[PATCH 0/2] netlink: implement socket diag for netlink sockets

[PATCH 0/2] netlink: implement socket diag for netlink sockets

[Andrey Vagin]

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Andrey Vagin <avagin@openvz.org>

Andrey Vagin (2):
  net: prepare netlink code for netlink diag
  netlink: Diag core and basic socket info dumping

 include/uapi/linux/netlink_diag.h |  40 ++++++++
 net/Kconfig                       |   1 +
 net/netlink/Kconfig               |  10 ++
 net/netlink/Makefile              |   3 +
 net/netlink/af_netlink.c          |  59 +-----------
 net/netlink/af_netlink.h          |  62 +++++++++++++
 net/netlink/diag.c                | 186 ++++++++++++++++++++++++++++++++++++++
 7 files changed, 307 insertions(+), 54 deletions(-)
 create mode 100644 include/uapi/linux/netlink_diag.h
 create mode 100644 net/netlink/Kconfig
 create mode 100644 net/netlink/af_netlink.h
 create mode 100644 net/netlink/diag.c

-- 
1.8.1.4

[PATCH 1/2] net: prepare netlink code for netlink diag

[Andrey Vagin]

Move a few declarations in a header.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 net/netlink/af_netlink.c | 59 ++++-----------------------------------------
 net/netlink/af_netlink.h | 62 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+), 54 deletions(-)
 create mode 100644 net/netlink/af_netlink.h

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 1e3fd5b..a500ce2 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -61,28 +61,7 @@
 #include <net/scm.h>
 #include <net/netlink.h>
 
-#define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
-#define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
-
-struct netlink_sock {
-	/* struct sock has to be the first member of netlink_sock */
-	struct sock		sk;
-	u32			portid;
-	u32			dst_portid;
-	u32			dst_group;
-	u32			flags;
-	u32			subscriptions;
-	u32			ngroups;
-	unsigned long		*groups;
-	unsigned long		state;
-	wait_queue_head_t	wait;
-	struct netlink_callback	*cb;
-	struct mutex		*cb_mutex;
-	struct mutex		cb_def_mutex;
-	void			(*netlink_rcv)(struct sk_buff *skb);
-	void			(*netlink_bind)(int group);
-	struct module		*module;
-};
+#include "af_netlink.h"
 
 struct listeners {
 	struct rcu_head		rcu;
@@ -94,48 +73,20 @@ struct listeners {
 #define NETLINK_BROADCAST_SEND_ERROR	0x4
 #define NETLINK_RECV_NO_ENOBUFS	0x8
 
-static inline struct netlink_sock *nlk_sk(struct sock *sk)
-{
-	return container_of(sk, struct netlink_sock, sk);
-}
-
 static inline int netlink_is_kernel(struct sock *sk)
 {
 	return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET;
 }
 
-struct nl_portid_hash {
-	struct hlist_head	*table;
-	unsigned long		rehash_time;
-
-	unsigned int		mask;
-	unsigned int		shift;
-
-	unsigned int		entries;
-	unsigned int		max_shift;
-
-	u32			rnd;
-};
-
-struct netlink_table {
-	struct nl_portid_hash	hash;
-	struct hlist_head	mc_list;
-	struct listeners __rcu	*listeners;
-	unsigned int		flags;
-	unsigned int		groups;
-	struct mutex		*cb_mutex;
-	struct module		*module;
-	void			(*bind)(int group);
-	int			registered;
-};
-
-static struct netlink_table *nl_table;
+struct netlink_table *nl_table;
+EXPORT_SYMBOL_GPL(nl_table);
 
 static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait);
 
 static int netlink_dump(struct sock *sk);
 
-static DEFINE_RWLOCK(nl_table_lock);
+DEFINE_RWLOCK(nl_table_lock);
+EXPORT_SYMBOL_GPL(nl_table_lock);
 static atomic_t nl_table_users = ATOMIC_INIT(0);
 
 #define nl_deref_protected(X) rcu_dereference_protected(X, lockdep_is_held(&nl_table_lock));
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
new file mode 100644
index 0000000..d9acb2a
--- /dev/null
+++ b/net/netlink/af_netlink.h
@@ -0,0 +1,62 @@
+#ifndef _AF_NETLINK_H
+#define _AF_NETLINK_H
+
+#include <net/sock.h>
+
+#define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
+#define NLGRPLONGS(x)	(NLGRPSZ(x)/sizeof(unsigned long))
+
+struct netlink_sock {
+	/* struct sock has to be the first member of netlink_sock */
+	struct sock		sk;
+	u32			portid;
+	u32			dst_portid;
+	u32			dst_group;
+	u32			flags;
+	u32			subscriptions;
+	u32			ngroups;
+	unsigned long		*groups;
+	unsigned long		state;
+	wait_queue_head_t	wait;
+	struct netlink_callback	*cb;
+	struct mutex		*cb_mutex;
+	struct mutex		cb_def_mutex;
+	void			(*netlink_rcv)(struct sk_buff *skb);
+	void			(*netlink_bind)(int group);
+	struct module		*module;
+};
+
+static inline struct netlink_sock *nlk_sk(struct sock *sk)
+{
+	return container_of(sk, struct netlink_sock, sk);
+}
+
+struct nl_portid_hash {
+	struct hlist_head	*table;
+	unsigned long		rehash_time;
+
+	unsigned int		mask;
+	unsigned int		shift;
+
+	unsigned int		entries;
+	unsigned int		max_shift;
+
+	u32			rnd;
+};
+
+struct netlink_table {
+	struct nl_portid_hash	hash;
+	struct hlist_head	mc_list;
+	struct listeners __rcu	*listeners;
+	unsigned int		flags;
+	unsigned int		groups;
+	struct mutex		*cb_mutex;
+	struct module		*module;
+	void			(*bind)(int group);
+	int			registered;
+};
+
+extern struct netlink_table *nl_table;
+extern rwlock_t nl_table_lock;
+
+#endif
-- 
1.8.1.4

[PATCH 2/2] netlink: Diag core and basic socket info dumping

[Andrey Vagin]

The netlink_diag can be built as a module, just like it's done in
unix sockets.

The core dumping message carries the basic info about netlink sockets:
family, type and protocol, portis, dst_group, dst_portid, state.

Groups can be received as an optional parameter NETLINK_DIAG_GROUPS.

Netlink sockets cab be filtered by protocols.

The socket inode number and cookie is reserved for future per-socket info
retrieving. The per-protocol filtering is also reserved for future by
requiring the sdiag_protocol to be zero.

The file /proc/net/netlink doesn't provide enough information for
dumping netlink sockets. It doesn't provide dst_group, dst_portid,
groups above 32.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 include/uapi/linux/netlink_diag.h |  40 ++++++++
 net/Kconfig                       |   1 +
 net/netlink/Kconfig               |  10 ++
 net/netlink/Makefile              |   3 +
 net/netlink/diag.c                | 188 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 242 insertions(+)
 create mode 100644 include/uapi/linux/netlink_diag.h
 create mode 100644 net/netlink/Kconfig
 create mode 100644 net/netlink/diag.c

diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
new file mode 100644
index 0000000..9328866
--- /dev/null
+++ b/include/uapi/linux/netlink_diag.h
@@ -0,0 +1,40 @@
+#ifndef __NETLINK_DIAG_H__
+#define __NETLINK_DIAG_H__
+
+#include <linux/types.h>
+
+struct netlink_diag_req {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+	__u16	pad;
+	__u32	ndiag_ino;
+	__u32	ndiag_show;
+	__u32	ndiag_cookie[2];
+};
+
+struct netlink_diag_msg {
+	__u8	ndiag_family;
+	__u8	ndiag_type;
+	__u8	ndiag_protocol;
+	__u8	ndiag_state;
+
+	__u32	ndiag_portid;
+	__u32	ndiag_dst_portid;
+	__u32	ndiag_dst_group;
+	__u32	ndiag_ino;
+	__u32	ndiag_cookie[2];
+};
+
+enum {
+	NETLINK_DIAG_MEMINFO,
+	NETLINK_DIAG_GROUPS,
+
+	NETLINK_DIAG_MAX,
+};
+
+#define NDIAG_PROTO_ALL		((__u8) ~0)
+
+#define NDIAG_SHOW_MEMINFO	0x00000001 /* show memory info of a socket */
+#define NDIAG_SHOW_GROUPS	0x00000002 /* show groups of a netlink socket */
+
+#endif
diff --git a/net/Kconfig b/net/Kconfig
index 6f676ab..2ddc904 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -217,6 +217,7 @@ source "net/dns_resolver/Kconfig"
 source "net/batman-adv/Kconfig"
 source "net/openvswitch/Kconfig"
 source "net/vmw_vsock/Kconfig"
+source "net/netlink/Kconfig"
 
 config RPS
 	boolean
diff --git a/net/netlink/Kconfig b/net/netlink/Kconfig
new file mode 100644
index 0000000..5d6e8c0
--- /dev/null
+++ b/net/netlink/Kconfig
@@ -0,0 +1,10 @@
+#
+# Netlink Sockets
+#
+
+config NETLINK_DIAG
+	tristate "NETLINK: socket monitoring interface"
+	default n
+	---help---
+	  Support for NETLINK socket monitoring interface used by the ss tool.
+	  If unsure, say Y.
diff --git a/net/netlink/Makefile b/net/netlink/Makefile
index bdd6ddf..e837917 100644
--- a/net/netlink/Makefile
+++ b/net/netlink/Makefile
@@ -3,3 +3,6 @@
 #
 
 obj-y  				:= af_netlink.o genetlink.o
+
+obj-$(CONFIG_NETLINK_DIAG)	+= netlink_diag.o
+netlink_diag-y			:= diag.o
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
new file mode 100644
index 0000000..5ffb1d1
--- /dev/null
+++ b/net/netlink/diag.c
@@ -0,0 +1,188 @@
+#include <linux/module.h>
+
+#include <net/sock.h>
+#include <linux/netlink.h>
+#include <linux/sock_diag.h>
+#include <linux/netlink_diag.h>
+
+#include "af_netlink.h"
+
+static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (nlk->groups == NULL)
+		return 0;
+
+	return nla_put(nlskb, NETLINK_DIAG_GROUPS, NLGRPSZ(nlk->ngroups),
+		       nlk->groups);
+}
+
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
+			struct netlink_diag_req *req,
+			u32 portid, u32 seq, u32 flags, int sk_ino)
+{
+	struct nlmsghdr *nlh;
+	struct netlink_diag_msg *rep;
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep),
+			flags);
+	if (!nlh)
+		return -EMSGSIZE;
+
+	rep = nlmsg_data(nlh);
+	rep->ndiag_family	= AF_NETLINK;
+	rep->ndiag_type		= sk->sk_type;
+	rep->ndiag_protocol	= sk->sk_protocol;
+	rep->ndiag_state	= sk->sk_state;
+
+	rep->ndiag_ino		= sk_ino;
+	rep->ndiag_portid	= nlk->portid;
+	rep->ndiag_dst_portid	= nlk->dst_portid;
+	rep->ndiag_dst_group	= nlk->dst_group;
+	sock_diag_save_cookie(sk, rep->ndiag_cookie);
+
+	if ((req->ndiag_show & NDIAG_SHOW_GROUPS) &&
+	    sk_diag_dump_groups(sk, skb))
+		goto out_nlmsg_trim;
+
+	if ((req->ndiag_show & NDIAG_SHOW_MEMINFO) &&
+	    sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
+		goto out_nlmsg_trim;
+
+	return nlmsg_end(skb, nlh);
+
+out_nlmsg_trim:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+				int protocol, int s_num)
+{
+	struct netlink_table *tbl = &nl_table[protocol];
+	struct nl_portid_hash *hash = &tbl->hash;
+	struct net *net = sock_net(skb->sk);
+	struct netlink_diag_req *req;
+	struct sock *sk;
+	int ret = 0, num = 0, i;
+
+	req = nlmsg_data(cb->nlh);
+
+	for (i = 0; i <= hash->mask; i++) {
+		sk_for_each(sk, &hash->table[i]) {
+			if (!net_eq(sock_net(sk), net))
+				continue;
+			if (num < s_num) {
+				num++;
+				continue;
+			}
+
+			if (sk_diag_fill(sk, skb, req,
+					 NETLINK_CB(cb->skb).portid,
+					 cb->nlh->nlmsg_seq,
+					 NLM_F_MULTI,
+					 sock_i_ino(sk)) < 0) {
+				ret = 1;
+				goto done;
+			}
+
+			num++;
+		}
+	}
+
+	sk_for_each_bound(sk, &tbl->mc_list) {
+		if (sk_hashed(sk))
+			continue;
+		if (!net_eq(sock_net(sk), net))
+			continue;
+		if (num < s_num) {
+			num++;
+			continue;
+		}
+
+		if (sk_diag_fill(sk, skb, req,
+				 NETLINK_CB(cb->skb).portid,
+				 cb->nlh->nlmsg_seq,
+				 NLM_F_MULTI,
+				 sock_i_ino(sk)) < 0) {
+			ret = 1;
+			goto done;
+		}
+		num++;
+	}
+done:
+	cb->args[0] = num;
+	cb->args[1] = protocol;
+
+	return ret;
+}
+
+static int netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct netlink_diag_req *req;
+	int s_num = cb->args[0];
+
+	req = nlmsg_data(cb->nlh);
+
+	read_lock(&nl_table_lock);
+
+	if (req->sdiag_protocol == NDIAG_PROTO_ALL) {
+		int i;
+
+		for (i = cb->args[1]; i < MAX_LINKS; i++) {
+			if (__netlink_diag_dump(skb, cb, i, s_num))
+				break;
+			s_num = 0;
+		}
+	} else {
+		if (req->sdiag_protocol >= MAX_LINKS) {
+			read_unlock(&nl_table_lock);
+			return -ENOENT;
+		}
+
+		__netlink_diag_dump(skb, cb, req->sdiag_protocol, s_num);
+	}
+
+	read_unlock(&nl_table_lock);
+
+	return skb->len;
+}
+
+static int netlink_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+	int hdrlen = sizeof(struct netlink_diag_req);
+	struct net *net = sock_net(skb->sk);
+
+	if (nlmsg_len(h) < hdrlen)
+		return -EINVAL;
+
+	if (h->nlmsg_flags & NLM_F_DUMP) {
+		struct netlink_dump_control c = {
+			.dump = netlink_diag_dump,
+		};
+		return netlink_dump_start(net->diag_nlsk, skb, h, &c);
+	} else
+		return -EOPNOTSUPP;
+}
+
+static const struct sock_diag_handler netlink_diag_handler = {
+	.family = AF_NETLINK,
+	.dump = netlink_diag_handler_dump,
+};
+
+static int __init netlink_diag_init(void)
+{
+	return sock_diag_register(&netlink_diag_handler);
+}
+
+static void __exit netlink_diag_exit(void)
+{
+	sock_diag_unregister(&netlink_diag_handler);
+}
+
+module_init(netlink_diag_init);
+module_exit(netlink_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 16 /* AF_NETLINK */);
-- 
1.8.1.4

Re: [PATCH 2/2] netlink: Diag core and basic socket info dumping

[Pavel Emelyanov]

On 03/21/2013 01:21 PM, Andrey Vagin wrote:
> The netlink_diag can be built as a module, just like it's done in
> unix sockets.
> 
> The core dumping message carries the basic info about netlink sockets:
> family, type and protocol, portis, dst_group, dst_portid, state.
> 
> Groups can be received as an optional parameter NETLINK_DIAG_GROUPS.
> 
> Netlink sockets cab be filtered by protocols.
> 
> The socket inode number and cookie is reserved for future per-socket info
> retrieving. The per-protocol filtering is also reserved for future by
> requiring the sdiag_protocol to be zero.
> 
> The file /proc/net/netlink doesn't provide enough information for
> dumping netlink sockets. It doesn't provide dst_group, dst_portid,
> groups above 32.
> 
> Cc: "David S. Miller" <davem@davemloft.net>
> Cc: Eric Dumazet <edumazet@google.com>
> Cc: Pavel Emelyanov <xemul@parallels.com>
> Cc: Pablo Neira Ayuso <pablo@netfilter.org>
> Cc: "Eric W. Biederman" <ebiederm@xmission.com>
> Cc: Gao feng <gaofeng@cn.fujitsu.com>
> Signed-off-by: Andrey Vagin <avagin@openvz.org>

Acked-by: Pavel Emelyanov <xemul@parallels.com>

Re: [PATCH 2/2] netlink: Diag core and basic socket info dumping

[Thomas Graf]

On 03/21/13 at 01:21pm, Andrey Vagin wrote:
> diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
> new file mode 100644
> index 0000000..9328866
> --- /dev/null
> +++ b/include/uapi/linux/netlink_diag.h
> +enum {
> +	NETLINK_DIAG_MEMINFO,
> +	NETLINK_DIAG_GROUPS,
> +
> +	NETLINK_DIAG_MAX,
> +};

Please follow the common pattern and define NETLINK_DIAG_MAX as
NETLINK_DIAG_GROUPS like other by doing>

	[...] 
        __NETLINK_DIAG_MAX,
};
 
#define NETLINK_DIAG_MAX (__NETLINK_DIAG_MAX - 1)
 
Everyone is used to do:
 
        struct nlattr *attrs[NETLINK_DIAG_MAX+1];
         
        nla_parse([...], NETLINK_DIAG_MAX, [...]

In fact, the follow-up patch to ss is buggy because of this.
UNIX_DIAG_MAX suffers from the same problem which is problem the
cause for this.

Re: [PATCH 2/2] netlink: Diag core and basic socket info dumping

[Andrew Vagin]

On Thu, Mar 21, 2013 at 12:52:30PM +0000, Thomas Graf wrote:
> On 03/21/13 at 01:21pm, Andrey Vagin wrote:
> > diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
> > new file mode 100644
> > index 0000000..9328866
> > --- /dev/null
> > +++ b/include/uapi/linux/netlink_diag.h
> > +enum {
> > +	NETLINK_DIAG_MEMINFO,
> > +	NETLINK_DIAG_GROUPS,
> > +
> > +	NETLINK_DIAG_MAX,
> > +};
> 
> Please follow the common pattern and define NETLINK_DIAG_MAX as
> NETLINK_DIAG_GROUPS like other by doing>
> 
> 	[...] 
>         __NETLINK_DIAG_MAX,
> };
>  
> #define NETLINK_DIAG_MAX (__NETLINK_DIAG_MAX - 1)
>  
> Everyone is used to do:
>  
>         struct nlattr *attrs[NETLINK_DIAG_MAX+1];
>          
>         nla_parse([...], NETLINK_DIAG_MAX, [...]
> 

Thank you for this issue. I sent the separate patch
"[PATCH] net: fix *_DIAG_MAX constants", because currently only
INET_DIAG_MAX is correct.

> In fact, the follow-up patch to ss is buggy because of this.
> UNIX_DIAG_MAX suffers from the same problem which is problem the
> cause for this.

The code in ss looks like you described:
        struct rtattr *tb[UNIX_DIAG_MAX+1];
...
        parse_rtattr(tb, UNIX_DIAG_MAX, (struct rtattr*)(r+1),
                     nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));


        struct rtattr *tb[NETLINK_DIAG_MAX+1];
...
        parse_rtattr(tb, NETLINK_DIAG_MAX, (struct rtattr*)(r+1),
                     nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)))

I think I should only update headers... Or I don't understand something.

Re: [PATCH 2/2] netlink: Diag core and basic socket info dumping

[Thomas Graf]

On 03/21/13 at 06:31pm, Andrew Vagin wrote:
> The code in ss looks like you described:
>         struct rtattr *tb[UNIX_DIAG_MAX+1];
> ...
>         parse_rtattr(tb, UNIX_DIAG_MAX, (struct rtattr*)(r+1),
>                      nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
> 
> 
>         struct rtattr *tb[NETLINK_DIAG_MAX+1];
> ...
>         parse_rtattr(tb, NETLINK_DIAG_MAX, (struct rtattr*)(r+1),
>                      nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)))
> 
> I think I should only update headers... Or I don't understand something.

Right, fixing the headers will resolve the issue.

[PATCH 0/4] ss: Get netlink sockets info via sock-diag

[Andrey Vagin]

Cc: Stephen Hemminger <stephen@networkplumber.org>

Andrey Vagin (4):
  ss: handle socket diag request in a separate function
  ss: create a frunction to print info about netlink sockets
  ss: show destination address for netlink sockets
  ss: Get netlink sockets info via sock-diag

 include/linux/netlink_diag.h |  40 ++++++++
 misc/ss.c                    | 235 +++++++++++++++++++++++++++++--------------
 2 files changed, 198 insertions(+), 77 deletions(-)
 create mode 100644 include/linux/netlink_diag.h

-- 
1.7.11.7

[PATCH 1/4] ss: handle socket diag request in a separate function

[Andrey Vagin]

It will be reused to show netlink sockets

Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 misc/ss.c | 49 +++++++++++++++++++++++++++++--------------------
 1 file changed, 29 insertions(+), 20 deletions(-)

diff --git a/misc/ss.c b/misc/ss.c
index da9d32c..bde344a 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -2206,31 +2206,17 @@ static int unix_show_sock(struct nlmsghdr *nlh, struct filter *f)
 	return 0;
 }
 
-static int unix_show_netlink(struct filter *f, FILE *dump_fp)
+static int handle_netlink_request(struct filter *f, FILE *dump_fp,
+				  struct nlmsghdr *req, size_t size,
+				  int (* show_one_sock)(struct nlmsghdr *nlh, struct filter *f))
 {
 	int fd;
-	struct {
-		struct nlmsghdr nlh;
-		struct unix_diag_req r;
-	} req;
 	char	buf[8192];
 
 	if ((fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_INET_DIAG)) < 0)
 		return -1;
 
-	memset(&req, 0, sizeof(req));
-	req.nlh.nlmsg_len = sizeof(req);
-	req.nlh.nlmsg_type = SOCK_DIAG_BY_FAMILY;
-	req.nlh.nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
-	req.nlh.nlmsg_seq = 123456;
-
-	req.r.sdiag_family = AF_UNIX;
-	req.r.udiag_states = f->states;
-	req.r.udiag_show = UDIAG_SHOW_NAME | UDIAG_SHOW_PEER | UDIAG_SHOW_RQLEN;
-	if (show_mem)
-		req.r.udiag_show |= UDIAG_SHOW_MEMINFO;
-
-	if (send(fd, &req, sizeof(req), 0) < 0) {
+	if (send(fd, req, size, 0) < 0) {
 		close(fd);
 		return -1;
 	}
@@ -2275,13 +2261,13 @@ static int unix_show_netlink(struct filter *f, FILE *dump_fp)
 				} else {
 					errno = -err->error;
 					if (errno != ENOENT)
-						fprintf(stderr, "UDIAG answers %d\n", errno);
+						fprintf(stderr, "DIAG answers %d\n", errno);
 				}
 				close(fd);
 				return -1;
 			}
 			if (!dump_fp) {
-				err = unix_show_sock(h, f);
+				err = show_one_sock(h, f);
 				if (err < 0) {
 					close(fd);
 					return err;
@@ -2303,6 +2289,29 @@ close_it:
 	return 0;
 }
 
+static int unix_show_netlink(struct filter *f, FILE *dump_fp)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct unix_diag_req r;
+	} req;
+
+	memset(&req, 0, sizeof(req));
+	req.nlh.nlmsg_len = sizeof(req);
+	req.nlh.nlmsg_type = SOCK_DIAG_BY_FAMILY;
+	req.nlh.nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
+	req.nlh.nlmsg_seq = 123456;
+
+	req.r.sdiag_family = AF_UNIX;
+	req.r.udiag_states = f->states;
+	req.r.udiag_show = UDIAG_SHOW_NAME | UDIAG_SHOW_PEER | UDIAG_SHOW_RQLEN;
+	if (show_mem)
+		req.r.udiag_show |= UDIAG_SHOW_MEMINFO;
+
+	return handle_netlink_request(f, dump_fp, &req.nlh,
+					sizeof(req), unix_show_sock);
+}
+
 static int unix_show(struct filter *f)
 {
 	FILE *fp;
-- 
1.7.11.7

[PATCH 2/4] ss: create a function to print info about netlink sockets

[Andrey Vagin]

It will be reused for printing info about netlink sockets, when
socket diag is used for retrieving information.

Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 misc/ss.c | 130 ++++++++++++++++++++++++++++++++++----------------------------
 1 file changed, 72 insertions(+), 58 deletions(-)

diff --git a/misc/ss.c b/misc/ss.c
index bde344a..962f304 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -2474,6 +2474,73 @@ static int packet_show(struct filter *f)
 	return 0;
 }
 
+static void netlink_show_one(struct filter *f,
+				int prot, int pid, unsigned groups,
+				int rq, int wq,
+				unsigned long long sk, unsigned long long cb)
+{
+	if (f->f) {
+		struct tcpstat tst;
+		tst.local.family = AF_NETLINK;
+		tst.remote.family = AF_NETLINK;
+		tst.rport = -1;
+		tst.lport = pid;
+		tst.local.data[0] = prot;
+		tst.remote.data[0] = 0;
+		if (run_ssfilter(f->f, &tst) == 0)
+			return;
+	}
+
+	if (netid_width)
+		printf("%-*s ", netid_width, "nl");
+	if (state_width)
+		printf("%-*s ", state_width, "UNCONN");
+	printf("%-6d %-6d ", rq, wq);
+	if (resolve_services && prot == 0)
+		printf("%*s:", addr_width, "rtnl");
+	else if (resolve_services && prot == 3)
+		printf("%*s:", addr_width, "fw");
+	else if (resolve_services && prot == 4)
+		printf("%*s:", addr_width, "tcpdiag");
+	else
+		printf("%*d:", addr_width, prot);
+	if (pid == -1) {
+		printf("%-*s ", serv_width, "*");
+	} else if (resolve_services) {
+		int done = 0;
+		if (!pid) {
+			done = 1;
+			printf("%-*s ", serv_width, "kernel");
+		} else if (pid > 0) {
+			char procname[64];
+			FILE *fp;
+			sprintf(procname, "%s/%d/stat",
+				getenv("PROC_ROOT") ? : "/proc", pid);
+			if ((fp = fopen(procname, "r")) != NULL) {
+				if (fscanf(fp, "%*d (%[^)])", procname) == 1) {
+					sprintf(procname+strlen(procname), "/%d", pid);
+					printf("%-*s ", serv_width, procname);
+					done = 1;
+				}
+				fclose(fp);
+			}
+		}
+		if (!done)
+			printf("%-*d ", serv_width, pid);
+	} else {
+		printf("%-*d ", serv_width, pid);
+	}
+	printf("%*s*%-*s",
+	       addr_width, "", serv_width, "");
+
+	if (show_details) {
+		printf(" sk=%llx cb=%llx groups=0x%08x", sk, cb, groups);
+	}
+	printf("\n");
+
+	return;
+}
+
 static int netlink_show(struct filter *f)
 {
 	FILE *fp;
@@ -2486,6 +2553,10 @@ static int netlink_show(struct filter *f)
 	if (!(f->states & (1<<SS_CLOSE)))
 		return 0;
 
+	if (!getenv("PROC_NET_NETLINK") && !getenv("PROC_ROOT") &&
+		netlink_show_netlink(f, NULL) == 0)
+		return 0;
+
 	if ((fp = net_netlink_open()) == NULL)
 		return -1;
 	fgets(buf, sizeof(buf)-1, fp);
@@ -2495,64 +2566,7 @@ static int netlink_show(struct filter *f)
 		       &sk,
 		       &prot, &pid, &groups, &rq, &wq, &cb, &rc);
 
-		if (f->f) {
-			struct tcpstat tst;
-			tst.local.family = AF_NETLINK;
-			tst.remote.family = AF_NETLINK;
-			tst.rport = -1;
-			tst.lport = pid;
-			tst.local.data[0] = prot;
-			tst.remote.data[0] = 0;
-			if (run_ssfilter(f->f, &tst) == 0)
-				continue;
-		}
-
-		if (netid_width)
-			printf("%-*s ", netid_width, "nl");
-		if (state_width)
-			printf("%-*s ", state_width, "UNCONN");
-		printf("%-6d %-6d ", rq, wq);
-		if (resolve_services && prot == 0)
-			printf("%*s:", addr_width, "rtnl");
-		else if (resolve_services && prot == 3)
-			printf("%*s:", addr_width, "fw");
-		else if (resolve_services && prot == 4)
-			printf("%*s:", addr_width, "tcpdiag");
-		else
-			printf("%*d:", addr_width, prot);
-		if (pid == -1) {
-			printf("%-*s ", serv_width, "*");
-		} else if (resolve_services) {
-			int done = 0;
-			if (!pid) {
-				done = 1;
-				printf("%-*s ", serv_width, "kernel");
-			} else if (pid > 0) {
-				char procname[64];
-				FILE *fp;
-				sprintf(procname, "%s/%d/stat",
-					getenv("PROC_ROOT") ? : "/proc", pid);
-				if ((fp = fopen(procname, "r")) != NULL) {
-					if (fscanf(fp, "%*d (%[^)])", procname) == 1) {
-						sprintf(procname+strlen(procname), "/%d", pid);
-						printf("%-*s ", serv_width, procname);
-						done = 1;
-					}
-					fclose(fp);
-				}
-			}
-			if (!done)
-				printf("%-*d ", serv_width, pid);
-		} else {
-			printf("%-*d ", serv_width, pid);
-		}
-		printf("%*s*%-*s",
-		       addr_width, "", serv_width, "");
-
-		if (show_details) {
-			printf(" sk=%llx cb=%llx groups=0x%08x", sk, cb, groups);
-		}
-		printf("\n");
+		netlink_show_one(f, prot, pid, groups, rq, wq, sk, cb);
 	}
 
 	return 0;
-- 
1.7.11.7

[PATCH 3/4] ss: show destination address for netlink sockets

[Andrey Vagin]

A netlink socket may be connected to a specific group.

Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 misc/ss.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/misc/ss.c b/misc/ss.c
index 962f304..1af677a 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -2476,6 +2476,7 @@ static int packet_show(struct filter *f)
 
 static void netlink_show_one(struct filter *f,
 				int prot, int pid, unsigned groups,
+				int state, int dst_pid, unsigned dst_group,
 				int rq, int wq,
 				unsigned long long sk, unsigned long long cb)
 {
@@ -2530,8 +2531,14 @@ static void netlink_show_one(struct filter *f,
 	} else {
 		printf("%-*d ", serv_width, pid);
 	}
-	printf("%*s*%-*s",
-	       addr_width, "", serv_width, "");
+
+	if (state == NETLINK_CONNECTED) {
+		printf("%*d:%-*d",
+		       addr_width, dst_group, serv_width, dst_pid);
+	} else {
+		printf("%*s*%-*s",
+		       addr_width, "", serv_width, "");
+	}
 
 	if (show_details) {
 		printf(" sk=%llx cb=%llx groups=0x%08x", sk, cb, groups);
@@ -2566,7 +2573,7 @@ static int netlink_show(struct filter *f)
 		       &sk,
 		       &prot, &pid, &groups, &rq, &wq, &cb, &rc);
 
-		netlink_show_one(f, prot, pid, groups, rq, wq, sk, cb);
+		netlink_show_one(f, prot, pid, groups, TCP_CLOSE, 0, 0, rq, wq, sk, cb);
 	}
 
 	return 0;
-- 
1.7.11.7

[PATCH 4/4] ss: Get netlink sockets info via sock-diag

[Andrey Vagin]

Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 include/linux/netlink_diag.h | 40 +++++++++++++++++++++++++++++++
 misc/ss.c                    | 56 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 96 insertions(+)
 create mode 100644 include/linux/netlink_diag.h

diff --git a/include/linux/netlink_diag.h b/include/linux/netlink_diag.h
new file mode 100644
index 0000000..9328866
--- /dev/null
+++ b/include/linux/netlink_diag.h
@@ -0,0 +1,40 @@
+#ifndef __NETLINK_DIAG_H__
+#define __NETLINK_DIAG_H__
+
+#include <linux/types.h>
+
+struct netlink_diag_req {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+	__u16	pad;
+	__u32	ndiag_ino;
+	__u32	ndiag_show;
+	__u32	ndiag_cookie[2];
+};
+
+struct netlink_diag_msg {
+	__u8	ndiag_family;
+	__u8	ndiag_type;
+	__u8	ndiag_protocol;
+	__u8	ndiag_state;
+
+	__u32	ndiag_portid;
+	__u32	ndiag_dst_portid;
+	__u32	ndiag_dst_group;
+	__u32	ndiag_ino;
+	__u32	ndiag_cookie[2];
+};
+
+enum {
+	NETLINK_DIAG_MEMINFO,
+	NETLINK_DIAG_GROUPS,
+
+	NETLINK_DIAG_MAX,
+};
+
+#define NDIAG_PROTO_ALL		((__u8) ~0)
+
+#define NDIAG_SHOW_MEMINFO	0x00000001 /* show memory info of a socket */
+#define NDIAG_SHOW_GROUPS	0x00000002 /* show groups of a netlink socket */
+
+#endif
diff --git a/misc/ss.c b/misc/ss.c
index 1af677a..49312f1 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -36,6 +36,7 @@
 #include <linux/sock_diag.h>
 #include <linux/inet_diag.h>
 #include <linux/unix_diag.h>
+#include <linux/netlink_diag.h>
 
 int resolve_hosts = 0;
 int resolve_services = 1;
@@ -2548,6 +2549,61 @@ static void netlink_show_one(struct filter *f,
 	return;
 }
 
+static int netlink_show_sock(struct nlmsghdr *nlh, struct filter *f)
+{
+	struct netlink_diag_msg *r = NLMSG_DATA(nlh);
+	struct rtattr *tb[NETLINK_DIAG_MAX+1];
+	int rq = 0, wq = 0;
+	unsigned long groups = 0;
+
+	parse_rtattr(tb, NETLINK_DIAG_MAX, (struct rtattr*)(r+1),
+		     nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+
+	if (tb[NETLINK_DIAG_GROUPS] && RTA_PAYLOAD(tb[NETLINK_DIAG_GROUPS]))
+		groups = *(unsigned long *) RTA_DATA(tb[NETLINK_DIAG_GROUPS]);
+
+	if (tb[NETLINK_DIAG_MEMINFO]) {
+		const __u32 *skmeminfo;
+		skmeminfo = RTA_DATA(tb[NETLINK_DIAG_MEMINFO]);
+
+		rq = skmeminfo[SK_MEMINFO_RMEM_ALLOC];
+		wq = skmeminfo[SK_MEMINFO_WMEM_ALLOC];
+	}
+
+	netlink_show_one(f, r->ndiag_protocol, r->ndiag_portid, groups,
+			 r->ndiag_state, r->ndiag_dst_portid, r->ndiag_dst_group,
+			 rq, wq, 0, 0);
+
+	if (show_mem) {
+		printf("\t");
+		print_skmeminfo(tb, NETLINK_DIAG_MEMINFO);
+		printf("\n");
+	}
+
+	return 0;
+}
+
+static int netlink_show_netlink(struct filter *f, FILE *dump_fp)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct netlink_diag_req r;
+	} req;
+
+	memset(&req, 0, sizeof(req));
+	req.nlh.nlmsg_len = sizeof(req);
+	req.nlh.nlmsg_type = SOCK_DIAG_BY_FAMILY;
+	req.nlh.nlmsg_flags = NLM_F_ROOT|NLM_F_MATCH|NLM_F_REQUEST;
+	req.nlh.nlmsg_seq = 123456;
+
+	req.r.sdiag_family = AF_NETLINK;
+	req.r.sdiag_protocol = NDIAG_PROTO_ALL;
+	req.r.ndiag_show = NDIAG_SHOW_GROUPS | NDIAG_SHOW_MEMINFO;
+
+	return handle_netlink_request(f, dump_fp, &req.nlh,
+					sizeof(req), netlink_show_sock);
+}
+
 static int netlink_show(struct filter *f)
 {
 	FILE *fp;
-- 
1.7.11.7

Re: [PATCH 0/4] ss: Get netlink sockets info via sock-diag

[Stephen Hemminger]

On Thu, 21 Mar 2013 13:33:22 +0400
Andrey Vagin <avagin@openvz.org> wrote:

> Cc: Stephen Hemminger <stephen@networkplumber.org>
> 
> Andrey Vagin (4):
>   ss: handle socket diag request in a separate function
>   ss: create a frunction to print info about netlink sockets
>   ss: show destination address for netlink sockets
>   ss: Get netlink sockets info via sock-diag
> 
>  include/linux/netlink_diag.h |  40 ++++++++
>  misc/ss.c                    | 235 +++++++++++++++++++++++++++++--------------
>  2 files changed, 198 insertions(+), 77 deletions(-)
>  create mode 100644 include/linux/netlink_diag.h
> 

Since this depends on functionality not in the upstream kernel.
Resubmit this during the 3.10 merge window. At the start of the merge
window, headers are synchronized with the kernel headers.

[PATCH 0/4] ss: Get netlink sockets info via sock-diag (v2)

[Andrey Vagin]

On Thu, Mar 21, 2013 at 10:00:25AM -0700, Stephen Hemminger wrote:
> Since this depends on functionality not in the upstream kernel.
> Resubmit this during the 3.10 merge window. At the start of the merge
> window, headers are synchronized with the kernel headers.

Netlink socket diag is in the upstream kernel since 3.10-rc1.

v2: Update kernel headers

Andrey Vagin (4):
  ss: handle socket diag request in a separate function
  ss: create a function to print info about netlink sockets
  ss: show destination address for netlink sockets
  ss: Get netlink sockets info via sock-diag (v2)

 include/linux/netlink_diag.h |  52 ++++++++++
 misc/ss.c                    | 242 +++++++++++++++++++++++++++++--------------
 2 files changed, 216 insertions(+), 78 deletions(-)
 create mode 100644 include/linux/netlink_diag.h

-- 
1.8.2

[PATCH 3/4] ss: show destination address for netlink sockets

[Andrey Vagin]

A netlink socket may be connected to a specific group.

Cc: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Andrey Vagin <avagin@openvz.org>
---
 misc/ss.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/misc/ss.c b/misc/ss.c
index 469ffd0..c8534ff 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -2674,6 +2674,7 @@ static int packet_show(struct filter *f)
 
 static void netlink_show_one(struct filter *f,
 				int prot, int pid, unsigned groups,
+				int state, int dst_pid, unsigned dst_group,
 				int rq, int wq,
 				unsigned long long sk, unsigned long long cb)
 {
@@ -2728,8 +2729,14 @@ static void netlink_show_one(struct filter *f,
 	} else {
 		printf("%-*d ", serv_width, pid);
 	}
-	printf("%*s*%-*s",
-	       addr_width, "", serv_width, "");
+
+	if (state == NETLINK_CONNECTED) {
+		printf("%*d:%-*d",
+		       addr_width, dst_group, serv_width, dst_pid);
+	} else {
+		printf("%*s*%-*s",
+		       addr_width, "", serv_width, "");
+	}
 
 	if (show_details) {
 		printf(" sk=%llx cb=%llx groups=0x%08x", sk, cb, groups);
@@ -2764,7 +2771,7 @@ static int netlink_show(struct filter *f)
 		       &sk,
 		       &prot, &pid, &groups, &rq, &wq, &cb, &rc);
 
-		netlink_show_one(f, prot, pid, groups, rq, wq, sk, cb);
+		netlink_show_one(f, prot, pid, groups, 0, 0, 0, rq, wq, sk, cb);
 	}
 
 	return 0;
-- 
1.8.1.4