From 0884d7aa24e15e72b3c07f7da910a13bb7df3592 Mon Sep 17 00:00:00 2001 From: Alexey Moiseytsev Date: Mon, 21 Nov 2011 13:35:25 +0000 Subject: AF_UNIX: Fix poll blocking problem when reading from a stream socket poll() call may be blocked by concurrent reading from the same stream socket. Signed-off-by: Alexey Moiseytsev Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/af_unix.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 466fbcc5cf77..b595a3d8679f 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1957,6 +1957,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if ((UNIXCB(skb).pid != siocb->scm->pid) || (UNIXCB(skb).cred != siocb->scm->cred)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } else { @@ -1974,6 +1975,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, chunk = min_t(unsigned int, skb->len, size); if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); if (copied == 0) copied = -EFAULT; break; @@ -1991,6 +1993,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put the skb back if we didn't use it up.. */ if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } @@ -2006,6 +2009,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, /* put message back and return */ skb_queue_head(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk, skb->len); break; } } while (size); -- cgit v1.2.3 From fa7ff56f75add89bbedaf2dfcfa8f6661e8e8b3a Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:44:03 +0000 Subject: af_unix: Export stuff required for diag module Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/af_unix.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b595a3d8679f..e1b9358a211d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -115,8 +115,10 @@ #include #include -static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; -static DEFINE_SPINLOCK(unix_table_lock); +struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1]; +EXPORT_SYMBOL_GPL(unix_socket_table); +DEFINE_SPINLOCK(unix_table_lock); +EXPORT_SYMBOL_GPL(unix_table_lock); static atomic_long_t unix_nr_socks; #define unix_sockets_unbound (&unix_socket_table[UNIX_HASH_SIZE]) @@ -172,7 +174,7 @@ static inline int unix_recvq_full(struct sock const *sk) return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; } -static struct sock *unix_peer_get(struct sock *s) +struct sock *unix_peer_get(struct sock *s) { struct sock *peer; @@ -183,6 +185,7 @@ static struct sock *unix_peer_get(struct sock *s) unix_state_unlock(s); return peer; } +EXPORT_SYMBOL_GPL(unix_peer_get); static inline void unix_release_addr(struct unix_address *addr) { -- cgit v1.2.3 From 22931d3b906cd0a1726a49a09713f9220a5fab8a Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:44:35 +0000 Subject: unix_diag: Basic module skeleton Includes basic module_init/_exit functionality, dump/get_exact stubs and declares the basic API structures for request and response. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) create mode 100644 net/unix/diag.c (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c new file mode 100644 index 000000000000..6be16c0ad38f --- /dev/null +++ b/net/unix/diag.c @@ -0,0 +1,57 @@ +#include +#include +#include +#include +#include +#include +#include +#include + +#define UNIX_DIAG_PUT(skb, attrtype, attrlen) \ + RTA_DATA(__RTA_PUT(skb, attrtype, attrlen)) + +static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + return 0; +} + +static int unix_diag_get_exact(struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + struct unix_diag_req *req) +{ + return -EAFNOSUPPORT; +} + +static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) +{ + int hdrlen = sizeof(struct unix_diag_req); + + if (nlmsg_len(h) < hdrlen) + return -EINVAL; + + if (h->nlmsg_flags & NLM_F_DUMP) + return netlink_dump_start(sock_diag_nlsk, skb, h, + unix_diag_dump, NULL, 0); + else + return unix_diag_get_exact(skb, h, (struct unix_diag_req *)NLMSG_DATA(h)); +} + +static struct sock_diag_handler unix_diag_handler = { + .family = AF_UNIX, + .dump = unix_diag_handler_dump, +}; + +static int __init unix_diag_init(void) +{ + return sock_diag_register(&unix_diag_handler); +} + +static void __exit unix_diag_exit(void) +{ + sock_diag_unregister(&unix_diag_handler); +} + +module_init(unix_diag_init); +module_exit(unix_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */); -- cgit v1.2.3 From 45a96b9be6ec1b7d248642d17ceee59ff5f64451 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:44:52 +0000 Subject: unix_diag: Dumping all sockets core Walk the unix sockets table and fill the core response structure, which includes type, state and inode. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 75 insertions(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 6be16c0ad38f..86d85abf90c6 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,9 +10,83 @@ #define UNIX_DIAG_PUT(skb, attrtype, attrlen) \ RTA_DATA(__RTA_PUT(skb, attrtype, attrlen)) +static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, + u32 pid, u32 seq, u32 flags, int sk_ino) +{ + unsigned char *b = skb_tail_pointer(skb); + struct nlmsghdr *nlh; + struct unix_diag_msg *rep; + + nlh = NLMSG_PUT(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep)); + nlh->nlmsg_flags = flags; + + rep = NLMSG_DATA(nlh); + + rep->udiag_family = AF_UNIX; + rep->udiag_type = sk->sk_type; + rep->udiag_state = sk->sk_state; + rep->udiag_ino = sk_ino; + sock_diag_save_cookie(sk, rep->udiag_cookie); + + nlh->nlmsg_len = skb_tail_pointer(skb) - b; + return skb->len; + +nlmsg_failure: + nlmsg_trim(skb, b); + return -EMSGSIZE; +} + +static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, + u32 pid, u32 seq, u32 flags) +{ + int sk_ino; + + unix_state_lock(sk); + sk_ino = sock_i_ino(sk); + unix_state_unlock(sk); + + if (!sk_ino) + return 0; + + return sk_diag_fill(sk, skb, req, pid, seq, flags, sk_ino); +} + static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { - return 0; + struct unix_diag_req *req; + int num, s_num, slot, s_slot; + + req = NLMSG_DATA(cb->nlh); + + s_slot = cb->args[0]; + num = s_num = cb->args[1]; + + spin_lock(&unix_table_lock); + for (slot = s_slot; slot <= UNIX_HASH_SIZE; s_num = 0, slot++) { + struct sock *sk; + struct hlist_node *node; + + num = 0; + sk_for_each(sk, node, &unix_socket_table[slot]) { + if (num < s_num) + goto next; + if (!(req->udiag_states & (1 << sk->sk_state))) + goto next; + if (sk_diag_dump(sk, skb, req, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + goto done; +next: + num++; + } + } +done: + spin_unlock(&unix_table_lock); + cb->args[0] = slot; + cb->args[1] = num; + + return skb->len; } static int unix_diag_get_exact(struct sk_buff *in_skb, -- cgit v1.2.3 From 5d3cae8bc39dd38d1aa5fd4bbc788c7b43fcaa71 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:45:07 +0000 Subject: unix_diag: Dumping exact socket core The socket inode is used as a key for lookup. This is effectively the only really unique ID of a unix socket, but using this for search currently has one problem -- it is O(number of sockets) :( Does it worth fixing this lookup or inventing some other ID for unix sockets? Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 67 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 66 insertions(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 86d85abf90c6..d7bd48c49ee5 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -89,11 +89,76 @@ done: return skb->len; } +static struct sock *unix_lookup_by_ino(int ino) +{ + int i; + struct sock *sk; + + spin_lock(&unix_table_lock); + for (i = 0; i <= UNIX_HASH_SIZE; i++) { + struct hlist_node *node; + + sk_for_each(sk, node, &unix_socket_table[i]) + if (ino == sock_i_ino(sk)) { + sock_hold(sk); + spin_unlock(&unix_table_lock); + + return sk; + } + } + + spin_unlock(&unix_table_lock); + return NULL; +} + static int unix_diag_get_exact(struct sk_buff *in_skb, const struct nlmsghdr *nlh, struct unix_diag_req *req) { - return -EAFNOSUPPORT; + int err = -EINVAL; + struct sock *sk; + struct sk_buff *rep; + unsigned int extra_len; + + if (req->udiag_ino == 0) + goto out_nosk; + + sk = unix_lookup_by_ino(req->udiag_ino); + err = -ENOENT; + if (sk == NULL) + goto out_nosk; + + err = sock_diag_check_cookie(sk, req->udiag_cookie); + if (err) + goto out; + + extra_len = 256; +again: + err = -ENOMEM; + rep = alloc_skb(NLMSG_SPACE((sizeof(struct unix_diag_msg) + extra_len)), + GFP_KERNEL); + if (!rep) + goto out; + + err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid, + nlh->nlmsg_seq, 0, req->udiag_ino); + if (err < 0) { + kfree_skb(rep); + extra_len += 256; + if (extra_len >= PAGE_SIZE) + goto out; + + goto again; + } + err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + MSG_DONTWAIT); + if (err > 0) + err = 0; +out: + if (sk) + sock_put(sk); +out_nosk: + return err; } static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) -- cgit v1.2.3 From f5248b48a64c221dd6157ab9cbee5a36ee45e6ed Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:45:24 +0000 Subject: unix_diag: Unix socket name NLA Report the sun_path when requested as NLA. With leading '\0' if present but without the leading AF_UNIX bits. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index d7bd48c49ee5..161ce6c05e31 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,6 +10,22 @@ #define UNIX_DIAG_PUT(skb, attrtype, attrlen) \ RTA_DATA(__RTA_PUT(skb, attrtype, attrlen)) +static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) +{ + struct unix_address *addr = unix_sk(sk)->addr; + char *s; + + if (addr) { + s = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short)); + memcpy(s, addr->name->sun_path, addr->len - sizeof(short)); + } + + return 0; + +rtattr_failure: + return -EMSGSIZE; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { @@ -28,6 +44,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r rep->udiag_ino = sk_ino; sock_diag_save_cookie(sk, rep->udiag_cookie); + if ((req->udiag_show & UDIAG_SHOW_NAME) && + sk_diag_dump_name(sk, skb)) + goto nlmsg_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -- cgit v1.2.3 From 5f7b0569460b7d8d01ca776430a00505a68b7584 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:45:43 +0000 Subject: unix_diag: Unix inode info NLA Actually, the socket path if it's not anonymous doesn't give a clue to which file the socket is bound to. Even if the path is absolute, it can be unlinked and then new socket can be bound to it. With this NLA it's possible to check which file a particular socket is really bound to. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 161ce6c05e31..83799ef19b49 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -26,6 +26,23 @@ rtattr_failure: return -EMSGSIZE; } +static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb) +{ + struct dentry *dentry = unix_sk(sk)->dentry; + struct unix_diag_vfs *uv; + + if (dentry) { + uv = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_VFS, sizeof(*uv)); + uv->udiag_vfs_ino = dentry->d_inode->i_ino; + uv->udiag_vfs_dev = dentry->d_sb->s_dev; + } + + return 0; + +rtattr_failure: + return -EMSGSIZE; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { @@ -48,6 +65,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sk_diag_dump_name(sk, skb)) goto nlmsg_failure; + if ((req->udiag_show & UDIAG_SHOW_VFS) && + sk_diag_dump_vfs(sk, skb)) + goto nlmsg_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -- cgit v1.2.3 From ac02be8d96af9f66a4de86781ee9facc2dff99d4 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:45:58 +0000 Subject: unix_diag: Unix peer inode NLA Report the peer socket inode ID as NLA. With this it's finally possible to find out the other end of an interesting unix connection. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 83799ef19b49..0e0fda786afe 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -43,6 +43,26 @@ rtattr_failure: return -EMSGSIZE; } +static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb) +{ + struct sock *peer; + int ino; + + peer = unix_peer_get(sk); + if (peer) { + unix_state_lock(peer); + ino = sock_i_ino(peer); + unix_state_unlock(peer); + sock_put(peer); + + RTA_PUT_U32(nlskb, UNIX_DIAG_PEER, ino); + } + + return 0; +rtattr_failure: + return -EMSGSIZE; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { @@ -69,6 +89,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sk_diag_dump_vfs(sk, skb)) goto nlmsg_failure; + if ((req->udiag_show & UDIAG_SHOW_PEER) && + sk_diag_dump_peer(sk, skb)) + goto nlmsg_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -- cgit v1.2.3 From 2aac7a2cb0d9d8c65fc7dde3e19e46b3e878d23d Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:46:14 +0000 Subject: unix_diag: Pending connections IDs NLA When establishing a unix connection on stream sockets the server end receives an skb with socket in its receive queue. Report who is waiting for these ends to be accepted for listening sockets via NLA. There's a lokcing issue with this -- the unix sk state lock is required to access the peer, and it is taken under the listening sk's queue lock. Strictly speaking the queue lock should be taken inside the state lock, but since in this case these two sockets are different it shouldn't lead to deadlock. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 0e0fda786afe..24c7a65d9cb1 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -63,6 +63,41 @@ rtattr_failure: return -EMSGSIZE; } +static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) +{ + struct sk_buff *skb; + u32 *buf; + int i; + + if (sk->sk_state == TCP_LISTEN) { + spin_lock(&sk->sk_receive_queue.lock); + buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS, sk->sk_receive_queue.qlen); + i = 0; + skb_queue_walk(&sk->sk_receive_queue, skb) { + struct sock *req, *peer; + + req = skb->sk; + /* + * The state lock is outer for the same sk's + * queue lock. With the other's queue locked it's + * OK to lock the state. + */ + unix_state_lock_nested(req); + peer = unix_sk(req)->peer; + if (peer) + buf[i++] = sock_i_ino(peer); + unix_state_unlock(req); + } + spin_unlock(&sk->sk_receive_queue.lock); + } + + return 0; + +rtattr_failure: + spin_unlock(&sk->sk_receive_queue.lock); + return -EMSGSIZE; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { @@ -93,6 +128,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sk_diag_dump_peer(sk, skb)) goto nlmsg_failure; + if ((req->udiag_show & UDIAG_SHOW_ICONS) && + sk_diag_dump_icons(sk, skb)) + goto nlmsg_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -- cgit v1.2.3 From cbf391958afb9b82c72324a15891eb3102200085 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:46:31 +0000 Subject: unix_diag: Receive queue lenght NLA Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 24c7a65d9cb1..a5c4aab0380d 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -98,6 +98,15 @@ rtattr_failure: return -EMSGSIZE; } +static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) +{ + RTA_PUT_U32(nlskb, UNIX_DIAG_RQLEN, sk->sk_receive_queue.qlen); + return 0; + +rtattr_failure: + return -EMSGSIZE; +} + static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, u32 pid, u32 seq, u32 flags, int sk_ino) { @@ -132,6 +141,10 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sk_diag_dump_icons(sk, skb)) goto nlmsg_failure; + if ((req->udiag_show & UDIAG_SHOW_RQLEN) && + sk_diag_show_rqlen(sk, skb)) + goto nlmsg_failure; + nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; -- cgit v1.2.3 From 5d531aaa64a06622874f06e5068b8eefca048feb Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Thu, 15 Dec 2011 02:46:50 +0000 Subject: unix_diag: Write it into kbuild Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/Kconfig | 7 +++++++ net/unix/Makefile | 3 +++ 2 files changed, 10 insertions(+) (limited to 'net/unix') diff --git a/net/unix/Kconfig b/net/unix/Kconfig index 5a69733bcdad..c2128b10e5f9 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -19,3 +19,10 @@ config UNIX Say Y unless you know what you are doing. +config UNIX_DIAG + tristate "UNIX: socket monitoring interface" + depends on UNIX + default UNIX + ---help--- + Support for UNIX socket monitoring interface used by the ss tool. + If unsure, say Y. diff --git a/net/unix/Makefile b/net/unix/Makefile index b852a2bde9a8..b663c607b1c6 100644 --- a/net/unix/Makefile +++ b/net/unix/Makefile @@ -6,3 +6,6 @@ obj-$(CONFIG_UNIX) += unix.o unix-y := af_unix.o garbage.o unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o + +obj-$(CONFIG_UNIX_DIAG) += unix_diag.o +unix_diag-y := diag.o -- cgit v1.2.3 From 2ea744a583d0f40901b2ea43059ae007d9cf2602 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Tue, 20 Dec 2011 04:33:03 +0000 Subject: net: unix -- Add missing module.h inclusion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Otherwise getting | net/unix/diag.c:312:16: error: expected declaration specifiers or ‘...’ before string constant | net/unix/diag.c:313:1: error: expected declaration specifiers or ‘...’ before string constant Signed-off-by: Cyrill Gorcunov Signed-off-by: David S. Miller --- net/unix/diag.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index a5c4aab0380d..91d57828499c 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 3b0723c12e825e26aa5fc0c6970108425824b51d Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Mon, 26 Dec 2011 14:08:47 -0500 Subject: unix_diag: Fix incoming connections nla length The NLA_PUT macro should accept the actual attribute length, not the amount of elements in array :( Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 91d57828499c..39e44c98176a 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -72,7 +72,8 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) if (sk->sk_state == TCP_LISTEN) { spin_lock(&sk->sk_receive_queue.lock); - buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS, sk->sk_receive_queue.qlen); + buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS, + sk->sk_receive_queue.qlen * sizeof(u32)); i = 0; skb_queue_walk(&sk->sk_receive_queue, skb) { struct sock *req, *peer; -- cgit v1.2.3 From e09e9d189bc2d31dc365a3d846a09086317350b6 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 26 Dec 2011 14:41:55 -0500 Subject: unix: If we happen to find peer NULL when diag dumping, write zero. Otherwise we leave uninitialized kernel memory in there. Reported-by: Eric Dumazet Signed-off-by: David S. Miller --- net/unix/diag.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 39e44c98176a..c5bdbcb1c30b 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -86,8 +86,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) */ unix_state_lock_nested(req); peer = unix_sk(req)->peer; - if (peer) - buf[i++] = sock_i_ino(peer); + buf[i++] = (peer ? sock_i_ino(peer) : 0); unix_state_unlock(req); } spin_unlock(&sk->sk_receive_queue.lock); -- cgit v1.2.3 From 257b529876cb45ec791eaa89e3d2ee0d16b49383 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 30 Dec 2011 09:27:43 +0000 Subject: unix_diag: Add the MEMINFO extension [ Fix indentation of sock_diag*() calls. -DaveM ] Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index c5bdbcb1c30b..98945f29da4f 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -127,23 +127,27 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r sock_diag_save_cookie(sk, rep->udiag_cookie); if ((req->udiag_show & UDIAG_SHOW_NAME) && - sk_diag_dump_name(sk, skb)) + sk_diag_dump_name(sk, skb)) goto nlmsg_failure; if ((req->udiag_show & UDIAG_SHOW_VFS) && - sk_diag_dump_vfs(sk, skb)) + sk_diag_dump_vfs(sk, skb)) goto nlmsg_failure; if ((req->udiag_show & UDIAG_SHOW_PEER) && - sk_diag_dump_peer(sk, skb)) + sk_diag_dump_peer(sk, skb)) goto nlmsg_failure; if ((req->udiag_show & UDIAG_SHOW_ICONS) && - sk_diag_dump_icons(sk, skb)) + sk_diag_dump_icons(sk, skb)) goto nlmsg_failure; if ((req->udiag_show & UDIAG_SHOW_RQLEN) && - sk_diag_show_rqlen(sk, skb)) + sk_diag_show_rqlen(sk, skb)) + goto nlmsg_failure; + + if ((req->udiag_show & UDIAG_SHOW_MEMINFO) && + sock_diag_put_meminfo(sk, skb, UNIX_DIAG_MEMINFO)) goto nlmsg_failure; nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -191,9 +195,9 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!(req->udiag_states & (1 << sk->sk_state))) goto next; if (sk_diag_dump(sk, skb, req, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI) < 0) + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) goto done; next: num++; -- cgit v1.2.3 From 885ee74d5d3058e4a904671ed7929c9540c95fa5 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 30 Dec 2011 00:54:11 +0000 Subject: af_unix: Move CINQ/COUTQ code to helpers Currently tcp diag reports rqlen and wqlen values similar to how the CINQ/COUTQ iotcls do. To make unix diag report these values in the same way move the respective code into helpers. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/af_unix.c | 59 +++++++++++++++++++++++++++++++++--------------------- 1 file changed, 36 insertions(+), 23 deletions(-) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e1b9358a211d..7cc3d7b23d1c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2065,6 +2065,36 @@ static int unix_shutdown(struct socket *sock, int mode) return 0; } +long unix_inq_len(struct sock *sk) +{ + struct sk_buff *skb; + long amount = 0; + + if (sk->sk_state == TCP_LISTEN) + return -EINVAL; + + spin_lock(&sk->sk_receive_queue.lock); + if (sk->sk_type == SOCK_STREAM || + sk->sk_type == SOCK_SEQPACKET) { + skb_queue_walk(&sk->sk_receive_queue, skb) + amount += skb->len; + } else { + skb = skb_peek(&sk->sk_receive_queue); + if (skb) + amount = skb->len; + } + spin_unlock(&sk->sk_receive_queue.lock); + + return amount; +} +EXPORT_SYMBOL_GPL(unix_inq_len); + +long unix_outq_len(struct sock *sk) +{ + return sk_wmem_alloc_get(sk); +} +EXPORT_SYMBOL_GPL(unix_outq_len); + static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; @@ -2073,33 +2103,16 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) switch (cmd) { case SIOCOUTQ: - amount = sk_wmem_alloc_get(sk); + amount = unix_outq_len(sk); err = put_user(amount, (int __user *)arg); break; case SIOCINQ: - { - struct sk_buff *skb; - - if (sk->sk_state == TCP_LISTEN) { - err = -EINVAL; - break; - } - - spin_lock(&sk->sk_receive_queue.lock); - if (sk->sk_type == SOCK_STREAM || - sk->sk_type == SOCK_SEQPACKET) { - skb_queue_walk(&sk->sk_receive_queue, skb) - amount += skb->len; - } else { - skb = skb_peek(&sk->sk_receive_queue); - if (skb) - amount = skb->len; - } - spin_unlock(&sk->sk_receive_queue.lock); + amount = unix_inq_len(sk); + if (amount < 0) + err = amount; + else err = put_user(amount, (int __user *)arg); - break; - } - + break; default: err = -ENOIOCTLCMD; break; -- cgit v1.2.3 From c9da99e6475f92653139e43f3c30c0cd011a0fd8 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Fri, 30 Dec 2011 00:54:39 +0000 Subject: unix_diag: Fixup RQLEN extension report While it's not too late fix the recently added RQLEN diag extension to report rqlen and wqlen in the same way as TCP does. I.e. for listening sockets the ack backlog length (which is the input queue length for socket) in rqlen and the max ack backlog length in wqlen, and what the CINQ/OUTQ ioctls do for established. Signed-off-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/unix/diag.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/diag.c b/net/unix/diag.c index 98945f29da4f..6b7697fd911b 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -101,7 +101,18 @@ rtattr_failure: static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) { - RTA_PUT_U32(nlskb, UNIX_DIAG_RQLEN, sk->sk_receive_queue.qlen); + struct unix_diag_rqlen *rql; + + rql = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_RQLEN, sizeof(*rql)); + + if (sk->sk_state == TCP_LISTEN) { + rql->udiag_rqueue = sk->sk_receive_queue.qlen; + rql->udiag_wqueue = sk->sk_max_ack_backlog; + } else { + rql->udiag_rqueue = (__u32)unix_inq_len(sk); + rql->udiag_wqueue = (__u32)unix_outq_len(sk); + } + return 0; rtattr_failure: -- cgit v1.2.3 From 04fc66e789a896e684bfdca30208e57eb832dd96 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 21 Nov 2011 14:58:38 -0500 Subject: switch ->path_mknod() to umode_t Signed-off-by: Al Viro --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index b595a3d8679f..412a99f4a3f7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -847,7 +847,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) atomic_set(&addr->refcnt, 1); if (sun_path[0]) { - unsigned int mode; + umode_t mode; err = 0; /* * Get the parent directory, calculate the hash for last -- cgit v1.2.3 From 6d62a66e4211546f9e5c5d1ad586749a51cf30db Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Sat, 7 Jan 2012 12:13:06 -0800 Subject: net: Default UDP and UNIX diag to 'n'. Signed-off-by: David S. Miller --- net/unix/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/unix') diff --git a/net/unix/Kconfig b/net/unix/Kconfig index c2128b10e5f9..8b31ab85d050 100644 --- a/net/unix/Kconfig +++ b/net/unix/Kconfig @@ -22,7 +22,7 @@ config UNIX config UNIX_DIAG tristate "UNIX: socket monitoring interface" depends on UNIX - default UNIX + default n ---help--- Support for UNIX socket monitoring interface used by the ss tool. If unsure, say Y. -- cgit v1.2.3 From 6f01fd6e6f6809061b56e78f1e8d143099716d70 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 28 Jan 2012 16:11:03 +0000 Subject: af_unix: fix EPOLLET regression for stream sockets Commit 0884d7aa24 (AF_UNIX: Fix poll blocking problem when reading from a stream socket) added a regression for epoll() in Edge Triggered mode (EPOLLET) Appropriate fix is to use skb_peek()/skb_unlink() instead of skb_dequeue(), and only call skb_unlink() when skb is fully consumed. This remove the need to requeue a partial skb into sk_receive_queue head and the extra sk->sk_data_ready() calls that added the regression. This is safe because once skb is given to sk_receive_queue, it is not modified by a writer, and readers are serialized by u->readlock mutex. This also reduce number of spinlock acquisition for small reads or MSG_PEEK users so should improve overall performance. Reported-by: Nick Mathewson Signed-off-by: Eric Dumazet Cc: Alexey Moiseytsev Signed-off-by: David S. Miller --- net/unix/af_unix.c | 19 ++++--------------- 1 file changed, 4 insertions(+), 15 deletions(-) (limited to 'net/unix') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index aad8fb699989..85d3bb7490aa 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1918,7 +1918,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, struct sk_buff *skb; unix_state_lock(sk); - skb = skb_dequeue(&sk->sk_receive_queue); + skb = skb_peek(&sk->sk_receive_queue); if (skb == NULL) { unix_sk(sk)->recursion_level = 0; if (copied >= target) @@ -1958,11 +1958,8 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (check_creds) { /* Never glue messages from different writers */ if ((UNIXCB(skb).pid != siocb->scm->pid) || - (UNIXCB(skb).cred != siocb->scm->cred)) { - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + (UNIXCB(skb).cred != siocb->scm->cred)) break; - } } else { /* Copy credentials */ scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred); @@ -1977,8 +1974,6 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, chunk = min_t(unsigned int, skb->len, size); if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) { - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); if (copied == 0) copied = -EFAULT; break; @@ -1993,13 +1988,10 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (UNIXCB(skb).fp) unix_detach_fds(siocb->scm, skb); - /* put the skb back if we didn't use it up.. */ - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); + if (skb->len) break; - } + skb_unlink(skb, &sk->sk_receive_queue); consume_skb(skb); if (siocb->scm->fp) @@ -2010,9 +2002,6 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock, if (UNIXCB(skb).fp) siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp); - /* put message back and return */ - skb_queue_head(&sk->sk_receive_queue, skb); - sk->sk_data_ready(sk, skb->len); break; } } while (size); -- cgit v1.2.3