net: rename SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA
Subsystems (15)
PATCH 1/2 net: rename SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA
This patch is a cleanup to make following patch easier to review.
Goal is to move SOCK_ASYNC_NOSPACE and SOCK_ASYNC_WAITDATA from (struct socket)->flags to a (struct socket_wq)->flags to benefit from RCU protection in sock_wake_async()
To ease backports, we rename both constants.
Two new helpers, sk_set_bit(int nr, struct sock *sk) and sk_clear_bit(int net, struct sock *sk) are added so that following patch can change their implementation.
--- crypto/algif_aead.c | 4 ++-- crypto/algif_skcipher.c | 6 +++--- drivers/net/macvtap.c | 4 ++-- drivers/net/tun.c | 4 ++-- fs/dlm/lowcomms.c | 4 ++-- include/linux/net.h | 6 +++--- include/net/sock.h | 10 ++++++++++ net/bluetooth/af_bluetooth.c | 6 +++--- net/caif/caif_socket.c | 4 ++-- net/core/datagram.c | 2 +- net/core/sock.c | 8 ++++---- net/core/stream.c | 4 ++-- net/dccp/proto.c | 3 +-- net/decnet/af_decnet.c | 8 ++++---- net/ipv4/tcp.c | 7 +++---- net/iucv/af_iucv.c | 2 +- net/nfc/llcp_sock.c | 2 +- net/rxrpc/ar-output.c | 2 +- net/sctp/socket.c | 2 +- net/socket.c | 4 ++-- net/sunrpc/xprtsock.c | 14 +++++++------- net/unix/af_unix.c | 6 +++--- 22 files changed, 60 insertions(+), 52 deletions(-)
crypto/algif_aead.c +2 -2
@@ -125,7 +125,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags)if (flags &MSG_DONTWAIT )return -EAGAIN ; -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk);for (;;) {if (signal_pending (current))
@@ -139,7 +139,7 @@ static int aead_wait_for_data(struct sock *sk, unsigned flags) }finish_wait (sk_sleep (sk), &wait); -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk);return err; }
crypto/algif_skcipher.c +3 -3
@@ -212,7 +212,7 @@ static int skcipher_wait_for_wmem(struct sock *sk, unsigned flags)if (flags &MSG_DONTWAIT )return -EAGAIN ; -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);for (;;) {if (signal_pending (current))
@@ -258,7 +258,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags)return -EAGAIN ; } -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk);for (;;) {if (signal_pending (current))
@@ -272,7 +272,7 @@ static int skcipher_wait_for_data(struct sock *sk, unsigned flags) }finish_wait (sk_sleep (sk), &wait); -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk);return err; }
drivers/net/macvtap.c +2 -2
@@ -498,7 +498,7 @@ 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)) + !test_and_clear_bit (SOCKWQ_ASYNC_NOSPACE , &sk->sk_socket->flags))return ; wqueue =sk_sleep (sk);
@@ -585,7 +585,7 @@ static unsigned int macvtap_poll(struct file *file, poll_table * wait) mask |=POLLIN |POLLRDNORM ;if (sock_writeable (&q->sk) || - (!test_and_set_bit (SOCK_ASYNC_NOSPACE , &q->sock.flags) && + (!test_and_set_bit (SOCKWQ_ASYNC_NOSPACE , &q->sock.flags) &&sock_writeable (&q->sk))) mask |=POLLOUT |POLLWRNORM ;
drivers/net/tun.c +2 -2
@@ -1040,7 +1040,7 @@ static unsigned int tun_chr_poll(struct file *file, poll_table *wait) mask |=POLLIN |POLLRDNORM ;if (sock_writeable (sk) || - (!test_and_set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags) && + (!test_and_set_bit (SOCKWQ_ASYNC_NOSPACE , &sk->sk_socket->flags) &&sock_writeable (sk))) mask |=POLLOUT |POLLWRNORM ;
@@ -1488,7 +1488,7 @@ static void tun_sock_write_space(struct sock *sk)if (!sock_writeable (sk))return ; -if (!test_and_clear_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags)) +if (!test_and_clear_bit (SOCKWQ_ASYNC_NOSPACE , &sk->sk_socket->flags))return ; wqueue =sk_sleep (sk);
fs/dlm/lowcomms.c +2 -2
@@ -421,7 +421,7 @@ static void lowcomms_write_space(struct sock *sk)if (test_and_clear_bit (CF_APP_LIMITED , &con->flags)) { con->sock->sk->sk_write_pending--; -clear_bit (SOCK_ASYNC_NOSPACE , &con->sock->flags); +clear_bit (SOCKWQ_ASYNC_NOSPACE , &con->sock->flags); }if (!test_and_set_bit (CF_WRITE_PENDING , &con->flags))
@@ -1448,7 +1448,7 @@ static void send_to_sock(struct connection *con) msg_flags);if (ret == -EAGAIN || ret ==0 ) {if (ret == -EAGAIN && -test_bit (SOCK_ASYNC_NOSPACE , &con->sock->flags) && +test_bit (SOCKWQ_ASYNC_NOSPACE , &con->sock->flags) && !test_and_set_bit (CF_APP_LIMITED , &con->flags)) {/* Notify TCP that we're limited by the * application window size.
include/linux/net.h +3 -3
@@ -34,8 +34,8 @@ struct inode;struct file ;struct net ; -#define SOCK_ASYNC_NOSPACE 0 -#define SOCK_ASYNC_WAITDATA 1 +#define SOCKWQ_ASYNC_NOSPACE 0 +#define SOCKWQ_ASYNC_WAITDATA 1#define SOCK_NOSPACE 2#define SOCK_PASSCRED 3#define SOCK_PASSSEC 4
@@ -96,7 +96,7 @@ struct socket_wq {* struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) * @type: socket type (%SOCK_STREAM, etc) -* @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc) +* @flags: socket flags (%SOCK_NOSPACE, etc) * @ops: protocol specific socket operations * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation
include/net/sock.h +10 -0
@@ -2005,6 +2005,16 @@ static inline unsigned long sock_wspace(struct sock *sk)return amt; } +static inline void sk_set_bit (int nr,struct sock *sk) +{ +set_bit (nr, &sk->sk_socket->flags); +} + +static inline void sk_clear_bit (int nr,struct sock *sk) +{ +clear_bit (nr, &sk->sk_socket->flags); +} +static inline void sk_wake_async (struct sock *sk,int how,int band) {if (sock_flag (sk,SOCK_FASYNC ))
net/bluetooth/af_bluetooth.c +3 -3
@@ -271,11 +271,11 @@ static long bt_sock_data_wait(struct sock *sk, long timeo)if (signal_pending (current) || !timeo)break ; -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk);release_sock (sk); timeo =schedule_timeout (timeo);lock_sock (sk); -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk); }__set_current_state (TASK_RUNNING );
@@ -441,7 +441,7 @@ unsigned int bt_sock_poll(struct file *file, struct socket *sock,if (!test_bit (BT_SK_SUSPEND , &bt_sk (sk)->flags) &&sock_writeable (sk)) mask |=POLLOUT |POLLWRNORM |POLLWRBAND ;else -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);return mask; }
net/caif/caif_socket.c +2 -2
@@ -323,7 +323,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo) !timeo)break ; -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk);release_sock (sk); timeo =schedule_timeout (timeo);lock_sock (sk);
@@ -331,7 +331,7 @@ static long caif_stream_data_wait(struct sock *sk, long timeo)if (sock_flag (sk,SOCK_DEAD ))break ; -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk); }finish_wait (sk_sleep (sk), &wait);
net/core/datagram.c +1 -1
@@ -785,7 +785,7 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,if (sock_writeable (sk)) mask |=POLLOUT |POLLWRNORM |POLLWRBAND ;else -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);return mask; }
net/core/sock.c +4 -4
@@ -1815,7 +1815,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) {DEFINE_WAIT (wait); -clear_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_NOSPACE , sk);for (;;) {if (!timeo)break ;
@@ -1861,7 +1861,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,if (sk_wmem_alloc_get (sk) < sk->sk_sndbuf)break ; -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);set_bit (SOCK_NOSPACE , &sk->sk_socket->flags); err = -EAGAIN ;if (!timeo)
@@ -2048,9 +2048,9 @@ int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)DEFINE_WAIT (wait);prepare_to_wait (sk_sleep (sk), &wait,TASK_INTERRUPTIBLE ); -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk); rc =sk_wait_event (sk, timeo,skb_peek_tail (&sk->sk_receive_queue) != skb); -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk);finish_wait (sk_sleep (sk), &wait);return rc; }
net/core/stream.c +2 -2
@@ -126,7 +126,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) current_timeo = vm_wait = (prandom_u32 () % (HZ /5 )) +2 ;while (1 ) { -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);prepare_to_wait (sk_sleep (sk), &wait,TASK_INTERRUPTIBLE );
@@ -139,7 +139,7 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) }if (signal_pending (current)) goto do_interrupted; -clear_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_NOSPACE , sk);if (sk_stream_memory_free (sk) && !vm_wait)break ;
net/dccp/proto.c +1 -2
@@ -339,8 +339,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock,if (sk_stream_is_writeable (sk)) { mask |=POLLOUT |POLLWRNORM ; }else {/* send SIGIO later */ -set_bit (SOCK_ASYNC_NOSPACE , - &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);set_bit (SOCK_NOSPACE , &sk->sk_socket->flags);/* Race breaker. If space is freed after
net/decnet/af_decnet.c +4 -4
@@ -1747,9 +1747,9 @@ static int dn_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, }prepare_to_wait (sk_sleep (sk), &wait,TASK_INTERRUPTIBLE ); -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk);sk_wait_event (sk, &timeo,dn_data_ready (sk, queue, flags, target)); -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk);finish_wait (sk_sleep (sk), &wait); }
@@ -2004,10 +2004,10 @@ static int dn_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) }prepare_to_wait (sk_sleep (sk), &wait,TASK_INTERRUPTIBLE ); -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk);sk_wait_event (sk, &timeo, !dn_queue_too_long (scp, queue, flags)); -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk);finish_wait (sk_sleep (sk), &wait);continue ; }
net/ipv4/tcp.c +3 -4
@@ -517,8 +517,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)if (sk_stream_is_writeable (sk)) { mask |=POLLOUT |POLLWRNORM ; }else {/* send SIGIO later */ -set_bit (SOCK_ASYNC_NOSPACE , - &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);set_bit (SOCK_NOSPACE , &sk->sk_socket->flags);/* Race breaker. If space is freed after
@@ -906,7 +905,7 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, goto out_err; } -clear_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_NOSPACE , sk); mss_now =tcp_send_mss (sk, &size_goal, flags); copied =0 ;
@@ -1134,7 +1133,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) }/* This should be in poll */ -clear_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_NOSPACE , sk); mss_now =tcp_send_mss (sk, &size_goal, flags);
net/iucv/af_iucv.c +1 -1
@@ -1483,7 +1483,7 @@ unsigned int iucv_sock_poll(struct file *file, struct socket *sock,if (sock_writeable (sk) &&iucv_below_msglim (sk)) mask |=POLLOUT |POLLWRNORM |POLLWRBAND ;else -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);return mask; }
net/nfc/llcp_sock.c +1 -1
@@ -572,7 +572,7 @@ static unsigned int llcp_sock_poll(struct file *file, struct socket *sock,if (sock_writeable (sk) && sk->sk_state ==LLCP_CONNECTED ) mask |=POLLOUT |POLLWRNORM |POLLWRBAND ;else -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);pr_debug ("mask 0x%x\n" , mask);
net/rxrpc/ar-output.c +1 -1
@@ -531,7 +531,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, timeo =sock_sndtimeo (sk, msg->msg_flags &MSG_DONTWAIT );/* this should be in poll */ -clear_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_NOSPACE , sk);if (sk->sk_err || (sk->sk_shutdown &SEND_SHUTDOWN ))return -EPIPE ;
net/sctp/socket.c +1 -1
@@ -6458,7 +6458,7 @@ unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait)if (sctp_writeable (sk)) { mask |=POLLOUT |POLLWRNORM ; }else { -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);/* * Since the socket is not locked, the buffer * might be made available after the writeable check and
net/socket.c +2 -2
@@ -1072,11 +1072,11 @@ int sock_wake_async(struct socket *sock, int how, int band) }switch (how) {case SOCK_WAKE_WAITD : -if (test_bit (SOCK_ASYNC_WAITDATA , &sock->flags)) +if (test_bit (SOCKWQ_ASYNC_WAITDATA , &sock->flags))break ; goto call_kill;case SOCK_WAKE_SPACE : -if (!test_and_clear_bit (SOCK_ASYNC_NOSPACE , &sock->flags)) +if (!test_and_clear_bit (SOCKWQ_ASYNC_NOSPACE , &sock->flags))break ;/* fall through */ case SOCK_WAKE_IO :
net/sunrpc/xprtsock.c +7 -7
@@ -398,7 +398,7 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen,if (unlikely (!sock))return -ENOTSOCK ; -clear_bit (SOCK_ASYNC_NOSPACE , &sock->flags); +clear_bit (SOCKWQ_ASYNC_NOSPACE , &sock->flags);if (base !=0 ) { addr =NULL ; addrlen =0 ;
@@ -442,7 +442,7 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; -clear_bit (SOCK_ASYNC_NOSPACE , &transport->sock->flags); +clear_bit (SOCKWQ_ASYNC_NOSPACE , &transport->sock->flags); }/**
@@ -467,7 +467,7 @@ static int xs_nospace(struct rpc_task *task)/* Don't race with disconnect */ if (xprt_connected (xprt)) { -if (test_bit (SOCK_ASYNC_NOSPACE , &transport->sock->flags)) { +if (test_bit (SOCKWQ_ASYNC_NOSPACE , &transport->sock->flags)) {/* * Notify TCP that we're limited by the application * window size
@@ -478,7 +478,7 @@ static int xs_nospace(struct rpc_task *task)xprt_wait_for_buffer_space (task, xs_nospace_callback); } }else { -clear_bit (SOCK_ASYNC_NOSPACE , &transport->sock->flags); +clear_bit (SOCKWQ_ASYNC_NOSPACE , &transport->sock->flags); ret = -ENOTCONN ; }
@@ -626,7 +626,7 @@ process_status:case -EPERM :/* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ -clear_bit (SOCK_ASYNC_NOSPACE , &transport->sock->flags); +clear_bit (SOCKWQ_ASYNC_NOSPACE , &transport->sock->flags); }return status;
@@ -715,7 +715,7 @@ static int xs_tcp_send_request(struct rpc_task *task)case -EADDRINUSE :case -ENOBUFS :case -EPIPE : -clear_bit (SOCK_ASYNC_NOSPACE , &transport->sock->flags); +clear_bit (SOCKWQ_ASYNC_NOSPACE , &transport->sock->flags); }return status;
@@ -1618,7 +1618,7 @@ static void xs_write_space(struct sock *sk)if (unlikely (!(xprt =xprt_from_sock (sk))))return ; -if (test_and_clear_bit (SOCK_ASYNC_NOSPACE , &sock->flags) ==0 ) +if (test_and_clear_bit (SOCKWQ_ASYNC_NOSPACE , &sock->flags) ==0 )return ;xprt_write_space (xprt);
net/unix/af_unix.c +3 -3
@@ -2139,7 +2139,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, !timeo)break ; -set_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_WAITDATA , sk);unix_state_unlock (sk); timeo =freezable_schedule_timeout (timeo);unix_state_lock (sk);
@@ -2147,7 +2147,7 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,if (sock_flag (sk,SOCK_DEAD ))break ; -clear_bit (SOCK_ASYNC_WAITDATA , &sk->sk_socket->flags); +sk_clear_bit (SOCKWQ_ASYNC_WAITDATA , sk); }finish_wait (sk_sleep (sk), &wait);
@@ -2634,7 +2634,7 @@ static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,if (writable) mask |=POLLOUT |POLLWRNORM |POLLWRBAND ;else -set_bit (SOCK_ASYNC_NOSPACE , &sk->sk_socket->flags); +sk_set_bit (SOCKWQ_ASYNC_NOSPACE , sk);return mask; }
Signature · 1 line
2.6.0.rc2.230.g3dd15c0
PATCH 2/2 net: fix sock_wake_async() rcu protection
Dmitry provided a syzkaller (http://github.com/google/syzkaller)
triggering a fault in sock_wake_async() when async IO is requested.
Said program stressed af_unix sockets, but the issue is generic and should be addressed in core networking stack.
The problem is that by the time sock_wake_async() is called, we should not access the @flags field of 'struct socket', as the inode containing this socket might be freed without further notice, and without RCU grace period.
We already maintain an RCU protected structure, "struct socket_wq" so moving SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA into it is the safe route.
It also reduces number of cache lines needing dirtying, so might provide a performance improvement anyway.
In followup patches, we might move remaining flags (SOCK_NOSPACE, SOCK_PASSCRED, SOCK_PASSSEC) to save 8 bytes and let 'struct socket' being mostly read and let it being shared between cpus.
--- include/linux/net.h | 7 ++++++- include/net/sock.h | 23 ++++++++++++++++------- net/core/stream.c | 2 +- net/sctp/socket.c | 24 ++++++++++++++---------- net/socket.c | 21 +++++++-------------- 5 files changed, 44 insertions(+), 33 deletions(-)
include/linux/net.h +6 -1
@@ -34,6 +34,10 @@ struct inode;struct file ;struct net ; +/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located +* in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. +* Eventually all flags will be in sk->sk_wq_flags. +*/ #define SOCKWQ_ASYNC_NOSPACE 0#define SOCKWQ_ASYNC_WAITDATA 1#define SOCK_NOSPACE 2
@@ -89,6 +93,7 @@ struct socket_wq {/* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait;struct fasync_struct *fasync_list; +unsigned long flags;/* %SOCKWQ_ASYNC_NOSPACE, etc */ struct rcu_head rcu; }____cacheline_aligned_in_smp ;
@@ -202,7 +207,7 @@ enum { SOCK_WAKE_URG, }; -int sock_wake_async (struct socket *sk,int how,int band); +int sock_wake_async (struct socket_wq *sk_wq,int how,int band);int sock_register (const struct net_proto_family *fam);void sock_unregister (int family); int __sock_create(struct net *net, int family, int type, int proto,
include/net/sock.h +16 -7
@@ -384,8 +384,10 @@ struct sock {int sk_rcvbuf;struct sk_filter __rcu *sk_filter; -struct socket_wq __rcu *sk_wq; - +union { +struct socket_wq __rcu *sk_wq; +struct socket_wq *sk_wq_raw; + };#ifdef CONFIG_XFRM struct xfrm_policy *sk_policy[2 ];#endif
@@ -2005,20 +2007,27 @@ static inline unsigned long sock_wspace(struct sock *sk)return amt; } +/* Note: +* We use sk->sk_wq_raw, from contexts knowing this +* pointer is not NULL and cannot disappear/change. +*/ static inline void sk_set_bit (int nr,struct sock *sk) { -set_bit (nr, &sk->sk_socket->flags); +set_bit (nr, &sk->sk_wq_raw->flags); }static inline void sk_clear_bit (int nr,struct sock *sk) { -clear_bit (nr, &sk->sk_socket->flags); +clear_bit (nr, &sk->sk_wq_raw->flags); } -static inline void sk_wake_async (struct sock *sk,int how,int band) +static inline void sk_wake_async (const struct sock *sk,int how,int band) { -if (sock_flag (sk,SOCK_FASYNC )) -sock_wake_async (sk->sk_socket, how, band); +if (sock_flag (sk,SOCK_FASYNC )) { +rcu_read_lock (); +sock_wake_async (rcu_dereference (sk->sk_wq), how, band); +rcu_read_unlock (); + } }/* Since sk_{r,w}mem_alloc sums skb->truesize, even a small frame might
net/core/stream.c +1 -1
@@ -39,7 +39,7 @@ void sk_stream_write_space(struct sock *sk)wake_up_interruptible_poll (&wq->wait,POLLOUT |POLLWRNORM |POLLWRBAND );if (wq && wq->fasync_list && !(sk->sk_shutdown &SEND_SHUTDOWN )) -sock_wake_async (sock,SOCK_WAKE_SPACE ,POLL_OUT ); +sock_wake_async (wq,SOCK_WAKE_SPACE ,POLL_OUT );rcu_read_unlock (); } }
net/sctp/socket.c +14 -10
@@ -6801,26 +6801,30 @@ no_packet:static void __sctp_write_space (struct sctp_association *asoc) {struct sock *sk = asoc->base.sk; -struct socket *sock = sk->sk_socket; -if ((sctp_wspace (asoc) >0 ) && sock) { -if (waitqueue_active (&asoc->wait)) -wake_up_interruptible (&asoc->wait); +if (sctp_wspace (asoc) <=0 ) +return ; + +if (waitqueue_active (&asoc->wait)) +wake_up_interruptible (&asoc->wait); -if (sctp_writeable (sk)) { -wait_queue_head_t *wq =sk_sleep (sk); +if (sctp_writeable (sk)) { +struct socket_wq *wq; -if (wq &&waitqueue_active (wq)) -wake_up_interruptible (wq); +rcu_read_lock (); + wq =rcu_dereference (sk->sk_wq); +if (wq) { +if (waitqueue_active (&wq->wait)) +wake_up_interruptible (&wq->wait);/* Note that we try to include the Async I/O support * here by modeling from the current TCP/UDP code. * We have not tested with it yet. */ if (!(sk->sk_shutdown &SEND_SHUTDOWN )) -sock_wake_async (sock, -SOCK_WAKE_SPACE ,POLL_OUT ); +sock_wake_async (wq,SOCK_WAKE_SPACE ,POLL_OUT ); } +rcu_read_unlock (); } }
net/socket.c +7 -14
@@ -1056,27 +1056,20 @@ 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 or rcu_lock */ +/* This function may be called only under rcu_lock */ -int sock_wake_async (struct socket *sock,int how,int band) +int sock_wake_async (struct socket_wq *wq,int how,int band) { -struct socket_wq *wq; - -if (!sock) -return -1 ; -rcu_read_lock (); - wq =rcu_dereference (sock->wq); -if (!wq || !wq->fasync_list) { -rcu_read_unlock (); +if (!wq || !wq->fasync_list)return -1 ; - } +switch (how) {case SOCK_WAKE_WAITD : -if (test_bit (SOCKWQ_ASYNC_WAITDATA , &sock->flags)) +if (test_bit (SOCKWQ_ASYNC_WAITDATA , &wq->flags))break ; goto call_kill;case SOCK_WAKE_SPACE : -if (!test_and_clear_bit (SOCKWQ_ASYNC_NOSPACE , &sock->flags)) +if (!test_and_clear_bit (SOCKWQ_ASYNC_NOSPACE , &wq->flags))break ;/* fall through */ case SOCK_WAKE_IO :
@@ -1086,7 +1079,7 @@ call_kill:case SOCK_WAKE_URG :kill_fasync (&wq->fasync_list,SIGURG , band); } -rcu_read_unlock (); +return 0 ; }EXPORT_SYMBOL (sock_wake_async);
Signature · 1 line
2.6.0.rc2.230.g3dd15c0
David Miller
maintainerRe: [PATCH net 2/2] net: fix sock_wake_async() rcu protection
From: Eric Dumazet <[email protected]>
Date: Sun, 29 Nov 2015 20:03:11 -0800
Quoted 18 lines
Dmitry provided a syzkaller (http://github.com/google/syzkaller)
triggering a fault insock_wake_async()when async IO is requested.Said program stressed
af_unixsockets, but the issue is generic and should be addressed in core networking stack.The problem is that by the time
sock_wake_async()is called, we should not access the @flags field of 'struct socket', as the inode containing this socket might be freed without further notice, and without RCU grace period.We already maintain an RCU protected structure, "struct
socket_wq" so movingSOCKWQ_ASYNC_NOSPACE&SOCKWQ_ASYNC_WAITDATAinto it is the safe route.It also reduces number of cache lines needing dirtying, so might provide a performance improvement anyway.
Quoted 6 lines
In followup patches, we might move remaining flags (
SOCK_NOSPACE,SOCK_PASSCRED,SOCK_PASSSEC) to save 8 bytes and let 'struct socket' being mostly read and let it being shared between cpus.Reported-by Dmitry Vyukov <[email protected]>Signed-off-by Eric Dumazet <[email protected]>
Applied and queued up for -stable.
David Miller
maintainerFrom: Eric Dumazet <[email protected]>
Date: Sun, 29 Nov 2015 20:03:10 -0800
Quoted 7 lines
This patch is a cleanup to make following patch easier to review.
Goal is to move
SOCK_ASYNC_NOSPACEandSOCK_ASYNC_WAITDATAfrom (struct socket)->flags to a (struct socket_wq)->flags to benefit from RCU protection insock_wake_async()
Quoted 7 lines
To ease backports, we rename both constants.
Two new helpers,
sk_set_bit(int nr, struct sock *sk)andsk_clear_bit(int net, struct sock *sk)are added so that following patch can change their implementation.Signed-off-by Eric Dumazet <[email protected]>
Applied and queued up for -stable.