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 --- net/unix/af_unix.c | 10 +++++----- 1 file changed, 5 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 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? */ -- cgit v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 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 v1.2.3-70-g09d2 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 v1.2.3-70-g09d2