[NET]: Rework dev_base via list_head (v3)
Cleanup of dev_base list use, with the aim to simplify making device
list per-namespace. In almost every occasion, use of dev_base variable
and dev->next pointer could be easily replaced by for_each_netdev
loop. A few most complicated places were converted to using
first_netdev()/next_netdev().
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Acked-by: Kirill Korotaev <dev@openvz.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/core/dev.c b/net/core/dev.c
index c305819..f27d4ab 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -156,13 +156,13 @@
#endif
/*
- * The @dev_base list is protected by @dev_base_lock and the rtnl
+ * The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
*
* Pure readers hold dev_base_lock for reading.
*
* Writers must hold the rtnl semaphore while they loop through the
- * dev_base list, and hold dev_base_lock for writing when they do the
+ * dev_base_head list, and hold dev_base_lock for writing when they do the
* actual updates. This allows pure readers to access the list even
* while a writer is preparing to update it.
*
@@ -174,11 +174,10 @@
* unregister_netdevice(), which must be called with the rtnl
* semaphore held.
*/
-struct net_device *dev_base;
-static struct net_device **dev_tail = &dev_base;
+LIST_HEAD(dev_base_head);
DEFINE_RWLOCK(dev_base_lock);
-EXPORT_SYMBOL(dev_base);
+EXPORT_SYMBOL(dev_base_head);
EXPORT_SYMBOL(dev_base_lock);
#define NETDEV_HASHBITS 8
@@ -567,11 +566,12 @@
ASSERT_RTNL();
- for (dev = dev_base; dev; dev = dev->next)
+ for_each_netdev(dev)
if (dev->type == type &&
!memcmp(dev->dev_addr, ha, dev->addr_len))
- break;
- return dev;
+ return dev;
+
+ return NULL;
}
EXPORT_SYMBOL(dev_getbyhwaddr);
@@ -581,11 +581,11 @@
struct net_device *dev;
ASSERT_RTNL();
- for (dev = dev_base; dev; dev = dev->next) {
+ for_each_netdev(dev)
if (dev->type == type)
- break;
- }
- return dev;
+ return dev;
+
+ return NULL;
}
EXPORT_SYMBOL(__dev_getfirstbyhwtype);
@@ -617,17 +617,19 @@
struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short mask)
{
- struct net_device *dev;
+ struct net_device *dev, *ret;
+ ret = NULL;
read_lock(&dev_base_lock);
- for (dev = dev_base; dev != NULL; dev = dev->next) {
+ for_each_netdev(dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
dev_hold(dev);
+ ret = dev;
break;
}
}
read_unlock(&dev_base_lock);
- return dev;
+ return ret;
}
/**
@@ -693,7 +695,7 @@
if (!inuse)
return -ENOMEM;
- for (d = dev_base; d; d = d->next) {
+ for_each_netdev(d) {
if (!sscanf(d->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
@@ -975,7 +977,7 @@
rtnl_lock();
err = raw_notifier_chain_register(&netdev_chain, nb);
if (!err) {
- for (dev = dev_base; dev; dev = dev->next) {
+ for_each_netdev(dev) {
nb->notifier_call(nb, NETDEV_REGISTER, dev);
if (dev->flags & IFF_UP)
@@ -2049,7 +2051,7 @@
*/
total = 0;
- for (dev = dev_base; dev; dev = dev->next) {
+ for_each_netdev(dev) {
for (i = 0; i < NPROTO; i++) {
if (gifconf_list[i]) {
int done;
@@ -2081,26 +2083,28 @@
* This is invoked by the /proc filesystem handler to display a device
* in detail.
*/
-static struct net_device *dev_get_idx(loff_t pos)
-{
- struct net_device *dev;
- loff_t i;
-
- for (i = 0, dev = dev_base; dev && i < pos; ++i, dev = dev->next);
-
- return i == pos ? dev : NULL;
-}
-
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
{
+ loff_t off;
+ struct net_device *dev;
+
read_lock(&dev_base_lock);
- return *pos ? dev_get_idx(*pos - 1) : SEQ_START_TOKEN;
+ if (!*pos)
+ return SEQ_START_TOKEN;
+
+ off = 1;
+ for_each_netdev(dev)
+ if (off++ == *pos)
+ return dev;
+
+ return NULL;
}
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
- return v == SEQ_START_TOKEN ? dev_base : ((struct net_device *)v)->next;
+ return v == SEQ_START_TOKEN ?
+ first_net_device() : next_net_device((struct net_device *)v);
}
void dev_seq_stop(struct seq_file *seq, void *v)
@@ -3082,11 +3086,9 @@
set_bit(__LINK_STATE_PRESENT, &dev->state);
- dev->next = NULL;
dev_init_scheduler(dev);
write_lock_bh(&dev_base_lock);
- *dev_tail = dev;
- dev_tail = &dev->next;
+ list_add_tail(&dev->dev_list, &dev_base_head);
hlist_add_head(&dev->name_hlist, head);
hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
dev_hold(dev);
@@ -3360,8 +3362,6 @@
void unregister_netdevice(struct net_device *dev)
{
- struct net_device *d, **dp;
-
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
@@ -3381,19 +3381,11 @@
dev_close(dev);
/* And unlink it from device chain. */
- for (dp = &dev_base; (d = *dp) != NULL; dp = &d->next) {
- if (d == dev) {
- write_lock_bh(&dev_base_lock);
- hlist_del(&dev->name_hlist);
- hlist_del(&dev->index_hlist);
- if (dev_tail == &dev->next)
- dev_tail = dp;
- *dp = d->next;
- write_unlock_bh(&dev_base_lock);
- break;
- }
- }
- BUG_ON(!d);
+ write_lock_bh(&dev_base_lock);
+ list_del(&dev->dev_list);
+ hlist_del(&dev->name_hlist);
+ hlist_del(&dev->index_hlist);
+ write_unlock_bh(&dev_base_lock);
dev->reg_state = NETREG_UNREGISTERING;
diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c
index 7d57bf7..5a54053 100644
--- a/net/core/dev_mcast.c
+++ b/net/core/dev_mcast.c
@@ -223,7 +223,7 @@
loff_t off = 0;
read_lock(&dev_base_lock);
- for (dev = dev_base; dev; dev = dev->next) {
+ for_each_netdev(dev) {
if (off++ == *pos)
return dev;
}
@@ -232,9 +232,8 @@
static void *dev_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct net_device *dev = v;
++*pos;
- return dev->next;
+ return next_net_device((struct net_device *)v);
}
static void dev_mc_seq_stop(struct seq_file *seq, void *v)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cec1111..8c971a2 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -539,13 +539,16 @@
int s_idx = cb->args[0];
struct net_device *dev;
- for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) {
+ idx = 0;
+ for_each_netdev(dev) {
if (idx < s_idx)
- continue;
+ goto cont;
if (rtnl_fill_ifinfo(skb, dev, NULL, 0, RTM_NEWLINK,
NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0)
break;
+cont:
+ idx++;
}
cb->args[0] = idx;
