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>

2 files changed, 72 insertions, 1 deletions

diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
new file mode 100644
index 000000000000..ef2df1475b51
--- /dev/null
+++ b/include/net/cls_cgroup.h
@@ -0,0 +1,63 @@
+/*
+ * cls_cgroup.h                 Control Group Classifier
+ *
+ * Authors:     Thomas Graf <tgraf@suug.ch>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _NET_CLS_CGROUP_H
+#define _NET_CLS_CGROUP_H
+
+#include <linux/cgroup.h>
+#include <linux/hardirq.h>
+#include <linux/rcupdate.h>
+
+#ifdef CONFIG_CGROUPS
+struct cgroup_cls_state
+{
+        struct cgroup_subsys_state css;
+        u32 classid;
+};
+
+#ifdef CONFIG_NET_CLS_CGROUP
+static inline u32 task_cls_classid(struct task_struct *p)
+{
+        if (in_interrupt())
+                return 0;
+
+        return container_of(task_subsys_state(p, net_cls_subsys_id),
+                            struct cgroup_cls_state, css).classid;
+}
+#else
+extern int net_cls_subsys_id;
+
+static inline u32 task_cls_classid(struct task_struct *p)
+{
+        int id;
+        u32 classid;
+
+        if (in_interrupt())
+                return 0;
+
+        rcu_read_lock();
+        id = rcu_dereference(net_cls_subsys_id);
+        if (id >= 0)
+                classid = container_of(task_subsys_state(p, id),
+                                       struct cgroup_cls_state, css)->classid;
+        rcu_read_unlock();
+
+        return classid;
+}
+#endif
+#else
+static inline u32 task_cls_classid(struct task_struct *p)
+{
+        return 0;
+}
+#endif
+#endif  /* _NET_CLS_CGROUP_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 5697caf8cc76..d24f382cb712 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -312,7 +312,7 @@ struct sock {
         void                    *sk_security;
 #endif
         __u32                   sk_mark;
-        /* XXX 4 bytes hole on 64 bit */
+        u32                     sk_classid;
         void                    (*sk_state_change)(struct sock *sk);
         void                    (*sk_data_ready)(struct sock *sk, int bytes);
         void                    (*sk_write_space)(struct sock *sk);
@@ -1074,6 +1074,14 @@ extern void *sock_kmalloc(struct sock *sk, int size,
 extern void sock_kfree_s(struct sock *sk, void *mem, int size);
 extern void sk_send_sigurg(struct sock *sk);
 
+#ifdef CONFIG_CGROUPS
+extern void sock_update_classid(struct sock *sk);
+#else
+static inline void sock_update_classid(struct sock *sk)
+{
+}
+#endif
+
 /*
  * Functions to fill in entries in struct proto_ops when a protocol
  * does not implement a particular function.