netdev - [PATCH 1/3] netlink: allow to set peeking offset for sockets

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:	Sun, 12 Jun 2016 23:07:19 -0700
From:	Andrey Vagin <avagin@...nvz.org>
To:	netdev@...r.kernel.org
Cc:	criu@...nvz.org, Andrey Vagin <avagin@...nvz.org>,
	Pavel Emelyanov <xemul@...tuozzo.com>,
	"David S. Miller" <davem@...emloft.net>,
	Ken-ichirou MATSUZAWA <chamaken@...il.com>,
	Daniel Borkmann <daniel@...earbox.net>,
	Florian Westphal <fw@...len.de>,
	Herbert Xu <herbert@...dor.apana.org.au>,
	David Herrmann <dh.herrmann@...il.com>,
	Christophe Ricard <christophe.ricard@...il.com>
Subject: [PATCH 1/3] netlink: allow to set peeking offset for sockets

This allows us to read socket's queue without removing skbs from it.

The same logic was implemented for unix and inet sockets and we use this
to dump and restore sockets in CRIU.

Here is a question whether sk_peek_off has to be protected by locks.
Currently it isn't protected and an user who uses sk_peek_off has to be
sure that nobody calls recvmsg for a socket except him.

Signed-off-by: Andrey Vagin <avagin@...nvz.org>
---
 net/netlink/af_netlink.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 627f898..d334ffc 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1796,17 +1796,18 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
-	int noblock = flags&MSG_DONTWAIT;
 	size_t copied;
 	struct sk_buff *skb, *data_skb;
+	int peeked, skip;
 	int err, ret;
 
 	if (flags&MSG_OOB)
 		return -EOPNOTSUPP;
 
 	copied = 0;
+	skip = sk_peek_offset(sk, flags);
 
-	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	skb = __skb_recv_datagram(sk, flags, &peeked, &skip, &err);
 	if (skb == NULL)
 		goto out;
 
@@ -1834,14 +1835,20 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
 				     16384);
 
-	copied = data_skb->len;
+	copied = data_skb->len - skip;
 	if (len < copied) {
 		msg->msg_flags |= MSG_TRUNC;
 		copied = len;
 	}
 
 	skb_reset_transport_header(data_skb);
-	err = skb_copy_datagram_msg(data_skb, 0, msg, copied);
+	err = skb_copy_datagram_msg(data_skb, skip, msg, copied);
+
+	if (flags & MSG_PEEK)
+		sk_peek_offset_fwd(sk, copied);
+	else
+		sk_peek_offset_bwd(sk, skb->len);
+
 
 	if (msg->msg_name) {
 		DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
@@ -1860,7 +1867,7 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	memset(&scm, 0, sizeof(scm));
 	scm.creds = *NETLINK_CREDS(skb);
 	if (flags & MSG_TRUNC)
-		copied = data_skb->len;
+		copied = data_skb->len - skip;
 
 	skb_free_datagram(sk, skb);
 
@@ -2496,6 +2503,13 @@ int netlink_unregister_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(netlink_unregister_notifier);
 
+static int netlink_set_peek_off(struct sock *sk, int val)
+{
+	sk->sk_peek_off = val;
+
+	return 0;
+}
+
 static const struct proto_ops netlink_ops = {
 	.family =	PF_NETLINK,
 	.owner =	THIS_MODULE,
@@ -2515,6 +2529,7 @@ static const struct proto_ops netlink_ops = {
 	.recvmsg =	netlink_recvmsg,
 	.mmap =		sock_no_mmap,
 	.sendpage =	sock_no_sendpage,
+	.set_peek_off = netlink_set_peek_off,
 };
 
 static const struct net_proto_family netlink_family_ops = {
-- 
2.5.5