1 files changed, 362 insertions, 15 deletions

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 59cfc7d8fc45..99e7052d7323 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -14,9 +14,12 @@
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
 #include <linux/slab.h>
+#include <linux/nsproxy.h>
 #include <net/sock.h>
+#include <net/net_namespace.h>
 #include <linux/rtnetlink.h>
 #include <linux/wireless.h>
+#include <linux/vmalloc.h>
 #include <net/wext.h>
 
 #include "net-sysfs.h"
@@ -466,18 +469,345 @@ static struct attribute_group wireless_group = {
         .attrs = wireless_attrs,
 };
 #endif
-
 #endif /* CONFIG_SYSFS */
 
+#ifdef CONFIG_RPS
+/*
+ * RX queue sysfs structures and functions.
+ */
+struct rx_queue_attribute {
+        struct attribute attr;
+        ssize_t (*show)(struct netdev_rx_queue *queue,
+            struct rx_queue_attribute *attr, char *buf);
+        ssize_t (*store)(struct netdev_rx_queue *queue,
+            struct rx_queue_attribute *attr, const char *buf, size_t len);
+};
+#define to_rx_queue_attr(_attr) container_of(_attr,             \
+    struct rx_queue_attribute, attr)
+
+#define to_rx_queue(obj) container_of(obj, struct netdev_rx_queue, kobj)
+
+static ssize_t rx_queue_attr_show(struct kobject *kobj, struct attribute *attr,
+                                  char *buf)
+{
+        struct rx_queue_attribute *attribute = to_rx_queue_attr(attr);
+        struct netdev_rx_queue *queue = to_rx_queue(kobj);
+
+        if (!attribute->show)
+                return -EIO;
+
+        return attribute->show(queue, attribute, buf);
+}
+
+static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr,
+                                   const char *buf, size_t count)
+{
+        struct rx_queue_attribute *attribute = to_rx_queue_attr(attr);
+        struct netdev_rx_queue *queue = to_rx_queue(kobj);
+
+        if (!attribute->store)
+                return -EIO;
+
+        return attribute->store(queue, attribute, buf, count);
+}
+
+static struct sysfs_ops rx_queue_sysfs_ops = {
+        .show = rx_queue_attr_show,
+        .store = rx_queue_attr_store,
+};
+
+static ssize_t show_rps_map(struct netdev_rx_queue *queue,
+                            struct rx_queue_attribute *attribute, char *buf)
+{
+        struct rps_map *map;
+        cpumask_var_t mask;
+        size_t len = 0;
+        int i;
+
+        if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
+                return -ENOMEM;
+
+        rcu_read_lock();
+        map = rcu_dereference(queue->rps_map);
+        if (map)
+                for (i = 0; i < map->len; i++)
+                        cpumask_set_cpu(map->cpus[i], mask);
+
+        len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask);
+        if (PAGE_SIZE - len < 3) {
+                rcu_read_unlock();
+                free_cpumask_var(mask);
+                return -EINVAL;
+        }
+        rcu_read_unlock();
+
+        free_cpumask_var(mask);
+        len += sprintf(buf + len, "\n");
+        return len;
+}
+
+static void rps_map_release(struct rcu_head *rcu)
+{
+        struct rps_map *map = container_of(rcu, struct rps_map, rcu);
+
+        kfree(map);
+}
+
+static ssize_t store_rps_map(struct netdev_rx_queue *queue,
+                      struct rx_queue_attribute *attribute,
+                      const char *buf, size_t len)
+{
+        struct rps_map *old_map, *map;
+        cpumask_var_t mask;
+        int err, cpu, i;
+        static DEFINE_SPINLOCK(rps_map_lock);
+
+        if (!capable(CAP_NET_ADMIN))
+                return -EPERM;
+
+        if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+                return -ENOMEM;
+
+        err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits);
+        if (err) {
+                free_cpumask_var(mask);
+                return err;
+        }
+
+        map = kzalloc(max_t(unsigned,
+            RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES),
+            GFP_KERNEL);
+        if (!map) {
+                free_cpumask_var(mask);
+                return -ENOMEM;
+        }
+
+        i = 0;
+        for_each_cpu_and(cpu, mask, cpu_online_mask)
+                map->cpus[i++] = cpu;
+
+        if (i)
+                map->len = i;
+        else {
+                kfree(map);
+                map = NULL;
+        }
+
+        spin_lock(&rps_map_lock);
+        old_map = queue->rps_map;
+        rcu_assign_pointer(queue->rps_map, map);
+        spin_unlock(&rps_map_lock);
+
+        if (old_map)
+                call_rcu(&old_map->rcu, rps_map_release);
+
+        free_cpumask_var(mask);
+        return len;
+}
+
+static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
+                                           struct rx_queue_attribute *attr,
+                                           char *buf)
+{
+        struct rps_dev_flow_table *flow_table;
+        unsigned int val = 0;
+
+        rcu_read_lock();
+        flow_table = rcu_dereference(queue->rps_flow_table);
+        if (flow_table)
+                val = flow_table->mask + 1;
+        rcu_read_unlock();
+
+        return sprintf(buf, "%u\n", val);
+}
+
+static void rps_dev_flow_table_release_work(struct work_struct *work)
+{
+        struct rps_dev_flow_table *table = container_of(work,
+            struct rps_dev_flow_table, free_work);
+
+        vfree(table);
+}
+
+static void rps_dev_flow_table_release(struct rcu_head *rcu)
+{
+        struct rps_dev_flow_table *table = container_of(rcu,
+            struct rps_dev_flow_table, rcu);
+
+        INIT_WORK(&table->free_work, rps_dev_flow_table_release_work);
+        schedule_work(&table->free_work);
+}
+
+static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
+                                     struct rx_queue_attribute *attr,
+                                     const char *buf, size_t len)
+{
+        unsigned int count;
+        char *endp;
+        struct rps_dev_flow_table *table, *old_table;
+        static DEFINE_SPINLOCK(rps_dev_flow_lock);
+
+        if (!capable(CAP_NET_ADMIN))
+                return -EPERM;
+
+        count = simple_strtoul(buf, &endp, 0);
+        if (endp == buf)
+                return -EINVAL;
+
+        if (count) {
+                int i;
+
+                if (count > 1<<30) {
+                        /* Enforce a limit to prevent overflow */
+                        return -EINVAL;
+                }
+                count = roundup_pow_of_two(count);
+                table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count));
+                if (!table)
+                        return -ENOMEM;
+
+                table->mask = count - 1;
+                for (i = 0; i < count; i++)
+                        table->flows[i].cpu = RPS_NO_CPU;
+        } else
+                table = NULL;
+
+        spin_lock(&rps_dev_flow_lock);
+        old_table = queue->rps_flow_table;
+        rcu_assign_pointer(queue->rps_flow_table, table);
+        spin_unlock(&rps_dev_flow_lock);
+
+        if (old_table)
+                call_rcu(&old_table->rcu, rps_dev_flow_table_release);
+
+        return len;
+}
+
+static struct rx_queue_attribute rps_cpus_attribute =
+        __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map);
+
+
+static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute =
+        __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR,
+            show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt);
+
+static struct attribute *rx_queue_default_attrs[] = {
+        &rps_cpus_attribute.attr,
+        &rps_dev_flow_table_cnt_attribute.attr,
+        NULL
+};
+
+static void rx_queue_release(struct kobject *kobj)
+{
+        struct netdev_rx_queue *queue = to_rx_queue(kobj);
+        struct netdev_rx_queue *first = queue->first;
+
+        if (queue->rps_map)
+                call_rcu(&queue->rps_map->rcu, rps_map_release);
+
+        if (queue->rps_flow_table)
+                call_rcu(&queue->rps_flow_table->rcu,
+                    rps_dev_flow_table_release);
+
+        if (atomic_dec_and_test(&first->count))
+                kfree(first);
+}
+
+static struct kobj_type rx_queue_ktype = {
+        .sysfs_ops = &rx_queue_sysfs_ops,
+        .release = rx_queue_release,
+        .default_attrs = rx_queue_default_attrs,
+};
+
+static int rx_queue_add_kobject(struct net_device *net, int index)
+{
+        struct netdev_rx_queue *queue = net->_rx + index;
+        struct kobject *kobj = &queue->kobj;
+        int error = 0;
+
+        kobj->kset = net->queues_kset;
+        error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL,
+            "rx-%u", index);
+        if (error) {
+                kobject_put(kobj);
+                return error;
+        }
+
+        kobject_uevent(kobj, KOBJ_ADD);
+
+        return error;
+}
+
+static int rx_queue_register_kobjects(struct net_device *net)
+{
+        int i;
+        int error = 0;
+
+        net->queues_kset = kset_create_and_add("queues",
+            NULL, &net->dev.kobj);
+        if (!net->queues_kset)
+                return -ENOMEM;
+        for (i = 0; i < net->num_rx_queues; i++) {
+                error = rx_queue_add_kobject(net, i);
+                if (error)
+                        break;
+        }
+
+        if (error)
+                while (--i >= 0)
+                        kobject_put(&net->_rx[i].kobj);
+
+        return error;
+}
+
+static void rx_queue_remove_kobjects(struct net_device *net)
+{
+        int i;
+
+        for (i = 0; i < net->num_rx_queues; i++)
+                kobject_put(&net->_rx[i].kobj);
+        kset_unregister(net->queues_kset);
+}
+#endif /* CONFIG_RPS */
+
+static const void *net_current_ns(void)
+{
+        return current->nsproxy->net_ns;
+}
+
+static const void *net_initial_ns(void)
+{
+        return &init_net;
+}
+
+static const void *net_netlink_ns(struct sock *sk)
+{
+        return sock_net(sk);
+}
+
+static struct kobj_ns_type_operations net_ns_type_operations = {
+        .type = KOBJ_NS_TYPE_NET,
+        .current_ns = net_current_ns,
+        .netlink_ns = net_netlink_ns,
+        .initial_ns = net_initial_ns,
+};
+
+static void net_kobj_ns_exit(struct net *net)
+{
+        kobj_ns_exit(KOBJ_NS_TYPE_NET, net);
+}
+
+static struct pernet_operations kobj_net_ops = {
+        .exit = net_kobj_ns_exit,
+};
+
+
 #ifdef CONFIG_HOTPLUG
 static int netdev_uevent(struct device *d, struct kobj_uevent_env *env)
 {
         struct net_device *dev = to_net_dev(d);
         int retval;
 
-        if (!net_eq(dev_net(dev), &init_net))
-                return 0;
-
         /* pass interface to uevent. */
         retval = add_uevent_var(env, "INTERFACE=%s", dev->name);
         if (retval)
@@ -507,6 +837,13 @@ static void netdev_release(struct device *d)
         kfree((char *)dev - dev->padded);
 }
 
+static const void *net_namespace(struct device *d)
+{
+        struct net_device *dev;
+        dev = container_of(d, struct net_device, dev);
+        return dev_net(dev);
+}
+
 static struct class net_class = {
         .name = "net",
         .dev_release = netdev_release,
@@ -516,6 +853,8 @@ static struct class net_class = {
 #ifdef CONFIG_HOTPLUG
         .dev_uevent = netdev_uevent,
 #endif
+        .ns_type = &net_ns_type_operations,
+        .namespace = net_namespace,
 };
 
 /* Delete sysfs entries but hold kobject reference until after all
@@ -527,8 +866,9 @@ void netdev_unregister_kobject(struct net_device * net)
 
         kobject_get(&dev->kobj);
 
-        if (!net_eq(dev_net(net), &init_net))
-                return;
+#ifdef CONFIG_RPS
+        rx_queue_remove_kobjects(net);
+#endif
 
         device_del(dev);
 }
@@ -538,7 +878,9 @@ int netdev_register_kobject(struct net_device *net)
 {
         struct device *dev = &(net->dev);
         const struct attribute_group **groups = net->sysfs_groups;
+        int error = 0;
 
+        device_initialize(dev);
         dev->class = &net_class;
         dev->platform_data = net;
         dev->groups = groups;
@@ -561,10 +903,19 @@ int netdev_register_kobject(struct net_device *net)
 #endif
 #endif /* CONFIG_SYSFS */
 
-        if (!net_eq(dev_net(net), &init_net))
-                return 0;
+        error = device_add(dev);
+        if (error)
+                return error;
+
+#ifdef CONFIG_RPS
+        error = rx_queue_register_kobjects(net);
+        if (error) {
+                device_del(dev);
+                return error;
+        }
+#endif
 
-        return device_add(dev);
+        return error;
 }
 
 int netdev_class_create_file(struct class_attribute *class_attr)
@@ -580,13 +931,9 @@ void netdev_class_remove_file(struct class_attribute *class_attr)
 EXPORT_SYMBOL(netdev_class_create_file);
 EXPORT_SYMBOL(netdev_class_remove_file);
 
-void netdev_initialize_kobject(struct net_device *net)
-{
-        struct device *device = &(net->dev);
-        device_initialize(device);
-}
-
 int netdev_kobject_init(void)
 {
+        kobj_ns_type_register(&net_ns_type_operations);
+        register_pernet_subsys(&kobj_net_ops);
         return class_register(&net_class);
 }