- hlist_for_each_entry_rcu(ifp, node, &inet6_addr_lst[hash], addr_lst) {
+ hlist_for_each_entry_rcu_bh(ifp, node, &inet6_addr_lst[hash], addr_lst) {
if (!net_eq(dev_net(ifp->idev->dev), net))
continue;
if (ipv6_addr_equal(&ifp->addr, addr)) {
@@ -2958,7 +2959,7 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq)
for (state->bucket = 0; state->bucket < IN6_ADDR_HSIZE; ++state->bucket) {
struct hlist_node *n;
- hlist_for_each_entry_rcu(ifa, n, &inet6_addr_lst[state->bucket],
+ hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket],
addr_lst)
if (net_eq(dev_net(ifa->idev->dev), net))
return ifa;
@@ -2973,12 +2974,12 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
struct net *net = seq_file_net(seq);
struct hlist_node *n = &ifa->addr_lst;
- hlist_for_each_entry_continue_rcu(ifa, n, addr_lst)
+ hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst)
if (net_eq(dev_net(ifa->idev->dev), net))
return ifa;
while (++state->bucket < IN6_ADDR_HSIZE) {
- hlist_for_each_entry(ifa, n,
+ hlist_for_each_entry_rcu_bh(ifa, n,
&inet6_addr_lst[state->bucket], addr_lst) {
if (net_eq(dev_net(ifa->idev->dev), net))
return ifa;
@@ -2999,7 +3000,7 @@ static struct inet6_ifaddr *if6_get_idx(struct seq_file *seq, loff_t pos)
}
static void *if6_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(rcu)
+ __acquires(rcu_bh)
{
rcu_read_lock_bh();
return if6_get_idx(seq, *pos);
@@ -3015,7 +3016,7 @@ static void *if6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
}
static void if6_seq_stop(struct seq_file *seq, void *v)
- __releases(rcu)
+ __releases(rcu_bh)
{
rcu_read_unlock_bh();
}
@@ -3092,7 +3093,7 @@ int ipv6_chk_home_addr(struct net *net, struct in6_addr *addr)
unsigned int hash = ipv6_addr_hash(addr);
rcu_read_lock_bh();
- hlist_for_each_entry_rcu(ifp, n, &inet6_addr_lst[hash], addr_lst) {
+ hlist_for_each_entry_rcu_bh(ifp, n, &inet6_addr_lst[hash], addr_lst) {
if (!net_eq(dev_net(ifp->idev->dev), net))
continue;
if (ipv6_addr_equal(&ifp->addr, addr) &&
@@ -3126,7 +3127,7 @@ static void addrconf_verify(unsigned long foo)
for (i = 0; i < IN6_ADDR_HSIZE; i++) {
restart:
- hlist_for_each_entry_rcu(ifp, node,
+ hlist_for_each_entry_rcu_bh(ifp, node,
&inet6_addr_lst[i], addr_lst) {
unsigned long age;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3192aa02ba5..d2df3144429 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -417,6 +417,9 @@ void inet6_destroy_sock(struct sock *sk)
if ((skb = xchg(&np->pktoptions, NULL)) != NULL)
kfree_skb(skb);
+ if ((skb = xchg(&np->rxpmtu, NULL)) != NULL)
+ kfree_skb(skb);
+
/* Free flowlabels */
fl6_free_socklist(sk);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 622dc7939a1..5959230bc6c 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -278,6 +278,45 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi *fl, u32 info)
kfree_skb(skb);
}
+void ipv6_local_rxpmtu(struct sock *sk, struct flowi *fl, u32 mtu)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6hdr *iph;
+ struct sk_buff *skb;
+ struct ip6_mtuinfo *mtu_info;
+
+ if (!np->rxopt.bits.rxpmtu)
+ return;
+
+ skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
+ if (!skb)
+ return;
+
+ skb_put(skb, sizeof(struct ipv6hdr));
+ skb_reset_network_header(skb);
+ iph = ipv6_hdr(skb);
+ ipv6_addr_copy(&iph->daddr, &fl->fl6_dst);
+
+ mtu_info = IP6CBMTU(skb);
+ if (!mtu_info) {
+ kfree_skb(skb);
+ return;
+ }
+
+ mtu_info->ip6m_mtu = mtu;
+ mtu_info->ip6m_addr.sin6_family = AF_INET6;
+ mtu_info->ip6m_addr.sin6_port = 0;
+ mtu_info->ip6m_addr.sin6_flowinfo = 0;
+ mtu_info->ip6m_addr.sin6_scope_id = fl->oif;
+ ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
+
+ __skb_pull(skb, skb_tail_pointer(skb) - skb->data);
+ skb_reset_transport_header(skb);
+
+ skb = xchg(&np->rxpmtu, skb);
+ kfree_skb(skb);
+}
+
/*
* Handle MSG_ERRQUEUE
*/
@@ -381,6 +420,54 @@ out:
return err;
}
+/*
+ * Handle IPV6_RECVPATHMTU
+ */
+int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
+{
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct sk_buff *skb;
+ struct sockaddr_in6 *sin;
+ struct ip6_mtuinfo mtu_info;
+ int err;
+ int copied;
+
+ err = -EAGAIN;
+ skb = xchg(&np->rxpmtu, NULL);
+ if (skb == NULL)
+ goto out;
+
+ copied = skb->len;
+ if (copied > len) {
+ msg->msg_flags |= MSG_TRUNC;
+ copied = len;
+ }
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
+ if (err)
+ goto out_free_skb;
+
+ sock_recv_timestamp(msg, sk, skb);
+
+ memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
+
+ sin = (struct sockaddr_in6 *)msg->msg_name;
+ if (sin) {
+ sin->sin6_family = AF_INET6;
+ sin->sin6_flowinfo = 0;
+ sin->sin6_port = 0;
+ sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
+ ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr);
+ }
+
+ put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
+
+ err = copied;
+
+out_free_skb:
+ kfree_skb(skb);
+out:
+ return err;
+}
int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
@@ -497,7 +584,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
int datagram_send_ctl(struct net *net,
struct msghdr *msg, struct flowi *fl,
struct ipv6_txoptions *opt,
- int *hlimit, int *tclass)
+ int *hlimit, int *tclass, int *dontfrag)
{
struct in6_pktinfo *src_info;
struct cmsghdr *cmsg;
@@ -737,6 +824,25 @@ int datagram_send_ctl(struct net *net,
break;
}
+
+ case IPV6_DONTFRAG:
+ {
+ int df;
+
+ err = -EINVAL;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(int))) {
+ goto exit_f;
+ }
+
+ df = *(int *)CMSG_DATA(cmsg);
+ if (df < 0 || df > 1)
+ goto exit_f;
+
+ err = 0;
+ *dontfrag = df;
+
+ break;
+ }
default:
LIMIT_NETDEBUG(KERN_DEBUG "invalid cmsg type: %d\n",
cmsg->cmsg_type);
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 8124f16f2ac..8e44f8f9c18 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -237,8 +237,8 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
+ nla_total_size(16); /* src */
}
-static struct fib_rules_ops fib6_rules_ops_template = {
- .family = FIB_RULES_IPV6,
+static const struct fib_rules_ops __net_initdata fib6_rules_ops_template = {
+ .family = AF_INET6,
.rule_size = sizeof(struct fib6_rule),
.addr_size = sizeof(struct in6_addr),
.action = fib6_rule_action,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 12d2fa42657..ce799298255 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -481,7 +481,7 @@ route_done:
len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr), hlimit,
np->tclass, NULL, &fl, (struct rt6_info*)dst,
- MSG_DONTWAIT);
+ MSG_DONTWAIT, np->dontfrag);
if (err) {
ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
ip6_flush_pending_frames(sk);
@@ -561,7 +561,8 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
sizeof(struct icmp6hdr), hlimit, np->tclass, NULL, &fl,
- (struct rt6_info*)dst, MSG_DONTWAIT);
+ (struct rt6_info*)dst, MSG_DONTWAIT,
+ np->dontfrag);
if (err) {
ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index dc6e0b8f260..92a122b7795 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -144,7 +144,8 @@ static __inline__ __be32 addr_bit_set(void *token, int fn_bit)
* htonl(1 << ((~fn_bit)&0x1F))
* See include/asm-generic/bitops/le.h.
*/
- return (1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) & addr[fn_bit >> 5];
+ return (__force __be32)(1 << ((~fn_bit ^ BITOP_BE32_SWIZZLE) & 0x1f)) &
+ addr[fn_bit >> 5];
}
static __inline__ struct fib6_node * node_alloc(void)
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 14e23216eb2..13654686aea 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -360,7 +360,8 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
msg.msg_control = (void*)(fl->opt+1);
flowi.oif = 0;
- err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk);
+ err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk,
+ &junk, &junk);
if (err)
goto done;
err = -EINVAL;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7f12e30cfa7..5173acaeb50 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -92,7 +92,7 @@ static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
newskb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(newskb));
- netif_rx(newskb);
+ netif_rx_ni(newskb);
return 0;
}
@@ -216,8 +216,7 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
}
kfree_skb(skb);
skb = skb2;
- if (sk)
- skb_set_owner_w(skb, sk);
+ skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
@@ -623,7 +622,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
/* We must not fragment if the socket is set to force MTU discovery
* or if the skb it not generated by a local socket.
*/
- if (!skb->local_df) {
+ if (!skb->local_df && skb->len > mtu) {
skb->dev = skb_dst(skb)->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
@@ -1103,7 +1102,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
- struct rt6_info *rt, unsigned int flags)
+ struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -1217,15 +1216,23 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
*/
inet->cork.length += length;
- if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
- (rt->u.dst.dev->features & NETIF_F_UFO)) {
+ if (length > mtu) {
+ int proto = sk->sk_protocol;
+ if (dontfrag && (proto == IPPROTO_UDP || proto == IPPROTO_RAW)){
+ ipv6_local_rxpmtu(sk, fl, mtu-exthdrlen);
+ return -EMSGSIZE;
+ }
- err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len,
- fragheaderlen, transhdrlen, mtu,
- flags);
- if (err)
- goto error;
- return 0;
+ if (proto == IPPROTO_UDP &&
+ (rt->u.dst.dev->features & NETIF_F_UFO)) {
+
+ err = ip6_ufo_append_data(sk, getfrag, from, length,
+ hh_len, fragheaderlen,
+ transhdrlen, mtu, flags);
+ if (err)
+ goto error;
+ return 0;
+ }
}
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 1160400e9db..bd43f0152c2 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -337,6 +337,13 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
retv = 0;
break;
+ case IPV6_RECVPATHMTU:
+ if (optlen < sizeof(int))
+ goto e_inval;
+ np->rxopt.bits.rxpmtu = valbool;
+ retv = 0;
+ break;
+
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
@@ -451,7 +458,8 @@ sticky_done:
msg.msg_controllen = optlen;
msg.msg_control = (void*)(opt+1);
- retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk);
+ retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk,
+ &junk);
if (retv)
goto done;
update:
@@ -767,6 +775,17 @@ pref_skip_coa:
break;
}
+ case IPV6_MINHOPCOUNT:
+ if (optlen < sizeof(int))
+ goto e_inval;
+ if (val < 0 || val > 255)
+ goto e_inval;
+ np->min_hopcount = val;
+ break;
+ case IPV6_DONTFRAG:
+ np->dontfrag = valbool;
+ retv = 0;
+ break;
}
release_sock(sk);
@@ -1055,6 +1074,38 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val = np->rxopt.bits.rxflow;
break;
+ case IPV6_RECVPATHMTU:
+ val = np->rxopt.bits.rxpmtu;
+ break;
+
+ case IPV6_PATHMTU:
+ {
+ struct dst_entry *dst;
+ struct ip6_mtuinfo mtuinfo;
+
+ if (len < sizeof(mtuinfo))
+ return -EINVAL;
+
+ len = sizeof(mtuinfo);
+ memset(&mtuinfo, 0, sizeof(mtuinfo));
+
+ rcu_read_lock();
+ dst = __sk_dst_get(sk);
+ if (dst)
+ mtuinfo.ip6m_mtu = dst_mtu(dst);
+ rcu_read_unlock();
+ if (!mtuinfo.ip6m_mtu)
+ return -ENOTCONN;
+
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &mtuinfo, len))
+ return -EFAULT;
+
+ return 0;
+ break;
+ }
+
case IPV6_UNICAST_HOPS:
case IPV6_MULTICAST_HOPS:
{
@@ -1116,6 +1167,14 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
val |= IPV6_PREFER_SRC_HOME;
break;
+ case IPV6_MINHOPCOUNT:
+ val = np->min_hopcount;
+ break;
+
+ case IPV6_DONTFRAG:
+ val = np->dontfrag;
+ break;
+
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index f9d05ce4e03..59f1881968c 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -44,6 +44,7 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
+#include <net/mld.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
@@ -71,54 +72,11 @@
#define MDBG(x)
#endif
-/*
- * These header formats should be in a separate include file, but icmpv6.h
- * doesn't have in6_addr defined in all cases, there is no __u128, and no
- * other files reference these.
- *
- * +-DLS 4/14/03
- */
-
-/* Multicast Listener Discovery version 2 headers */
-
-struct mld2_grec {
- __u8 grec_type;
- __u8 grec_auxwords;
- __be16 grec_nsrcs;
- struct in6_addr grec_mca;
- struct in6_addr grec_src[0];
-};
-
-struct mld2_report {
- __u8 type;
- __u8 resv1;
- __sum16 csum;
- __be16 resv2;
- __be16 ngrec;
- struct mld2_grec grec[0];
-};
-
-struct mld2_query {
- __u8 type;
- __u8 code;
- __sum16 csum;
- __be16 mrc;
- __be16 resv1;
- struct in6_addr mca;
-#if defined(__LITTLE_ENDIAN_BITFIELD)
- __u8 qrv:3,
- suppress:1,
- resv2:4;
-#elif defined(__BIG_ENDIAN_BITFIELD)
- __u8 resv2:4,
- suppress:1,
- qrv:3;
-#else
-#error "Please fix <asm/byteorder.h>"
-#endif
- __u8 qqic;
- __be16 nsrcs;
- struct in6_addr srcs[0];
+/* Ensure that we have struct in6_addr aligned on 32bit word. */
+static void *__mld2_query_bugs[] __attribute__((__unused__)) = {
+ BUILD_BUG_ON_NULL(offsetof(struct mld2_query, mld2q_srcs) % 4),
+ BUILD_BUG_ON_NULL(offsetof(struct mld2_report, mld2r_grec) % 4),
+ BUILD_BUG_ON_NULL(offsetof(struct mld2_grec, grec_mca) % 4)
};
static struct in6_addr mld2_all_mcr = MLD2_ALL_MCR_INIT;
@@ -157,14 +115,6 @@ static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
((idev)->mc_v1_seen && \
time_before(jiffies, (idev)->mc_v1_seen)))
-#define MLDV2_MASK(value, nb) ((nb)>=32 ? (value) : ((1<<(nb))-1) & (value))
-#define MLDV2_EXP(thresh, nbmant, nbexp, value) \
- ((value) < (thresh) ? (value) : \
- ((MLDV2_MASK(value, nbmant) | (1<<(nbmant))) << \
- (MLDV2_MASK((value) >> (nbmant), nbexp) + (nbexp))))
-
-#define MLDV2_MRC(value) MLDV2_EXP(0x8000, 12, 3, value)
-
#define IPV6_MLD_MAX_MSF 64
int sysctl_mld_max_msf __read_mostly = IPV6_MLD_MAX_MSF;
@@ -1161,7 +1111,7 @@ int igmp6_event_query(struct sk_buff *skb)
struct in6_addr *group;
unsigned long max_delay;
struct inet6_dev *idev;
- struct icmp6hdr *hdr;
+ struct mld_msg *mld;
int group_type;
int mark = 0;
int len;
@@ -1182,8 +1132,8 @@ int igmp6_event_query(struct sk_buff *skb)
if (idev == NULL)
return 0;
- hdr = icmp6_hdr(skb);
- group = (struct in6_addr *) (hdr + 1);
+ mld = (struct mld_msg *)icmp6_hdr(skb);
+ group = &mld->mld_mca;
group_type = ipv6_addr_type(group);
if (group_type != IPV6_ADDR_ANY &&
@@ -1197,7 +1147,7 @@ int igmp6_event_query(struct sk_buff *skb)
/* MLDv1 router present */
/* Translate milliseconds to jiffies */
- max_delay = (ntohs(hdr->icmp6_maxdelay)*HZ)/1000;
+ max_delay = (ntohs(mld->mld_maxdelay)*HZ)/1000;
switchback = (idev->mc_qrv + 1) * max_delay;
idev->mc_v1_seen = jiffies + switchback;
@@ -1216,14 +1166,14 @@ int igmp6_event_query(struct sk_buff *skb)
return -EINVAL;
}
mlh2 = (struct mld2_query *)skb_transport_header(skb);
- max_delay = (MLDV2_MRC(ntohs(mlh2->mrc))*HZ)/1000;
+ max_delay = (MLDV2_MRC(ntohs(mlh2->mld2q_mrc))*HZ)/1000;
if (!max_delay)
max_delay = 1;
idev->mc_maxdelay = max_delay;
- if (mlh2->qrv)
- idev->mc_qrv = mlh2->qrv;
+ if (mlh2->mld2q_qrv)
+ idev->mc_qrv = mlh2->mld2q_qrv;
if (group_type == IPV6_ADDR_ANY) { /* general query */
- if (mlh2->nsrcs) {
+ if (mlh2->mld2q_nsrcs) {
in6_dev_put(idev);
return -EINVAL; /* no sources allowed */
}
@@ -1232,9 +1182,9 @@ int igmp6_event_query(struct sk_buff *skb)
return 0;
}
/* mark sources to include, if group & source-specific */
- if (mlh2->nsrcs != 0) {
+ if (mlh2->mld2q_nsrcs != 0) {
if (!pskb_may_pull(skb, srcs_offset +
- ntohs(mlh2->nsrcs) * sizeof(struct in6_addr))) {
+ ntohs(mlh2->mld2q_nsrcs) * sizeof(struct in6_addr))) {
in6_dev_put(idev);
return -EINVAL;
}
@@ -1270,7 +1220,7 @@ int igmp6_event_query(struct sk_buff *skb)
ma->mca_flags &= ~MAF_GSQUERY;
}
if (!(ma->mca_flags & MAF_GSQUERY) ||
- mld_marksources(ma, ntohs(mlh2->nsrcs), mlh2->srcs))
+ mld_marksources(ma, ntohs(mlh2->mld2q_nsrcs), mlh2->mld2q_srcs))
igmp6_group_queried(ma, max_delay);
spin_unlock_bh(&ma->mca_lock);
break;
@@ -1286,9 +1236,8 @@ int igmp6_event_query(struct sk_buff *skb)
int igmp6_event_report(struct sk_buff *skb)
{
struct ifmcaddr6 *ma;
- struct in6_addr *addrp;
struct inet6_dev *idev;
- struct icmp6hdr *hdr;
+ struct mld_msg *mld;
int addr_type;
/* Our own report looped back. Ignore it. */
@@ -1300,10 +1249,10 @@ int igmp6_event_report(struct sk_buff *skb)
skb->pkt_type != PACKET_BROADCAST)
return 0;
- if (!pskb_may_pull(skb, sizeof(struct in6_addr)))
+ if (!pskb_may_pull(skb, sizeof(*mld) - sizeof(struct icmp6hdr)))
return -EINVAL;
- hdr = icmp6_hdr(skb);
+ mld = (struct mld_msg *)icmp6_hdr(skb);
/* Drop reports with not link local source */
addr_type = ipv6_addr_type(&ipv6_hdr(skb)->saddr);
@@ -1311,8 +1260,6 @@ int igmp6_event_report(struct sk_buff *skb)
!(addr_type&IPV6_ADDR_LINKLOCAL))
return -EINVAL;
- addrp = (struct in6_addr *) (hdr + 1);
-
idev = in6_dev_get(skb->dev);
if (idev == NULL)
return -ENODEV;
@@ -1323,7 +1270,7 @@ int igmp6_event_report(struct sk_buff *skb)
read_lock_bh(&idev->lock);
for (ma = idev->mc_list; ma; ma=ma->next) {
- if (ipv6_addr_equal(&ma->mca_addr, addrp)) {
+ if (ipv6_addr_equal(&ma->mca_addr, &mld->mld_mca)) {
spin_lock(&ma->mca_lock);
if (del_timer(&ma->mca_timer))
atomic_dec(&ma->mca_refcnt);
@@ -1432,11 +1379,11 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size)
skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data);
skb_put(skb, sizeof(*pmr));
pmr = (struct mld2_report *)skb_transport_header(skb);
- pmr->type = ICMPV6_MLD2_REPORT;
- pmr->resv1 = 0;
- pmr->csum = 0;
- pmr->resv2 = 0;
- pmr->ngrec = 0;
+ pmr->mld2r_type = ICMPV6_MLD2_REPORT;
+ pmr->mld2r_resv1 = 0;
+ pmr->mld2r_cksum = 0;
+ pmr->mld2r_resv2 = 0;
+ pmr->mld2r_ngrec = 0;
return skb;
}
@@ -1458,9 +1405,10 @@ static void mld_sendpack(struct sk_buff *skb)
mldlen = skb->tail - skb->transport_header;
pip6->payload_len = htons(payload_len);
- pmr->csum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen,
- IPPROTO_ICMPV6, csum_partial(skb_transport_header(skb),
- mldlen, 0));
+ pmr->mld2r_cksum = csum_ipv6_magic(&pip6->saddr, &pip6->daddr, mldlen,
+ IPPROTO_ICMPV6,
+ csum_partial(skb_transport_header(skb),
+ mldlen, 0));
dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
@@ -1521,7 +1469,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = 0;
pgr->grec_mca = pmc->mca_addr; /* structure copy */
pmr = (struct mld2_report *)skb_transport_header(skb);
- pmr->ngrec = htons(ntohs(pmr->ngrec)+1);
+ pmr->mld2r_ngrec = htons(ntohs(pmr->mld2r_ngrec)+1);
*ppgr = pgr;
return skb;
}
@@ -1557,7 +1505,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
/* EX and TO_EX get a fresh packet, if needed */
if (truncate) {
- if (pmr && pmr->ngrec &&
+ if (pmr && pmr->mld2r_ngrec &&
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
@@ -1770,9 +1718,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
struct sock *sk = net->ipv6.igmp_sk;
struct inet6_dev *idev;
struct sk_buff *skb;
- struct icmp6hdr *hdr;
+ struct mld_msg *hdr;
const struct in6_addr *snd_addr, *saddr;
- struct in6_addr *addrp;
struct in6_addr addr_buf;
int err, len, payload_len, full_len;
u8 ra[8] = { IPPROTO_ICMPV6, 0,
@@ -1820,16 +1767,14 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
memcpy(skb_put(skb, sizeof(ra)), ra, sizeof(ra));
- hdr = (struct icmp6hdr *) skb_put(skb, sizeof(struct icmp6hdr));
- memset(hdr, 0, sizeof(struct icmp6hdr));
- hdr->icmp6_type = type;
+ hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg));
+ memset(hdr, 0, sizeof(struct mld_msg));
+ hdr->mld_type = type;
+ ipv6_addr_copy(&hdr->mld_mca, addr);
- addrp = (struct in6_addr *) skb_put(skb, sizeof(struct in6_addr));
- ipv6_addr_copy(addrp, addr);
-
- hdr->icmp6_cksum = csum_ipv6_magic(saddr, snd_addr, len,
- IPPROTO_ICMPV6,
- csum_partial(hdr, len, 0));
+ hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len,
+ IPPROTO_ICMPV6,
+ csum_partial(hdr, len, 0));
idev = in6_dev_get(skb->dev);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 554b48b6e99..4a4dcbe4f8b 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -381,7 +381,7 @@ static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb)
}
/* Charge it to the socket. */
- if (sock_queue_rcv_skb(sk, skb) < 0) {
+ if (ip_queue_rcv_skb(sk, skb) < 0) {
kfree_skb(skb);
return NET_RX_DROP;
}
@@ -461,6 +461,9 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len);
+ if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ return ipv6_recv_rxpmtu(sk, msg, len);
+
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
goto out;
@@ -733,6 +736,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
int addr_len = msg->msg_namelen;
int hlimit = -1;
int tclass = -1;
+ int dontfrag = -1;
u16 proto;
int err;
@@ -811,7 +815,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(struct ipv6_txoptions);
- err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
+ err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+ &tclass, &dontfrag);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -880,6 +885,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (tclass < 0)
tclass = np->tclass;
+ if (dontfrag < 0)
+ dontfrag = np->dontfrag;
+
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
@@ -890,7 +898,7 @@ back_from_confirm:
lock_sock(sk);
err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov,
len, 0, hlimit, tclass, opt, &fl, (struct rt6_info*)dst,
- msg->msg_flags);
+ msg->msg_flags, dontfrag);
if (err)
ip6_flush_pending_frames(sk);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c2438e8cb9d..05ebd783304 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -815,7 +815,7 @@ struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
{
int flags = 0;
- if (rt6_need_strict(&fl->fl6_dst))
+ if (fl->oif || rt6_need_strict(&fl->fl6_dst))
flags |= RT6_LOOKUP_F_IFACE;
if (!ipv6_addr_any(&fl->fl6_src))
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index bd5ef7b6e48..6603511e367 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -353,6 +353,11 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (sk->sk_state == TCP_CLOSE)
goto out;
+ if (ipv6_hdr(skb)->hop_limit < inet6_sk(sk)->min_hopcount) {
+ NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+ goto out;
+ }
+
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
@@ -1018,7 +1023,7 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);
t1 = (struct tcphdr *) skb_push(buff, tot_len);
- skb_reset_transport_header(skb);
+ skb_reset_transport_header(buff);
/* Swap the send and the receive. */
memset(t1, 0, sizeof(*t1));
@@ -1050,12 +1055,13 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
}
#endif
- buff->csum = csum_partial(t1, tot_len, 0);
-
memset(&fl, 0, sizeof(fl));
ipv6_addr_copy(&fl.fl6_dst, &ipv6_hdr(skb)->saddr);
ipv6_addr_copy(&fl.fl6_src, &ipv6_hdr(skb)->daddr);
+ buff->ip_summed = CHECKSUM_PARTIAL;
+ buff->csum = 0;
+
__tcp_v6_send_check(buff, &fl.fl6_src, &fl.fl6_dst);
fl.proto = IPPROTO_TCP;
@@ -1234,12 +1240,12 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_free;
/* Secret recipe starts with IP addresses */
- d = &ipv6_hdr(skb)->daddr.s6_addr32[0];
+ d = (__force u32 *)&ipv6_hdr(skb)->daddr.s6_addr32[0];
*mess++ ^= *d++;
*mess++ ^= *d++;
*mess++ ^= *d++;
*mess++ ^= *d++;
- d = &ipv6_hdr(skb)->saddr.s6_addr32[0];
+ d = (__force u32 *)&ipv6_hdr(skb)->saddr.s6_addr32[0];
*mess++ ^= *d++;
*mess++ ^= *d++;
*mess++ ^= *d++;
@@ -1677,6 +1683,7 @@ ipv6_pktoptions:
static int tcp_v6_rcv(struct sk_buff *skb)
{
struct tcphdr *th;
+ struct ipv6hdr *hdr;
struct sock *sk;
int ret;
struct net *net = dev_net(skb->dev);
@@ -1703,12 +1710,13 @@ static int tcp_v6_rcv(struct sk_buff *skb)
goto bad_packet;
th = tcp_hdr(skb);
+ hdr = ipv6_hdr(skb);
TCP_SKB_CB(skb)->seq = ntohl(th->seq);
TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
skb->len - th->doff*4);
TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
TCP_SKB_CB(skb)->when = 0;
- TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(ipv6_hdr(skb));
+ TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(hdr);
TCP_SKB_CB(skb)->sacked = 0;
sk = __inet6_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
@@ -1719,6 +1727,11 @@ process:
if (sk->sk_state == TCP_TIME_WAIT)
goto do_time_wait;
+ if (hdr->hop_limit < inet6_sk(sk)->min_hopcount) {
+ NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
+ goto discard_and_relse;
+ }
+
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto discard_and_relse;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 90824852f59..3d7a2c0b836 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -91,9 +91,9 @@ static unsigned int udp6_portaddr_hash(struct net *net,
if (ipv6_addr_any(addr6))
hash = jhash_1word(0, mix);
else if (ipv6_addr_v4mapped(addr6))
- hash = jhash_1word(addr6->s6_addr32[3], mix);
+ hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix);
else
- hash = jhash2(addr6->s6_addr32, 4, mix);
+ hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix);
return hash ^ port;
}
@@ -335,6 +335,9 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len);
+ if (np->rxpmtu && np->rxopt.bits.rxpmtu)
+ return ipv6_recv_rxpmtu(sk, msg, len);
+
try_again:
skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
&peeked, &err);
@@ -421,7 +424,7 @@ out:
return err;
csum_copy_err:
- lock_sock(sk);
+ lock_sock_bh(sk);
if (!skb_kill_datagram(sk, skb, flags)) {
if (is_udp4)
UDP_INC_STATS_USER(sock_net(sk),
@@ -430,7 +433,7 @@ csum_copy_err:
UDP6_INC_STATS_USER(sock_net(sk),
UDP_MIB_INERRORS, is_udplite);
}
- release_sock(sk);
+ unlock_sock_bh(sk);
if (flags & MSG_DONTWAIT)
return -EAGAIN;
@@ -511,7 +514,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
goto drop;
}
- if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
+ if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM)
UDP6_INC_STATS_BH(sock_net(sk),
@@ -581,6 +584,10 @@ static void flush_stack(struct sock **stack, unsigned int count,
sk = stack[i];
if (skb1) {
+ if (sk_rcvqueues_full(sk, skb)) {
+ kfree_skb(skb1);
+ goto drop;
+ }
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
udpv6_queue_rcv_skb(sk, skb1);
@@ -692,7 +699,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
u32 ulen = 0;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- goto short_packet;
+ goto discard;
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
@@ -756,6 +763,10 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
/* deliver */
+ if (sk_rcvqueues_full(sk, skb)) {
+ sock_put(sk);
+ goto discard;
+ }
bh_lock_sock(sk);
if (!sock_owned_by_user(sk))
udpv6_queue_rcv_skb(sk, skb);
@@ -770,9 +781,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
return 0;
short_packet:
- LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n",
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
proto == IPPROTO_UDPLITE ? "-Lite" : "",
- ulen, skb->len);
+ saddr,
+ ntohs(uh->source),
+ ulen,
+ skb->len,
+ daddr,
+ ntohs(uh->dest));
discard:
UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
@@ -919,6 +935,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
int ulen = len;
int hlimit = -1;
int tclass = -1;
+ int dontfrag = -1;
int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
int err;
int connected = 0;
@@ -1049,7 +1066,8 @@ do_udp_sendmsg:
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(*opt);
- err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
+ err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit,
+ &tclass, &dontfrag);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
@@ -1120,6 +1138,9 @@ do_udp_sendmsg:
if (tclass < 0)
tclass = np->tclass;
+ if (dontfrag < 0)
+ dontfrag = np->dontfrag;
+
if (msg->msg_flags&MSG_CONFIRM)
goto do_confirm;
back_from_confirm:
@@ -1143,7 +1164,7 @@ do_append_data:
err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
sizeof(struct udphdr), hlimit, tclass, opt, &fl,
(struct rt6_info*)dst,
- corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
+ corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag);
if (err)
udp_v6_flush_pending_frames(sk);
else if (!corkreq)
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 8c452fd5cea..4a0e77e1446 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -94,7 +94,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.dst.dev = dev;
dev_hold(dev);
- xdst->u.rt6.rt6i_idev = in6_dev_get(rt->u.dst.dev);
+ xdst->u.rt6.rt6i_idev = in6_dev_get(dev);
if (!xdst->u.rt6.rt6i_idev)
return -ENODEV;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 2a4efcea342..79986a674f6 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -347,7 +347,7 @@ static void irda_flow_indication(void *instance, void *sap, LOCAL_FLOW flow)
self->tx_flow = flow;
IRDA_DEBUG(1, "%s(), IrTTP wants us to start again\n",
__func__);
- wake_up_interruptible(sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(sk));
break;
default:
IRDA_DEBUG(0, "%s(), Unknown flow command!\n", __func__);
@@ -900,7 +900,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
if (flags & O_NONBLOCK)
goto out;
- err = wait_event_interruptible(*(sk->sk_sleep),
+ err = wait_event_interruptible(*(sk_sleep(sk)),
skb_peek(&sk->sk_receive_queue));
if (err)
goto out;
@@ -1066,7 +1066,7 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
goto out;
err = -ERESTARTSYS;
- if (wait_event_interruptible(*(sk->sk_sleep),
+ if (wait_event_interruptible(*(sk_sleep(sk)),
(sk->sk_state != TCP_SYN_SENT)))
goto out;
@@ -1318,7 +1318,7 @@ static int irda_sendmsg(struct kiocb *iocb, struct socket *sock,
/* Check if IrTTP is wants us to slow down */
- if (wait_event_interruptible(*(sk->sk_sleep),
+ if (wait_event_interruptible(*(sk_sleep(sk)),
(self->tx_flow != FLOW_STOP || sk->sk_state != TCP_ESTABLISHED))) {
err = -ERESTARTSYS;
goto out;
@@ -1477,7 +1477,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
if (copied >= target)
break;
- prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/*
* POSIX 1003.1g mandates this order.
@@ -1497,7 +1497,7 @@ static int irda_recvmsg_stream(struct kiocb *iocb, struct socket *sock,
/* Wait process until data arrives */
schedule();
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err)
goto out;
@@ -1787,7 +1787,7 @@ static unsigned int irda_poll(struct file * file, struct socket *sock,
IRDA_DEBUG(4, "%s()\n", __func__);
lock_kernel();
- poll_wait(file, sk->sk_sleep, wait);
+ poll_wait(file, sk_sleep(sk), wait);
mask = 0;
/* Exceptional events? */
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index c18286a2167..8be324fe08b 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -59,7 +59,7 @@ do { \
DEFINE_WAIT(__wait); \
long __timeo = timeo; \
ret = 0; \
- prepare_to_wait(sk->sk_sleep, &__wait, TASK_INTERRUPTIBLE); \
+ prepare_to_wait(sk_sleep(sk), &__wait, TASK_INTERRUPTIBLE); \
while (!(condition)) { \
if (!__timeo) { \
ret = -EAGAIN; \
@@ -76,7 +76,7 @@ do { \
if (ret) \
break; \
} \
- finish_wait(sk->sk_sleep, &__wait); \
+ finish_wait(sk_sleep(sk), &__wait); \
} while (0)
#define iucv_sock_wait(sk, condition, timeo) \
@@ -305,11 +305,14 @@ static inline int iucv_below_msglim(struct sock *sk)
*/
static void iucv_sock_wake_msglim(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
- if (sk_has_sleeper(sk))
- wake_up_interruptible_all(sk->sk_sleep);
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_all(&wq->wait);
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
/* Timers */
@@ -795,7 +798,7 @@ static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
/* Wait for an incoming connection */
- add_wait_queue_exclusive(sk->sk_sleep, &wait);
+ add_wait_queue_exclusive(sk_sleep(sk), &wait);
while (!(nsk = iucv_accept_dequeue(sk, newsock))) {
set_current_state(TASK_INTERRUPTIBLE);
if (!timeo) {
@@ -819,7 +822,7 @@ static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
}
set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (err)
goto done;
@@ -1269,7 +1272,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk;
unsigned int mask = 0;
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == IUCV_LISTEN)
return iucv_accept_poll(sk);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ecc7aea9efe..1712af1c7b3 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1617,14 +1617,9 @@ EXPORT_SYMBOL_GPL(l2tp_session_create);
static __net_init int l2tp_init_net(struct net *net)
{
- struct l2tp_net *pn;
- int err;
+ struct l2tp_net *pn = net_generic(net, l2tp_net_id);
int hash;
- pn = kzalloc(sizeof(*pn), GFP_KERNEL);
- if (!pn)
- return -ENOMEM;
-
INIT_LIST_HEAD(&pn->l2tp_tunnel_list);
spin_lock_init(&pn->l2tp_tunnel_list_lock);
@@ -1633,33 +1628,11 @@ static __net_init int l2tp_init_net(struct net *net)
spin_lock_init(&pn->l2tp_session_hlist_lock);
- err = net_assign_generic(net, l2tp_net_id, pn);
- if (err)
- goto out;
-
return 0;
-
-out:
- kfree(pn);
- return err;
-}
-
-static __net_exit void l2tp_exit_net(struct net *net)
-{
- struct l2tp_net *pn;
-
- pn = net_generic(net, l2tp_net_id);
- /*
- * if someone has cached our net then
- * further net_generic call will return NULL
- */
- net_assign_generic(net, l2tp_net_id, NULL);
- kfree(pn);
}
static struct pernet_operations l2tp_net_ops = {
.init = l2tp_init_net,
- .exit = l2tp_exit_net,
.id = &l2tp_net_id,
.size = sizeof(struct l2tp_net),
};
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index ca1164afeb7..58c6c4cda73 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -276,43 +276,16 @@ out:
static __net_init int l2tp_eth_init_net(struct net *net)
{
- struct l2tp_eth_net *pn;
- int err;
-
- pn = kzalloc(sizeof(*pn), GFP_KERNEL);
- if (!pn)
- return -ENOMEM;
+ struct l2tp_eth_net *pn = net_generic(net, l2tp_eth_net_id);
INIT_LIST_HEAD(&pn->l2tp_eth_dev_list);
spin_lock_init(&pn->l2tp_eth_lock);
- err = net_assign_generic(net, l2tp_eth_net_id, pn);
- if (err)
- goto out;
-
return 0;
-
-out:
- kfree(pn);
- return err;
-}
-
-static __net_exit void l2tp_eth_exit_net(struct net *net)
-{
- struct l2tp_eth_net *pn;
-
- pn = net_generic(net, l2tp_eth_net_id);
- /*
- * if someone has cached our net then
- * further net_generic call will return NULL
- */
- net_assign_generic(net, l2tp_eth_net_id, NULL);
- kfree(pn);
}
static __net_initdata struct pernet_operations l2tp_eth_net_ops = {
.init = l2tp_eth_init_net,
- .exit = l2tp_eth_exit_net,
.id = &l2tp_eth_net_id,
.size = sizeof(struct l2tp_eth_net),
};
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 2db6a9f7591..023ba820236 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -536,7 +536,7 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout)
int rc = 0;
while (1) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (sk_wait_event(sk, &timeout, sk->sk_state == TCP_CLOSE))
break;
rc = -ERESTARTSYS;
@@ -547,7 +547,7 @@ static int llc_ui_wait_for_disc(struct sock *sk, long timeout)
break;
rc = 0;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return rc;
}
@@ -556,13 +556,13 @@ static int llc_ui_wait_for_conn(struct sock *sk, long timeout)
DEFINE_WAIT(wait);
while (1) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (sk_wait_event(sk, &timeout, sk->sk_state != TCP_SYN_SENT))
break;
if (signal_pending(current) || !timeout)
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return timeout;
}
@@ -573,7 +573,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout)
int rc;
while (1) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
rc = 0;
if (sk_wait_event(sk, &timeout,
(sk->sk_shutdown & RCV_SHUTDOWN) ||
@@ -588,7 +588,7 @@ static int llc_ui_wait_for_busy_core(struct sock *sk, long timeout)
if (!timeout)
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return rc;
}
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 9598fdb4ad0..6bb9a9a9496 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -19,8 +19,9 @@
#include "ieee80211_i.h"
#include "driver-ops.h"
-void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
- u16 initiator, u16 reason)
+static void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
+ u16 initiator, u16 reason,
+ bool from_timer)
{
struct ieee80211_local *local = sta->local;
struct tid_ampdu_rx *tid_rx;
@@ -70,10 +71,17 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
spin_unlock_bh(&sta->lock);
- del_timer_sync(&tid_rx->session_timer);
+ if (!from_timer)
+ del_timer_sync(&tid_rx->session_timer);
kfree(tid_rx);
}
+void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid,
+ u16 initiator, u16 reason)
+{
+ ___ieee80211_stop_rx_ba_session(sta, tid, initiator, reason, false);
+}
+
/*
* After accepting the AddBA Request we activated a timer,
* resetting it after each frame that arrives from the originator.
@@ -92,8 +100,8 @@ static void sta_rx_agg_session_timer_expired(unsigned long data)
#ifdef CONFIG_MAC80211_HT_DEBUG
printk(KERN_DEBUG "rx session timer expired on tid %d\n", (u16)*ptid);
#endif
- __ieee80211_stop_rx_ba_session(sta, *ptid, WLAN_BACK_RECIPIENT,
- WLAN_REASON_QSTA_TIMEOUT);
+ ___ieee80211_stop_rx_ba_session(sta, *ptid, WLAN_BACK_RECIPIENT,
+ WLAN_REASON_QSTA_TIMEOUT, true);
}
static void ieee80211_send_addba_resp(struct ieee80211_sub_if_data *sdata, u8 *da, u16 tid,
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 608063f1179..c163d0a149f 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -184,10 +184,9 @@ static void sta_addba_resp_timer_expired(unsigned long data)
HT_AGG_STATE_REQ_STOP_BA_MSK)) !=
HT_ADDBA_REQUESTED_MSK) {
spin_unlock_bh(&sta->lock);
- *state = HT_AGG_STATE_IDLE;
#ifdef CONFIG_MAC80211_HT_DEBUG
printk(KERN_DEBUG "timer expired on tid %d but we are not "
- "(or no longer) expecting addBA response there",
+ "(or no longer) expecting addBA response there\n",
tid);
#endif
return;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 7dd7cda75cf..ae37270a063 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -97,9 +97,6 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
params->mesh_id_len,
params->mesh_id);
- if (sdata->vif.type != NL80211_IFTYPE_MONITOR || !flags)
- return 0;
-
if (type == NL80211_IFTYPE_AP_VLAN &&
params && params->use_4addr == 0)
rcu_assign_pointer(sdata->u.vlan.sta, NULL);
@@ -107,7 +104,9 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
params && params->use_4addr >= 0)
sdata->u.mgd.use_4addr = params->use_4addr;
- sdata->u.mntr_flags = *flags;
+ if (sdata->vif.type == NL80211_IFTYPE_MONITOR && flags)
+ sdata->u.mntr_flags = *flags;
+
return 0;
}
@@ -411,6 +410,17 @@ static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev,
return ret;
}
+static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev,
+ int idx, struct survey_info *survey)
+{
+ struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr);
+
+ if (!local->ops->get_survey)
+ return -EOPNOTSUPP;
+
+ return drv_get_survey(local, idx, survey);
+}
+
static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev,
u8 *mac, struct station_info *sinfo)
{
@@ -1104,6 +1114,13 @@ static int ieee80211_change_bss(struct wiphy *wiphy,
changed |= BSS_CHANGED_BASIC_RATES;
}
+ if (params->ap_isolate >= 0) {
+ if (params->ap_isolate)
+ sdata->flags |= IEEE80211_SDATA_DONT_BRIDGE_PACKETS;
+ else
+ sdata->flags &= ~IEEE80211_SDATA_DONT_BRIDGE_PACKETS;
+ }
+
ieee80211_bss_info_change_notify(sdata, changed);
return 0;
@@ -1388,11 +1405,11 @@ static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
return -EOPNOTSUPP;
if (enabled == sdata->u.mgd.powersave &&
- timeout == conf->dynamic_ps_timeout)
+ timeout == conf->dynamic_ps_forced_timeout)
return 0;
sdata->u.mgd.powersave = enabled;
- conf->dynamic_ps_timeout = timeout;
+ conf->dynamic_ps_forced_timeout = timeout;
/* no change, but if automatic follow powersave */
mutex_lock(&sdata->u.mgd.mtx);
@@ -1508,6 +1525,7 @@ struct cfg80211_ops mac80211_config_ops = {
.change_station = ieee80211_change_station,
.get_station = ieee80211_get_station,
.dump_station = ieee80211_dump_station,
+ .dump_survey = ieee80211_dump_survey,
#ifdef CONFIG_MAC80211_MESH
.add_mpath = ieee80211_add_mpath,
.del_mpath = ieee80211_del_mpath,
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 6bc9b07c3ed..e763f1529dd 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -39,6 +39,13 @@ static const struct file_operations sta_ ##name## _ops = { \
.open = mac80211_open_file_generic, \
}
+#define STA_OPS_RW(name) \
+static const struct file_operations sta_ ##name## _ops = { \
+ .read = sta_##name##_read, \
+ .write = sta_##name##_write, \
+ .open = mac80211_open_file_generic, \
+}
+
#define STA_FILE(name, field, format) \
STA_READ_##format(name, field) \
STA_OPS(name)
@@ -156,7 +163,63 @@ static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf,
return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
}
-STA_OPS(agg_status);
+
+static ssize_t sta_agg_status_write(struct file *file, const char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ char _buf[12], *buf = _buf;
+ struct sta_info *sta = file->private_data;
+ bool start, tx;
+ unsigned long tid;
+ int ret;
+
+ if (count > sizeof(_buf))
+ return -EINVAL;
+
+ if (copy_from_user(buf, userbuf, count))
+ return -EFAULT;
+
+ buf[sizeof(_buf) - 1] = '\0';
+
+ if (strncmp(buf, "tx ", 3) == 0) {
+ buf += 3;
+ tx = true;
+ } else if (strncmp(buf, "rx ", 3) == 0) {
+ buf += 3;
+ tx = false;
+ } else
+ return -EINVAL;
+
+ if (strncmp(buf, "start ", 6) == 0) {
+ buf += 6;
+ start = true;
+ if (!tx)
+ return -EINVAL;
+ } else if (strncmp(buf, "stop ", 5) == 0) {
+ buf += 5;
+ start = false;
+ } else
+ return -EINVAL;
+
+ tid = simple_strtoul(buf, NULL, 0);
+
+ if (tid >= STA_TID_NUM)
+ return -EINVAL;
+
+ if (tx) {
+ if (start)
+ ret = ieee80211_start_tx_ba_session(&sta->sta, tid);
+ else
+ ret = ieee80211_stop_tx_ba_session(&sta->sta, tid,
+ WLAN_BACK_RECIPIENT);
+ } else {
+ __ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, 3);
+ ret = 0;
+ }
+
+ return ret ?: count;
+}
+STA_OPS_RW(agg_status);
static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf,
size_t count, loff_t *ppos)
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 9179196da26..ee8b63f92f7 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -152,14 +152,15 @@ static inline void drv_update_tkip_key(struct ieee80211_local *local,
}
static inline int drv_hw_scan(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
struct cfg80211_scan_request *req)
{
int ret;
might_sleep();
- ret = local->ops->hw_scan(&local->hw, req);
- trace_drv_hw_scan(local, req, ret);
+ ret = local->ops->hw_scan(&local->hw, &sdata->vif, req);
+ trace_drv_hw_scan(local, sdata, req, ret);
return ret;
}
@@ -344,6 +345,15 @@ static inline int drv_ampdu_action(struct ieee80211_local *local,
return ret;
}
+static inline int drv_get_survey(struct ieee80211_local *local, int idx,
+ struct survey_info *survey)
+{
+ int ret = -EOPNOTSUPP;
+ if (local->ops->conf_tx)
+ ret = local->ops->get_survey(&local->hw, idx, survey);
+ /* trace_drv_get_survey(local, idx, survey, ret); */
+ return ret;
+}
static inline void drv_rfkill_poll(struct ieee80211_local *local)
{
diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h
index e209cb82ff2..ce734b58d07 100644
--- a/net/mac80211/driver-trace.h
+++ b/net/mac80211/driver-trace.h
@@ -363,23 +363,26 @@ TRACE_EVENT(drv_update_tkip_key,
TRACE_EVENT(drv_hw_scan,
TP_PROTO(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata,
struct cfg80211_scan_request *req, int ret),
- TP_ARGS(local, req, ret),
+ TP_ARGS(local, sdata, req, ret),
TP_STRUCT__entry(
LOCAL_ENTRY
+ VIF_ENTRY
__field(int, ret)
),
TP_fast_assign(
LOCAL_ASSIGN;
+ VIF_ASSIGN;
__entry->ret = ret;
),
TP_printk(
- LOCAL_PR_FMT " ret:%d",
- LOCAL_PR_ARG, __entry->ret
+ LOCAL_PR_FMT VIF_PR_FMT " ret:%d",
+ LOCAL_PR_ARG,VIF_PR_ARG, __entry->ret
)
);
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index e6f3b0c7a71..b72ee6435fa 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -92,6 +92,12 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
if (memcmp(ifibss->bssid, bssid, ETH_ALEN))
sta_info_flush(sdata->local, sdata);
+ /* if merging, indicate to driver that we leave the old IBSS */
+ if (sdata->vif.bss_conf.ibss_joined) {
+ sdata->vif.bss_conf.ibss_joined = false;
+ ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_IBSS);
+ }
+
memcpy(ifibss->bssid, bssid, ETH_ALEN);
sdata->drop_unencrypted = capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0;
@@ -171,6 +177,8 @@ static void __ieee80211_sta_join_ibss(struct ieee80211_sub_if_data *sdata,
bss_change |= BSS_CHANGED_BSSID;
bss_change |= BSS_CHANGED_BEACON;
bss_change |= BSS_CHANGED_BEACON_ENABLED;
+ bss_change |= BSS_CHANGED_IBSS;
+ sdata->vif.bss_conf.ibss_joined = true;
ieee80211_bss_info_change_notify(sdata, bss_change);
ieee80211_sta_def_wmm_params(sdata, sband->n_bitrates, supp_rates);
@@ -481,7 +489,9 @@ static void ieee80211_sta_merge_ibss(struct ieee80211_sub_if_data *sdata)
printk(KERN_DEBUG "%s: No active IBSS STAs - trying to scan for other "
"IBSS networks with same SSID (merge)\n", sdata->name);
- ieee80211_request_internal_scan(sdata, ifibss->ssid, ifibss->ssid_len);
+ ieee80211_request_internal_scan(sdata,
+ ifibss->ssid, ifibss->ssid_len,
+ ifibss->fixed_channel ? ifibss->channel : NULL);
}
static void ieee80211_sta_create_ibss(struct ieee80211_sub_if_data *sdata)
@@ -588,8 +598,9 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata)
printk(KERN_DEBUG "%s: Trigger new scan to find an IBSS to "
"join\n", sdata->name);
- ieee80211_request_internal_scan(sdata, ifibss->ssid,
- ifibss->ssid_len);
+ ieee80211_request_internal_scan(sdata,
+ ifibss->ssid, ifibss->ssid_len,
+ ifibss->fixed_channel ? ifibss->channel : NULL);
} else {
int interval = IEEE80211_SCAN_INTERVAL;
@@ -897,6 +908,12 @@ int ieee80211_ibss_join(struct ieee80211_sub_if_data *sdata,
sdata->u.ibss.channel = params->channel;
sdata->u.ibss.fixed_channel = params->channel_fixed;
+ /* fix ourselves to that channel now already */
+ if (params->channel_fixed) {
+ sdata->local->oper_channel = params->channel;
+ sdata->local->oper_channel_type = NL80211_CHAN_NO_HT;
+ }
+
if (params->ie) {
sdata->u.ibss.ie = kmemdup(params->ie, params->ie_len,
GFP_KERNEL);
@@ -951,7 +968,9 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata)
kfree(sdata->u.ibss.ie);
skb = sdata->u.ibss.presp;
rcu_assign_pointer(sdata->u.ibss.presp, NULL);
- ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED);
+ sdata->vif.bss_conf.ibss_joined = false;
+ ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED |
+ BSS_CHANGED_IBSS);
synchronize_rcu();
kfree_skb(skb);
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index c9712f35e59..cbaf4981e11 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1019,7 +1019,8 @@ void ieee80211_ibss_restart(struct ieee80211_sub_if_data *sdata);
/* scan/BSS handling */
void ieee80211_scan_work(struct work_struct *work);
int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata,
- const u8 *ssid, u8 ssid_len);
+ const u8 *ssid, u8 ssid_len,
+ struct ieee80211_channel *chan);
int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata,
struct cfg80211_scan_request *req);
void ieee80211_scan_cancel(struct ieee80211_local *local);
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index e8f6e3b252d..8d4b41787dc 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -140,6 +140,7 @@ static void ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
struct ieee80211_sub_if_data,
u.ap);
+ key->conf.ap_addr = sdata->dev->dev_addr;
ret = drv_set_key(key->local, SET_KEY, sdata, sta, &key->conf);
if (!ret) {
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 011ee85bcd5..bd632e1ee2c 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -442,7 +442,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
struct ieee80211_local *local = hw_to_local(hw);
int result;
enum ieee80211_band band;
- int channels, i, j, max_bitrates;
+ int channels, max_bitrates;
bool supp_ht;
static const u32 cipher_suites[] = {
WLAN_CIPHER_SUITE_WEP40,
@@ -572,6 +572,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
local->hw.conf.listen_interval = local->hw.max_listen_interval;
+ local->hw.conf.dynamic_ps_forced_timeout = -1;
+
result = sta_info_start(local);
if (result < 0)
goto fail_sta_info;
@@ -606,21 +608,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
ieee80211_led_init(local);
- /* alloc internal scan request */
- i = 0;
- local->int_scan_req->ssids = &local->scan_ssid;
- local->int_scan_req->n_ssids = 1;
- for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
- if (!hw->wiphy->bands[band])
- continue;
- for (j = 0; j < hw->wiphy->bands[band]->n_channels; j++) {
- local->int_scan_req->channels[i] =
- &hw->wiphy->bands[band]->channels[j];
- i++;
- }
- }
- local->int_scan_req->n_channels = i;
-
local->network_latency_notifier.notifier_call =
ieee80211_max_network_latency;
result = pm_qos_add_notifier(PM_QOS_NETWORK_LATENCY,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 35d850223a7..358226f63b8 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -175,6 +175,8 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
ht_changed = conf_is_ht(&local->hw.conf) != enable_ht ||
channel_type != local->hw.conf.channel_type;
+ if (local->tmp_channel)
+ local->tmp_channel_type = channel_type;
local->oper_channel_type = channel_type;
if (ht_changed) {
@@ -476,6 +478,7 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency)
{
struct ieee80211_sub_if_data *sdata, *found = NULL;
int count = 0;
+ int timeout;
if (!(local->hw.flags & IEEE80211_HW_SUPPORTS_PS)) {
local->ps_sdata = NULL;
@@ -509,6 +512,26 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency)
beaconint_us = ieee80211_tu_to_usec(
found->vif.bss_conf.beacon_int);
+ timeout = local->hw.conf.dynamic_ps_forced_timeout;
+ if (timeout < 0) {
+ /*
+ * The 2 second value is there for compatibility until
+ * the PM_QOS_NETWORK_LATENCY is configured with real
+ * values.
+ */
+ if (latency == 2000000000)
+ timeout = 100;
+ else if (latency <= 50000)
+ timeout = 300;
+ else if (latency <= 100000)
+ timeout = 100;
+ else if (latency <= 500000)
+ timeout = 50;
+ else
+ timeout = 0;
+ }
+ local->hw.conf.dynamic_ps_timeout = timeout;
+
if (beaconint_us > latency) {
local->ps_sdata = NULL;
} else {
@@ -1331,12 +1354,17 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_sub_if_data *sdata,
mutex_lock(&sdata->local->iflist_mtx);
ieee80211_recalc_ps(sdata->local, -1);
mutex_unlock(&sdata->local->iflist_mtx);
+
+ if (sdata->local->hw.flags & IEEE80211_HW_CONNECTION_MONITOR)
+ return;
+
/*
* We've received a probe response, but are not sure whether
* we have or will be receiving any beacons or data, so let's
* schedule the timers again, just in case.
*/
mod_beacon_timer(sdata);
+
mod_timer(&ifmgd->conn_mon_timer,
round_jiffies_up(jiffies +
IEEE80211_CONNECTION_IDLE_TIME));
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 72efbd87c1e..9a08f2c446c 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -81,8 +81,6 @@ ieee80211_rx_radiotap_len(struct ieee80211_local *local,
len += 8;
if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
len += 1;
- if (local->hw.flags & IEEE80211_HW_NOISE_DBM)
- len += 1;
if (len & 1) /* padding for RX_FLAGS if necessary */
len++;
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index e1a3defdf58..e14c44195ae 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -85,7 +85,7 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
{
struct cfg80211_bss *cbss;
struct ieee80211_bss *bss;
- int clen;
+ int clen, srlen;
s32 signal = 0;
if (local->hw.flags & IEEE80211_HW_SIGNAL_DBM)
@@ -114,23 +114,24 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
bss->dtim_period = tim_ie->dtim_period;
}
- bss->supp_rates_len = 0;
+ /* replace old supported rates if we get new values */
+ srlen = 0;
if (elems->supp_rates) {
- clen = IEEE80211_MAX_SUPP_RATES - bss->supp_rates_len;
+ clen = IEEE80211_MAX_SUPP_RATES;
if (clen > elems->supp_rates_len)
clen = elems->supp_rates_len;
- memcpy(&bss->supp_rates[bss->supp_rates_len], elems->supp_rates,
- clen);
- bss->supp_rates_len += clen;
+ memcpy(bss->supp_rates, elems->supp_rates, clen);
+ srlen += clen;
}
if (elems->ext_supp_rates) {
- clen = IEEE80211_MAX_SUPP_RATES - bss->supp_rates_len;
+ clen = IEEE80211_MAX_SUPP_RATES - srlen;
if (clen > elems->ext_supp_rates_len)
clen = elems->ext_supp_rates_len;
- memcpy(&bss->supp_rates[bss->supp_rates_len],
- elems->ext_supp_rates, clen);
- bss->supp_rates_len += clen;
+ memcpy(bss->supp_rates + srlen, elems->ext_supp_rates, clen);
+ srlen += clen;
}
+ if (srlen)
+ bss->supp_rates_len = srlen;
bss->wmm_used = elems->wmm_param || elems->wmm_info;
bss->uapsd_supported = is_uapsd_supported(elems);
@@ -411,7 +412,7 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
if (local->ops->hw_scan) {
WARN_ON(!ieee80211_prep_hw_scan(local));
- rc = drv_hw_scan(local, local->hw_scan_req);
+ rc = drv_hw_scan(local, sdata, local->hw_scan_req);
} else
rc = ieee80211_start_sw_scan(local);
@@ -655,7 +656,7 @@ void ieee80211_scan_work(struct work_struct *work)
}
if (local->hw_scan_req) {
- int rc = drv_hw_scan(local, local->hw_scan_req);
+ int rc = drv_hw_scan(local, sdata, local->hw_scan_req);
mutex_unlock(&local->scan_mtx);
if (rc)
ieee80211_scan_completed(&local->hw, true);
@@ -728,10 +729,12 @@ int ieee80211_request_scan(struct ieee80211_sub_if_data *sdata,
}
int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata,
- const u8 *ssid, u8 ssid_len)
+ const u8 *ssid, u8 ssid_len,
+ struct ieee80211_channel *chan)
{
struct ieee80211_local *local = sdata->local;
int ret = -EBUSY;
+ enum nl80211_band band;
mutex_lock(&local->scan_mtx);
@@ -739,6 +742,30 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata,
if (local->scan_req)
goto unlock;
+ /* fill internal scan request */
+ if (!chan) {
+ int i, nchan = 0;
+
+ for (band = 0; band < IEEE80211_NUM_BANDS; band++) {
+ if (!local->hw.wiphy->bands[band])
+ continue;
+ for (i = 0;
+ i < local->hw.wiphy->bands[band]->n_channels;
+ i++) {
+ local->int_scan_req->channels[nchan] =
+ &local->hw.wiphy->bands[band]->channels[i];
+ nchan++;
+ }
+ }
+
+ local->int_scan_req->n_channels = nchan;
+ } else {
+ local->int_scan_req->channels[0] = chan;
+ local->int_scan_req->n_channels = 1;
+ }
+
+ local->int_scan_req->ssids = &local->scan_ssid;
+ local->int_scan_req->n_ssids = 1;
memcpy(local->int_scan_req->ssids[0].ssid, ssid, IEEE80211_MAX_SSID_LEN);
local->int_scan_req->ssids[0].ssid_len = ssid_len;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index ff0eb948917..730197591ab 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -575,7 +575,7 @@ static int sta_info_buffer_expired(struct sta_info *sta,
}
-static void sta_info_cleanup_expire_buffered(struct ieee80211_local *local,
+static bool sta_info_cleanup_expire_buffered(struct ieee80211_local *local,
struct sta_info *sta)
{
unsigned long flags;
@@ -583,7 +583,7 @@ static void sta_info_cleanup_expire_buffered(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata;
if (skb_queue_empty(&sta->ps_tx_buf))
- return;
+ return false;
for (;;) {
spin_lock_irqsave(&sta->ps_tx_buf.lock, flags);
@@ -608,6 +608,8 @@ static void sta_info_cleanup_expire_buffered(struct ieee80211_local *local,
if (skb_queue_empty(&sta->ps_tx_buf))
sta_info_clear_tim_bit(sta);
}
+
+ return true;
}
static int __must_check __sta_info_destroy(struct sta_info *sta)
@@ -755,15 +757,20 @@ static void sta_info_cleanup(unsigned long data)
{
struct ieee80211_local *local = (struct ieee80211_local *) data;
struct sta_info *sta;
+ bool timer_needed = false;
rcu_read_lock();
list_for_each_entry_rcu(sta, &local->sta_list, list)
- sta_info_cleanup_expire_buffered(local, sta);
+ if (sta_info_cleanup_expire_buffered(local, sta))
+ timer_needed = true;
rcu_read_unlock();
if (local->quiescing)
return;
+ if (!timer_needed)
+ return;
+
local->sta_cleanup.expires =
round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL);
add_timer(&local->sta_cleanup);
@@ -848,8 +855,12 @@ struct ieee80211_sta *ieee80211_find_sta_by_hw(struct ieee80211_hw *hw,
struct sta_info *sta, *nxt;
/* Just return a random station ... first in list ... */
- for_each_sta_info(hw_to_local(hw), addr, sta, nxt)
+ for_each_sta_info(hw_to_local(hw), addr, sta, nxt) {
+ if (!sta->uploaded)
+ return NULL;
return &sta->sta;
+ }
+
return NULL;
}
EXPORT_SYMBOL_GPL(ieee80211_find_sta_by_hw);
@@ -857,14 +868,19 @@ EXPORT_SYMBOL_GPL(ieee80211_find_sta_by_hw);
struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif,
const u8 *addr)
{
- struct ieee80211_sub_if_data *sdata;
+ struct sta_info *sta;
if (!vif)
return NULL;
- sdata = vif_to_sdata(vif);
+ sta = sta_info_get_bss(vif_to_sdata(vif), addr);
+ if (!sta)
+ return NULL;
+
+ if (!sta->uploaded)
+ return NULL;
- return ieee80211_find_sta_by_hw(&sdata->local->hw, addr);
+ return &sta->sta;
}
EXPORT_SYMBOL(ieee80211_find_sta);
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 11805a3a626..94613af009f 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -171,6 +171,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
struct net_device *prev_dev = NULL;
struct sta_info *sta, *tmp;
int retry_count = -1, i;
+ int rates_idx = -1;
bool send_to_cooked;
for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
@@ -178,6 +179,8 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
if (i >= hw->max_rates) {
info->status.rates[i].idx = -1;
info->status.rates[i].count = 0;
+ } else if (info->status.rates[i].idx >= 0) {
+ rates_idx = i;
}
retry_count += info->status.rates[i].count;
@@ -206,6 +209,10 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
return;
}
+ if ((local->hw.flags & IEEE80211_HW_HAS_RATE_CONTROL) &&
+ (rates_idx != -1))
+ sta->last_tx_rate = info->status.rates[rates_idx];
+
if ((info->flags & IEEE80211_TX_STAT_AMPDU_NO_BACK) &&
(ieee80211_is_data_qos(fc))) {
u16 tid, ssn;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 2cb77267f73..f3841f43249 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -429,6 +429,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
struct sta_info *sta = tx->sta;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)tx->skb->data;
+ struct ieee80211_local *local = tx->local;
u32 staflags;
if (unlikely(!sta ||
@@ -476,6 +477,12 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
info->control.vif = &tx->sdata->vif;
info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
skb_queue_tail(&sta->ps_tx_buf, tx->skb);
+
+ if (!timer_pending(&local->sta_cleanup))
+ mod_timer(&local->sta_cleanup,
+ round_jiffies(jiffies +
+ STA_INFO_CLEANUP_INTERVAL));
+
return TX_QUEUED;
}
#ifdef CONFIG_MAC80211_VERBOSE_PS_DEBUG
@@ -586,7 +593,8 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx)
struct ieee80211_hdr *hdr = (void *)tx->skb->data;
struct ieee80211_supported_band *sband;
struct ieee80211_rate *rate;
- int i, len;
+ int i;
+ u32 len;
bool inval = false, rts = false, short_preamble = false;
struct ieee80211_tx_rate_control txrc;
u32 sta_flags;
@@ -595,7 +603,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx)
sband = tx->local->hw.wiphy->bands[tx->channel->band];
- len = min_t(int, tx->skb->len + FCS_LEN,
+ len = min_t(u32, tx->skb->len + FCS_LEN,
tx->local->hw.wiphy->frag_threshold);
/* set up the tx rate control struct we give the RC algo */
diff --git a/net/mac80211/work.c b/net/mac80211/work.c
index bdb1d05b16f..3dd07600199 100644
--- a/net/mac80211/work.c
+++ b/net/mac80211/work.c
@@ -213,15 +213,25 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata,
sband = local->hw.wiphy->bands[wk->chan->band];
- /*
- * Get all rates supported by the device and the AP as
- * some APs don't like getting a superset of their rates
- * in the association request (e.g. D-Link DAP 1353 in
- * b-only mode)...
- */
- rates_len = ieee80211_compatible_rates(wk->assoc.supp_rates,
- wk->assoc.supp_rates_len,
- sband, &rates);
+ if (wk->assoc.supp_rates_len) {
+ /*
+ * Get all rates supported by the device and the AP as
+ * some APs don't like getting a superset of their rates
+ * in the association request (e.g. D-Link DAP 1353 in
+ * b-only mode)...
+ */
+ rates_len = ieee80211_compatible_rates(wk->assoc.supp_rates,
+ wk->assoc.supp_rates_len,
+ sband, &rates);
+ } else {
+ /*
+ * In case AP not provide any supported rates information
+ * before association, we send information element(s) with
+ * all rates that we support.
+ */
+ rates = ~0;
+ rates_len = sband->n_bitrates;
+ }
skb = alloc_skb(local->hw.extra_tx_headroom +
sizeof(*mgmt) + /* bit too much but doesn't matter */
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 8fb0ae61676..7ba06939829 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -802,7 +802,7 @@ static int sync_thread_backup(void *data)
ip_vs_backup_mcast_ifn, ip_vs_backup_syncid);
while (!kthread_should_stop()) {
- wait_event_interruptible(*tinfo->sock->sk->sk_sleep,
+ wait_event_interruptible(*sk_sleep(tinfo->sock->sk),
!skb_queue_empty(&tinfo->sock->sk->sk_receive_queue)
|| kthread_should_stop());
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index fa07f044b59..06cb02796a0 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -739,7 +739,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr,
DEFINE_WAIT(wait);
for (;;) {
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
if (sk->sk_state != TCP_SYN_SENT)
break;
@@ -752,7 +752,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr,
err = -ERESTARTSYS;
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err)
goto out_release;
}
@@ -798,7 +798,7 @@ static int nr_accept(struct socket *sock, struct socket *newsock, int flags)
* hooked into the SABM we saved
*/
for (;;) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
skb = skb_dequeue(&sk->sk_receive_queue);
if (skb)
break;
@@ -816,7 +816,7 @@ static int nr_accept(struct socket *sock, struct socket *newsock, int flags)
err = -ERESTARTSYS;
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err)
goto out_release;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f162d59d816..2078a277e06 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2228,8 +2228,6 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd,
case SIOCGIFDSTADDR:
case SIOCSIFDSTADDR:
case SIOCSIFFLAGS:
- if (!net_eq(sock_net(sk), &init_net))
- return -ENOIOCTLCMD;
return inet_dgram_ops.ioctl(sock, cmd, arg);
#endif
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index e2a95762abd..af4d38bc3b2 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -664,12 +664,12 @@ static int pep_wait_connreq(struct sock *sk, int noblock)
if (signal_pending(tsk))
return sock_intr_errno(timeo);
- prepare_to_wait_exclusive(&sk->sk_socket->wait, &wait,
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
release_sock(sk);
timeo = schedule_timeout(timeo);
lock_sock(sk);
- finish_wait(&sk->sk_socket->wait, &wait);
+ finish_wait(sk_sleep(sk), &wait);
}
return 0;
@@ -910,10 +910,10 @@ disabled:
goto out;
}
- prepare_to_wait(&sk->sk_socket->wait, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
done = sk_wait_event(sk, &timeo, atomic_read(&pn->tx_credits));
- finish_wait(&sk->sk_socket->wait, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (sk->sk_state != TCP_ESTABLISHED)
goto disabled;
diff --git a/net/phonet/pn_dev.c b/net/phonet/pn_dev.c
index 9b4ced6e096..c33da657694 100644
--- a/net/phonet/pn_dev.c
+++ b/net/phonet/pn_dev.c
@@ -46,9 +46,16 @@ struct phonet_net {
int phonet_net_id __read_mostly;
+static struct phonet_net *phonet_pernet(struct net *net)
+{
+ BUG_ON(!net);
+
+ return net_generic(net, phonet_net_id);
+}
+
struct phonet_device_list *phonet_device_list(struct net *net)
{
- struct phonet_net *pnn = net_generic(net, phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(net);
return &pnn->pndevs;
}
@@ -261,7 +268,7 @@ static int phonet_device_autoconf(struct net_device *dev)
static void phonet_route_autodel(struct net_device *dev)
{
- struct phonet_net *pnn = net_generic(dev_net(dev), phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(dev_net(dev));
unsigned i;
DECLARE_BITMAP(deleted, 64);
@@ -313,7 +320,7 @@ static struct notifier_block phonet_device_notifier = {
/* Per-namespace Phonet devices handling */
static int __net_init phonet_init_net(struct net *net)
{
- struct phonet_net *pnn = net_generic(net, phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(net);
if (!proc_net_fops_create(net, "phonet", 0, &pn_sock_seq_fops))
return -ENOMEM;
@@ -326,7 +333,7 @@ static int __net_init phonet_init_net(struct net *net)
static void __net_exit phonet_exit_net(struct net *net)
{
- struct phonet_net *pnn = net_generic(net, phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(net);
struct net_device *dev;
unsigned i;
@@ -376,7 +383,7 @@ void phonet_device_exit(void)
int phonet_route_add(struct net_device *dev, u8 daddr)
{
- struct phonet_net *pnn = net_generic(dev_net(dev), phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(dev_net(dev));
struct phonet_routes *routes = &pnn->routes;
int err = -EEXIST;
@@ -393,7 +400,7 @@ int phonet_route_add(struct net_device *dev, u8 daddr)
int phonet_route_del(struct net_device *dev, u8 daddr)
{
- struct phonet_net *pnn = net_generic(dev_net(dev), phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(dev_net(dev));
struct phonet_routes *routes = &pnn->routes;
daddr = daddr >> 2;
@@ -413,7 +420,7 @@ int phonet_route_del(struct net_device *dev, u8 daddr)
struct net_device *phonet_route_get(struct net *net, u8 daddr)
{
- struct phonet_net *pnn = net_generic(net, phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(net);
struct phonet_routes *routes = &pnn->routes;
struct net_device *dev;
@@ -428,7 +435,7 @@ struct net_device *phonet_route_get(struct net *net, u8 daddr)
struct net_device *phonet_route_output(struct net *net, u8 daddr)
{
- struct phonet_net *pnn = net_generic(net, phonet_net_id);
+ struct phonet_net *pnn = phonet_pernet(net);
struct phonet_routes *routes = &pnn->routes;
struct net_device *dev;
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index c785bfd0744..6e9848bf037 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -265,7 +265,7 @@ static unsigned int pn_socket_poll(struct file *file, struct socket *sock,
struct pep_sock *pn = pep_sk(sk);
unsigned int mask = 0;
- poll_wait(file, &sock->wait, wait);
+ poll_wait(file, sk_sleep(sk), wait);
switch (sk->sk_state) {
case TCP_LISTEN:
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index 7919a9edb8e..aebfecbdb84 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -158,7 +158,7 @@ static unsigned int rds_poll(struct file *file, struct socket *sock,
unsigned int mask = 0;
unsigned long flags;
- poll_wait(file, sk->sk_sleep, wait);
+ poll_wait(file, sk_sleep(sk), wait);
if (rs->rs_seen_congestion)
poll_wait(file, &rds_poll_waitq, wait);
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 5ea82fc47c3..e599ba2f950 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -133,7 +133,7 @@ static int __init rds_rdma_listen_init(void)
ret = PTR_ERR(cm_id);
printk(KERN_ERR "RDS/RDMA: failed to setup listener, "
"rdma_create_id() returned %d\n", ret);
- goto out;
+ return ret;
}
sin.sin_family = AF_INET,
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 4bec6e2ed49..c224b5bb3ba 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -492,7 +492,7 @@ void rds_sock_put(struct rds_sock *rs);
void rds_wake_sk_sleep(struct rds_sock *rs);
static inline void __rds_wake_sk_sleep(struct sock *sk)
{
- wait_queue_head_t *waitq = sk->sk_sleep;
+ wait_queue_head_t *waitq = sk_sleep(sk);
if (!sock_flag(sk, SOCK_DEAD) && waitq)
wake_up(waitq);
diff --git a/net/rds/recv.c b/net/rds/recv.c
index e2a2b9344f7..795a00b7f2c 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -432,7 +432,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
break;
}
- timeo = wait_event_interruptible_timeout(*sk->sk_sleep,
+ timeo = wait_event_interruptible_timeout(*sk_sleep(sk),
(!list_empty(&rs->rs_notify_queue) ||
rs->rs_cong_notify ||
rds_next_incoming(rs, &inc)), timeo);
diff --git a/net/rds/send.c b/net/rds/send.c
index 53d6795ac9d..9c1c6bcaa6c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -915,7 +915,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
goto out;
}
- timeo = wait_event_interruptible_timeout(*sk->sk_sleep,
+ timeo = wait_event_interruptible_timeout(*sk_sleep(sk),
rds_send_queue_rm(rs, conn, rm,
rs->rs_bound_port,
dport,
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index 4fb711a035f..8e45e76a95f 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -845,7 +845,7 @@ rose_try_next_neigh:
DEFINE_WAIT(wait);
for (;;) {
- prepare_to_wait(sk->sk_sleep, &wait,
+ prepare_to_wait(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
if (sk->sk_state != TCP_SYN_SENT)
break;
@@ -858,7 +858,7 @@ rose_try_next_neigh:
err = -ERESTARTSYS;
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err)
goto out_release;
@@ -911,7 +911,7 @@ static int rose_accept(struct socket *sock, struct socket *newsock, int flags)
* hooked into the SABM we saved
*/
for (;;) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
skb = skb_dequeue(&sk->sk_receive_queue);
if (skb)
@@ -930,7 +930,7 @@ static int rose_accept(struct socket *sock, struct socket *newsock, int flags)
err = -ERESTARTSYS;
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
if (err)
goto out_release;
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index c060095b27c..0b9bb2085ce 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -62,13 +62,15 @@ static inline int rxrpc_writable(struct sock *sk)
static void rxrpc_write_space(struct sock *sk)
{
_enter("%p", sk);
- read_lock(&sk->sk_callback_lock);
+ rcu_read_lock();
if (rxrpc_writable(sk)) {
- if (sk_has_sleeper(sk))
- wake_up_interruptible(sk->sk_sleep);
+ struct socket_wq *wq = rcu_dereference(sk->sk_wq);
+
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible(&wq->wait);
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
/*
@@ -589,7 +591,7 @@ static unsigned int rxrpc_poll(struct file *file, struct socket *sock,
unsigned int mask;
struct sock *sk = sock->sk;
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
mask = 0;
/* the socket is readable if there are any messages waiting on the Rx
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 60c2b94e6b5..0c65013e3bf 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -91,7 +91,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
/* wait for a message to turn up */
release_sock(&rx->sk);
- prepare_to_wait_exclusive(rx->sk.sk_sleep, &wait,
+ prepare_to_wait_exclusive(sk_sleep(&rx->sk), &wait,
TASK_INTERRUPTIBLE);
ret = sock_error(&rx->sk);
if (ret)
@@ -102,7 +102,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
goto wait_interrupted;
timeo = schedule_timeout(timeo);
}
- finish_wait(rx->sk.sk_sleep, &wait);
+ finish_wait(sk_sleep(&rx->sk), &wait);
lock_sock(&rx->sk);
continue;
}
@@ -356,7 +356,7 @@ csum_copy_error:
wait_interrupted:
ret = sock_intr_errno(timeo);
wait_error:
- finish_wait(rx->sk.sk_sleep, &wait);
+ finish_wait(sk_sleep(&rx->sk), &wait);
if (continue_call)
rxrpc_put_call(continue_call);
if (copied)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index aeddabfb8e4..a969b111bd7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -94,7 +94,7 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb,
* Another cpu is holding lock, requeue & delay xmits for
* some time.
*/
- __get_cpu_var(netdev_rx_stat).cpu_collision++;
+ __get_cpu_var(softnet_data).cpu_collision++;
ret = dev_requeue_skb(skb, q);
}
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index c5a9ac56600..c65762823f5 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -123,8 +123,8 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
case htons(ETH_P_IP):
{
const struct iphdr *iph = ip_hdr(skb);
- h = iph->daddr;
- h2 = iph->saddr ^ iph->protocol;
+ h = (__force u32)iph->daddr;
+ h2 = (__force u32)iph->saddr ^ iph->protocol;
if (!(iph->frag_off&htons(IP_MF|IP_OFFSET)) &&
(iph->protocol == IPPROTO_TCP ||
iph->protocol == IPPROTO_UDP ||
@@ -138,8 +138,8 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
case htons(ETH_P_IPV6):
{
struct ipv6hdr *iph = ipv6_hdr(skb);
- h = iph->daddr.s6_addr32[3];
- h2 = iph->saddr.s6_addr32[3] ^ iph->nexthdr;
+ h = (__force u32)iph->daddr.s6_addr32[3];
+ h2 = (__force u32)iph->saddr.s6_addr32[3] ^ iph->nexthdr;
if (iph->nexthdr == IPPROTO_TCP ||
iph->nexthdr == IPPROTO_UDP ||
iph->nexthdr == IPPROTO_UDPLITE ||
@@ -150,7 +150,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
break;
}
default:
- h = (unsigned long)skb_dst(skb) ^ skb->protocol;
+ h = (unsigned long)skb_dst(skb) ^ (__force u32)skb->protocol;
h2 = (unsigned long)skb->sk;
}
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index 58b3e882a18..126b014eb79 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -37,6 +37,18 @@ menuconfig IP_SCTP
if IP_SCTP
+config NET_SCTPPROBE
+ tristate "SCTP: Association probing"
+ depends on PROC_FS && KPROBES
+ ---help---
+ This module allows for capturing the changes to SCTP association
+ state in response to incoming packets. It is used for debugging
+ SCTP congestion control algorithms. If you don't understand
+ what was just said, you don't need it: say N.
+
+ To compile this code as a module, choose M here: the
+ module will be called sctp_probe.
+
config SCTP_DBG_MSG
bool "SCTP: Debug messages"
help
diff --git a/net/sctp/Makefile b/net/sctp/Makefile
index 6b794734380..5c30b7a873d 100644
--- a/net/sctp/Makefile
+++ b/net/sctp/Makefile
@@ -3,6 +3,7 @@
#
obj-$(CONFIG_IP_SCTP) += sctp.o
+obj-$(CONFIG_NET_SCTPPROBE) += sctp_probe.o
sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
protocol.o endpointola.o associola.o \
@@ -11,6 +12,8 @@ sctp-y := sm_statetable.o sm_statefuns.o sm_sideeffect.o \
tsnmap.o bind_addr.o socket.o primitive.o \
output.o input.o debug.o ssnmap.o auth.o
+sctp_probe-y := probe.o
+
sctp-$(CONFIG_SCTP_DBG_OBJCNT) += objcnt.o
sctp-$(CONFIG_PROC_FS) += proc.o
sctp-$(CONFIG_SYSCTL) += sysctl.o
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index df5abbff63e..3912420cedc 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -87,9 +87,6 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a
/* Retrieve the SCTP per socket area. */
sp = sctp_sk((struct sock *)sk);
- /* Init all variables to a known value. */
- memset(asoc, 0, sizeof(struct sctp_association));
-
/* Discarding const is appropriate here. */
asoc->ep = (struct sctp_endpoint *)ep;
sctp_endpoint_hold(asoc->ep);
@@ -762,7 +759,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
asoc->peer.retran_path = peer;
}
- if (asoc->peer.active_path == asoc->peer.retran_path) {
+ if (asoc->peer.active_path == asoc->peer.retran_path &&
+ peer->state != SCTP_UNCONFIRMED) {
asoc->peer.retran_path = peer;
}
@@ -1194,8 +1192,10 @@ void sctp_assoc_update(struct sctp_association *asoc,
/* Remove any peer addresses not present in the new association. */
list_for_each_safe(pos, temp, &asoc->peer.transport_addr_list) {
trans = list_entry(pos, struct sctp_transport, transports);
- if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr))
- sctp_assoc_del_peer(asoc, &trans->ipaddr);
+ if (!sctp_assoc_lookup_paddr(new, &trans->ipaddr)) {
+ sctp_assoc_rm_peer(asoc, trans);
+ continue;
+ }
if (asoc->state >= SCTP_STATE_ESTABLISHED)
sctp_transport_reset(trans);
@@ -1318,12 +1318,13 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc)
/* Keep track of the next transport in case
* we don't find any active transport.
*/
- if (!next)
+ if (t->state != SCTP_UNCONFIRMED && !next)
next = t;
}
}
- asoc->peer.retran_path = t;
+ if (t)
+ asoc->peer.retran_path = t;
SCTP_DEBUG_PRINTK_IPADDR("sctp_assoc_update_retran_path:association"
" %p addr: ",
@@ -1483,7 +1484,7 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned len)
if (asoc->rwnd >= len) {
asoc->rwnd -= len;
if (over) {
- asoc->rwnd_press = asoc->rwnd;
+ asoc->rwnd_press += asoc->rwnd;
asoc->rwnd = 0;
}
} else {
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index 3eab6db59a3..476caaf100e 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -58,9 +58,9 @@ static void sctp_datamsg_init(struct sctp_datamsg *msg)
msg->send_failed = 0;
msg->send_error = 0;
msg->can_abandon = 0;
+ msg->can_delay = 1;
msg->expires_at = 0;
INIT_LIST_HEAD(&msg->chunks);
- msg->msg_size = 0;
}
/* Allocate and initialize datamsg. */
@@ -157,7 +157,6 @@ static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chu
{
sctp_datamsg_hold(msg);
chunk->msg = msg;
- msg->msg_size += chunk->skb->len;
}
@@ -247,6 +246,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
if (msg_len >= first_len) {
msg_len -= first_len;
whole = 1;
+ msg->can_delay = 0;
}
/* How many full sized? How many bytes leftover? */
diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c
index 905fda582b9..e10acc01c75 100644
--- a/net/sctp/endpointola.c
+++ b/net/sctp/endpointola.c
@@ -70,8 +70,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
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;
@@ -144,6 +142,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
/* Use SCTP specific send buffer space queues. */
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);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index fad261d41ec..a646681f5ac 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -429,24 +429,17 @@ int sctp_packet_transmit(struct sctp_packet *packet)
list_for_each_entry_safe(chunk, tmp, &packet->chunk_list, list) {
list_del_init(&chunk->list);
if (sctp_chunk_is_data(chunk)) {
+ /* 6.3.1 C4) When data is in flight and when allowed
+ * by rule C5, a new RTT measurement MUST be made each
+ * round trip. Furthermore, new RTT measurements
+ * SHOULD be made no more than once per round-trip
+ * for a given destination transport address.
+ */
- if (!chunk->resent) {
-
- /* 6.3.1 C4) When data is in flight and when allowed
- * by rule C5, a new RTT measurement MUST be made each
- * round trip. Furthermore, new RTT measurements
- * SHOULD be made no more than once per round-trip
- * for a given destination transport address.
- */
-
- if (!tp->rto_pending) {
- chunk->rtt_in_progress = 1;
- tp->rto_pending = 1;
- }
+ if (!tp->rto_pending) {
+ chunk->rtt_in_progress = 1;
+ tp->rto_pending = 1;
}
-
- chunk->resent = 1;
-
has_data = 1;
}
@@ -681,7 +674,7 @@ static sctp_xmit_t sctp_packet_can_append_data(struct sctp_packet *packet,
* Don't delay large message writes that may have been
* fragmeneted into small peices.
*/
- if ((len < max) && (chunk->msg->msg_size < max)) {
+ if ((len < max) && chunk->msg->can_delay) {
retval = SCTP_XMIT_NAGLE_DELAY;
goto finish;
}
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index abfc0b8dee7..5d057178ce0 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -62,7 +62,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
struct list_head *transmitted_queue,
struct sctp_transport *transport,
struct sctp_sackhdr *sack,
- __u32 highest_new_tsn);
+ __u32 *highest_new_tsn);
static void sctp_mark_missing(struct sctp_outq *q,
struct list_head *transmitted_queue,
@@ -308,7 +308,7 @@ int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
/* If it is data, queue it up, otherwise, send it
* immediately.
*/
- if (SCTP_CID_DATA == chunk->chunk_hdr->type) {
+ if (sctp_chunk_is_data(chunk)) {
/* Is it OK to queue data chunks? */
/* From 9. Termination of Association
*
@@ -598,11 +598,23 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
if (fast_rtx && !chunk->fast_retransmit)
continue;
+redo:
/* Attempt to append this chunk to the packet. */
status = sctp_packet_append_chunk(pkt, chunk);
switch (status) {
case SCTP_XMIT_PMTU_FULL:
+ if (!pkt->has_data && !pkt->has_cookie_echo) {
+ /* If this packet did not contain DATA then
+ * retransmission did not happen, so do it
+ * again. We'll ignore the error here since
+ * control chunks are already freed so there
+ * is nothing we can do.
+ */
+ sctp_packet_transmit(pkt);
+ goto redo;
+ }
+
/* Send this packet. */
error = sctp_packet_transmit(pkt);
@@ -647,14 +659,6 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
if (chunk->fast_retransmit == SCTP_NEED_FRTX)
chunk->fast_retransmit = SCTP_DONT_FRTX;
- /* Force start T3-rtx timer when fast retransmitting
- * the earliest outstanding TSN
- */
- if (!timer && fast_rtx &&
- ntohl(chunk->subh.data_hdr->tsn) ==
- asoc->ctsn_ack_point + 1)
- timer = 2;
-
q->empty = 0;
break;
}
@@ -854,6 +858,12 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
if (status != SCTP_XMIT_OK) {
/* put the chunk back */
list_add(&chunk->list, &q->control_chunk_list);
+ } else if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN) {
+ /* PR-SCTP C5) If a FORWARD TSN is sent, the
+ * sender MUST assure that at least one T3-rtx
+ * timer is running.
+ */
+ sctp_transport_reset_timers(transport);
}
break;
@@ -906,8 +916,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
rtx_timeout, &start_timer);
if (start_timer)
- sctp_transport_reset_timers(transport,
- start_timer-1);
+ sctp_transport_reset_timers(transport);
/* This can happen on COOKIE-ECHO resend. Only
* one chunk can get bundled with a COOKIE-ECHO.
@@ -1040,7 +1049,7 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
list_add_tail(&chunk->transmitted_list,
&transport->transmitted);
- sctp_transport_reset_timers(transport, 0);
+ sctp_transport_reset_timers(transport);
q->empty = 0;
@@ -1100,32 +1109,6 @@ static void sctp_sack_update_unack_data(struct sctp_association *assoc,
assoc->unack_data = unack_data;
}
-/* Return the highest new tsn that is acknowledged by the given SACK chunk. */
-static __u32 sctp_highest_new_tsn(struct sctp_sackhdr *sack,
- struct sctp_association *asoc)
-{
- struct sctp_transport *transport;
- struct sctp_chunk *chunk;
- __u32 highest_new_tsn, tsn;
- struct list_head *transport_list = &asoc->peer.transport_addr_list;
-
- highest_new_tsn = ntohl(sack->cum_tsn_ack);
-
- list_for_each_entry(transport, transport_list, transports) {
- list_for_each_entry(chunk, &transport->transmitted,
- transmitted_list) {
- tsn = ntohl(chunk->subh.data_hdr->tsn);
-
- if (!chunk->tsn_gap_acked &&
- TSN_lt(highest_new_tsn, tsn) &&
- sctp_acked(sack, tsn))
- highest_new_tsn = tsn;
- }
- }
-
- return highest_new_tsn;
-}
-
/* This is where we REALLY process a SACK.
*
* Process the SACK against the outqueue. Mostly, this just frees
@@ -1145,6 +1128,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_sackhdr *sack)
struct sctp_transport *primary = asoc->peer.primary_path;
int count_of_newacks = 0;
int gap_ack_blocks;
+ u8 accum_moved = 0;
/* Grab the association's destination address list. */
transport_list = &asoc->peer.transport_addr_list;
@@ -1193,18 +1177,15 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_sackhdr *sack)
if (gap_ack_blocks)
highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end);
- if (TSN_lt(asoc->highest_sacked, highest_tsn)) {
- highest_new_tsn = highest_tsn;
+ if (TSN_lt(asoc->highest_sacked, highest_tsn))
asoc->highest_sacked = highest_tsn;
- } else {
- highest_new_tsn = sctp_highest_new_tsn(sack, asoc);
- }
+ highest_new_tsn = sack_ctsn;
/* Run through the retransmit queue. Credit bytes received
* and free those chunks that we can.
*/
- sctp_check_transmitted(q, &q->retransmit, NULL, sack, highest_new_tsn);
+ sctp_check_transmitted(q, &q->retransmit, NULL, sack, &highest_new_tsn);
/* Run through the transmitted queue.
* Credit bytes received and free those chunks which we can.
@@ -1213,7 +1194,7 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_sackhdr *sack)
*/
list_for_each_entry(transport, transport_list, transports) {
sctp_check_transmitted(q, &transport->transmitted,
- transport, sack, highest_new_tsn);
+ transport, sack, &highest_new_tsn);
/*
* SFR-CACC algorithm:
* C) Let count_of_newacks be the number of
@@ -1223,16 +1204,22 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_sackhdr *sack)
count_of_newacks ++;
}
+ /* Move the Cumulative TSN Ack Point if appropriate. */
+ if (TSN_lt(asoc->ctsn_ack_point, sack_ctsn)) {
+ asoc->ctsn_ack_point = sack_ctsn;
+ accum_moved = 1;
+ }
+
if (gap_ack_blocks) {
+
+ if (asoc->fast_recovery && accum_moved)
+ highest_new_tsn = highest_tsn;
+
list_for_each_entry(transport, transport_list, transports)
sctp_mark_missing(q, &transport->transmitted, transport,
highest_new_tsn, count_of_newacks);
}
- /* Move the Cumulative TSN Ack Point if appropriate. */
- if (TSN_lt(asoc->ctsn_ack_point, sack_ctsn))
- asoc->ctsn_ack_point = sack_ctsn;
-
/* Update unack_data field in the assoc. */
sctp_sack_update_unack_data(asoc, sack);
@@ -1315,7 +1302,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
struct list_head *transmitted_queue,
struct sctp_transport *transport,
struct sctp_sackhdr *sack,
- __u32 highest_new_tsn_in_sack)
+ __u32 *highest_new_tsn_in_sack)
{
struct list_head *lchunk;
struct sctp_chunk *tchunk;
@@ -1387,7 +1374,6 @@ static void sctp_check_transmitted(struct sctp_outq *q,
* instance).
*/
if (!tchunk->tsn_gap_acked &&
- !tchunk->resent &&
tchunk->rtt_in_progress) {
tchunk->rtt_in_progress = 0;
rtt = jiffies - tchunk->sent_at;
@@ -1404,6 +1390,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
*/
if (!tchunk->tsn_gap_acked) {
tchunk->tsn_gap_acked = 1;
+ *highest_new_tsn_in_sack = tsn;
bytes_acked += sctp_data_size(tchunk);
if (!tchunk->transport)
migrate_bytes += sctp_data_size(tchunk);
@@ -1677,7 +1664,8 @@ static void sctp_mark_missing(struct sctp_outq *q,
struct sctp_chunk *chunk;
__u32 tsn;
char do_fast_retransmit = 0;
- struct sctp_transport *primary = q->asoc->peer.primary_path;
+ struct sctp_association *asoc = q->asoc;
+ struct sctp_transport *primary = asoc->peer.primary_path;
list_for_each_entry(chunk, transmitted_queue, transmitted_list) {
diff --git a/net/sctp/probe.c b/net/sctp/probe.c
new file mode 100644
index 00000000000..db3a42b8b34
--- /dev/null
+++ b/net/sctp/probe.c
@@ -0,0 +1,214 @@
+/*
+ * sctp_probe - Observe the SCTP flow with kprobes.
+ *
+ * The idea for this came from Werner Almesberger's umlsim
+ * Copyright (C) 2004, Stephen Hemminger <shemminger@osdl.org>
+ *
+ * Modified for SCTP from Stephen Hemminger's code
+ * Copyright (C) 2010, Wei Yongjun <yjwei@cn.fujitsu.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/socket.h>
+#include <linux/sctp.h>
+#include <linux/proc_fs.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/kfifo.h>
+#include <linux/time.h>
+#include <net/net_namespace.h>
+
+#include <net/sctp/sctp.h>
+#include <net/sctp/sm.h>
+
+MODULE_AUTHOR("Wei Yongjun <yjwei@cn.fujitsu.com>");
+MODULE_DESCRIPTION("SCTP snooper");
+MODULE_LICENSE("GPL");
+
+static int port __read_mostly = 0;
+MODULE_PARM_DESC(port, "Port to match (0=all)");
+module_param(port, int, 0);
+
+static int bufsize __read_mostly = 64 * 1024;
+MODULE_PARM_DESC(bufsize, "Log buffer size (default 64k)");
+module_param(bufsize, int, 0);
+
+static int full __read_mostly = 1;
+MODULE_PARM_DESC(full, "Full log (1=every ack packet received, 0=only cwnd changes)");
+module_param(full, int, 0);
+
+static const char procname[] = "sctpprobe";
+
+static struct {
+ struct kfifo fifo;
+ spinlock_t lock;
+ wait_queue_head_t wait;
+ struct timespec tstart;
+} sctpw;
+
+static void printl(const char *fmt, ...)
+{
+ va_list args;
+ int len;
+ char tbuf[256];
+
+ va_start(args, fmt);
+ len = vscnprintf(tbuf, sizeof(tbuf), fmt, args);
+ va_end(args);
+
+ kfifo_in_locked(&sctpw.fifo, tbuf, len, &sctpw.lock);
+ wake_up(&sctpw.wait);
+}
+
+static int sctpprobe_open(struct inode *inode, struct file *file)
+{
+ kfifo_reset(&sctpw.fifo);
+ getnstimeofday(&sctpw.tstart);
+
+ return 0;
+}
+
+static ssize_t sctpprobe_read(struct file *file, char __user *buf,
+ size_t len, loff_t *ppos)
+{
+ int error = 0, cnt = 0;
+ unsigned char *tbuf;
+
+ if (!buf)
+ return -EINVAL;
+
+ if (len == 0)
+ return 0;
+
+ tbuf = vmalloc(len);
+ if (!tbuf)
+ return -ENOMEM;
+
+ error = wait_event_interruptible(sctpw.wait,
+ kfifo_len(&sctpw.fifo) != 0);
+ if (error)
+ goto out_free;
+
+ cnt = kfifo_out_locked(&sctpw.fifo, tbuf, len, &sctpw.lock);
+ error = copy_to_user(buf, tbuf, cnt) ? -EFAULT : 0;
+
+out_free:
+ vfree(tbuf);
+
+ return error ? error : cnt;
+}
+
+static const struct file_operations sctpprobe_fops = {
+ .owner = THIS_MODULE,
+ .open = sctpprobe_open,
+ .read = sctpprobe_read,
+};
+
+sctp_disposition_t jsctp_sf_eat_sack(const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const sctp_subtype_t type,
+ void *arg,
+ sctp_cmd_seq_t *commands)
+{
+ struct sctp_transport *sp;
+ static __u32 lcwnd = 0;
+ struct timespec now;
+
+ sp = asoc->peer.primary_path;
+
+ if ((full || sp->cwnd != lcwnd) &&
+ (!port || asoc->peer.port == port ||
+ ep->base.bind_addr.port == port)) {
+ lcwnd = sp->cwnd;
+
+ getnstimeofday(&now);
+ now = timespec_sub(now, sctpw.tstart);
+
+ printl("%lu.%06lu ", (unsigned long) now.tv_sec,
+ (unsigned long) now.tv_nsec / NSEC_PER_USEC);
+
+ printl("%p %5d %5d %5d %8d %5d ", asoc,
+ ep->base.bind_addr.port, asoc->peer.port,
+ asoc->pathmtu, asoc->peer.rwnd, asoc->unack_data);
+
+ list_for_each_entry(sp, &asoc->peer.transport_addr_list,
+ transports) {
+ if (sp == asoc->peer.primary_path)
+ printl("*");
+
+ if (sp->ipaddr.sa.sa_family == AF_INET)
+ printl("%pI4 ", &sp->ipaddr.v4.sin_addr);
+ else
+ printl("%pI6 ", &sp->ipaddr.v6.sin6_addr);
+
+ printl("%2u %8u %8u %8u %8u %8u ",
+ sp->state, sp->cwnd, sp->ssthresh,
+ sp->flight_size, sp->partial_bytes_acked,
+ sp->pathmtu);
+ }
+ printl("\n");
+ }
+
+ jprobe_return();
+ return 0;
+}
+
+static struct jprobe sctp_recv_probe = {
+ .kp = {
+ .symbol_name = "sctp_sf_eat_sack_6_2",
+ },
+ .entry = jsctp_sf_eat_sack,
+};
+
+static __init int sctpprobe_init(void)
+{
+ int ret = -ENOMEM;
+
+ init_waitqueue_head(&sctpw.wait);
+ spin_lock_init(&sctpw.lock);
+ if (kfifo_alloc(&sctpw.fifo, bufsize, GFP_KERNEL))
+ return ret;
+
+ if (!proc_net_fops_create(&init_net, procname, S_IRUSR,
+ &sctpprobe_fops))
+ goto free_kfifo;
+
+ ret = register_jprobe(&sctp_recv_probe);
+ if (ret)
+ goto remove_proc;
+
+ pr_info("SCTP probe registered (port=%d)\n", port);
+
+ return 0;
+
+remove_proc:
+ proc_net_remove(&init_net, procname);
+free_kfifo:
+ kfifo_free(&sctpw.fifo);
+ return ret;
+}
+
+static __exit void sctpprobe_exit(void)
+{
+ kfifo_free(&sctpw.fifo);
+ proc_net_remove(&init_net, procname);
+ unregister_jprobe(&sctp_recv_probe);
+}
+
+module_init(sctpprobe_init);
+module_exit(sctpprobe_exit);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 704298f4b28..182749867c7 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -474,13 +474,17 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
memset(&fl, 0x0, sizeof(struct flowi));
fl.fl4_dst = daddr->v4.sin_addr.s_addr;
+ fl.fl_ip_dport = daddr->v4.sin_port;
fl.proto = IPPROTO_SCTP;
if (asoc) {
fl.fl4_tos = RT_CONN_FLAGS(asoc->base.sk);
fl.oif = asoc->base.sk->sk_bound_dev_if;
+ fl.fl_ip_sport = htons(asoc->base.bind_addr.port);
}
- if (saddr)
+ if (saddr) {
fl.fl4_src = saddr->v4.sin_addr.s_addr;
+ fl.fl_ip_sport = saddr->v4.sin_port;
+ }
SCTP_DEBUG_PRINTK("%s: DST:%pI4, SRC:%pI4 - ",
__func__, &fl.fl4_dst, &fl.fl4_src);
@@ -528,6 +532,7 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc,
if ((laddr->state == SCTP_ADDR_SRC) &&
(AF_INET == laddr->a.sa.sa_family)) {
fl.fl4_src = laddr->a.v4.sin_addr.s_addr;
+ fl.fl_ip_sport = laddr->a.v4.sin_port;
if (!ip_route_output_key(&init_net, &rt, &fl)) {
dst = &rt->u.dst;
goto out_unlock;
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 17cb400ecd6..d8261f3d771 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -108,7 +108,7 @@ static const struct sctp_paramhdr prsctp_param = {
cpu_to_be16(sizeof(struct sctp_paramhdr)),
};
-/* A helper to initialize to initialize an op error inside a
+/* A helper to initialize an op error inside a
* provided chunk, as most cause codes will be embedded inside an
* abort chunk.
*/
@@ -125,6 +125,29 @@ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code,
chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(sctp_errhdr_t), &err);
}
+/* A helper to initialize an op error inside a
+ * provided chunk, as most cause codes will be embedded inside an
+ * abort chunk. Differs from sctp_init_cause in that it won't oops
+ * if there isn't enough space in the op error chunk
+ */
+int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code,
+ size_t paylen)
+{
+ sctp_errhdr_t err;
+ __u16 len;
+
+ /* Cause code constants are now defined in network order. */
+ err.cause = cause_code;
+ len = sizeof(sctp_errhdr_t) + paylen;
+ err.length = htons(len);
+
+ if (skb_tailroom(chunk->skb) > len)
+ return -ENOSPC;
+ chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk,
+ sizeof(sctp_errhdr_t),
+ &err);
+ return 0;
+}
/* 3.3.2 Initiation (INIT) (1)
*
* This chunk is used to initiate a SCTP association between two
@@ -208,7 +231,8 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
sp = sctp_sk(asoc->base.sk);
num_types = sp->pf->supported_addrs(sp, types);
- chunksize = sizeof(init) + addrs_len + SCTP_SAT_LEN(num_types);
+ chunksize = sizeof(init) + addrs_len;
+ chunksize += WORD_ROUND(SCTP_SAT_LEN(num_types));
chunksize += sizeof(ecap_param);
if (sctp_prsctp_enable)
@@ -238,14 +262,14 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
/* Add HMACS parameter length if any were defined */
auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs;
if (auth_hmacs->length)
- chunksize += ntohs(auth_hmacs->length);
+ chunksize += WORD_ROUND(ntohs(auth_hmacs->length));
else
auth_hmacs = NULL;
/* Add CHUNKS parameter length */
auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks;
if (auth_chunks->length)
- chunksize += ntohs(auth_chunks->length);
+ chunksize += WORD_ROUND(ntohs(auth_chunks->length));
else
auth_chunks = NULL;
@@ -255,7 +279,8 @@ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc,
/* If we have any extensions to report, account for that */
if (num_ext)
- chunksize += sizeof(sctp_supported_ext_param_t) + num_ext;
+ chunksize += WORD_ROUND(sizeof(sctp_supported_ext_param_t) +
+ num_ext);
/* RFC 2960 3.3.2 Initiation (INIT) (1)
*
@@ -397,13 +422,13 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
auth_hmacs = (sctp_paramhdr_t *)asoc->c.auth_hmacs;
if (auth_hmacs->length)
- chunksize += ntohs(auth_hmacs->length);
+ chunksize += WORD_ROUND(ntohs(auth_hmacs->length));
else
auth_hmacs = NULL;
auth_chunks = (sctp_paramhdr_t *)asoc->c.auth_chunks;
if (auth_chunks->length)
- chunksize += ntohs(auth_chunks->length);
+ chunksize += WORD_ROUND(ntohs(auth_chunks->length));
else
auth_chunks = NULL;
@@ -412,17 +437,25 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
}
if (num_ext)
- chunksize += sizeof(sctp_supported_ext_param_t) + num_ext;
+ chunksize += WORD_ROUND(sizeof(sctp_supported_ext_param_t) +
+ num_ext);
/* Now allocate and fill out the chunk. */
retval = sctp_make_chunk(asoc, SCTP_CID_INIT_ACK, 0, chunksize);
if (!retval)
goto nomem_chunk;
- /* Per the advice in RFC 2960 6.4, send this reply to
- * the source of the INIT packet.
+ /* RFC 2960 6.4 Multi-homed SCTP Endpoints
+ *
+ * An endpoint SHOULD transmit reply chunks (e.g., SACK,
+ * HEARTBEAT ACK, * etc.) to the same destination transport
+ * address from which it received the DATA or control chunk
+ * to which it is replying.
+ *
+ * [INIT ACK back to where the INIT came from.]
*/
retval->transport = chunk->transport;
+
retval->subh.init_hdr =
sctp_addto_chunk(retval, sizeof(initack), &initack);
retval->param_hdr.v = sctp_addto_chunk(retval, addrs_len, addrs.v);
@@ -461,18 +494,6 @@ struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc,
/* We need to remove the const qualifier at this point. */
retval->asoc = (struct sctp_association *) asoc;
- /* RFC 2960 6.4 Multi-homed SCTP Endpoints
- *
- * An endpoint SHOULD transmit reply chunks (e.g., SACK,
- * HEARTBEAT ACK, * etc.) to the same destination transport
- * address from which it received the DATA or control chunk
- * to which it is replying.
- *
- * [INIT ACK back to where the INIT came from.]
- */
- if (chunk)
- retval->transport = chunk->transport;
-
nomem_chunk:
kfree(cookie);
nomem_cookie:
@@ -1129,6 +1150,24 @@ nodata:
return retval;
}
+/* Create an Operation Error chunk of a fixed size,
+ * specifically, max(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT)
+ * This is a helper function to allocate an error chunk for
+ * for those invalid parameter codes in which we may not want
+ * to report all the errors, if the incomming chunk is large
+ */
+static inline struct sctp_chunk *sctp_make_op_error_fixed(
+ const struct sctp_association *asoc,
+ const struct sctp_chunk *chunk)
+{
+ size_t size = asoc ? asoc->pathmtu : 0;
+
+ if (!size)
+ size = SCTP_DEFAULT_MAXSEGMENT;
+
+ return sctp_make_op_error_space(asoc, chunk, size);
+}
+
/* Create an Operation Error chunk. */
struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc,
const struct sctp_chunk *chunk,
@@ -1210,7 +1249,6 @@ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb,
INIT_LIST_HEAD(&retval->list);
retval->skb = skb;
retval->asoc = (struct sctp_association *)asoc;
- retval->resent = 0;
retval->has_tsn = 0;
retval->has_ssn = 0;
retval->rtt_in_progress = 0;
@@ -1371,6 +1409,18 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data)
return target;
}
+/* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient
+ * space in the chunk
+ */
+void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk,
+ int len, const void *data)
+{
+ if (skb_tailroom(chunk->skb) > len)
+ return sctp_addto_chunk(chunk, len, data);
+ else
+ return NULL;
+}
+
/* Append bytes from user space to the end of a chunk. Will panic if
* chunk is not big enough.
* Returns a kernel err value.
@@ -1974,13 +2024,12 @@ static sctp_ierror_t sctp_process_unk_param(const struct sctp_association *asoc,
* returning multiple unknown parameters.
*/
if (NULL == *errp)
- *errp = sctp_make_op_error_space(asoc, chunk,
- ntohs(chunk->chunk_hdr->length));
+ *errp = sctp_make_op_error_fixed(asoc, chunk);
if (*errp) {
- sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM,
+ sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM,
WORD_ROUND(ntohs(param.p->length)));
- sctp_addto_chunk(*errp,
+ sctp_addto_chunk_fixed(*errp,
WORD_ROUND(ntohs(param.p->length)),
param.v);
} else {
@@ -3315,21 +3364,6 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
sctp_chunk_free(asconf);
asoc->addip_last_asconf = NULL;
- /* Send the next asconf chunk from the addip chunk queue. */
- if (!list_empty(&asoc->addip_chunk_list)) {
- struct list_head *entry = asoc->addip_chunk_list.next;
- asconf = list_entry(entry, struct sctp_chunk, list);
-
- list_del_init(entry);
-
- /* Hold the chunk until an ASCONF_ACK is received. */
- sctp_chunk_hold(asconf);
- if (sctp_primitive_ASCONF(asoc, asconf))
- sctp_chunk_free(asconf);
- else
- asoc->addip_last_asconf = asconf;
- }
-
return retval;
}
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 4c5bed9af4e..3b7230ef77c 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -697,11 +697,15 @@ static void sctp_cmd_setup_t2(sctp_cmd_seq_t *cmds,
{
struct sctp_transport *t;
- t = sctp_assoc_choose_alter_transport(asoc,
+ if (chunk->transport)
+ t = chunk->transport;
+ else {
+ t = sctp_assoc_choose_alter_transport(asoc,
asoc->shutdown_last_sent_to);
+ chunk->transport = t;
+ }
asoc->shutdown_last_sent_to = t;
asoc->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] = t->rto;
- chunk->transport = t;
}
/* Helper function to change the state of an association. */
@@ -962,6 +966,29 @@ static int sctp_cmd_send_msg(struct sctp_association *asoc,
}
+/* Sent the next ASCONF packet currently stored in the association.
+ * This happens after the ASCONF_ACK was succeffully processed.
+ */
+static void sctp_cmd_send_asconf(struct sctp_association *asoc)
+{
+ /* Send the next asconf chunk from the addip chunk
+ * queue.
+ */
+ if (!list_empty(&asoc->addip_chunk_list)) {
+ struct list_head *entry = asoc->addip_chunk_list.next;
+ struct sctp_chunk *asconf = list_entry(entry,
+ struct sctp_chunk, list);
+ list_del_init(entry);
+
+ /* Hold the chunk until an ASCONF_ACK is received. */
+ sctp_chunk_hold(asconf);
+ if (sctp_primitive_ASCONF(asoc, asconf))
+ sctp_chunk_free(asconf);
+ else
+ asoc->addip_last_asconf = asconf;
+ }
+}
+
/* These three macros allow us to pull the debugging code out of the
* main flow of sctp_do_sm() to keep attention focused on the real
@@ -1617,6 +1644,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
}
error = sctp_cmd_send_msg(asoc, cmd->obj.msg);
break;
+ case SCTP_CMD_SEND_NEXT_ASCONF:
+ sctp_cmd_send_asconf(asoc);
+ break;
default:
printk(KERN_WARNING "Impossible command: %u, %p\n",
cmd->verb, cmd->obj.ptr);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index abf601a1b84..24b2cd55563 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3676,8 +3676,14 @@ sctp_disposition_t sctp_sf_do_asconf_ack(const struct sctp_endpoint *ep,
SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
if (!sctp_process_asconf_ack((struct sctp_association *)asoc,
- asconf_ack))
+ asconf_ack)) {
+ /* Successfully processed ASCONF_ACK. We can
+ * release the next asconf if we have one.
+ */
+ sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF,
+ SCTP_NULL());
return SCTP_DISPOSITION_CONSUME;
+ }
abort = sctp_make_abort(asoc, asconf_ack,
sizeof(sctp_errhdr_t));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index c1941276f6e..ba1add0b13c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3719,12 +3719,9 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk)
sp->hmac = NULL;
SCTP_DBG_OBJCNT_INC(sock);
- percpu_counter_inc(&sctp_sockets_allocated);
-
- /* Set socket backlog limit. */
- sk->sk_backlog.limit = sysctl_sctp_rmem[1];
local_bh_disable();
+ percpu_counter_inc(&sctp_sockets_allocated);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
local_bh_enable();
@@ -3741,8 +3738,8 @@ SCTP_STATIC void sctp_destroy_sock(struct sock *sk)
/* Release our hold on the endpoint. */
ep = sctp_sk(sk)->ep;
sctp_endpoint_free(ep);
- percpu_counter_dec(&sctp_sockets_allocated);
local_bh_disable();
+ percpu_counter_dec(&sctp_sockets_allocated);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
}
@@ -4387,7 +4384,7 @@ static int sctp_getsockopt_peer_addrs(struct sock *sk, int len,
transports) {
memcpy(&temp, &from->ipaddr, sizeof(temp));
sctp_get_pf_specific(sk->sk_family)->addr_v4map(sp, &temp);
- addrlen = sctp_get_af_specific(sk->sk_family)->sockaddr_len;
+ addrlen = sctp_get_af_specific(temp.sa.sa_family)->sockaddr_len;
if (space_left < addrlen)
return -ENOMEM;
if (copy_to_user(to, &temp, addrlen))
@@ -5702,7 +5699,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
struct sctp_sock *sp = sctp_sk(sk);
unsigned int mask;
- poll_wait(file, sk->sk_sleep, wait);
+ poll_wait(file, sk_sleep(sk), wait);
/* A TCP-style listening socket becomes readable when the accept queue
* is not empty.
@@ -5943,7 +5940,7 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p)
int error;
DEFINE_WAIT(wait);
- prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
/* Socket errors? */
error = sock_error(sk);
@@ -5980,14 +5977,14 @@ static int sctp_wait_for_packet(struct sock * sk, int *err, long *timeo_p)
sctp_lock_sock(sk);
ready:
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return 0;
interrupted:
error = sock_intr_errno(*timeo_p);
out:
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
*err = error;
return error;
}
@@ -6061,14 +6058,14 @@ static void __sctp_write_space(struct sctp_association *asoc)
wake_up_interruptible(&asoc->wait);
if (sctp_writeable(sk)) {
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
/* Note that we try to include the Async I/O support
* here by modeling from the current TCP/UDP code.
* We have not tested with it yet.
*/
- if (sock->fasync_list &&
+ if (sock->wq->fasync_list &&
!(sk->sk_shutdown & SEND_SHUTDOWN))
sock_wake_async(sock,
SOCK_WAKE_SPACE, POLL_OUT);
@@ -6188,6 +6185,19 @@ do_nonblock:
goto out;
}
+void sctp_data_ready(struct sock *sk, int len)
+{
+ struct socket_wq *wq;
+
+ rcu_read_lock();
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_sync_poll(&wq->wait, POLLIN |
+ POLLRDNORM | POLLRDBAND);
+ sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+ rcu_read_unlock();
+}
+
/* If socket sndbuf has changed, wake up all per association waiters. */
void sctp_write_space(struct sock *sk)
{
@@ -6296,7 +6306,7 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo)
for (;;) {
- prepare_to_wait_exclusive(sk->sk_sleep, &wait,
+ prepare_to_wait_exclusive(sk_sleep(sk), &wait,
TASK_INTERRUPTIBLE);
if (list_empty(&ep->asocs)) {
@@ -6322,7 +6332,7 @@ static int sctp_wait_for_accept(struct sock *sk, long timeo)
break;
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
return err;
}
@@ -6332,7 +6342,7 @@ static void sctp_wait_for_close(struct sock *sk, long timeout)
DEFINE_WAIT(wait);
do {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (list_empty(&sctp_sk(sk)->ep->asocs))
break;
sctp_release_sock(sk);
@@ -6340,7 +6350,7 @@ static void sctp_wait_for_close(struct sock *sk, long timeout)
sctp_lock_sock(sk);
} while (!signal_pending(current) && timeout);
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
}
static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk)
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index be4d63d5a5c..fccf4947aff 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -64,9 +64,6 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
/* Copy in the address. */
peer->ipaddr = *addr;
peer->af_specific = sctp_get_af_specific(addr->sa.sa_family);
- peer->asoc = NULL;
-
- peer->dst = NULL;
memset(&peer->saddr, 0, sizeof(union sctp_addr));
/* From 6.3.1 RTO Calculation:
@@ -76,34 +73,21 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
* parameter 'RTO.Initial'.
*/
peer->rto = msecs_to_jiffies(sctp_rto_initial);
- peer->rtt = 0;
- peer->rttvar = 0;
- peer->srtt = 0;
- peer->rto_pending = 0;
- peer->hb_sent = 0;
- peer->fast_recovery = 0;
peer->last_time_heard = jiffies;
peer->last_time_ecne_reduced = jiffies;
- peer->init_sent_count = 0;
-
peer->param_flags = SPP_HB_DISABLE |
SPP_PMTUD_ENABLE |
SPP_SACKDELAY_ENABLE;
- peer->hbinterval = 0;
/* Initialize the default path max_retrans. */
peer->pathmaxrxt = sctp_max_retrans_path;
- peer->error_count = 0;
INIT_LIST_HEAD(&peer->transmitted);
INIT_LIST_HEAD(&peer->send_ready);
INIT_LIST_HEAD(&peer->transports);
- peer->T3_rtx_timer.expires = 0;
- peer->hb_timer.expires = 0;
-
setup_timer(&peer->T3_rtx_timer, sctp_generate_t3_rtx_event,
(unsigned long)peer);
setup_timer(&peer->hb_timer, sctp_generate_heartbeat_event,
@@ -113,15 +97,6 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer,
get_random_bytes(&peer->hb_nonce, sizeof(peer->hb_nonce));
atomic_set(&peer->refcnt, 1);
- peer->dead = 0;
-
- peer->malloced = 0;
-
- /* Initialize the state information for SFR-CACC */
- peer->cacc.changeover_active = 0;
- peer->cacc.cycling_changeover = 0;
- peer->cacc.next_tsn_at_change = 0;
- peer->cacc.cacc_saw_newack = 0;
return peer;
}
@@ -195,7 +170,7 @@ static void sctp_transport_destroy(struct sctp_transport *transport)
/* Start T3_rtx timer if it is not already running and update the heartbeat
* timer. This routine is called every time a DATA chunk is sent.
*/
-void sctp_transport_reset_timers(struct sctp_transport *transport, int force)
+void sctp_transport_reset_timers(struct sctp_transport *transport)
{
/* RFC 2960 6.3.2 Retransmission Timer Rules
*
@@ -205,7 +180,7 @@ void sctp_transport_reset_timers(struct sctp_transport *transport, int force)
* address.
*/
- if (force || !timer_pending(&transport->T3_rtx_timer))
+ if (!timer_pending(&transport->T3_rtx_timer))
if (!mod_timer(&transport->T3_rtx_timer,
jiffies + transport->rto))
sctp_transport_hold(transport);
@@ -403,15 +378,16 @@ void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt)
void sctp_transport_raise_cwnd(struct sctp_transport *transport,
__u32 sack_ctsn, __u32 bytes_acked)
{
+ struct sctp_association *asoc = transport->asoc;
__u32 cwnd, ssthresh, flight_size, pba, pmtu;
cwnd = transport->cwnd;
flight_size = transport->flight_size;
/* See if we need to exit Fast Recovery first */
- if (transport->fast_recovery &&
- TSN_lte(transport->fast_recovery_exit, sack_ctsn))
- transport->fast_recovery = 0;
+ if (asoc->fast_recovery &&
+ TSN_lte(asoc->fast_recovery_exit, sack_ctsn))
+ asoc->fast_recovery = 0;
/* The appropriate cwnd increase algorithm is performed if, and only
* if the cumulative TSN whould advanced and the congestion window is
@@ -440,7 +416,7 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport,
* 2) the destination's path MTU. This upper bound protects
* against the ACK-Splitting attack outlined in [SAVAGE99].
*/
- if (transport->fast_recovery)
+ if (asoc->fast_recovery)
return;
if (bytes_acked > pmtu)
@@ -491,6 +467,8 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport,
void sctp_transport_lower_cwnd(struct sctp_transport *transport,
sctp_lower_cwnd_t reason)
{
+ struct sctp_association *asoc = transport->asoc;
+
switch (reason) {
case SCTP_LOWER_CWND_T3_RTX:
/* RFC 2960 Section 7.2.3, sctpimpguide
@@ -501,11 +479,11 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport,
* partial_bytes_acked = 0
*/
transport->ssthresh = max(transport->cwnd/2,
- 4*transport->asoc->pathmtu);
- transport->cwnd = transport->asoc->pathmtu;
+ 4*asoc->pathmtu);
+ transport->cwnd = asoc->pathmtu;
- /* T3-rtx also clears fast recovery on the transport */
- transport->fast_recovery = 0;
+ /* T3-rtx also clears fast recovery */
+ asoc->fast_recovery = 0;
break;
case SCTP_LOWER_CWND_FAST_RTX:
@@ -521,15 +499,15 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport,
* cwnd = ssthresh
* partial_bytes_acked = 0
*/
- if (transport->fast_recovery)
+ if (asoc->fast_recovery)
return;
/* Mark Fast recovery */
- transport->fast_recovery = 1;
- transport->fast_recovery_exit = transport->asoc->next_tsn - 1;
+ asoc->fast_recovery = 1;
+ asoc->fast_recovery_exit = asoc->next_tsn - 1;
transport->ssthresh = max(transport->cwnd/2,
- 4*transport->asoc->pathmtu);
+ 4*asoc->pathmtu);
transport->cwnd = transport->ssthresh;
break;
@@ -549,7 +527,7 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport,
if (time_after(jiffies, transport->last_time_ecne_reduced +
transport->rtt)) {
transport->ssthresh = max(transport->cwnd/2,
- 4*transport->asoc->pathmtu);
+ 4*asoc->pathmtu);
transport->cwnd = transport->ssthresh;
transport->last_time_ecne_reduced = jiffies;
}
@@ -565,7 +543,7 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport,
* interval.
*/
transport->cwnd = max(transport->cwnd/2,
- 4*transport->asoc->pathmtu);
+ 4*asoc->pathmtu);
break;
}
@@ -650,7 +628,6 @@ void sctp_transport_reset(struct sctp_transport *t)
t->error_count = 0;
t->rto_pending = 0;
t->hb_sent = 0;
- t->fast_recovery = 0;
/* Initialize the state information for SFR-CACC */
t->cacc.changeover_active = 0;
diff --git a/net/socket.c b/net/socket.c
index 35bc198bbf6..dae8c6b84a0 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -252,9 +252,14 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
- init_waitqueue_head(&ei->socket.wait);
+ ei->socket.wq = kmalloc(sizeof(struct socket_wq), GFP_KERNEL);
+ if (!ei->socket.wq) {
+ kmem_cache_free(sock_inode_cachep, ei);
+ return NULL;
+ }
+ init_waitqueue_head(&ei->socket.wq->wait);
+ ei->socket.wq->fasync_list = NULL;
- ei->socket.fasync_list = NULL;
ei->socket.state = SS_UNCONNECTED;
ei->socket.flags = 0;
ei->socket.ops = NULL;
@@ -264,10 +269,21 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
return &ei->vfs_inode;
}
+
+static void wq_free_rcu(struct rcu_head *head)
+{
+ struct socket_wq *wq = container_of(head, struct socket_wq, rcu);
+
+ kfree(wq);
+}
+
static void sock_destroy_inode(struct inode *inode)
{
- kmem_cache_free(sock_inode_cachep,
- container_of(inode, struct socket_alloc, vfs_inode));
+ struct socket_alloc *ei;
+
+ ei = container_of(inode, struct socket_alloc, vfs_inode);
+ call_rcu(&ei->socket.wq->rcu, wq_free_rcu);
+ kmem_cache_free(sock_inode_cachep, ei);
}
static void init_once(void *foo)
@@ -513,7 +529,7 @@ void sock_release(struct socket *sock)
module_put(owner);
}
- if (sock->fasync_list)
+ if (sock->wq->fasync_list)
printk(KERN_ERR "sock_release: fasync list not empty!\n");
percpu_sub(sockets_in_use, 1);
@@ -655,13 +671,13 @@ inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff
sizeof(__u32), &skb->dropcount);
}
-void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
+void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb)
{
sock_recv_timestamp(msg, sk, skb);
sock_recv_drops(msg, sk, skb);
}
-EXPORT_SYMBOL_GPL(sock_recv_ts_and_drops);
+EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size, int flags)
@@ -1067,87 +1083,44 @@ static int sock_close(struct inode *inode, struct file *filp)
* 1. fasync_list is modified only under process context socket lock
* i.e. under semaphore.
* 2. fasync_list is used under read_lock(&sk->sk_callback_lock)
- * or under socket lock.
- * 3. fasync_list can be used from softirq context, so that
- * modification under socket lock have to be enhanced with
- * write_lock_bh(&sk->sk_callback_lock).
- * --ANK (990710)
+ * or under socket lock
*/
static int sock_fasync(int fd, struct file *filp, int on)
{
- struct fasync_struct *fa, *fna = NULL, **prev;
- struct socket *sock;
- struct sock *sk;
-
- if (on) {
- fna = kmalloc(sizeof(struct fasync_struct), GFP_KERNEL);
- if (fna == NULL)
- return -ENOMEM;
- }
-
- sock = filp->private_data;
+ struct socket *sock = filp->private_data;
+ struct sock *sk = sock->sk;
- sk = sock->sk;
- if (sk == NULL) {
- kfree(fna);
+ if (sk == NULL)
return -EINVAL;
- }
lock_sock(sk);
- spin_lock(&filp->f_lock);
- if (on)
- filp->f_flags |= FASYNC;
- else
- filp->f_flags &= ~FASYNC;
- spin_unlock(&filp->f_lock);
-
- prev = &(sock->fasync_list);
-
- for (fa = *prev; fa != NULL; prev = &fa->fa_next, fa = *prev)
- if (fa->fa_file == filp)
- break;
-
- if (on) {
- if (fa != NULL) {
- write_lock_bh(&sk->sk_callback_lock);
- fa->fa_fd = fd;
- write_unlock_bh(&sk->sk_callback_lock);
+ fasync_helper(fd, filp, on, &sock->wq->fasync_list);
- kfree(fna);
- goto out;
- }
- fna->fa_file = filp;
- fna->fa_fd = fd;
- fna->magic = FASYNC_MAGIC;
- fna->fa_next = sock->fasync_list;
- write_lock_bh(&sk->sk_callback_lock);
- sock->fasync_list = fna;
+ if (!sock->wq->fasync_list)
+ sock_reset_flag(sk, SOCK_FASYNC);
+ else
sock_set_flag(sk, SOCK_FASYNC);
- write_unlock_bh(&sk->sk_callback_lock);
- } else {
- if (fa != NULL) {
- write_lock_bh(&sk->sk_callback_lock);
- *prev = fa->fa_next;
- if (!sock->fasync_list)
- sock_reset_flag(sk, SOCK_FASYNC);
- write_unlock_bh(&sk->sk_callback_lock);
- kfree(fa);
- }
- }
-out:
- release_sock(sock->sk);
+ release_sock(sk);
return 0;
}
-/* This function may be called only under socket lock or callback_lock */
+/* This function may be called only under socket lock or callback_lock or rcu_lock */
int sock_wake_async(struct socket *sock, int how, int band)
{
- if (!sock || !sock->fasync_list)
+ struct socket_wq *wq;
+
+ if (!sock)
return -1;
+ rcu_read_lock();
+ wq = rcu_dereference(sock->wq);
+ if (!wq || !wq->fasync_list) {
+ rcu_read_unlock();
+ return -1;
+ }
switch (how) {
case SOCK_WAKE_WAITD:
if (test_bit(SOCK_ASYNC_WAITDATA, &sock->flags))
@@ -1159,11 +1132,12 @@ int sock_wake_async(struct socket *sock, int how, int band)
/* fall through */
case SOCK_WAKE_IO:
call_kill:
- __kill_fasync(sock->fasync_list, SIGIO, band);
+ kill_fasync(&wq->fasync_list, SIGIO, band);
break;
case SOCK_WAKE_URG:
- __kill_fasync(sock->fasync_list, SIGURG, band);
+ kill_fasync(&wq->fasync_list, SIGURG, band);
}
+ rcu_read_unlock();
return 0;
}
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index a29f259204e..ce0d5b35c2a 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -419,8 +419,8 @@ static void svc_udp_data_ready(struct sock *sk, int count)
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
}
/*
@@ -436,10 +436,10 @@ static void svc_write_space(struct sock *sk)
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) {
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) {
dprintk("RPC svc_write_space: someone sleeping on %p\n",
svsk);
- wake_up_interruptible(sk->sk_sleep);
+ wake_up_interruptible(sk_sleep(sk));
}
}
@@ -757,8 +757,8 @@ static void svc_tcp_listen_data_ready(struct sock *sk, int count_unused)
printk("svc: socket %p: no user data\n", sk);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_all(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible_all(sk_sleep(sk));
}
/*
@@ -777,8 +777,8 @@ static void svc_tcp_state_change(struct sock *sk)
set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_all(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible_all(sk_sleep(sk));
}
static void svc_tcp_data_ready(struct sock *sk, int count)
@@ -791,8 +791,8 @@ static void svc_tcp_data_ready(struct sock *sk, int count)
set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
svc_xprt_enqueue(&svsk->sk_xprt);
}
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
}
/*
@@ -1494,8 +1494,8 @@ static void svc_sock_detach(struct svc_xprt *xprt)
sk->sk_data_ready = svsk->sk_odata;
sk->sk_write_space = svsk->sk_owspace;
- if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
}
/*
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 42f09ade004..699ade68aac 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -974,7 +974,7 @@ void xprt_reserve(struct rpc_task *task)
static inline __be32 xprt_alloc_xid(struct rpc_xprt *xprt)
{
- return xprt->xid++;
+ return (__force __be32)xprt->xid++;
}
static inline void xprt_init_xid(struct rpc_xprt *xprt)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index fd90eb89842..edea15a54e5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -679,7 +679,10 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
int ret;
dprintk("svcrdma: Creating RDMA socket\n");
-
+ if (sa->sa_family != AF_INET) {
+ dprintk("svcrdma: Address family %d is not supported.\n", sa->sa_family);
+ return ERR_PTR(-EAFNOSUPPORT);
+ }
cma_xprt = rdma_create_xprt(serv, 1);
if (!cma_xprt)
return ERR_PTR(-ENOMEM);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index cfb20b80b3a..66e889ba48f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -446,7 +446,7 @@ static unsigned int poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk;
u32 mask;
- poll_wait(file, sk->sk_sleep, wait);
+ poll_wait(file, sk_sleep(sk), wait);
if (!skb_queue_empty(&sk->sk_receive_queue) ||
(sock->state == SS_UNCONNECTED) ||
@@ -591,7 +591,7 @@ static int send_msg(struct kiocb *iocb, struct socket *sock,
break;
}
release_sock(sk);
- res = wait_event_interruptible(*sk->sk_sleep,
+ res = wait_event_interruptible(*sk_sleep(sk),
!tport->congested);
lock_sock(sk);
if (res)
@@ -650,7 +650,7 @@ static int send_packet(struct kiocb *iocb, struct socket *sock,
break;
}
release_sock(sk);
- res = wait_event_interruptible(*sk->sk_sleep,
+ res = wait_event_interruptible(*sk_sleep(sk),
(!tport->congested || !tport->connected));
lock_sock(sk);
if (res)
@@ -931,7 +931,7 @@ restart:
goto exit;
}
release_sock(sk);
- res = wait_event_interruptible(*sk->sk_sleep,
+ res = wait_event_interruptible(*sk_sleep(sk),
(!skb_queue_empty(&sk->sk_receive_queue) ||
(sock->state == SS_DISCONNECTING)));
lock_sock(sk);
@@ -1064,7 +1064,7 @@ restart:
goto exit;
}
release_sock(sk);
- res = wait_event_interruptible(*sk->sk_sleep,
+ res = wait_event_interruptible(*sk_sleep(sk),
(!skb_queue_empty(&sk->sk_receive_queue) ||
(sock->state == SS_DISCONNECTING)));
lock_sock(sk);
@@ -1271,8 +1271,8 @@ static u32 filter_rcv(struct sock *sk, struct sk_buff *buf)
tipc_disconnect_port(tipc_sk_port(sk));
}
- if (waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
return TIPC_OK;
}
@@ -1343,8 +1343,8 @@ static void wakeupdispatch(struct tipc_port *tport)
{
struct sock *sk = (struct sock *)tport->usr_handle;
- if (waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
}
/**
@@ -1426,7 +1426,7 @@ static int connect(struct socket *sock, struct sockaddr *dest, int destlen,
/* Wait until an 'ACK' or 'RST' arrives, or a timeout occurs */
release_sock(sk);
- res = wait_event_interruptible_timeout(*sk->sk_sleep,
+ res = wait_event_interruptible_timeout(*sk_sleep(sk),
(!skb_queue_empty(&sk->sk_receive_queue) ||
(sock->state != SS_CONNECTING)),
sk->sk_rcvtimeo);
@@ -1521,7 +1521,7 @@ static int accept(struct socket *sock, struct socket *new_sock, int flags)
goto exit;
}
release_sock(sk);
- res = wait_event_interruptible(*sk->sk_sleep,
+ res = wait_event_interruptible(*sk_sleep(sk),
(!skb_queue_empty(&sk->sk_receive_queue)));
lock_sock(sk);
if (res)
@@ -1632,8 +1632,8 @@ restart:
/* Discard any unreceived messages; wake up sleeping tasks */
discard_rx_queue(sk);
- if (waitqueue_active(sk->sk_sleep))
- wake_up_interruptible(sk->sk_sleep);
+ if (waitqueue_active(sk_sleep(sk)))
+ wake_up_interruptible(sk_sleep(sk));
res = 0;
break;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 3d9122e78f4..fef2cc5e9d2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -313,13 +313,16 @@ static inline int unix_writable(struct sock *sk)
static void unix_write_space(struct sock *sk)
{
- read_lock(&sk->sk_callback_lock);
+ struct socket_wq *wq;
+
+ rcu_read_lock();
if (unix_writable(sk)) {
- if (sk_has_sleeper(sk))
- wake_up_interruptible_sync(sk->sk_sleep);
+ wq = rcu_dereference(sk->sk_wq);
+ if (wq_has_sleeper(wq))
+ wake_up_interruptible_sync(&wq->wait);
sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
}
- read_unlock(&sk->sk_callback_lock);
+ rcu_read_unlock();
}
/* When dgram socket disconnects (or changes its peer), we clear its receive
@@ -406,9 +409,7 @@ static int unix_release_sock(struct sock *sk, int embrion)
skpair->sk_err = ECONNRESET;
unix_state_unlock(skpair);
skpair->sk_state_change(skpair);
- read_lock(&skpair->sk_callback_lock);
sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
- read_unlock(&skpair->sk_callback_lock);
}
sock_put(skpair); /* It may now die */
unix_peer(sk) = NULL;
@@ -1142,7 +1143,7 @@ restart:
newsk->sk_peercred.pid = task_tgid_vnr(current);
current_euid_egid(&newsk->sk_peercred.uid, &newsk->sk_peercred.gid);
newu = unix_sk(newsk);
- newsk->sk_sleep = &newu->peer_wait;
+ newsk->sk_wq = &newu->peer_wq;
otheru = unix_sk(other);
/* copy address information from listening to new sock*/
@@ -1736,7 +1737,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo)
unix_state_lock(sk);
for (;;) {
- prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (!skb_queue_empty(&sk->sk_receive_queue) ||
sk->sk_err ||
@@ -1752,7 +1753,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo)
clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
}
- finish_wait(sk->sk_sleep, &wait);
+ finish_wait(sk_sleep(sk), &wait);
unix_state_unlock(sk);
return timeo;
}
@@ -1931,12 +1932,10 @@ static int unix_shutdown(struct socket *sock, int mode)
other->sk_shutdown |= peer_mode;
unix_state_unlock(other);
other->sk_state_change(other);
- read_lock(&other->sk_callback_lock);
if (peer_mode == SHUTDOWN_MASK)
sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
else if (peer_mode & RCV_SHUTDOWN)
sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
- read_unlock(&other->sk_callback_lock);
}
if (other)
sock_put(other);
@@ -1991,7 +1990,7 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table
struct sock *sk = sock->sk;
unsigned int mask;
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
mask = 0;
/* exceptional events? */
@@ -2028,7 +2027,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
struct sock *sk = sock->sk, *other;
unsigned int mask, writable;
- sock_poll_wait(file, sk->sk_sleep, wait);
+ sock_poll_wait(file, sk_sleep(sk), wait);
mask = 0;
/* exceptional events? */
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 14c22c3768d..c8df6fda0b1 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -153,15 +153,6 @@ void unix_notinflight(struct file *fp)
}
}
-static inline struct sk_buff *sock_queue_head(struct sock *sk)
-{
- return (struct sk_buff *)&sk->sk_receive_queue;
-}
-
-#define receive_queue_for_each_skb(sk, next, skb) \
- for (skb = sock_queue_head(sk)->next, next = skb->next; \
- skb != sock_queue_head(sk); skb = next, next = skb->next)
-
static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
struct sk_buff_head *hitlist)
{
@@ -169,7 +160,7 @@ static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
struct sk_buff *next;
spin_lock(&x->sk_receive_queue.lock);
- receive_queue_for_each_skb(x, next, skb) {
+ skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
/*
* Do we have file descriptors ?
*/
@@ -225,7 +216,7 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *),
* and perform a scan on them as well.
*/
spin_lock(&x->sk_receive_queue.lock);
- receive_queue_for_each_skb(x, next, skb) {
+ skb_queue_walk_safe(&x->sk_receive_queue, skb, next) {
u = unix_sk(skb->sk);
/*
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 6ac70c10152..37d0e0ab443 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -705,7 +705,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb,
wdev->ps = true;
else
wdev->ps = false;
- wdev->ps_timeout = 100;
+ /* allow mac80211 to determine the timeout */
+ wdev->ps_timeout = -1;
if (rdev->ops->set_power_mgmt)
if (rdev->ops->set_power_mgmt(wdev->wiphy, dev,
wdev->ps,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 356a84a5dae..01da83ddcff 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -152,6 +152,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = {
[NL80211_ATTR_PS_STATE] = { .type = NLA_U32 },
[NL80211_ATTR_CQM] = { .type = NLA_NESTED, },
[NL80211_ATTR_LOCAL_STATE_CHANGE] = { .type = NLA_FLAG },
+ [NL80211_ATTR_AP_ISOLATE] = { .type = NLA_U8 },
};
/* policy for the attributes */
@@ -2442,6 +2443,7 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info)
params.use_cts_prot = -1;
params.use_short_preamble = -1;
params.use_short_slot_time = -1;
+ params.ap_isolate = -1;
if (info->attrs[NL80211_ATTR_BSS_CTS_PROT])
params.use_cts_prot =
@@ -2458,6 +2460,8 @@ static int nl80211_set_bss(struct sk_buff *skb, struct genl_info *info)
params.basic_rates_len =
nla_len(info->attrs[NL80211_ATTR_BSS_BASIC_RATES]);
}
+ if (info->attrs[NL80211_ATTR_AP_ISOLATE])
+ params.ap_isolate = !!nla_get_u8(info->attrs[NL80211_ATTR_AP_ISOLATE]);
rtnl_lock();
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index c2735775ec1..8ddf5ae0dd0 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -518,12 +518,16 @@ void cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
ev->type = EVENT_CONNECT_RESULT;
if (bssid)
memcpy(ev->cr.bssid, bssid, ETH_ALEN);
- ev->cr.req_ie = ((u8 *)ev) + sizeof(*ev);
- ev->cr.req_ie_len = req_ie_len;
- memcpy((void *)ev->cr.req_ie, req_ie, req_ie_len);
- ev->cr.resp_ie = ((u8 *)ev) + sizeof(*ev) + req_ie_len;
- ev->cr.resp_ie_len = resp_ie_len;
- memcpy((void *)ev->cr.resp_ie, resp_ie, resp_ie_len);
+ if (req_ie_len) {
+ ev->cr.req_ie = ((u8 *)ev) + sizeof(*ev);
+ ev->cr.req_ie_len = req_ie_len;
+ memcpy((void *)ev->cr.req_ie, req_ie, req_ie_len);
+ }
+ if (resp_ie_len) {
+ ev->cr.resp_ie = ((u8 *)ev) + sizeof(*ev) + req_ie_len;
+ ev->cr.resp_ie_len = resp_ie_len;
+ memcpy((void *)ev->cr.resp_ie, resp_ie, resp_ie_len);
+ }
ev->cr.status = status;
spin_lock_irqsave(&wdev->event_lock, flags);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index cbddd0cb83f..296e65e0106 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -402,6 +402,7 @@ static void __x25_destroy_socket(struct sock *sk)
/*
* Queue the unaccepted socket for death
*/
+ skb->sk->sk_state = TCP_LISTEN;
sock_set_flag(skb->sk, SOCK_DEAD);
x25_start_heartbeat(skb->sk);
x25_sk(skb->sk)->state = X25_STATE_0;
@@ -718,7 +719,7 @@ static int x25_wait_for_connection_establishment(struct sock *sk)
DECLARE_WAITQUEUE(wait, current);
int rc;
- add_wait_queue_exclusive(sk->sk_sleep, &wait);
+ add_wait_queue_exclusive(sk_sleep(sk), &wait);
for (;;) {
__set_current_state(TASK_INTERRUPTIBLE);
rc = -ERESTARTSYS;
@@ -738,7 +739,7 @@ static int x25_wait_for_connection_establishment(struct sock *sk)
break;
}
__set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
@@ -838,7 +839,7 @@ static int x25_wait_for_data(struct sock *sk, long timeout)
DECLARE_WAITQUEUE(wait, current);
int rc = 0;
- add_wait_queue_exclusive(sk->sk_sleep, &wait);
+ add_wait_queue_exclusive(sk_sleep(sk), &wait);
for (;;) {
__set_current_state(TASK_INTERRUPTIBLE);
if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -858,7 +859,7 @@ static int x25_wait_for_data(struct sock *sk, long timeout)
break;
}
__set_current_state(TASK_RUNNING);
- remove_wait_queue(sk->sk_sleep, &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return rc;
}
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index b9ef682230a..9005f6daeab 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -24,6 +24,7 @@
#include <net/sock.h>
#include <linux/if_arp.h>
#include <net/x25.h>
+#include <net/x25device.h>
static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb)
{
@@ -115,19 +116,22 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev,
}
switch (skb->data[0]) {
- case 0x00:
- skb_pull(skb, 1);
- if (x25_receive_data(skb, nb)) {
- x25_neigh_put(nb);
- goto out;
- }
- break;
- case 0x01:
- x25_link_established(nb);
- break;
- case 0x02:
- x25_link_terminated(nb);
- break;
+
+ case X25_IFACE_DATA:
+ skb_pull(skb, 1);
+ if (x25_receive_data(skb, nb)) {
+ x25_neigh_put(nb);
+ goto out;
+ }
+ break;
+
+ case X25_IFACE_CONNECT:
+ x25_link_established(nb);
+ break;
+
+ case X25_IFACE_DISCONNECT:
+ x25_link_terminated(nb);
+ break;
}
x25_neigh_put(nb);
drop:
@@ -148,7 +152,7 @@ void x25_establish_link(struct x25_neigh *nb)
return;
}
ptr = skb_put(skb, 1);
- *ptr = 0x01;
+ *ptr = X25_IFACE_CONNECT;
break;
#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
@@ -184,7 +188,7 @@ void x25_terminate_link(struct x25_neigh *nb)
}
ptr = skb_put(skb, 1);
- *ptr = 0x02;
+ *ptr = X25_IFACE_DISCONNECT;
skb->protocol = htons(ETH_P_X25);
skb->dev = nb->dev;
@@ -200,7 +204,7 @@ void x25_send_frame(struct sk_buff *skb, struct x25_neigh *nb)
switch (nb->dev->type) {
case ARPHRD_X25:
dptr = skb_push(skb, 1);
- *dptr = 0x00;
+ *dptr = X25_IFACE_DATA;
break;
#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h
index e5195c99f71..1396572d2ad 100644
--- a/net/xfrm/xfrm_hash.h
+++ b/net/xfrm/xfrm_hash.h
@@ -16,7 +16,8 @@ static inline unsigned int __xfrm6_addr_hash(xfrm_address_t *addr)
static inline unsigned int __xfrm4_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr)
{
- return ntohl(daddr->a4 + saddr->a4);
+ u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4;
+ return ntohl((__force __be32)sum);
}
static inline unsigned int __xfrm6_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr)
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7430ac26ec4..31f4ba43b48 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1732,7 +1732,7 @@ int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl,
struct dst_entry *dst, *dst_orig = *dst_p, *route;
u16 family = dst_orig->ops->family;
u8 dir = policy_to_flow_dir(XFRM_POLICY_OUT);
- int i, err, num_pols, num_xfrms, drop_pols = 0;
+ int i, err, num_pols, num_xfrms = 0, drop_pols = 0;
restart:
dst = NULL;