cgroup: net_cls: traffic counter based on classification control cgroup

Hello

I'm sorry for previous email with attachments.

I would like to represent next version of patch I sent before
cgroup: "net_cls: traffic counter based on classification control cgroup"

The main idea is the same as was. It keeping counter in control groups, but now uses atomic instead resource_counters.

I have a performance measurement for this patch. It was done by lmbench on physical machine. Results are not so representative for 20 tests and some numbers are real weird.

Daniel Wagner wrote what he is doing something similar, but using namespaces.

Proposed by me approach is used in upcoming Tizen release, but little bit different version.

---
 include/net/cls_cgroup.h         |  200 
++++++++++++++++++++++++++++++++++----
 include/net/cls_counter_holder.h |   26 +++++
 init/Kconfig                     |   25 +++++
 kernel/cgroup.c                  |    2 +
 kernel/res_counter.c             |    4 +
 net/core/dev.c                   |    6 ++
 net/ipv4/tcp.c                   |   29 +++++-
 net/ipv4/udp.c                   |    6 ++
 net/sched/Kconfig                |   11 ---
 net/sched/Makefile               |    1 +
 net/sched/cls_cgroup.c           |  193 
+++++++++++++++++++++++++++++++++++-
 net/sched/cls_counter_holder.c   |  144 +++++++++++++++++++++++++++
 12 files changed, 612 insertions(+), 35 deletions(-)
 create mode 100644 include/net/cls_counter_holder.h
 create mode 100644 net/sched/cls_counter_holder.c

index 2581638..304786d 100644
@@ -13,54 +13,197 @@
 #ifndef _NET_CLS_CGROUP_H
 #define _NET_CLS_CGROUP_H
 
+#include <linux/atomic.h>
 #include <linux/cgroup.h>
 #include <linux/hardirq.h>
 #include <linux/rcupdate.h>
 
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+#include <linux/nsproxy.h>
+#include <linux/string.h>
+#include <linux/skbuff.h>
+#include <net/cls_counter_holder.h>
+#include <net/sock.h>
+
+/*TODO hide all it to separate file*/
+
+struct cls_iface_cntrs {
+    char *dev_name;
+    atomic64_t snd_counter;
+    atomic64_t rcv_counter;
+    struct list_head link;
+};
+
+#endif /*CONFIG_NET_CLS_COUNTER*/
+
+
 #if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
 struct cgroup_cls_state
 {
     struct cgroup_subsys_state css;
     u32 classid;
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+    struct cls_iface_cntrs iface_stats;
+#endif /*CONFIG_NET_CLS_COUNTER*/
 };
 
 extern void sock_update_classid(struct sock *sk, struct task_struct 

*task);

-#if IS_BUILTIN(CONFIG_NET_CLS_CGROUP)
-static inline u32 task_cls_classid(struct task_struct *p)
+#if IS_MODULE(CONFIG_NET_CLS_CGROUP)
+static inline struct cgroup_cls_state *get_cls_cgroup(struct task_struct *p)
{
- u32 classid;
+ struct cgroup_subsys_state *css = task_subsys_state(p,
+ net_cls_subsys_id);
+ if (css)
+ return container_of(css,
+ struct cgroup_cls_state, css);
+ return NULL;
+}
+#elif IS_BUILTIN(CONFIG_NET_CLS_CGROUP)
+static inline struct cgroup_cls_state *get_cls_cgroup(struct task_struct *p) +{
+ return container_of(task_subsys_state(p, net_cls_subsys_id),
+ struct cgroup_cls_state, css);
+}
+#endif

- if (in_interrupt())
- return 0;

- rcu_read_lock();
- classid = container_of(task_subsys_state(p, net_cls_subsys_id),
- struct cgroup_cls_state, css)->classid;
- rcu_read_unlock();
+#endif /*CONFIG_NET_CLS_CGROUP*/

- return classid;
+#if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+static inline u32 skb_cls_classid(const struct sk_buff *skb) +{
+ return (skb && skb->sk) ? skb->sk->sk_classid : 0;
+}
+
+static inline int get_ifindex_from_skb(const struct sk_buff *skb) +{
+ int ifindex = 0;
+ if (skb)
+ ifindex = skb->skb_iif;
+ return ifindex;
+}
+
+static struct cls_iface_cntrs *find_cls_counter(

+    struct cgroup_cls_state *cls_cgroup,
+    const char *dev_name,
+    bool create)

+{
+ /*TODO Add lock*/
+ struct cls_iface_cntrs *entry = NULL;
+
+ if (!dev_name) {
+ pr_err("cls please provide valid dev name");
+ return NULL;
+ }
+
+ list_for_each_entry(entry, &cls_cgroup->iface_stats.link, link)
+ if (!strcmp(entry->dev_name, dev_name))
+ return entry;
+
+ if (!create)
+ return entry;
+

+    /*not found, insert*/
+    entry = kmalloc(sizeof(struct cls_iface_cntrs), GFP_ATOMIC);
+    entry->dev_name = kstrdup(dev_name, GFP_ATOMIC);
+    atomic64_set(&entry->rcv_counter, 0);
+    atomic64_set(&entry->snd_counter, 0);
+    list_add_tail(&entry->link, &cls_cgroup->iface_stats.link);
+    return entry;

}
-#elif IS_MODULE(CONFIG_NET_CLS_CGROUP)
+
+static void charge_net_cls_snd(struct cgroup_cls_state *cls_cgroup,
+ const u32 copied, const char *dev_name)
+{
+ struct cls_iface_cntrs *cnt = find_cls_counter(cls_cgroup,
+ dev_name, true);
+
+ if (!cnt)
+ return;
+
+ atomic64_add(copied, &cnt->snd_counter);
+}
+
+static char *get_dev_name(const int ifindex)
+{

+    struct net *net = NULL;
+    struct nsproxy *nsproxy = NULL;
+    struct net_device *net_dev = NULL;

+
+ nsproxy = task_nsproxy(current);
+ if (!nsproxy) {
+ pr_debug("cls cant find task_nsproxy");
+ return NULL;
+ }
+
+ net = get_net(nsproxy->net_ns);
+ if (!net) {
+ pr_debug("cls cant find net");
+ return NULL;
+ }
+ net_dev = dev_get_by_index(net, ifindex);
+
+ return net_dev ? net_dev->name : NULL;
+}
+
+static void charge_net_cls_rcv(struct cgroup_cls_state *cls_cgroup,
+ const u32 copied, const int ifindex)
+{
+ char *dev_name = get_dev_name(ifindex);
+ struct cls_iface_cntrs *cnt = find_cls_counter(cls_cgroup,
+ dev_name, true);
+
+ if (!cnt)
+ return;
+
+ atomic64_add(copied, &cnt->rcv_counter);
+}
+
+static inline void count_cls_rcv(struct task_struct *p, const u32 copied,
+ const int ifindex)
+{
+ struct cgroup_cls_state *cls_cgroup;
+
+ cls_cgroup = get_cls_cgroup(p);
+
+ if (cls_cgroup)
+ charge_net_cls_rcv(cls_cgroup, copied, ifindex);
+}
+
+static inline void count_cls_snd(u32 classid, const u32 copied,
+ const char *dev_name)
+{
+ struct cgroup_cls_state *cls_cgroup;
+
+ cls_cgroup = find_cls_cgroup_by_classid(classid);
+
+ if (cls_cgroup)
+ charge_net_cls_snd(cls_cgroup, copied, dev_name);
+}
+#endif /*CONFIG_NET_CLS_COUNTER*/
+
static inline u32 task_cls_classid(struct task_struct *p)
{

-    struct cgroup_subsys_state *css;
-    u32 classid = 0;
+    int classid = 0;
+    struct cgroup_cls_state *cls_cgroup = NULL;

     if (in_interrupt())
         return 0;

     rcu_read_lock();

- css = task_subsys_state(p, net_cls_subsys_id);
- if (css)
- classid = container_of(css,
- struct cgroup_cls_state, css)->classid;
+
+ cls_cgroup = get_cls_cgroup(p);
+ if (cls_cgroup)
+ classid = cls_cgroup->classid;
+

     rcu_read_unlock();

     return classid;

}
-#endif
-#else /* !CGROUP_NET_CLS_CGROUP */
+
+#else /* !CONFIG_NET_CLS_CGROUP */
static inline void sock_update_classid(struct sock *sk, struct
task_struct *task)
{
}
@@ -69,5 +212,22 @@ static inline u32 task_cls_classid(struct task_struct *p)

 {
     return 0;

}
-#endif /* CGROUP_NET_CLS_CGROUP */
+#endif /* CONFIG_NET_CLS_CGROUP */
+
+#if !IS_ENABLED(CONFIG_NET_CLS_CGROUP) || !IS_ENABLED(CONFIG_NET_CLS_COUNTER) +static inline void count_cls_rcv(struct task_struct *p,
+ const u32 copied, const int ifindex)
+{
+}
+
+static inline void count_cls_snd(u32 classid,
+ const u32 copied, const char *dev_name)
+{
+}
+
+static inline u32 skb_cls_classid(const struct sk_buff *skb)
+{
+ return 0;
+}
+#endif
#endif /* _NET_CLS_CGROUP_H */

new file mode 100644
index 0000000..a129baa
@@ -0,0 +1,26 @@
+/*
+ * cls_counter_holder.c  Interface for holding references of the
+ *                       net cls cgroup instances.
+ *
+ * Authors:    Alexey Perevalov, <[email protected]>
+ *
+ * Changes:
+ *        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_COUNTER_HOLDER_H_
+#define _NET_CLS_COUNTER_HOLDER_H_
+
+#include <net/cls_cgroup.h>
+
+struct cgroup_cls_state;
+
+void insert_cls_cgroup_entry(struct cgroup_cls_state *obj);
+void delete_cls_cgroup_entry(const u32 classid);
+struct cgroup_cls_state *find_cls_cgroup_by_classid(const u32 classid);
+
+
+#endif /* _NET_CLS_COUNTER_HOLDER_H_ */

index 6fdd6e3..2e6af85 100644
@@ -841,6 +841,31 @@ config CGROUP_HUGETLB
       control group is tracked in the third page lru pointer. This means
       that we cannot use the controller with huge page less than 3 pages.
 
+menuconfig NET_CLS_CGROUP
+    tristate "Control Group Classifier"
+    select NET_CLS
+    depends on CGROUPS
+    ---help---
+      Say Y here if you want to classify packets based on the control
+      cgroup of their process.
+
+      To compile this code as a module, choose M here: the
+      module will be called cls_cgroup.
+
+if NET_CLS_CGROUP
+config NET_CLS_COUNTER
+    bool "Network traffic counter for network Control Group Classifier"
+    select NET_CLS
+    default n
+    depends on NET_CLS_CGROUP && RESOURCE_COUNTERS
+    ---help---
+      Say Y here if you want to count traffic associate with the control
+      cgroup.
+
+      To add functionality to cls_cgroup select y.
+
+endif #NET_CLS_CGROUP
+
 config CGROUP_PERF
     bool "Enable perf_event per-cpu per-container group (cgroup) 

monitoring"

     depends on PERF_EVENTS && CGROUPS

index 13774b3..68a4a53 100644
@@ -2966,6 +2966,8 @@ int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
     cgroup_cfts_commit(ss, NULL, false);
     return -ENOENT;
 }
+EXPORT_SYMBOL_GPL(cgroup_rm_cftypes);
+
 
 /**
  * cgroup_task_count - count the number of tasks in a cgroup.

index ad581aa..f5767af 100644
@@ -13,6 +13,8 @@
 #include <linux/res_counter.h>
 #include <linux/uaccess.h>
 #include <linux/mm.h>
+#include <linux/export.h>
+
 
 void res_counter_init(struct res_counter *counter, struct res_counter 

*parent)
{
@@ -21,6 +23,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)

     counter->soft_limit = RESOURCE_MAX;
     counter->parent = parent;

}
+EXPORT_SYMBOL(res_counter_init);

int res_counter_charge_locked(struct res_counter *counter, unsigned
long val,
bool force)
@@ -170,6 +173,7 @@ u64 res_counter_read_u64(struct res_counter *counter, int member)

     return *res_counter_member(counter, member);

}
#endif
+EXPORT_SYMBOL(res_counter_read_u64);

int res_counter_memparse_write_strategy(const char *buf,
unsigned long long *res)

index b4978e2..61c9a61 100644
@@ -135,6 +135,7 @@
 #include <linux/net_tstamp.h>
 #include <linux/static_key.h>
 #include <net/flow_keys.h>
+#include <net/cls_cgroup.h>
 
 #include "net-sysfs.h"
 

@@ -2570,6 +2571,11 @@ int dev_queue_xmit(struct sk_buff *skb)
      */
     rcu_read_lock_bh();
 
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+    if (dev)
+        count_cls_snd(skb_cls_classid(skb), skb->len, dev->name);
+#endif
+
     skb_update_prio(skb);
 
     txq = netdev_pick_tx(dev, skb);

index eace049..ba54577 100644
@@ -276,6 +276,7 @@
 #include <net/ip.h>
 #include <net/netdma.h>
 #include <net/sock.h>
+#include <net/cls_cgroup.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>

@@ -1467,6 +1468,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
     u32 seq = tp->copied_seq;
     u32 offset;
     int copied = 0;
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+    int ifindex = 0;
+#endif
 
     if (sk->sk_state == TCP_LISTEN)
         return -ENOTCONN;

@@ -1509,6 +1513,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
             ++seq;
             break;
         }
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+        ifindex = get_ifindex_from_skb(skb);
+#endif
         sk_eat_skb(sk, skb, false);
         if (!desc->count)
             break;

@@ -1519,8 +1526,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
     tcp_rcv_space_adjust(sk);
 
     /* Clean up data we have read: This will do ACK frames. */
-    if (copied > 0)
+    if (copied > 0) {
         tcp_cleanup_rbuf(sk, copied);
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+        count_cls_rcv(current, copied, ifindex);
+#endif
+    }
     return copied;
 }
 EXPORT_SYMBOL(tcp_read_sock);

@@ -1548,6 +1559,9 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
     bool copied_early = false;
     struct sk_buff *skb;
     u32 urg_hole = 0;
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+    int ifindex = 0;
+#endif
 
     lock_sock(sk);
 

@@ -1872,6 +1886,9 @@ skip_copy:
         if (tcp_hdr(skb)->fin)
             goto found_fin_ok;
         if (!(flags & MSG_PEEK)) {
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+            ifindex = get_ifindex_from_skb(skb);
+#endif
             sk_eat_skb(sk, skb, copied_early);
             copied_early = false;
         }

@@ -1881,6 +1898,9 @@ skip_copy:
         /* Process the FIN. */
         ++*seq;
         if (!(flags & MSG_PEEK)) {
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+            ifindex = get_ifindex_from_skb(skb);
+#endif
             sk_eat_skb(sk, skb, copied_early);
             copied_early = false;
         }

@@ -1923,6 +1943,11 @@ skip_copy:
     /* Clean up data we have read: This will do ACK frames. */
     tcp_cleanup_rbuf(sk, copied);
 
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+    if (copied > 0)
+        count_cls_rcv(current, copied, ifindex);
+#endif
+
     release_sock(sk);
     return copied;
 

@@ -1932,6 +1957,8 @@ out:
 
 recv_urg:
     err = tcp_recv_urg(sk, msg, len, flags);
+    if (err > 0)
+        count_cls_rcv(current, err, ifindex);
     goto out;
 
 recv_sndq:

index 79c8dbe..a143629 100644
@@ -101,6 +101,7 @@
 #include <linux/skbuff.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <net/cls_cgroup.h>
 #include <net/net_namespace.h>
 #include <net/icmp.h>
 #include <net/route.h>

@@ -1254,6 +1255,11 @@ try_again:
     if (flags & MSG_TRUNC)
         err = ulen;
 
+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+    if (ulen > 0)
+        count_cls_rcv(current, ulen, get_ifindex_from_skb(skb));
+#endif
+
 out_free:
     skb_free_datagram_locked(sk, skb);
 out:

index 62fb51f..926dedf 100644
@@ -418,17 +418,6 @@ config NET_CLS_FLOW
       To compile this code as a module, choose M here: the
       module will be called cls_flow.
 
-config NET_CLS_CGROUP
-    tristate "Control Group Classifier"
-    select NET_CLS
-    depends on CGROUPS
-    ---help---
-      Say Y here if you want to classify packets based on the control
-      cgroup of their process.
-
-      To compile this code as a module, choose M here: the
-      module will be called cls_cgroup.
-
 config NET_EMATCH
     bool "Extended Matches"
     select NET_CLS

index 978cbf0..95dbb12 100644
@@ -49,6 +49,7 @@ obj-$(CONFIG_NET_CLS_RSVP6)    += cls_rsvp6.o
 obj-$(CONFIG_NET_CLS_BASIC)    += cls_basic.o
 obj-$(CONFIG_NET_CLS_FLOW)    += cls_flow.o
 obj-$(CONFIG_NET_CLS_CGROUP)    += cls_cgroup.o
+obj-$(CONFIG_NET_CLS_COUNTER)   += cls_counter_holder.o
 obj-$(CONFIG_NET_EMATCH)    += ematch.o
 obj-$(CONFIG_NET_EMATCH_CMP)    += em_cmp.o
 obj-$(CONFIG_NET_EMATCH_NBYTE)    += em_nbyte.o

value)
{

-    cgrp_cls_state(cgrp)->classid = (u32) value;
+    struct cgroup_cls_state *cgrp_cls = cgrp_cls_state(cgrp);
+    u32 *classid = &cgrp_cls->classid;

+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+ u32 oldclassid = *classid;
+
+ if (find_cls_cgroup_by_classid(value)) {
+ pr_err("cls: classid %llu already exists\n", value);
+ return -EINVAL;
+ }
+
+ insert_cls_cgroup_entry(cgrp_cls);
+
+ if (oldclassid)
+ delete_cls_cgroup_entry(oldclassid);
+#endif /* CONFIG_NET_CLS_COUNTER */
+ *classid = (u32) value;
+

     return 0;

}

@@ -307,17 +401,107 @@ static struct tcf_proto_ops cls_cgroup_ops __read_mostly = {
.owner = THIS_MODULE,
};

+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+static inline int add_cft_file_for_device(struct net_device *dev) +{
+ struct cftype *cft;
+ int ret = 0;
+
+ if (!dev)
+ return ret;
+
+ cft = kmalloc(sizeof(struct cftype) * 2,
+ GFP_KERNEL);
+ /* *2 and last 0 fill for terminator */
+ memset(cft, 0, sizeof(struct cftype) * 2);
+
+ snprintf(cft->name, MAX_CFTYPE_NAME,
+ "%s.usage_in_bytes", dev->name);

+    cft->read_map = read_stat;
+    cft->private = RES_USAGE;
+    ret = cgroup_add_cftypes(&net_cls_subsys, cft);
+    if (ret)

+ pr_err("cls error adding cft for counting at " \
+ "cls_cgroup %d\n", ret);
+ return ret;
+}
+
+static int device_state_cb(struct notifier_block *nb,
+ unsigned long state, void *arg)
+{
+ struct net_device *net = (struct net_device *)arg;
+ if (!nb || !net) {
+ pr_err("Not valid arguments for net_device notifier cb\n");
+ return 0;
+ }
+
+ if (state == NETDEV_REGISTER) {
+ pr_info("cls New device %s\n", net->name);
+ return add_cft_file_for_device(net);
+ }
+ return 0;
+}
+
+static inline int init_cgroup_counter(void) +{

+    int ret = 0;
+    struct net_device *dev;
+    counter_notifier.notifier_call = device_state_cb;

+
+ ret = register_netdevice_notifier(&counter_notifier);
+ if (ret)
+ pr_err("cls Cant register nofier\n");
+
+ for_each_netdev(&init_net, dev) {
+ ret = add_cft_file_for_device(dev);
+ if (ret)
+ goto unregister_notifier;
+ }
+
+ return ret;
+unregister_notifier:
+
+ unregister_netdevice_notifier(&counter_notifier);
+ return ret;
+}
+
+static void release_cft(void)
+{
+ struct list_head *pos, *q;
+ list_for_each_safe(pos, q, &net_cls_subsys.cftsets) {
+ struct cftype_set *set =
+ list_entry(pos, struct cftype_set, node);
+ int ret = cgroup_rm_cftypes(&net_cls_subsys, set->cfts);
+ if (!ret) {
+ pr_err("cls cant remove cftypes\n");
+ break;
+ }
+
+ kfree(set->cfts);
+ }
+}
+#endif
+
static int __init init_cgroup_cls(void)

 {
     int ret;
-
     ret = cgroup_load_subsys(&net_cls_subsys);
     if (ret)
         goto out;

+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+ ret = init_cgroup_counter();
+ if (ret)
+ goto unload;
+#endif
+

     ret = register_tcf_proto_ops(&cls_cgroup_ops);
     if (ret)

- cgroup_unload_subsys(&net_cls_subsys);
+ goto unload;
+
+ return 0;
+unload:
+ cgroup_unload_subsys(&net_cls_subsys);

out:

     return ret;
@@ -327,6 +511,9 @@ static void __exit exit_cgroup_cls(void)
 {
     unregister_tcf_proto_ops(&cls_cgroup_ops);

+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+ release_cft();
+#endif

     cgroup_unload_subsys(&net_cls_subsys);

}

1.7.9.5


The performance measurement results

*Local*	Communication			latencies	in	microseconds	smaller	is	better				

					2p/0K ctxsw	Pipe	AF Unix	UDP	RPC/UDP	TCP	RPC/TCP	TCP conn	
Kernel with	patch:			6.641	14.83	13.68	43.715	25.005	31.82	26.845	31.45	
Kernel without	patch:			6.5815	14.64	13.6895	48.6	28.74	35.745	26.875	31.6	
Kernel with patch and	created cgroups	6.456	14.54	13.88	50.145	33.735	32.26	26.92	31	

											
*Local*	Communication	bandwidths	in	MB/s	bigger	is	better				
					Pipe	AF Unix	TCP	File reread	Mmap reread	Bcopy (libc)	Bcopy (hand)	Mem read	Mem write
Kernel	with	patch:			724.8	6952.3	3366.8	4409.565	7534.86	6629.05	3490.055	5594.15	6701.1
Kernel	without	patch:			669.55	6839.85	3347.65	4412.215	7506.46	6579.53	3453.145	5579.5	6243.45
Kernel	with patch and	create cgroups	718.75	6882.65	3353.2	4422.95		7521.225	6629.665	3472.87	5591.05	6409.9



-- 
Best regards,
Alexey Perevalov

You should cc netdev mailing list.

Hi Alexey,

It seems something went wrong with the patch, e.g. indention is wrong and also I see '^M$' line endings. I assume you are sending your patches through an exchange server which is likely not to work.

+#if IS_ENABLED(CONFIG_NET_CLS_COUNTER)
+ if (copied > 0)
+ count_cls_rcv(current, copied, ifindex);
+#endif
+
release_sock(sk);
return copied;

Normally, distros will enable most config flags. Maybe you could use
a jump label to reduce the cost for the users which have CONFIG_NET_CLS_COUNTER enabled and do not use it?

Could you explain in the commit message how your patch is designed? I see you are using a RB tree. What's the purpose of it?

I am trying a different approach on this problem using iptables. I am playing around with a few patches which allow to install a iptables rule which matches on the security context, e.g.

iptables -t mangle -A OUTPUT -m secmark --secctx \
unconfined_u:unconfined_r:foo_t:s0-s0:c0.c1023 -j MARK --set-mark 1

So far it looks promising, but as I me previous networking experience is, that something will not work eventually.

Thanks,
Daniel

Hi Daniel,

Your right I'm behind MS Exchange server. I'll find the way to send normal patch without modification. Can you accept attachments?

Do your mean one big macro instead of #if #endif. I don't like #if #endif in this place too. For example skb_update_prio implemented in such way. Or your mean function callback which will be invoked in case of net_cls loaded? This variant is more flexible. I agree.

The main purpose - it's ability to count network traffic per application, application groups and application threads. Without huge overhead in user space. Also keep information about involved network interface. For example:
ChatOn application
consumed 100Mb on netinterface0 and 10Mb on netinterface1.

Why it wasn't done on the netfilter layer. Because of patent threat and big overhead for resolving incoming traffic. At the netfilter layer we know only source address, and destination address/port. And we need to make huge work to know to whom it addressed, even we use assumption like this, destination address for incoming is the same as source address for outgoing, but it true only for TCP.

In this patch I used already prepared buffer (size of buffer) which ready in tcp_recvmsg, tcp_read_sock,... functions. For outgoing traffic I count on the post routing (network interface already defined). But before netprio changing priority, I didn't test such case. And here on the post routing in dev_queue_xmit there is no valid current thread. To find appropriate cgroup by classid and increase counter in it I use RB tree.

BR,
Alexey Perevalov

Hello all,

also I got local benchmark result for 100 test.

It looks more trully

*Local* Communication latencies in microseconds
smaller is better

2p/0K ctxsw Pipe AF Unix UDP RPC/UDP TCP
RPC/TCP TCP conn
Kernel without patch Average values: 3.2809 9.12381 8.2354 16.327 18.825 24.274 22.759 30.64
Kernel with patch Average values: 3.4718 9.61495 8.5778 19.442 19.807 31.835 23.824 30.85

*Local* Communication bandwidths in MB/s bigger
is better
Pipe AF Unix TCP File reread Mmap reread Bcopy (libc) Bcopy (hand) Mem read Mem write
Kernel without patch Average values: 2119.25 6853.49 3499.27 4421.796 7543.785 6176.899 3483.647

     5603.29       6541.38

Kernel with patch Average values: 1966.7 6825.42 3413.67 4426.936 7534.443 6170.924 3481.583 5602.75 6520.42

Performance degradation exists. But I thing it can be solved, for example, by adding incrementation and searching appropriate cgroup to delayed timer (add_timer).

Best regards,
Alexey Perevalov,
Technical Leader,
phone: +7 (495) 797 25 00 ext 3969
e-mail: [email protected] <mailto:[email protected]>

Mobile group, Moscow Samsung Research Center
12 Dvintsev street, building 1
127018, Moscow, Russian Federation