net: add network priority cgroup infrastructure (v4)
This patch adds in the infrastructure code to create the network priority
cgroup. The cgroup, in addition to the standard processes file creates two
control files:
1) prioidx - This is a read-only file that exports the index of this cgroup.
This is a value that is both arbitrary and unique to a cgroup in this subsystem,
and is used to index the per-device priority map
2) priomap - This is a writeable file. On read it reports a table of 2-tuples
<name:priority> where name is the name of a network interface and priority is
indicates the priority assigned to frames egresessing on the named interface and
originating from a pid in this cgroup
This cgroup allows for skb priority to be set prior to a root qdisc getting
selected. This is benenficial for DCB enabled systems, in that it allows for any
application to use dcb configured priorities so without application modification
Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
CC: Robert Love <robert.w.love@intel.com>
CC: "David S. Miller" <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ac663c1..0bd390c 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -59,8 +59,16 @@
SUBSYS(blkio)
#endif
+/* */
+
#ifdef CONFIG_CGROUP_PERF
SUBSYS(perf)
#endif
/* */
+
+#ifdef CONFIG_NETPRIO_CGROUP
+SUBSYS(net_prio)
+#endif
+
+/* */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3eb383a..999bb26 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -50,6 +50,7 @@
#ifdef CONFIG_DCB
#include <net/dcbnl.h>
#endif
+#include <net/netprio_cgroup.h>
#include <linux/netdev_features.h>
@@ -1245,6 +1246,9 @@
/* max exchange id for FCoE LRO by ddp */
unsigned int fcoe_ddp_xid;
#endif
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+ struct netprio_map __rcu *priomap;
+#endif
/* phy device may attach itself for hardware timestamping */
struct phy_device *phydev;
diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
new file mode 100644
index 0000000..c432e99
--- /dev/null
+++ b/include/net/netprio_cgroup.h
@@ -0,0 +1,65 @@
+/*
+ * netprio_cgroup.h Control Group Priority set
+ *
+ *
+ * Authors: Neil Horman <nhorman@tuxdriver.com>
+ *
+ * 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 _NETPRIO_CGROUP_H
+#define _NETPRIO_CGROUP_H
+#include <linux/module.h>
+#include <linux/cgroup.h>
+#include <linux/hardirq.h>
+#include <linux/rcupdate.h>
+
+struct cgroup_netprio_state
+{
+ struct cgroup_subsys_state css;
+ u32 prioidx;
+};
+
+struct netprio_map {
+ struct rcu_head rcu;
+ u32 priomap_len;
+ u32 priomap[];
+};
+
+#ifdef CONFIG_CGROUPS
+
+#ifndef CONFIG_NETPRIO_CGROUP
+extern int net_prio_subsys_id;
+#endif
+
+extern void sock_update_netprioidx(struct sock *sk);
+
+static inline struct cgroup_netprio_state
+ *task_netprio_state(struct task_struct *p)
+{
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+ return container_of(task_subsys_state(p, net_prio_subsys_id),
+ struct cgroup_netprio_state, css);
+#else
+ return NULL;
+#endif
+}
+
+#else
+
+#define sock_update_netprioidx(sk)
+#define skb_update_prio(skb)
+
+static inline struct cgroup_netprio_state
+ *task_netprio_state(struct task_struct *p)
+{
+ return NULL;
+}
+
+#endif
+
+#endif /* _NET_CLS_CGROUP_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 1c28f39..8ac338c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -320,6 +320,9 @@
unsigned short sk_ack_backlog;
unsigned short sk_max_ack_backlog;
__u32 sk_priority;
+#ifdef CONFIG_CGROUPS
+ __u32 sk_cgrp_prioidx;
+#endif
struct pid *sk_peer_pid;
const struct cred *sk_peer_cred;
long sk_rcvtimeo;