summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorHerbert Xu <herbert@gondor.apana.org.au>2010-05-24 00:12:34 -0700
committerDavid S. Miller <davem@davemloft.net>2010-05-24 00:12:34 -0700
commitf845172531fb7410c7fb7780b1a6e51ee6df7d52 (patch)
treeef1030d0ad9d9dbc8fe800a145c587f04be50ade /net/core
parenteda6e6f86b5f95b982ac7ebf7cf5be2a29a291e9 (diff)
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>
Diffstat (limited to 'net/core')
-rw-r--r--net/core/sock.c18
1 files changed, 18 insertions, 0 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;