From 2c8c1e7297e19bdef3c178c3ea41d898a7716e3e Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 17 Jan 2010 03:35:32 +0000 Subject: net: spread __net_init, __net_exit __net_init/__net_exit are apparently not going away, so use them to full extent. In some cases __net_init was removed, because it was called from __net_exit code. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- net/unix/af_unix.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f2551190311..9bc9b92bc09 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2224,7 +2224,7 @@ static const struct net_proto_family unix_family_ops = { }; -static int unix_net_init(struct net *net) +static int __net_init unix_net_init(struct net *net) { int error = -ENOMEM; @@ -2243,7 +2243,7 @@ out: return error; } -static void unix_net_exit(struct net *net) +static void __net_exit unix_net_exit(struct net *net) { unix_sysctl_unregister(net); proc_net_remove(net, "unix"); -- cgit v1.2.3 From 663717f65c075eb4c6da7a123041295bd5295cc0 Mon Sep 17 00:00:00 2001 From: Stephen Hemminger Date: Thu, 18 Feb 2010 14:12:06 -0800 Subject: AF_UNIX: update locking comment The lock used in unix_state_lock() is a spin_lock not reader-writer. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 9bc9b92bc09..3d9122e78f4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -144,7 +144,7 @@ static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb) /* * SMP locking strategy: * hash table is protected with spinlock unix_table_lock - * each socket state is protected by separate rwlock. + * each socket state is protected by separate spin lock. */ static inline unsigned unix_hash_fold(__wsum n) -- cgit v1.2.3 From aa395145165cb06a0d0885221bbe0ce4a564391d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 20 Apr 2010 13:03:51 +0000 Subject: net: sk_sleep() helper Define a new function to return the waitqueue of a "struct sock". static inline wait_queue_head_t *sk_sleep(struct sock *sk) { return sk->sk_sleep; } Change all read occurrences of sk_sleep by a call to this function. Needed for a future RCU conversion. sk_sleep wont be a field directly available. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/atm/atmtcp.c | 6 ++-- drivers/net/macvtap.c | 4 +-- drivers/net/tun.c | 4 +-- drivers/scsi/iscsi_tcp.c | 4 +-- include/net/sock.h | 10 +++++-- include/net/tcp.h | 2 +- net/atm/common.c | 12 ++++---- net/atm/signaling.c | 2 +- net/atm/svc.c | 62 ++++++++++++++++++++--------------------- net/ax25/af_ax25.c | 8 +++--- net/bluetooth/af_bluetooth.c | 6 ++-- net/bluetooth/bnep/core.c | 8 +++--- net/bluetooth/bnep/netdev.c | 6 ++-- net/bluetooth/cmtp/cmtp.h | 2 +- net/bluetooth/cmtp/core.c | 4 +-- net/bluetooth/hidp/core.c | 10 +++---- net/bluetooth/hidp/hidp.h | 4 +-- net/bluetooth/l2cap.c | 4 +-- net/bluetooth/rfcomm/sock.c | 8 +++--- net/bluetooth/sco.c | 4 +-- net/caif/caif_socket.c | 2 +- net/core/datagram.c | 6 ++-- net/core/sock.c | 16 +++++------ net/core/stream.c | 16 +++++------ net/dccp/output.c | 6 ++-- net/dccp/proto.c | 2 +- net/decnet/af_decnet.c | 26 ++++++++--------- net/ipv4/af_inet.c | 6 ++-- net/ipv4/inet_connection_sock.c | 4 +-- net/ipv4/tcp.c | 2 +- net/irda/af_irda.c | 14 +++++----- net/iucv/af_iucv.c | 12 ++++---- net/llc/af_llc.c | 12 ++++---- net/netfilter/ipvs/ip_vs_sync.c | 2 +- net/netrom/af_netrom.c | 8 +++--- net/rds/af_rds.c | 2 +- net/rds/rds.h | 2 +- net/rds/recv.c | 2 +- net/rds/send.c | 2 +- net/rose/af_rose.c | 8 +++--- net/rxrpc/af_rxrpc.c | 4 +-- net/sctp/socket.c | 20 ++++++------- net/sunrpc/svcsock.c | 24 ++++++++-------- net/tipc/socket.c | 26 ++++++++--------- net/unix/af_unix.c | 10 +++---- net/x25/af_x25.c | 8 +++--- 46 files changed, 208 insertions(+), 204 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c index b86712167eb..b9101818b47 100644 --- a/drivers/atm/atmtcp.c +++ b/drivers/atm/atmtcp.c @@ -68,7 +68,7 @@ static int atmtcp_send_control(struct atm_vcc *vcc,int type, *(struct atm_vcc **) &new_msg->vcc = vcc; old_test = test_bit(flag,&vcc->flags); out_vcc->push(out_vcc,skb); - add_wait_queue(sk_atm(vcc)->sk_sleep, &wait); + add_wait_queue(sk_sleep(sk_atm(vcc)), &wait); while (test_bit(flag,&vcc->flags) == old_test) { mb(); out_vcc = PRIV(vcc->dev) ? PRIV(vcc->dev)->vcc : NULL; @@ -80,7 +80,7 @@ static int atmtcp_send_control(struct atm_vcc *vcc,int type, schedule(); } set_current_state(TASK_RUNNING); - remove_wait_queue(sk_atm(vcc)->sk_sleep, &wait); + remove_wait_queue(sk_sleep(sk_atm(vcc)), &wait); return error; } @@ -105,7 +105,7 @@ static int atmtcp_recv_control(const struct atmtcp_control *msg) msg->type); return -EINVAL; } - wake_up(sk_atm(vcc)->sk_sleep); + wake_up(sk_sleep(sk_atm(vcc))); return 0; } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index abba3cc81f1..85d6420f840 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -246,8 +246,8 @@ static void macvtap_sock_write_space(struct sock *sk) !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_poll(sk->sk_sleep, POLLOUT | POLLWRNORM | POLLWRBAND); + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); } static int macvtap_open(struct inode *inode, struct file *file) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 43265207d46..20a17938c62 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -868,8 +868,8 @@ static void tun_sock_write_space(struct sock *sk) if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT | + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); tun = tun_sk(sk)->tun; diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 0ee725ced51..9eae04afa9a 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -599,9 +599,9 @@ static void iscsi_sw_tcp_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx); write_unlock_bh(&tcp_sw_conn->sock->sk->sk_callback_lock); - if (sock->sk->sk_sleep && waitqueue_active(sock->sk->sk_sleep)) { + if (sk_sleep(sock->sk) && waitqueue_active(sk_sleep(sock->sk))) { sock->sk->sk_err = EIO; - wake_up_interruptible(sock->sk->sk_sleep); + wake_up_interruptible(sk_sleep(sock->sk)); } iscsi_conn_stop(cls_conn, flag); diff --git a/include/net/sock.h b/include/net/sock.h index 56df440a950..8ab05146a44 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1160,6 +1160,10 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) sk->sk_socket = sock; } +static inline wait_queue_head_t *sk_sleep(struct sock *sk) +{ + return sk->sk_sleep; +} /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. * Note that parent inode held reference count on this struct sock, @@ -1346,8 +1350,8 @@ static inline int sk_has_allocations(const struct sock *sk) * tp->rcv_nxt check sock_def_readable * ... { * schedule ... - * 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)) * ... * } * @@ -1368,7 +1372,7 @@ static inline int sk_has_sleeper(struct sock *sk) * This memory barrier is paired in the sock_poll_wait. */ smp_mb__after_lock(); - return sk->sk_sleep && waitqueue_active(sk->sk_sleep); + return sk_sleep(sk) && waitqueue_active(sk_sleep(sk)); } /** diff --git a/include/net/tcp.h b/include/net/tcp.h index 70c5159f4b3..b7d83d204a9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -939,7 +939,7 @@ static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb) tp->ucopy.memory = 0; } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) { - wake_up_interruptible_sync_poll(sk->sk_sleep, + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLIN | POLLRDNORM | POLLRDBAND); if (!inet_csk_ack_scheduled(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, diff --git a/net/atm/common.c b/net/atm/common.c index 97ed94aa0cb..e3e10e6f862 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -92,7 +92,7 @@ static void vcc_def_wakeup(struct sock *sk) { read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up(sk->sk_sleep); + wake_up(sk_sleep(sk)); read_unlock(&sk->sk_callback_lock); } @@ -110,7 +110,7 @@ static void vcc_write_space(struct sock *sk) if (vcc_writable(sk)) { if (sk_has_sleeper(sk)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } @@ -549,7 +549,7 @@ 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 +568,9 @@ 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 +595,7 @@ 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..c1e60eed5a9 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; 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/caif/caif_socket.c b/net/caif/caif_socket.c index cdf62b9fefa..90317e7d10b 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -689,7 +689,7 @@ static unsigned int caif_poll(struct file *file, struct socket *sock, 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); + poll_wait(file, sk_sleep(sk), wait); lock_sock(&(cf_sk->sk)); if (!STATE_IS_OPEN(cf_sk)) { if (!STATE_IS_PENDING(cf_sk)) diff --git a/net/core/datagram.c b/net/core/datagram.c index 2dccd4ee591..5574a5ddf90 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); @@ -726,7 +726,7 @@ 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/sock.c b/net/core/sock.c index 7effa1e689d..58ebd146ce5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1395,7 +1395,7 @@ 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 +1404,7 @@ 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 +1570,11 @@ 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); @@ -1798,7 +1798,7 @@ 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); + wake_up_interruptible_all(sk_sleep(sk)); read_unlock(&sk->sk_callback_lock); } @@ -1806,7 +1806,7 @@ 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); + wake_up_interruptible_poll(sk_sleep(sk), POLLERR); sk_wake_async(sk, SOCK_WAKE_IO, POLL_ERR); read_unlock(&sk->sk_callback_lock); } @@ -1815,7 +1815,7 @@ 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 | + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLIN | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); read_unlock(&sk->sk_callback_lock); @@ -1830,7 +1830,7 @@ static void sock_def_write_space(struct sock *sk) */ 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 | + wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); /* Should agree with poll, otherwise some programs break */ diff --git a/net/core/stream.c b/net/core/stream.c index a37debfeb1b..7b3c3f30b10 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -32,8 +32,8 @@ void sk_stream_write_space(struct sock *sk) 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 | + if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) + wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); if (sock->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT); @@ -66,13 +66,13 @@ 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 +96,13 @@ 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 +126,7 @@ 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 +157,7 @@ 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..2d3dcb39851 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -198,7 +198,7 @@ void dccp_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); @@ -225,7 +225,7 @@ 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 +241,7 @@ 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/ipv4/af_inet.c b/net/ipv4/af_inet.c index c5376c72550..5ca7290c2e6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -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; } 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/tcp.c b/net/ipv4/tcp.c index 0f8caf64caa..77208334a61 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); 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..9636b7d27b4 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) \ @@ -307,7 +307,7 @@ 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); + wake_up_interruptible_all(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); read_unlock(&sk->sk_callback_lock); } @@ -795,7 +795,7 @@ 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 +819,7 @@ 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 +1269,7 @@ 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/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/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/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/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..c432d76f415 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -65,7 +65,7 @@ static void rxrpc_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (rxrpc_writable(sk)) { if (sk_has_sleeper(sk)) - wake_up_interruptible(sk->sk_sleep); + wake_up_interruptible(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } read_unlock(&sk->sk_callback_lock); @@ -589,7 +589,7 @@ 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/sctp/socket.c b/net/sctp/socket.c index c1941276f6e..f34adcca8a8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5702,7 +5702,7 @@ 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 +5943,7 @@ 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 +5980,14 @@ 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; } @@ -6061,8 +6061,8 @@ 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. @@ -6296,7 +6296,7 @@ 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 +6322,7 @@ 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 +6332,7 @@ 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 +6340,7 @@ 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/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/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..87c0360eaa2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -316,7 +316,7 @@ static void unix_write_space(struct sock *sk) read_lock(&sk->sk_callback_lock); if (unix_writable(sk)) { if (sk_has_sleeper(sk)) - wake_up_interruptible_sync(sk->sk_sleep); + wake_up_interruptible_sync(sk_sleep(sk)); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } read_unlock(&sk->sk_callback_lock); @@ -1736,7 +1736,7 @@ 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 +1752,7 @@ 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; } @@ -1991,7 +1991,7 @@ 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 +2028,7 @@ 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/x25/af_x25.c b/net/x25/af_x25.c index cbddd0cb83f..6cffbc4da02 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -718,7 +718,7 @@ 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 +738,7 @@ 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 +838,7 @@ 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 +858,7 @@ 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; } -- cgit v1.2.3 From 43815482370c510c569fd18edb57afcb0fa8cab6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 29 Apr 2010 11:01:49 +0000 Subject: net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/macvtap.c | 13 +++++++++---- drivers/net/tun.c | 21 ++++++++++++--------- include/linux/net.h | 14 +++++++++----- include/net/af_unix.h | 20 +++++++++++--------- include/net/sock.h | 38 +++++++++++++++++++------------------- net/atm/common.c | 22 ++++++++++++++-------- net/core/sock.c | 50 +++++++++++++++++++++++++++++++------------------- net/core/stream.c | 10 +++++++--- net/dccp/output.c | 10 ++++++---- net/iucv/af_iucv.c | 11 +++++++---- net/phonet/pep.c | 8 ++++---- net/phonet/socket.c | 2 +- net/rxrpc/af_rxrpc.c | 10 ++++++---- net/sctp/socket.c | 2 +- net/socket.c | 47 ++++++++++++++++++++++++++++++++++++----------- net/unix/af_unix.c | 17 ++++++++--------- 16 files changed, 181 insertions(+), 114 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index d97e1fd234b..1c4110df343 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -37,6 +37,7 @@ struct macvtap_queue { struct sock sk; struct socket sock; + struct socket_wq wq; struct macvlan_dev *vlan; struct file *file; unsigned int flags; @@ -242,12 +243,15 @@ static struct rtnl_link_ops macvtap_link_ops __read_mostly = { static void macvtap_sock_write_space(struct sock *sk) { + wait_queue_head_t *wqueue; + if (!sock_writeable(sk) || !test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - wake_up_interruptible_poll(sk_sleep(sk), POLLOUT | POLLWRNORM | POLLWRBAND); + wqueue = sk_sleep(sk); + if (wqueue && waitqueue_active(wqueue)) + wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND); } static int macvtap_open(struct inode *inode, struct file *file) @@ -272,7 +276,8 @@ static int macvtap_open(struct inode *inode, struct file *file) if (!q) goto out; - init_waitqueue_head(&q->sock.wait); + q->sock.wq = &q->wq; + init_waitqueue_head(&q->wq.wait); q->sock.type = SOCK_RAW; q->sock.state = SS_CONNECTED; q->sock.file = file; @@ -308,7 +313,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait) goto out; mask = 0; - poll_wait(file, &q->sock.wait, wait); + poll_wait(file, &q->wq.wait, wait); if (!skb_queue_empty(&q->sk.sk_receive_queue)) mask |= POLLIN | POLLRDNORM; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 20a17938c62..e525a6cf558 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -109,7 +109,7 @@ struct tun_struct { struct tap_filter txflt; struct socket socket; - + struct socket_wq wq; #ifdef TUN_DEBUG int debug; #endif @@ -323,7 +323,7 @@ static void tun_net_uninit(struct net_device *dev) /* Inform the methods they need to stop using the dev. */ if (tfile) { - wake_up_all(&tun->socket.wait); + wake_up_all(&tun->wq.wait); if (atomic_dec_and_test(&tfile->count)) __tun_detach(tun); } @@ -398,7 +398,7 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) /* Notify and wake up reader process */ if (tun->flags & TUN_FASYNC) kill_fasync(&tun->fasync, SIGIO, POLL_IN); - wake_up_interruptible_poll(&tun->socket.wait, POLLIN | + wake_up_interruptible_poll(&tun->wq.wait, POLLIN | POLLRDNORM | POLLRDBAND); return NETDEV_TX_OK; @@ -498,7 +498,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table * wait) DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name); - poll_wait(file, &tun->socket.wait, wait); + poll_wait(file, &tun->wq.wait, wait); if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; @@ -773,7 +773,7 @@ static ssize_t tun_do_read(struct tun_struct *tun, DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name); - add_wait_queue(&tun->socket.wait, &wait); + add_wait_queue(&tun->wq.wait, &wait); while (len) { current->state = TASK_INTERRUPTIBLE; @@ -804,7 +804,7 @@ static ssize_t tun_do_read(struct tun_struct *tun, } current->state = TASK_RUNNING; - remove_wait_queue(&tun->socket.wait, &wait); + remove_wait_queue(&tun->wq.wait, &wait); return ret; } @@ -861,6 +861,7 @@ static struct rtnl_link_ops tun_link_ops __read_mostly = { static void tun_sock_write_space(struct sock *sk) { struct tun_struct *tun; + wait_queue_head_t *wqueue; if (!sock_writeable(sk)) return; @@ -868,8 +869,9 @@ static void tun_sock_write_space(struct sock *sk) if (!test_and_clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags)) return; - if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - wake_up_interruptible_sync_poll(sk_sleep(sk), POLLOUT | + wqueue = sk_sleep(sk); + if (wqueue && waitqueue_active(wqueue)) + wake_up_interruptible_sync_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND); tun = tun_sk(sk)->tun; @@ -1039,7 +1041,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) if (!sk) goto err_free_dev; - init_waitqueue_head(&tun->socket.wait); + tun->socket.wq = &tun->wq; + init_waitqueue_head(&tun->wq.wait); tun->socket.ops = &tun_socket_ops; sock_init_data(&tun->socket, sk); sk->sk_write_space = tun_sock_write_space; diff --git a/include/linux/net.h b/include/linux/net.h index 4157b5d42bd..2b4deeeb864 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -59,6 +59,7 @@ typedef enum { #include #include /* For O_CLOEXEC and O_NONBLOCK */ #include +#include struct poll_table_struct; struct pipe_inode_info; @@ -116,6 +117,12 @@ enum sock_shutdown_cmd { SHUT_RDWR = 2, }; +struct socket_wq { + wait_queue_head_t wait; + struct fasync_struct *fasync_list; + struct rcu_head rcu; +} ____cacheline_aligned_in_smp; + /** * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) @@ -135,11 +142,8 @@ struct socket { kmemcheck_bitfield_end(type); unsigned long flags; - /* - * Please keep fasync_list & wait fields in the same cache line - */ - struct fasync_struct *fasync_list; - wait_queue_head_t wait; + + struct socket_wq *wq; struct file *file; struct sock *sk; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 1614d78c60e..20725e213ae 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -30,7 +30,7 @@ struct unix_skb_parms { #endif }; -#define UNIXCB(skb) (*(struct unix_skb_parms*)&((skb)->cb)) +#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) #define UNIXCREDS(skb) (&UNIXCB((skb)).creds) #define UNIXSID(skb) (&UNIXCB((skb)).secid) @@ -45,21 +45,23 @@ struct unix_skb_parms { struct unix_sock { /* WARNING: sk has to be the first member */ struct sock sk; - struct unix_address *addr; - struct dentry *dentry; - struct vfsmount *mnt; + struct unix_address *addr; + struct dentry *dentry; + struct vfsmount *mnt; struct mutex readlock; - struct sock *peer; - struct sock *other; + struct sock *peer; + struct sock *other; struct list_head link; - atomic_long_t inflight; - spinlock_t lock; + atomic_long_t inflight; + spinlock_t lock; unsigned int gc_candidate : 1; unsigned int gc_maybe_cycle : 1; - wait_queue_head_t peer_wait; + struct socket_wq peer_wq; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) +#define peer_wait peer_wq.wait + #ifdef CONFIG_SYSCTL extern int unix_sysctl_register(struct net *net); extern void unix_sysctl_unregister(struct net *net); diff --git a/include/net/sock.h b/include/net/sock.h index e1777db5b9a..cc7f91ec972 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -159,7 +159,7 @@ struct sock_common { * @sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings * @sk_lock: synchronizer * @sk_rcvbuf: size of receive buffer in bytes - * @sk_sleep: sock wait queue + * @sk_wq: sock wait queue and async head * @sk_dst_cache: destination cache * @sk_dst_lock: destination cache lock * @sk_policy: flow policy @@ -257,7 +257,7 @@ struct sock { struct sk_buff *tail; int len; } sk_backlog; - wait_queue_head_t *sk_sleep; + struct socket_wq *sk_wq; struct dst_entry *sk_dst_cache; #ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2]; @@ -1219,7 +1219,7 @@ static inline void sk_set_socket(struct sock *sk, struct socket *sock) static inline wait_queue_head_t *sk_sleep(struct sock *sk) { - return sk->sk_sleep; + return &sk->sk_wq->wait; } /* Detach socket from process context. * Announce socket dead, detach it from wait queue and inode. @@ -1233,14 +1233,14 @@ static inline void sock_orphan(struct sock *sk) write_lock_bh(&sk->sk_callback_lock); sock_set_flag(sk, SOCK_DEAD); sk_set_socket(sk, NULL); - sk->sk_sleep = NULL; + sk->sk_wq = NULL; write_unlock_bh(&sk->sk_callback_lock); } static inline void sock_graft(struct sock *sk, struct socket *parent) { write_lock_bh(&sk->sk_callback_lock); - sk->sk_sleep = &parent->wait; + rcu_assign_pointer(sk->sk_wq, parent->wq); parent->sk = sk; sk_set_socket(sk, parent); security_sock_graft(sk, parent); @@ -1392,12 +1392,12 @@ static inline int sk_has_allocations(const struct sock *sk) } /** - * sk_has_sleeper - check if there are any waiting processes - * @sk: socket + * wq_has_sleeper - check if there are any waiting processes + * @sk: struct socket_wq * - * Returns true if socket has waiting processes + * Returns true if socket_wq has waiting processes * - * The purpose of the sk_has_sleeper and sock_poll_wait is to wrap the memory + * The purpose of the wq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. * * Consider following tcp code paths: @@ -1410,9 +1410,10 @@ static inline int sk_has_allocations(const struct sock *sk) * ... ... * tp->rcv_nxt check sock_def_readable * ... { - * schedule ... - * if (sk_sleep(sk) && waitqueue_active(sk_sleep(sk))) - * wake_up_interruptible(sk_sleep(sk)) + * schedule rcu_read_lock(); + * wq = rcu_dereference(sk->sk_wq); + * if (wq && waitqueue_active(&wq->wait)) + * wake_up_interruptible(&wq->wait) * ... * } * @@ -1421,19 +1422,18 @@ static inline int sk_has_allocations(const struct sock *sk) * could then endup calling schedule and sleep forever if there are no more * data on the socket. * - * The sk_has_sleeper is always called right after a call to read_lock, so we - * can use smp_mb__after_lock barrier. */ -static inline int sk_has_sleeper(struct sock *sk) +static inline bool wq_has_sleeper(struct socket_wq *wq) { + /* * We need to be sure we are in sync with the * add_wait_queue modifications to the wait queue. * * This memory barrier is paired in the sock_poll_wait. */ - smp_mb__after_lock(); - return sk_sleep(sk) && waitqueue_active(sk_sleep(sk)); + smp_mb(); + return wq && waitqueue_active(&wq->wait); } /** @@ -1442,7 +1442,7 @@ static inline int sk_has_sleeper(struct sock *sk) * @wait_address: socket wait queue * @p: poll_table * - * See the comments in the sk_has_sleeper function. + * See the comments in the wq_has_sleeper function. */ static inline void sock_poll_wait(struct file *filp, wait_queue_head_t *wait_address, poll_table *p) @@ -1453,7 +1453,7 @@ static inline void sock_poll_wait(struct file *filp, * We need to be sure we are in sync with the * socket flags modification. * - * This memory barrier is paired in the sk_has_sleeper. + * This memory barrier is paired in the wq_has_sleeper. */ smp_mb(); } diff --git a/net/atm/common.c b/net/atm/common.c index e3e10e6f862..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_sleep(sk)); - 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_sleep(sk)); + 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 = { diff --git a/net/core/sock.c b/net/core/sock.c index 51041759517..94c4affdda9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1211,7 +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); @@ -1800,41 +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_sleep(sk)); - 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_sleep(sk), 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_sleep(sk), 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_sleep(sk), 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 */ @@ -1842,7 +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) @@ -1896,10 +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 7b3c3f30b10..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_sleep(sk) && waitqueue_active(sk_sleep(sk))) - wake_up_interruptible_poll(sk_sleep(sk), 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(); } } diff --git a/net/dccp/output.c b/net/dccp/output.c index 2d3dcb39851..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_sleep(sk)); + 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(); } /** diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 9636b7d27b4..8be324fe08b 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -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_sleep(sk)); + 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 */ 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/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/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index c432d76f415..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_sleep(sk)); + 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(); } /* diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 13d8229f3a9..d54700af927 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -6065,7 +6065,7 @@ static void __sctp_write_space(struct sctp_association *asoc) * 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); diff --git a/net/socket.c b/net/socket.c index cb7c1f6c0d6..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); @@ -1080,9 +1096,9 @@ static int sock_fasync(int fd, struct file *filp, int on) lock_sock(sk); - fasync_helper(fd, filp, on, &sock->fasync_list); + fasync_helper(fd, filp, on, &sock->wq->fasync_list); - if (!sock->fasync_list) + if (!sock->wq->fasync_list) sock_reset_flag(sk, SOCK_FASYNC); else sock_set_flag(sk, SOCK_FASYNC); @@ -1091,12 +1107,20 @@ static int sock_fasync(int fd, struct file *filp, int on) 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)) @@ -1108,11 +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/unix/af_unix.c b/net/unix/af_unix.c index 87c0360eaa2..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_sleep(sk)); + 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*/ @@ -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); -- cgit v1.2.3 From 109f6e39fa07c48f580125f531f46cb7c245b528 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 13 Jun 2010 03:30:14 +0000 Subject: af_unix: Allow SO_PEERCRED to work across namespaces. Use struct pid and struct cred to store the peer credentials on struct sock. This gives enough information to convert the peer credential information to a value relative to whatever namespace the socket is in at the time. This removes nasty surprises when using SO_PEERCRED on socket connetions where the processes on either side are in different pid and user namespaces. Signed-off-by: Eric W. Biederman Acked-by: Daniel Lezcano Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/net/sock.h | 3 ++- net/core/sock.c | 18 ++++++++++++------ net/unix/af_unix.c | 37 ++++++++++++++++++++++++++++--------- 3 files changed, 42 insertions(+), 16 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/net/sock.h b/include/net/sock.h index f8acf38f092..4f26f2f83be 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -295,7 +295,8 @@ struct sock { unsigned short sk_ack_backlog; unsigned short sk_max_ack_backlog; __u32 sk_priority; - struct ucred sk_peercred; + struct pid *sk_peer_pid; + const struct cred *sk_peer_cred; long sk_rcvtimeo; long sk_sndtimeo; struct sk_filter *sk_filter; diff --git a/net/core/sock.c b/net/core/sock.c index db8335ad755..0229d5566a4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -915,11 +915,15 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PEERCRED: - if (len > sizeof(sk->sk_peercred)) - len = sizeof(sk->sk_peercred); - if (copy_to_user(optval, &sk->sk_peercred, len)) + { + struct ucred peercred; + if (len > sizeof(peercred)) + len = sizeof(peercred); + cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; + } case SO_PEERNAME: { @@ -1133,6 +1137,9 @@ static void __sk_free(struct sock *sk) printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", __func__, atomic_read(&sk->sk_omem_alloc)); + if (sk->sk_peer_cred) + put_cred(sk->sk_peer_cred); + put_pid(sk->sk_peer_pid); put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); } @@ -1968,9 +1975,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - sk->sk_peercred.pid = 0; - sk->sk_peercred.uid = -1; - sk->sk_peercred.gid = -1; + sk->sk_peer_pid = NULL; + sk->sk_peer_cred = NULL; sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index fef2cc5e9d2..e1f1349fae8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -450,11 +450,31 @@ static int unix_release_sock(struct sock *sk, int embrion) return 0; } +static void init_peercred(struct sock *sk) +{ + put_pid(sk->sk_peer_pid); + if (sk->sk_peer_cred) + put_cred(sk->sk_peer_cred); + sk->sk_peer_pid = get_pid(task_tgid(current)); + sk->sk_peer_cred = get_current_cred(); +} + +static void copy_peercred(struct sock *sk, struct sock *peersk) +{ + put_pid(sk->sk_peer_pid); + if (sk->sk_peer_cred) + put_cred(sk->sk_peer_cred); + sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); + sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); +} + static int unix_listen(struct socket *sock, int backlog) { int err; struct sock *sk = sock->sk; struct unix_sock *u = unix_sk(sk); + struct pid *old_pid = NULL; + const struct cred *old_cred = NULL; err = -EOPNOTSUPP; if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) @@ -470,12 +490,14 @@ static int unix_listen(struct socket *sock, int backlog) sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; /* set credentials so connect can copy them */ - sk->sk_peercred.pid = task_tgid_vnr(current); - current_euid_egid(&sk->sk_peercred.uid, &sk->sk_peercred.gid); + init_peercred(sk); err = 0; out_unlock: unix_state_unlock(sk); + put_pid(old_pid); + if (old_cred) + put_cred(old_cred); out: return err; } @@ -1140,8 +1162,7 @@ restart: unix_peer(newsk) = sk; newsk->sk_state = TCP_ESTABLISHED; newsk->sk_type = sk->sk_type; - newsk->sk_peercred.pid = task_tgid_vnr(current); - current_euid_egid(&newsk->sk_peercred.uid, &newsk->sk_peercred.gid); + init_peercred(newsk); newu = unix_sk(newsk); newsk->sk_wq = &newu->peer_wq; otheru = unix_sk(other); @@ -1157,7 +1178,7 @@ restart: } /* Set credentials */ - sk->sk_peercred = other->sk_peercred; + copy_peercred(sk, other); sock->state = SS_CONNECTED; sk->sk_state = TCP_ESTABLISHED; @@ -1199,10 +1220,8 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) sock_hold(skb); unix_peer(ska) = skb; unix_peer(skb) = ska; - ska->sk_peercred.pid = skb->sk_peercred.pid = task_tgid_vnr(current); - current_euid_egid(&skb->sk_peercred.uid, &skb->sk_peercred.gid); - ska->sk_peercred.uid = skb->sk_peercred.uid; - ska->sk_peercred.gid = skb->sk_peercred.gid; + init_peercred(ska); + init_peercred(skb); if (ska->sk_type != SOCK_DGRAM) { ska->sk_state = TCP_ESTABLISHED; -- cgit v1.2.3 From 7361c36c5224519b258219fe3d0e8abc865d8134 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 13 Jun 2010 03:34:33 +0000 Subject: af_unix: Allow credentials to work across user and pid namespaces. In unix_skb_parms store pointers to struct pid and struct cred instead of raw uid, gid, and pid values, then translate the credentials on reception into values that are meaningful in the receiving processes namespaces. Signed-off-by: Eric W. Biederman Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/net/af_unix.h | 4 ++-- net/unix/af_unix.c | 53 ++++++++++++++++++++++++++++++--------------------- 2 files changed, 33 insertions(+), 24 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 20725e213ae..90c9e2872f2 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -23,7 +23,8 @@ struct unix_address { }; struct unix_skb_parms { - struct ucred creds; /* Skb credentials */ + struct pid *pid; /* Skb credentials */ + const struct cred *cred; struct scm_fp_list *fp; /* Passed files */ #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ @@ -31,7 +32,6 @@ struct unix_skb_parms { }; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) -#define UNIXCREDS(skb) (&UNIXCB((skb)).creds) #define UNIXSID(skb) (&UNIXCB((skb)).secid) #define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e1f1349fae8..5fe9d6fe08b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1316,18 +1316,20 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) int i; scm->fp = UNIXCB(skb).fp; - skb->destructor = sock_wfree; UNIXCB(skb).fp = NULL; for (i = scm->fp->count-1; i >= 0; i--) unix_notinflight(scm->fp->fp[i]); } -static void unix_destruct_fds(struct sk_buff *skb) +static void unix_destruct_scm(struct sk_buff *skb) { struct scm_cookie scm; memset(&scm, 0, sizeof(scm)); - unix_detach_fds(&scm, skb); + scm.pid = UNIXCB(skb).pid; + scm.cred = UNIXCB(skb).cred; + if (UNIXCB(skb).fp) + unix_detach_fds(&scm, skb); /* Alas, it calls VFS */ /* So fscking what? fput() had been SMP-safe since the last Summer */ @@ -1350,10 +1352,22 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) for (i = scm->fp->count-1; i >= 0; i--) unix_inflight(scm->fp->fp[i]); - skb->destructor = unix_destruct_fds; return 0; } +static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) +{ + int err = 0; + UNIXCB(skb).pid = get_pid(scm->pid); + UNIXCB(skb).cred = get_cred(scm->cred); + UNIXCB(skb).fp = NULL; + if (scm->fp && send_fds) + err = unix_attach_fds(scm, skb); + + skb->destructor = unix_destruct_scm; + return err; +} + /* * Send AF_UNIX data. */ @@ -1410,12 +1424,9 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, if (skb == NULL) goto out; - memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); - if (siocb->scm->fp) { - err = unix_attach_fds(siocb->scm, skb); - if (err) - goto out_free; - } + err = unix_scm_to_skb(siocb->scm, skb, true); + if (err) + goto out_free; unix_get_secdata(siocb->scm, skb); skb_reset_transport_header(skb); @@ -1585,16 +1596,14 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, */ size = min_t(int, size, skb_tailroom(skb)); - memcpy(UNIXCREDS(skb), &siocb->scm->creds, sizeof(struct ucred)); + /* Only send the fds in the first buffer */ - if (siocb->scm->fp && !fds_sent) { - err = unix_attach_fds(siocb->scm, skb); - if (err) { - kfree_skb(skb); - goto out_err; - } - fds_sent = true; + err = unix_scm_to_skb(siocb->scm, skb, !fds_sent); + if (err) { + kfree_skb(skb); + goto out_err; } + fds_sent = true; err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); if (err) { @@ -1711,7 +1720,7 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, siocb->scm = &tmp_scm; memset(&tmp_scm, 0, sizeof(tmp_scm)); } - siocb->scm->creds = *UNIXCREDS(skb); + scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); unix_set_secdata(siocb->scm, skb); if (!(flags & MSG_PEEK)) { @@ -1860,14 +1869,14 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (check_creds) { /* Never glue messages from different writers */ - if (memcmp(UNIXCREDS(skb), &siocb->scm->creds, - sizeof(siocb->scm->creds)) != 0) { + if ((UNIXCB(skb).pid != siocb->scm->pid) || + (UNIXCB(skb).cred != siocb->scm->cred)) { skb_queue_head(&sk->sk_receive_queue, skb); break; } } else { /* Copy credentials */ - siocb->scm->creds = *UNIXCREDS(skb); + scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); check_creds = 1; } -- cgit v1.2.3 From 6616f7888c6088324727363276f6de05a1dca6fc Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 13 Jun 2010 03:35:48 +0000 Subject: af_unix: Allow connecting to sockets in other network namespaces. Remove the restriction that only allows connecting to a unix domain socket identified by unix path that is in the same network namespace. Crossing network namespaces is always tricky and we did not support this at first, because of a strict policy of don't mix the namespaces. Later after Pavel proposed this we did not support this because no one had performed the audit to make certain using unix domain sockets across namespaces is safe. What fundamentally makes connecting to af_unix sockets in other namespaces is safe is that you have to have the proper permissions on the unix domain socket inode that lives in the filesystem. If you want strict isolation you just don't create inodes where unfriendlys can get at them, or with permissions that allow unfriendlys to open them. All nicely handled for us by the mount namespace and other standard file system facilities. I looked through unix domain sockets and they are a very controlled environment so none of the work that goes on in dev_forward_skb to make crossing namespaces safe appears needed, we are not loosing controll of the skb and so do not need to set up the skb to look like it is comming in fresh from the outside world. Further the fields in struct unix_skb_parms should not have any problems crossing network namespaces. Now that we handle SCM_CREDENTIALS in a way that gives useable values across namespaces. There does not appear to be any operational problems with encouraging the use of unix domain sockets across containers either. Signed-off-by: Eric W. Biederman Acked-by: Daniel Lezcano Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/af_unix.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5fe9d6fe08b..75ba48b0d12 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -282,7 +282,7 @@ static inline struct sock *unix_find_socket_byname(struct net *net, return s; } -static struct sock *unix_find_socket_byinode(struct net *net, struct inode *i) +static struct sock *unix_find_socket_byinode(struct inode *i) { struct sock *s; struct hlist_node *node; @@ -292,9 +292,6 @@ static struct sock *unix_find_socket_byinode(struct net *net, struct inode *i) &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) { struct dentry *dentry = unix_sk(s)->dentry; - if (!net_eq(sock_net(s), net)) - continue; - if (dentry && dentry->d_inode == i) { sock_hold(s); goto found; @@ -758,7 +755,7 @@ static struct sock *unix_find_other(struct net *net, err = -ECONNREFUSED; if (!S_ISSOCK(inode->i_mode)) goto put_fail; - u = unix_find_socket_byinode(net, inode); + u = unix_find_socket_byinode(inode); if (!u) goto put_fail; -- cgit v1.2.3 From 70d4bf6d467a330ccc947df9b2608e329d9e7708 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Tue, 20 Jul 2010 06:45:56 +0000 Subject: drop_monitor: convert some kfree_skb call sites to consume_skb Convert a few calls from kfree_skb to consume_skb Noticed while I was working on dropwatch that I was detecting lots of internal skb drops in several places. While some are legitimate, several were not, freeing skbs that were at the end of their life, rather than being discarded due to an error. This patch converts those calls sites from using kfree_skb to consume_skb, which quiets the in-kernel drop_monitor code from detecting them as drops. Tested successfully by myself Signed-off-by: Neil Horman Signed-off-by: David S. Miller --- kernel/audit.c | 2 +- net/netlink/af_netlink.c | 9 +++++---- net/unix/af_unix.c | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/kernel/audit.c b/kernel/audit.c index c71bd26631a..8296aa516c5 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -407,7 +407,7 @@ static void kauditd_send_skb(struct sk_buff *skb) audit_hold_skb(skb); } else /* drop the extra reference if sent ok */ - kfree_skb(skb); + consume_skb(skb); } static int kauditd_thread(void *dummy) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 7aeaa83193d..8648a9922aa 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1076,14 +1076,15 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 pid, sk_for_each_bound(sk, node, &nl_table[ssk->sk_protocol].mc_list) do_one_broadcast(sk, &info); - kfree_skb(skb); + consume_skb(skb); netlink_unlock_table(); - kfree_skb(info.skb2); - - if (info.delivery_failure) + if (info.delivery_failure) { + kfree_skb(info.skb2); return -ENOBUFS; + } else + consume_skb(info.skb2); if (info.delivered) { if (info.congested && (allocation & __GFP_WAIT)) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 75ba48b0d12..4414a18c63b 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1906,7 +1906,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, break; } - kfree_skb(skb); + consume_skb(skb); if (siocb->scm->fp) break; -- cgit v1.2.3 From db40980fcdb560d7992b0511df16cdd3f7e381f3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Sep 2010 11:13:50 +0000 Subject: net: poll() optimizations No need to test twice sk->sk_shutdown & RCV_SHUTDOWN Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/bluetooth/af_bluetooth.c | 5 ++--- net/core/datagram.c | 5 ++--- net/sctp/socket.c | 5 ++--- net/unix/af_unix.c | 5 ++--- 4 files changed, 8 insertions(+), 12 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 421c45bd1b9..ed0f22f5766 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -297,13 +297,12 @@ unsigned int bt_sock_poll(struct file * file, struct socket *sock, poll_table *w mask |= POLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; if (sk->sk_state == BT_CLOSED) diff --git a/net/core/datagram.c b/net/core/datagram.c index 251997a9548..4df1b7a6c1b 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -746,13 +746,12 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* Connection-based need to check for termination and startup */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f4bec277235..cf6dcc908b8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5707,13 +5707,12 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; /* Is it readable? Reconsider this code with TCP-style support. */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* The association is either gone or not ready. */ diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4414a18c63b..9077b4ea00c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2024,11 +2024,10 @@ static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* Connection-based need to check for termination and startup */ -- cgit v1.2.3 From 8df73ff90f00f14d2c7ff7156f7ef153f7e9d3b7 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sat, 4 Sep 2010 01:34:28 +0000 Subject: UNIX: Do not loop forever at unix_autobind(). We assumed that unix_autobind() never fails if kzalloc() succeeded. But unix_autobind() allows only 1048576 names. If /proc/sys/fs/file-max is larger than 1048576 (e.g. systems with more than 10GB of RAM), a local user can consume all names using fork()/socket()/bind(). If all names are in use, those who call bind() with addr_len == sizeof(short) or connect()/sendmsg() with setsockopt(SO_PASSCRED) will continue while (1) yield(); loop at unix_autobind() till a name becomes available. This patch adds a loop counter in order to give up after 1048576 attempts. Calling yield() for once per 256 attempts may not be sufficient when many names are already in use, for __unix_find_socket_byname() can take long time under such circumstance. Therefore, this patch also adds cond_resched() call. Note that currently a local user can consume 2GB of kernel memory if the user is allowed to create and autobind 1048576 UNIX domain sockets. We should consider adding some restriction for autobind operation. Signed-off-by: Tetsuo Handa Signed-off-by: David S. Miller --- net/unix/af_unix.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4414a18c63b..0b39b2451ea 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -692,6 +692,7 @@ static int unix_autobind(struct socket *sock) static u32 ordernum = 1; struct unix_address *addr; int err; + unsigned int retries = 0; mutex_lock(&u->readlock); @@ -717,9 +718,17 @@ retry: if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type, addr->hash)) { spin_unlock(&unix_table_lock); - /* Sanity yield. It is unusual case, but yet... */ - if (!(ordernum&0xFF)) - yield(); + /* + * __unix_find_socket_byname() may take long time if many names + * are already in use. + */ + cond_resched(); + /* Give up if all names seems to be in use. */ + if (retries++ == 0xFFFFF) { + err = -ENOSPC; + kfree(addr); + goto out; + } goto retry; } addr->hash ^= sk->sk_type; -- cgit v1.2.3 From 3f66116e89521ef71ab0d63dc07a639def88a577 Mon Sep 17 00:00:00 2001 From: Alban Crequy Date: Mon, 4 Oct 2010 08:48:28 +0000 Subject: AF_UNIX: Implement SO_TIMESTAMP and SO_TIMETAMPNS on Unix sockets Userspace applications can already request to receive timestamps with: setsockopt(sockfd, SOL_SOCKET, SO_TIMESTAMP, ...) Although setsockopt() returns zero (success), timestamps are not added to the ancillary data. This patch fixes that on SOCK_DGRAM and SOCK_SEQPACKET Unix sockets. Signed-off-by: Alban Crequy Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/af_unix.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c586da3f4f1..0ebc777a666 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1511,6 +1511,8 @@ restart: goto restart; } + if (sock_flag(other, SOCK_RCVTSTAMP)) + __net_timestamp(skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); other->sk_data_ready(other, len); @@ -1722,6 +1724,9 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, if (err) goto out_free; + if (sock_flag(sk, SOCK_RCVTSTAMP)) + __sock_recv_timestamp(msg, sk, skb); + if (!siocb->scm) { siocb->scm = &tmp_scm; memset(&tmp_scm, 0, sizeof(tmp_scm)); -- cgit v1.2.3 From 518de9b39e854542de59bfb8b9f61c8f7ecf808b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Oct 2010 14:22:44 -0700 Subject: fs: allow for more than 2^31 files Robin Holt tried to boot a 16TB system and found af_unix was overflowing a 32bit value : We were seeing a failure which prevented boot. The kernel was incapable of creating either a named pipe or unix domain socket. This comes down to a common kernel function called unix_create1() which does: atomic_inc(&unix_nr_socks); if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) goto out; The function get_max_files() is a simple return of files_stat.max_files. files_stat.max_files is a signed integer and is computed in fs/file_table.c's files_init(). n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = n; In our case, mempages (total_ram_pages) is approx 3,758,096,384 (0xe0000000). That leaves max_files at approximately 1,503,238,553. This causes 2 * get_max_files() to integer overflow. Fix is to let /proc/sys/fs/file-nr & /proc/sys/fs/file-max use long integers, and change af_unix to use an atomic_long_t instead of atomic_t. get_max_files() is changed to return an unsigned long. get_nr_files() is changed to return a long. unix_nr_socks is changed from atomic_t to atomic_long_t, while not strictly needed to address Robin problem. Before patch (on a 64bit kernel) : # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max -18446744071562067968 After patch: # echo 2147483648 >/proc/sys/fs/file-max # cat /proc/sys/fs/file-max 2147483648 # cat /proc/sys/fs/file-nr 704 0 2147483648 Reported-by: Robin Holt Signed-off-by: Eric Dumazet Acked-by: David Miller Reviewed-by: Robin Holt Tested-by: Robin Holt Cc: Al Viro Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/file_table.c | 17 +++++++---------- include/linux/fs.h | 8 ++++---- kernel/sysctl.c | 6 +++--- net/unix/af_unix.c | 14 +++++++------- 4 files changed, 21 insertions(+), 24 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/fs/file_table.c b/fs/file_table.c index a04bdd81c11..c3dee381f1b 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -60,7 +60,7 @@ static inline void file_free(struct file *f) /* * Return the total number of open files in the system */ -static int get_nr_files(void) +static long get_nr_files(void) { return percpu_counter_read_positive(&nr_files); } @@ -68,7 +68,7 @@ static int get_nr_files(void) /* * Return the maximum number of open files in the system */ -int get_max_files(void) +unsigned long get_max_files(void) { return files_stat.max_files; } @@ -82,7 +82,7 @@ int proc_nr_files(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); - return proc_dointvec(table, write, buffer, lenp, ppos); + return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #else int proc_nr_files(ctl_table *table, int write, @@ -105,7 +105,7 @@ int proc_nr_files(ctl_table *table, int write, struct file *get_empty_filp(void) { const struct cred *cred = current_cred(); - static int old_max; + static long old_max; struct file * f; /* @@ -140,8 +140,7 @@ struct file *get_empty_filp(void) over: /* Ran out of filps - report that */ if (get_nr_files() > old_max) { - printk(KERN_INFO "VFS: file-max limit %d reached\n", - get_max_files()); + pr_info("VFS: file-max limit %lu reached\n", get_max_files()); old_max = get_nr_files(); } goto fail; @@ -487,7 +486,7 @@ retry: void __init files_init(unsigned long mempages) { - int n; + unsigned long n; filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); @@ -498,9 +497,7 @@ void __init files_init(unsigned long mempages) */ n = (mempages * (PAGE_SIZE / 1024)) / 10; - files_stat.max_files = n; - if (files_stat.max_files < NR_FILE) - files_stat.max_files = NR_FILE; + files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); lg_lock_init(files_lglock); percpu_counter_init(&nr_files, 0); diff --git a/include/linux/fs.h b/include/linux/fs.h index 4f34ff6e555..b2cdb6bc828 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -34,9 +34,9 @@ /* And dynamically-tunable limits and defaults: */ struct files_stat_struct { - int nr_files; /* read only */ - int nr_free_files; /* read only */ - int max_files; /* tunable */ + unsigned long nr_files; /* read only */ + unsigned long nr_free_files; /* read only */ + unsigned long max_files; /* tunable */ }; struct inodes_stat_t { @@ -400,7 +400,7 @@ extern void __init inode_init_early(void); extern void __init files_init(unsigned long); extern struct files_stat_struct files_stat; -extern int get_max_files(void); +extern unsigned long get_max_files(void); extern int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3a45c224770..694b140852c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1352,16 +1352,16 @@ static struct ctl_table fs_table[] = { { .procname = "file-nr", .data = &files_stat, - .maxlen = 3*sizeof(int), + .maxlen = sizeof(files_stat), .mode = 0444, .proc_handler = proc_nr_files, }, { .procname = "file-max", .data = &files_stat.max_files, - .maxlen = sizeof(int), + .maxlen = sizeof(files_stat.max_files), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax, }, { .procname = "nr_open", diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 0ebc777a666..3c95304a081 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -117,7 +117,7 @@ static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; static DEFINE_SPINLOCK(unix_table_lock); -static atomic_t unix_nr_socks = ATOMIC_INIT(0); +static atomic_long_t unix_nr_socks; #define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE]) @@ -360,13 +360,13 @@ static void unix_sock_destructor(struct sock *sk) if (u->addr) unix_release_addr(u->addr); - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); #ifdef UNIX_REFCNT_DEBUG - printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk, - atomic_read(&unix_nr_socks)); + printk(KERN_DEBUG "UNIX %p is destroyed, %ld are still alive.\n", sk, + atomic_long_read(&unix_nr_socks)); #endif } @@ -606,8 +606,8 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) struct sock *sk = NULL; struct unix_sock *u; - atomic_inc(&unix_nr_socks); - if (atomic_read(&unix_nr_socks) > 2 * get_max_files()) + atomic_long_inc(&unix_nr_socks); + if (atomic_long_read(&unix_nr_socks) > 2 * get_max_files()) goto out; sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto); @@ -632,7 +632,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock) unix_insert_socket(unix_sockets_unbound, sk); out: if (sk == NULL) - atomic_dec(&unix_nr_socks); + atomic_long_dec(&unix_nr_socks); else { local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); -- cgit v1.2.3 From 67426b756c4d52c511c4b22b269accea171692a8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 29 Oct 2010 20:44:44 +0000 Subject: af_unix: use keyed wakeups Instead of wakeup all sleepers, use wake_up_interruptible_sync_poll() to wakeup only ones interested into writing the socket. This patch is a specialization of commit 37e5540b3c9d (epoll keyed wakeups: make sockets use keyed wakeups). On a test program provided by Alan Crequy : Before: real 0m3.101s user 0m0.000s sys 0m6.104s After: real 0m0.211s user 0m0.000s sys 0m0.208s Reported-by: Alban Crequy Signed-off-by: Eric Dumazet Cc: Davide Libenzi Signed-off-by: David S. Miller --- net/unix/af_unix.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3c95304a081..f33c5958dbb 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -316,7 +316,8 @@ static void unix_write_space(struct sock *sk) if (unix_writable(sk)) { wq = rcu_dereference(sk->sk_wq); if (wq_has_sleeper(wq)) - wake_up_interruptible_sync(&wq->wait); + wake_up_interruptible_sync_poll(&wq->wait, + POLLOUT | POLLWRNORM | POLLWRBAND); sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); } rcu_read_unlock(); @@ -1710,7 +1711,8 @@ static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock, goto out_unlock; } - wake_up_interruptible_sync(&u->peer_wait); + wake_up_interruptible_sync_poll(&u->peer_wait, + POLLOUT | POLLWRNORM | POLLWRBAND); if (msg->msg_name) unix_copy_addr(msg, skb->sk); -- cgit v1.2.3 From 5456f09aaf88731e16dbcea7522cb330b6846415 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 31 Oct 2010 05:36:23 +0000 Subject: af_unix: fix unix_dgram_poll() behavior for EPOLLOUT event Alban Crequy reported a problem with connected dgram af_unix sockets and provided a test program. epoll() would miss to send an EPOLLOUT event when a thread unqueues a packet from the other peer, making its receive queue not full. This is because unix_dgram_poll() fails to call sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); if the socket is not writeable at the time epoll_ctl(ADD) is called. We must call sock_poll_wait(), regardless of 'writable' status, so that epoll can be notified later of states changes. Misc: avoids testing twice (sk->sk_shutdown & RCV_SHUTDOWN) Reported-by: Alban Crequy Cc: Davide Libenzi Signed-off-by: Eric Dumazet Acked-by: Davide Libenzi Signed-off-by: David S. Miller --- net/unix/af_unix.c | 24 +++++++++--------------- 1 file changed, 9 insertions(+), 15 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f33c5958dbb..e8898758dd3 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2074,13 +2074,12 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -2092,20 +2091,15 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, return mask; } - /* writable? */ writable = unix_writable(sk); - if (writable) { - other = unix_peer_get(sk); - if (other) { - if (unix_peer(other) != sk) { - sock_poll_wait(file, &unix_sk(other)->peer_wait, - wait); - if (unix_recvq_full(other)) - writable = 0; - } - - sock_put(other); + other = unix_peer_get(sk); + if (other) { + if (unix_peer(other) != sk) { + sock_poll_wait(file, &unix_sk(other)->peer_wait, wait); + if (unix_recvq_full(other)) + writable = 0; } + sock_put(other); } if (writable) -- cgit v1.2.3 From 973a34aa8593dbfe84386343c694f5beecb51d8a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 31 Oct 2010 05:38:25 +0000 Subject: af_unix: optimize unix_dgram_poll() unix_dgram_poll() is pretty expensive to check POLLOUT status, because it has to lock the socket to get its peer, take a reference on the peer to check its receive queue status, and queue another poll_wait on peer_wait. This all can be avoided if the process calling unix_dgram_poll() is not interested in POLLOUT status. It makes unix_dgram_recvmsg() faster by not queueing irrelevant pollers in peer_wait. On a test program provided by Alan Crequy : Before: real 0m0.211s user 0m0.000s sys 0m0.208s After: real 0m0.044s user 0m0.000s sys 0m0.040s Suggested-by: Davide Libenzi Reported-by: Alban Crequy Acked-by: Davide Libenzi Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/af_unix.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e8898758dd3..7ff31c60186 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2091,6 +2091,10 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, return mask; } + /* No write status requested, avoid expensive OUT tests. */ + if (wait && !(wait->key & (POLLWRBAND | POLLWRNORM | POLLOUT))) + return mask; + writable = unix_writable(sk); other = unix_peer_get(sk); if (other) { -- cgit v1.2.3 From 25888e30319f8896fc656fc68643e6a078263060 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 25 Nov 2010 04:11:39 +0000 Subject: af_unix: limit recursion level MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Its easy to eat all kernel memory and trigger NMI watchdog, using an exploit program that queues unix sockets on top of others. lkml ref : http://lkml.org/lkml/2010/11/25/8 This mechanism is used in applications, one choice we have is to have a recursion limit. Other limits might be needed as well (if we queue other types of files), since the passfd mechanism is currently limited by socket receive queue sizes only. Add a recursion_level to unix socket, allowing up to 4 levels. Each time we send an unix socket through sendfd mechanism, we copy its recursion level (plus one) to receiver. This recursion level is cleared when socket receive queue is emptied. Reported-by: Марк Коренберг Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/af_unix.h | 2 ++ net/unix/af_unix.c | 37 ++++++++++++++++++++++++++++++++----- net/unix/garbage.c | 2 +- 3 files changed, 35 insertions(+), 6 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 90c9e2872f2..18e5c3f6758 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -10,6 +10,7 @@ extern void unix_inflight(struct file *fp); extern void unix_notinflight(struct file *fp); extern void unix_gc(void); extern void wait_for_unix_gc(void); +extern struct sock *unix_get_socket(struct file *filp); #define UNIX_HASH_SIZE 256 @@ -56,6 +57,7 @@ struct unix_sock { spinlock_t lock; unsigned int gc_candidate : 1; unsigned int gc_maybe_cycle : 1; + unsigned char recursion_level; struct socket_wq peer_wq; }; #define unix_sk(__sk) ((struct unix_sock *)__sk) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3c95304a081..2268e679812 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1343,9 +1343,25 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +#define MAX_RECURSION_LEVEL 4 + static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) { int i; + unsigned char max_level = 0; + int unix_sock_count = 0; + + for (i = scm->fp->count - 1; i >= 0; i--) { + struct sock *sk = unix_get_socket(scm->fp->fp[i]); + + if (sk) { + unix_sock_count++; + max_level = max(max_level, + unix_sk(sk)->recursion_level); + } + } + if (unlikely(max_level > MAX_RECURSION_LEVEL)) + return -ETOOMANYREFS; /* * Need to duplicate file references for the sake of garbage @@ -1356,9 +1372,11 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - for (i = scm->fp->count-1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - return 0; + if (unix_sock_count) { + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->fp[i]); + } + return max_level; } static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds) @@ -1393,6 +1411,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sk_buff *skb; long timeo; struct scm_cookie tmp_scm; + int max_level; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1431,8 +1450,9 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, goto out; err = unix_scm_to_skb(siocb->scm, skb, true); - if (err) + if (err < 0) goto out_free; + max_level = err + 1; unix_get_secdata(siocb->scm, skb); skb_reset_transport_header(skb); @@ -1514,6 +1534,8 @@ restart: if (sock_flag(other, SOCK_RCVTSTAMP)) __net_timestamp(skb); skb_queue_tail(&other->sk_receive_queue, skb); + if (max_level > unix_sk(other)->recursion_level) + unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); other->sk_data_ready(other, len); sock_put(other); @@ -1544,6 +1566,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, int sent = 0; struct scm_cookie tmp_scm; bool fds_sent = false; + int max_level; if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1607,10 +1630,11 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, /* Only send the fds in the first buffer */ err = unix_scm_to_skb(siocb->scm, skb, !fds_sent); - if (err) { + if (err < 0) { kfree_skb(skb); goto out_err; } + max_level = err + 1; fds_sent = true; err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size); @@ -1626,6 +1650,8 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, goto pipe_err_free; skb_queue_tail(&other->sk_receive_queue, skb); + if (max_level > unix_sk(other)->recursion_level) + unix_sk(other)->recursion_level = max_level; unix_state_unlock(other); other->sk_data_ready(other, size); sent += size; @@ -1845,6 +1871,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, unix_state_lock(sk); skb = skb_dequeue(&sk->sk_receive_queue); if (skb == NULL) { + unix_sk(sk)->recursion_level = 0; if (copied >= target) goto unlock; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 40df93d1cf3..f89f83bf828 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -96,7 +96,7 @@ static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait); unsigned int unix_tot_inflight; -static struct sock *unix_get_socket(struct file *filp) +struct sock *unix_get_socket(struct file *filp) { struct sock *u_sock = NULL; struct inode *inode = filp->f_path.dentry->d_inode; -- cgit v1.2.3 From 3610cda53f247e176bcbb7a7cca64bc53b12acdb Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 5 Jan 2011 15:38:53 -0800 Subject: af_unix: Avoid socket->sk NULL OOPS in stream connect security hooks. unix_release() can asynchornously set socket->sk to NULL, and it does so without holding the unix_state_lock() on "other" during stream connects. However, the reverse mapping, sk->sk_socket, is only transitioned to NULL under the unix_state_lock(). Therefore make the security hooks follow the reverse mapping instead of the forward mapping. Reported-by: Jeremy Fitzhardinge Reported-by: Linus Torvalds Signed-off-by: David S. Miller --- include/linux/security.h | 15 +++++++-------- net/unix/af_unix.c | 2 +- security/capability.c | 2 +- security/security.c | 3 +-- security/selinux/hooks.c | 10 +++++----- security/smack/smack_lsm.c | 14 +++++++------- 6 files changed, 22 insertions(+), 24 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/include/linux/security.h b/include/linux/security.h index fd4d55fb884..d47a4c24b3e 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -796,8 +796,9 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @unix_stream_connect: * Check permissions before establishing a Unix domain stream connection * between @sock and @other. - * @sock contains the socket structure. - * @other contains the peer socket structure. + * @sock contains the sock structure. + * @other contains the peer sock structure. + * @newsk contains the new sock structure. * Return 0 if permission is granted. * @unix_may_send: * Check permissions before connecting or sending datagrams from @sock to @@ -1568,8 +1569,7 @@ struct security_operations { int (*inode_getsecctx)(struct inode *inode, void **ctx, u32 *ctxlen); #ifdef CONFIG_SECURITY_NETWORK - int (*unix_stream_connect) (struct socket *sock, - struct socket *other, struct sock *newsk); + int (*unix_stream_connect) (struct sock *sock, struct sock *other, struct sock *newsk); int (*unix_may_send) (struct socket *sock, struct socket *other); int (*socket_create) (int family, int type, int protocol, int kern); @@ -2525,8 +2525,7 @@ static inline int security_inode_getsecctx(struct inode *inode, void **ctx, u32 #ifdef CONFIG_SECURITY_NETWORK -int security_unix_stream_connect(struct socket *sock, struct socket *other, - struct sock *newsk); +int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk); int security_unix_may_send(struct socket *sock, struct socket *other); int security_socket_create(int family, int type, int protocol, int kern); int security_socket_post_create(struct socket *sock, int family, @@ -2567,8 +2566,8 @@ void security_tun_dev_post_create(struct sock *sk); int security_tun_dev_attach(struct sock *sk); #else /* CONFIG_SECURITY_NETWORK */ -static inline int security_unix_stream_connect(struct socket *sock, - struct socket *other, +static inline int security_unix_stream_connect(struct sock *sock, + struct sock *other, struct sock *newsk) { return 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 417d7a6c36c..dd419d28620 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1157,7 +1157,7 @@ restart: goto restart; } - err = security_unix_stream_connect(sock, other->sk_socket, newsk); + err = security_unix_stream_connect(sk, other, newsk); if (err) { unix_state_unlock(sk); goto out_unlock; diff --git a/security/capability.c b/security/capability.c index c773635ca3a..2a5df2b7da8 100644 --- a/security/capability.c +++ b/security/capability.c @@ -548,7 +548,7 @@ static int cap_sem_semop(struct sem_array *sma, struct sembuf *sops, } #ifdef CONFIG_SECURITY_NETWORK -static int cap_unix_stream_connect(struct socket *sock, struct socket *other, +static int cap_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return 0; diff --git a/security/security.c b/security/security.c index 1b798d3df71..e5fb07a3052 100644 --- a/security/security.c +++ b/security/security.c @@ -977,8 +977,7 @@ EXPORT_SYMBOL(security_inode_getsecctx); #ifdef CONFIG_SECURITY_NETWORK -int security_unix_stream_connect(struct socket *sock, struct socket *other, - struct sock *newsk) +int security_unix_stream_connect(struct sock *sock, struct sock *other, struct sock *newsk) { return security_ops->unix_stream_connect(sock, other, newsk); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index c82538a4b1a..6f637d2678a 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3921,18 +3921,18 @@ static int selinux_socket_shutdown(struct socket *sock, int how) return sock_has_perm(current, sock->sk, SOCKET__SHUTDOWN); } -static int selinux_socket_unix_stream_connect(struct socket *sock, - struct socket *other, +static int selinux_socket_unix_stream_connect(struct sock *sock, + struct sock *other, struct sock *newsk) { - struct sk_security_struct *sksec_sock = sock->sk->sk_security; - struct sk_security_struct *sksec_other = other->sk->sk_security; + struct sk_security_struct *sksec_sock = sock->sk_security; + struct sk_security_struct *sksec_other = other->sk_security; struct sk_security_struct *sksec_new = newsk->sk_security; struct common_audit_data ad; int err; COMMON_AUDIT_DATA_INIT(&ad, NET); - ad.u.net.sk = other->sk; + ad.u.net.sk = other; err = avc_has_perm(sksec_sock->sid, sksec_other->sid, sksec_other->sclass, diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 489a85afa47..ccb71a044a1 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -2408,22 +2408,22 @@ static int smack_setprocattr(struct task_struct *p, char *name, /** * smack_unix_stream_connect - Smack access on UDS - * @sock: one socket - * @other: the other socket + * @sock: one sock + * @other: the other sock * @newsk: unused * * Return 0 if a subject with the smack of sock could access * an object with the smack of other, otherwise an error code */ -static int smack_unix_stream_connect(struct socket *sock, - struct socket *other, struct sock *newsk) +static int smack_unix_stream_connect(struct sock *sock, + struct sock *other, struct sock *newsk) { - struct inode *sp = SOCK_INODE(sock); - struct inode *op = SOCK_INODE(other); + struct inode *sp = SOCK_INODE(sock->sk_socket); + struct inode *op = SOCK_INODE(other->sk_socket); struct smk_audit_info ad; smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_NET); - smk_ad_setfield_u_net_sk(&ad, other->sk); + smk_ad_setfield_u_net_sk(&ad, other); return smk_access(smk_of_inode(sp), smk_of_inode(op), MAY_READWRITE, &ad); } -- cgit v1.2.3