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 <[email protected]>
Signed-off-by: John Fastabend <[email protected]>
CC: Robert Love <[email protected]>
CC: "David S. Miller" <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

include/linux/cgroup_subsys.h

@@ -59,8 +59,16 @@ SUBSYS(net_cls)
 SUBSYS(blkio)
 #endif
 
+/* */
+
 #ifdef CONFIG_CGROUP_PERF
 SUBSYS(perf)
 #endif
 
 /* */
+
+#ifdef CONFIG_NETPRIO_CGROUP
+SUBSYS(net_prio)
+#endif
+
+/* */

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>
 
@@ -1244,6 +1245,9 @@ struct net_device {
 #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
 	/* 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;

include/net/netprio_cgroup.h

@@ -0,0 +1,65 @@
+/*
+ * netprio_cgroup.h			Control Group Priority set
+ *
+ *
+ * Authors:	Neil Horman <[email protected]>
+ *
+ * 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 */

include/net/sock.h

@@ -320,6 +320,9 @@ struct sock {
 	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;

net/Kconfig

@@ -232,6 +232,13 @@ config XPS
 	depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
 	default y
 
+config NETPRIO_CGROUP
+	tristate "Network priority cgroup"
+	depends on CGROUPS
+	---help---
+	  Cgroup subsystem for use in assigning processes to network priorities on
+	  a per-interface basis
+
 config HAVE_BPF_JIT
 	bool
 

net/core/Makefile

@@ -19,3 +19,4 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o
 obj-$(CONFIG_TRACEPOINTS) += net-traces.o
 obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
 obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
+obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o

net/core/dev.c

@@ -2449,6 +2449,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	return rc;
 }
 
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+static void skb_update_prio(struct sk_buff *skb)
+{
+	struct netprio_map *map = rcu_dereference(skb->dev->priomap);
+
+	if ((!skb->priority) && (skb->sk) && map)
+		skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx];
+}
+#else
+#define skb_update_prio(skb)
+#endif
+
 static DEFINE_PER_CPU(int, xmit_recursion);
 #define RECURSION_LIMIT 10
 
@@ -2489,6 +2501,8 @@ int dev_queue_xmit(struct sk_buff *skb)
 	 */
 	rcu_read_lock_bh();
 
+	skb_update_prio(skb);
+
 	txq = dev_pick_tx(dev, skb);
 	q = rcu_dereference_bh(txq->qdisc);