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 3d9122e78f41..87c0360eaa25 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 v1.2.2 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 --- net/unix/af_unix.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 87c0360eaa25..fef2cc5e9d2b 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 v1.2.2 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 --- net/unix/af_unix.c | 37 ++++++++++++++++++++++++++++--------- 1 file changed, 28 insertions(+), 9 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index fef2cc5e9d2b..e1f1349fae86 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 v1.2.2 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 --- net/unix/af_unix.c | 53 +++++++++++++++++++++++++++++++---------------------- 1 file changed, 31 insertions(+), 22 deletions(-) (limited to 'net/unix/af_unix.c') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e1f1349fae86..5fe9d6fe08b8 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 v1.2.2 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 5fe9d6fe08b8..75ba48b0d12a 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 v1.2.2 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 --- 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 75ba48b0d12a..4414a18c63b4 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 v1.2.2