cls_cgroup: Store classid in struct sock

Up until now cls_cgroup has relied on fetching the classid out of
the current executing thread.  This runs into trouble when a packet
processing is delayed in which case it may execute out of another
thread's context.

Furthermore, even when a packet is not delayed we may fail to
classify it if soft IRQs have been disabled, because this scenario
is indistinguishable from one where a packet unrelated to the
current thread is processed by a real soft IRQ.

In fact, the current semantics is inherently broken, as a single
skb may be constructed out of the writes of two different tasks.
A different manifestation of this problem is when the TCP stack
transmits in response of an incoming ACK.  This is currently
unclassified.

As we already have a concept of packet ownership for accounting
purposes in the skb->sk pointer, this is a natural place to store
the classid in a persistent manner.

This patch adds the cls_cgroup classid in struct sock, filling up
an existing hole on 64-bit :)

The value is set at socket creation time.  So all sockets created
via socket(2) automatically gains the ID of the thread creating it.
Whenever another process touches the socket by either reading or
writing to it, we will change the socket classid to that of the
process if it has a valid (non-zero) classid.

For sockets created on inbound connections through accept(2), we
inherit the classid of the original listening socket through
sk_clone, possibly preceding the actual accept(2) call.

In order to minimise risks, I have not made this the authoritative
classid.  For now it is only used as a backup when we execute
with soft IRQs disabled.  Once we're completely happy with its
semantics we can use it as the sole classid.

Footnote: I have rearranged the error path on cls_group module
creation.  If we didn't do this, then there is a window where
someone could create a tc rule using cls_group before the cgroup
subsystem has been registered.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 61 insertions, 16 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index bf88a167c8f2..a05ae7f9771e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -123,6 +123,7 @@
 #include <linux/net_tstamp.h>
 #include <net/xfrm.h>
 #include <linux/ipsec.h>
+#include <net/cls_cgroup.h>
 
 #include <linux/filter.h>
 
@@ -217,6 +218,11 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
+#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
+int net_cls_subsys_id = -1;
+EXPORT_SYMBOL_GPL(net_cls_subsys_id);
+#endif
+
 static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
 {
 	struct timeval tv;
@@ -1050,6 +1056,16 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
 	module_put(owner);
 }
 
+#ifdef CONFIG_CGROUPS
+void sock_update_classid(struct sock *sk)
+{
+	u32 classid = task_cls_classid(current);
+
+	if (classid && classid != sk->sk_classid)
+		sk->sk_classid = classid;
+}
+#endif
+
 /**
  *	sk_alloc - All socket objects are allocated here
  *	@net: the applicable net namespace
@@ -1073,6 +1089,8 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		sock_lock_init(sk);
 		sock_net_set(sk, get_net(net));
 		atomic_set(&sk->sk_wmem_alloc, 1);
+
+		sock_update_classid(sk);
 	}
 
 	return sk;
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 221180384fd7..78ef2c5e130b 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -16,14 +16,11 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <linux/cgroup.h>
+#include <linux/rcupdate.h>
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
-
-struct cgroup_cls_state
-{
-	struct cgroup_subsys_state css;
-	u32 classid;
-};
+#include <net/sock.h>
+#include <net/cls_cgroup.h>
 
 static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
 					       struct cgroup *cgrp);
@@ -112,6 +109,10 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
 	struct cls_cgroup_head *head = tp->root;
 	u32 classid;
 
+	rcu_read_lock();
+	classid = task_cls_state(current)->classid;
+	rcu_read_unlock();
+
 	/*
 	 * Due to the nature of the classifier it is required to ignore all
 	 * packets originating from softirq context as accessing `current'
@@ -122,12 +123,12 @@ static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp,
 	 * calls by looking at the number of nested bh disable calls because
 	 * softirqs always disables bh.
 	 */
-	if (softirq_count() != SOFTIRQ_OFFSET)
-		return -1;
-
-	rcu_read_lock();
-	classid = task_cls_state(current)->classid;
-	rcu_read_unlock();
+	if (softirq_count() != SOFTIRQ_OFFSET) {
+		/* If there is an sk_classid we'll use that. */
+		if (!skb->sk)
+			return -1;
+		classid = skb->sk->sk_classid;
+	}
 
 	if (!classid)
 		return -1;
@@ -289,18 +290,35 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
 
 static int __init init_cgroup_cls(void)
 {
-	int ret = register_tcf_proto_ops(&cls_cgroup_ops);
-	if (ret)
-		return ret;
+	int ret;
+
 	ret = cgroup_load_subsys(&net_cls_subsys);
 	if (ret)
-		unregister_tcf_proto_ops(&cls_cgroup_ops);
+		goto out;
+
+#ifndef CONFIG_NET_CLS_CGROUP
+	/* We can't use rcu_assign_pointer because this is an int. */
+	smp_wmb();
+	net_cls_subsys_id = net_cls_subsys.subsys_id;
+#endif
+
+	ret = register_tcf_proto_ops(&cls_cgroup_ops);
+	if (ret)
+		cgroup_unload_subsys(&net_cls_subsys);
+
+out:
 	return ret;
 }
 
 static void __exit exit_cgroup_cls(void)
 {
 	unregister_tcf_proto_ops(&cls_cgroup_ops);
+
+#ifndef CONFIG_NET_CLS_CGROUP
+	net_cls_subsys_id = -1;
+	synchronize_rcu();
+#endif
+
 	cgroup_unload_subsys(&net_cls_subsys);
 }
 
diff --git a/net/socket.c b/net/socket.c
index f9f7d0872cac..367d5477d00f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -94,6 +94,7 @@
 
 #include <net/compat.h>
 #include <net/wext.h>
+#include <net/cls_cgroup.h>
 
 #include <net/sock.h>
 #include <linux/netfilter.h>
@@ -558,6 +559,8 @@ static inline int __sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	struct sock_iocb *si = kiocb_to_siocb(iocb);
 	int err;
 
+	sock_update_classid(sock->sk);
+
 	si->sock = sock;
 	si->scm = NULL;
 	si->msg = msg;
@@ -684,6 +687,8 @@ static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
 {
 	struct sock_iocb *si = kiocb_to_siocb(iocb);
 
+	sock_update_classid(sock->sk);
+
 	si->sock = sock;
 	si->scm = NULL;
 	si->msg = msg;
@@ -777,6 +782,8 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	if (unlikely(!sock->ops->splice_read))
 		return -EINVAL;
 
+	sock_update_classid(sock->sk);
+
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
 
@@ -3069,6 +3076,8 @@ int kernel_setsockopt(struct socket *sock, int level, int optname,
 int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 		    size_t size, int flags)
 {
+	sock_update_classid(sock->sk);
+
 	if (sock->ops->sendpage)
 		return sock->ops->sendpage(sock, page, offset, size, flags);