aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile1
-rw-r--r--net/core/datagram.c14
-rw-r--r--net/core/dev.c1321
-rw-r--r--net/core/drop_monitor.c16
-rw-r--r--net/core/ethtool.c113
-rw-r--r--net/core/fib_rules.c107
-rw-r--r--net/core/filter.c6
-rw-r--r--net/core/gen_stats.c8
-rw-r--r--net/core/link_watch.c94
-rw-r--r--net/core/neighbour.c144
-rw-r--r--net/core/net-sysfs.c77
-rw-r--r--net/core/net_namespace.c305
-rw-r--r--net/core/netpoll.c6
-rw-r--r--net/core/pktgen.c835
-rw-r--r--net/core/rtnetlink.c204
-rw-r--r--net/core/skb_dma_map.c65
-rw-r--r--net/core/skbuff.c11
-rw-r--r--net/core/sock.c107
-rw-r--r--net/core/sysctl_net_core.c25
-rw-r--r--net/core/utils.c2
20 files changed, 1946 insertions, 1515 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index 796f46eece5f..08791ac3e05a 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -6,7 +6,6 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
gen_stats.o gen_estimator.o net_namespace.o
obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
-obj-$(CONFIG_HAS_DMA) += skb_dma_map.o
obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b0fe69211eef..95c2e0840d0d 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -55,6 +55,7 @@
#include <net/checksum.h>
#include <net/sock.h>
#include <net/tcp_states.h>
+#include <trace/events/skb.h>
/*
* Is a socket 'connection oriented' ?
@@ -223,6 +224,15 @@ void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
consume_skb(skb);
sk_mem_reclaim_partial(sk);
}
+EXPORT_SYMBOL(skb_free_datagram);
+
+void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
+{
+ lock_sock(sk);
+ skb_free_datagram(sk, skb);
+ release_sock(sk);
+}
+EXPORT_SYMBOL(skb_free_datagram_locked);
/**
* skb_kill_datagram - Free a datagram skbuff forcibly
@@ -261,6 +271,7 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
}
kfree_skb(skb);
+ atomic_inc(&sk->sk_drops);
sk_mem_reclaim_partial(sk);
return err;
@@ -284,6 +295,8 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
int i, copy = start - offset;
struct sk_buff *frag_iter;
+ trace_skb_copy_datagram_iovec(skb, len);
+
/* Copy header. */
if (copy > 0) {
if (copy > len)
@@ -749,5 +762,4 @@ unsigned int datagram_poll(struct file *file, struct socket *sock,
EXPORT_SYMBOL(datagram_poll);
EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
EXPORT_SYMBOL(skb_copy_datagram_iovec);
-EXPORT_SYMBOL(skb_free_datagram);
EXPORT_SYMBOL(skb_recv_datagram);
diff --git a/net/core/dev.c b/net/core/dev.c
index 6a94475aee85..c36a17aafcf3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -79,6 +79,7 @@
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
+#include <linux/hash.h>
#include <linux/sched.h>
#include <linux/mutex.h>
#include <linux/string.h>
@@ -104,6 +105,7 @@
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
+#include <net/xfrm.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/kmod.h>
@@ -175,7 +177,7 @@ static struct list_head ptype_all __read_mostly; /* Taps */
* The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
*
- * Pure readers hold dev_base_lock for reading.
+ * Pure readers hold dev_base_lock for reading, or rcu_read_lock()
*
* Writers must hold the rtnl semaphore while they loop through the
* dev_base_head list, and hold dev_base_lock for writing when they do the
@@ -191,21 +193,17 @@ static struct list_head ptype_all __read_mostly; /* Taps */
* semaphore held.
*/
DEFINE_RWLOCK(dev_base_lock);
-
EXPORT_SYMBOL(dev_base_lock);
-#define NETDEV_HASHBITS 8
-#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
-
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
- return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)];
+ return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
}
static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex)
{
- return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)];
+ return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)];
}
/* Device list insertion */
@@ -216,23 +214,26 @@ static int list_netdevice(struct net_device *dev)
ASSERT_RTNL();
write_lock_bh(&dev_base_lock);
- list_add_tail(&dev->dev_list, &net->dev_base_head);
- hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
- hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex));
+ list_add_tail_rcu(&dev->dev_list, &net->dev_base_head);
+ hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
+ hlist_add_head_rcu(&dev->index_hlist,
+ dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
return 0;
}
-/* Device list removal */
+/* Device list removal
+ * caller must respect a RCU grace period before freeing/reusing dev
+ */
static void unlist_netdevice(struct net_device *dev)
{
ASSERT_RTNL();
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
- list_del(&dev->dev_list);
- hlist_del(&dev->name_hlist);
- hlist_del(&dev->index_hlist);
+ list_del_rcu(&dev->dev_list);
+ hlist_del_rcu(&dev->name_hlist);
+ hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
}
@@ -248,6 +249,7 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
*/
DEFINE_PER_CPU(struct softnet_data, softnet_data);
+EXPORT_PER_CPU_SYMBOL(softnet_data);
#ifdef CONFIG_LOCKDEP
/*
@@ -269,10 +271,10 @@ static const unsigned short netdev_lock_type[] =
ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211,
ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET,
- ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_IEEE802154_PHY,
+ ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154,
ARPHRD_VOID, ARPHRD_NONE};
-static const char *netdev_lock_name[] =
+static const char *const netdev_lock_name[] =
{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
@@ -287,7 +289,7 @@ static const char *netdev_lock_name[] =
"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
"_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211",
"_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET",
- "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_IEEE802154_PHY",
+ "_xmit_PHONET_PIPE", "_xmit_IEEE802154",
"_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
@@ -381,6 +383,7 @@ void dev_add_pack(struct packet_type *pt)
}
spin_unlock_bh(&ptype_lock);
}
+EXPORT_SYMBOL(dev_add_pack);
/**
* __dev_remove_pack - remove packet handler
@@ -418,6 +421,8 @@ void __dev_remove_pack(struct packet_type *pt)
out:
spin_unlock_bh(&ptype_lock);
}
+EXPORT_SYMBOL(__dev_remove_pack);
+
/**
* dev_remove_pack - remove packet handler
* @pt: packet type declaration
@@ -436,6 +441,7 @@ void dev_remove_pack(struct packet_type *pt)
synchronize_net();
}
+EXPORT_SYMBOL(dev_remove_pack);
/******************************************************************************
@@ -499,6 +505,7 @@ int netdev_boot_setup_check(struct net_device *dev)
}
return 0;
}
+EXPORT_SYMBOL(netdev_boot_setup_check);
/**
@@ -582,15 +589,42 @@ __setup("netdev=", netdev_boot_setup);
struct net_device *__dev_get_by_name(struct net *net, const char *name)
{
struct hlist_node *p;
+ struct net_device *dev;
+ struct hlist_head *head = dev_name_hash(net, name);
- hlist_for_each(p, dev_name_hash(net, name)) {
- struct net_device *dev
- = hlist_entry(p, struct net_device, name_hlist);
+ hlist_for_each_entry(dev, p, head, name_hlist)
if (!strncmp(dev->name, name, IFNAMSIZ))
return dev;
- }
+
+ return NULL;
+}
+EXPORT_SYMBOL(__dev_get_by_name);
+
+/**
+ * dev_get_by_name_rcu - find a device by its name
+ * @net: the applicable net namespace
+ * @name: name to find
+ *
+ * Find an interface by name.
+ * If the name is found a pointer to the device is returned.
+ * If the name is not found then %NULL is returned.
+ * The reference counters are not incremented so the caller must be
+ * careful with locks. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
+{
+ struct hlist_node *p;
+ struct net_device *dev;
+ struct hlist_head *head = dev_name_hash(net, name);
+
+ hlist_for_each_entry_rcu(dev, p, head, name_hlist)
+ if (!strncmp(dev->name, name, IFNAMSIZ))
+ return dev;
+
return NULL;
}
+EXPORT_SYMBOL(dev_get_by_name_rcu);
/**
* dev_get_by_name - find a device by its name
@@ -608,13 +642,14 @@ struct net_device *dev_get_by_name(struct net *net, const char *name)
{
struct net_device *dev;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_name(net, name);
+ rcu_read_lock();
+ dev = dev_get_by_name_rcu(net, name);
if (dev)
dev_hold(dev);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return dev;
}
+EXPORT_SYMBOL(dev_get_by_name);
/**
* __dev_get_by_index - find a device by its ifindex
@@ -631,15 +666,41 @@ struct net_device *dev_get_by_name(struct net *net, const char *name)
struct net_device *__dev_get_by_index(struct net *net, int ifindex)
{
struct hlist_node *p;
+ struct net_device *dev;
+ struct hlist_head *head = dev_index_hash(net, ifindex);
- hlist_for_each(p, dev_index_hash(net, ifindex)) {
- struct net_device *dev
- = hlist_entry(p, struct net_device, index_hlist);
+ hlist_for_each_entry(dev, p, head, index_hlist)
if (dev->ifindex == ifindex)
return dev;
- }
+
+ return NULL;
+}
+EXPORT_SYMBOL(__dev_get_by_index);
+
+/**
+ * dev_get_by_index_rcu - find a device by its ifindex
+ * @net: the applicable net namespace
+ * @ifindex: index of device
+ *
+ * Search for an interface by index. Returns %NULL if the device
+ * is not found or a pointer to the device. The device has not
+ * had its reference counter increased so the caller must be careful
+ * about locking. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex)
+{
+ struct hlist_node *p;
+ struct net_device *dev;
+ struct hlist_head *head = dev_index_hash(net, ifindex);
+
+ hlist_for_each_entry_rcu(dev, p, head, index_hlist)
+ if (dev->ifindex == ifindex)
+ return dev;
+
return NULL;
}
+EXPORT_SYMBOL(dev_get_by_index_rcu);
/**
@@ -657,13 +718,14 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex)
{
struct net_device *dev;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_index(net, ifindex);
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifindex);
if (dev)
dev_hold(dev);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return dev;
}
+EXPORT_SYMBOL(dev_get_by_index);
/**
* dev_getbyhwaddr - find a device by its hardware address
@@ -693,7 +755,6 @@ struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *h
return NULL;
}
-
EXPORT_SYMBOL(dev_getbyhwaddr);
struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
@@ -707,7 +768,6 @@ struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
return NULL;
}
-
EXPORT_SYMBOL(__dev_getfirstbyhwtype);
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
@@ -721,7 +781,6 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
rtnl_unlock();
return dev;
}
-
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
@@ -736,22 +795,24 @@ EXPORT_SYMBOL(dev_getfirstbyhwtype);
* dev_put to indicate they have finished with it.
*/
-struct net_device * dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask)
+struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags,
+ unsigned short mask)
{
struct net_device *dev, *ret;
ret = NULL;
- read_lock(&dev_base_lock);
- for_each_netdev(net, dev) {
+ rcu_read_lock();
+ for_each_netdev_rcu(net, dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
dev_hold(dev);
ret = dev;
break;
}
}
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return ret;
}
+EXPORT_SYMBOL(dev_get_by_flags);
/**
* dev_valid_name - check if name is okay for network device
@@ -777,6 +838,7 @@ int dev_valid_name(const char *name)
}
return 1;
}
+EXPORT_SYMBOL(dev_valid_name);
/**
* __dev_alloc_name - allocate a name for a device
@@ -832,7 +894,8 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
free_page((unsigned long) inuse);
}
- snprintf(buf, IFNAMSIZ, name, i);
+ if (buf != name)
+ snprintf(buf, IFNAMSIZ, name, i);
if (!__dev_get_by_name(net, buf))
return i;
@@ -870,7 +933,23 @@ int dev_alloc_name(struct net_device *dev, const char *name)
strlcpy(dev->name, buf, IFNAMSIZ);
return ret;
}
+EXPORT_SYMBOL(dev_alloc_name);
+
+static int dev_get_valid_name(struct net *net, const char *name, char *buf,
+ bool fmt)
+{
+ if (!dev_valid_name(name))
+ return -EINVAL;
+
+ if (fmt && strchr(name, '%'))
+ return __dev_alloc_name(net, name, buf);
+ else if (__dev_get_by_name(net, name))
+ return -EEXIST;
+ else if (buf != name)
+ strlcpy(buf, name, IFNAMSIZ);
+ return 0;
+}
/**
* dev_change_name - change name of a device
@@ -894,29 +973,20 @@ int dev_change_name(struct net_device *dev, const char *newname)
if (dev->flags & IFF_UP)
return -EBUSY;
- if (!dev_valid_name(newname))
- return -EINVAL;
-
if (strncmp(newname, dev->name, IFNAMSIZ) == 0)
return 0;
memcpy(oldname, dev->name, IFNAMSIZ);
- if (strchr(newname, '%')) {
- err = dev_alloc_name(dev, newname);
- if (err < 0)
- return err;
- }
- else if (__dev_get_by_name(net, newname))
- return -EEXIST;
- else
- strlcpy(dev->name, newname, IFNAMSIZ);
+ err = dev_get_valid_name(net, newname, dev->name, 1);
+ if (err < 0)
+ return err;
rollback:
/* For now only devices in the initial network namespace
* are in sysfs.
*/
- if (net == &init_net) {
+ if (net_eq(net, &init_net)) {
ret = device_rename(&dev->dev, dev->name);
if (ret) {
memcpy(dev->name, oldname, IFNAMSIZ);
@@ -926,21 +996,27 @@ rollback:
write_lock_bh(&dev_base_lock);
hlist_del(&dev->name_hlist);
- hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
+ write_unlock_bh(&dev_base_lock);
+
+ synchronize_rcu();
+
+ write_lock_bh(&dev_base_lock);
+ hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
write_unlock_bh(&dev_base_lock);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
ret = notifier_to_errno(ret);
if (ret) {
- if (err) {
- printk(KERN_ERR
- "%s: name change rollback failed: %d.\n",
- dev->name, ret);
- } else {
+ /* err >= 0 after dev_alloc_name() or stores the first errno */
+ if (err >= 0) {
err = ret;
memcpy(dev->name, oldname, IFNAMSIZ);
goto rollback;
+ } else {
+ printk(KERN_ERR
+ "%s: name change rollback failed: %d.\n",
+ dev->name, ret);
}
}
@@ -970,7 +1046,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
return 0;
}
- dev->ifalias = krealloc(dev->ifalias, len+1, GFP_KERNEL);
+ dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
if (!dev->ifalias)
return -ENOMEM;
@@ -1006,10 +1082,11 @@ void netdev_state_change(struct net_device *dev)
rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
}
}
+EXPORT_SYMBOL(netdev_state_change);
-void netdev_bonding_change(struct net_device *dev)
+void netdev_bonding_change(struct net_device *dev, unsigned long event)
{
- call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, dev);
+ call_netdevice_notifiers(event, dev);
}
EXPORT_SYMBOL(netdev_bonding_change);
@@ -1027,13 +1104,14 @@ void dev_load(struct net *net, const char *name)
{
struct net_device *dev;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_name(net, name);
- read_unlock(&dev_base_lock);
+ rcu_read_lock();
+ dev = dev_get_by_name_rcu(net, name);
+ rcu_read_unlock();
- if (!dev && capable(CAP_SYS_MODULE))
+ if (!dev && capable(CAP_NET_ADMIN))
request_module("%s", name);
}
+EXPORT_SYMBOL(dev_load);
/**
* dev_open - prepare an interface for use.
@@ -1118,6 +1196,7 @@ int dev_open(struct net_device *dev)
return ret;
}
+EXPORT_SYMBOL(dev_open);
/**
* dev_close - shutdown an interface.
@@ -1184,6 +1263,7 @@ int dev_close(struct net_device *dev)
return 0;
}
+EXPORT_SYMBOL(dev_close);
/**
@@ -1273,12 +1353,14 @@ rollback:
nb->notifier_call(nb, NETDEV_DOWN, dev);
}
nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev);
}
}
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
+EXPORT_SYMBOL(register_netdevice_notifier);
/**
* unregister_netdevice_notifier - unregister a network notifier block
@@ -1299,6 +1381,7 @@ int unregister_netdevice_notifier(struct notifier_block *nb)
rtnl_unlock();
return err;
}
+EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
* call_netdevice_notifiers - call all network notifier blocks
@@ -1321,11 +1404,13 @@ void net_enable_timestamp(void)
{
atomic_inc(&netstamp_needed);
}
+EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
atomic_dec(&netstamp_needed);
}
+EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp(struct sk_buff *skb)
{
@@ -1335,6 +1420,45 @@ static inline void net_timestamp(struct sk_buff *skb)
skb->tstamp.tv64 = 0;
}
+/**
+ * dev_forward_skb - loopback an skb to another netif
+ *
+ * @dev: destination network device
+ * @skb: buffer to forward
+ *
+ * return values:
+ * NET_RX_SUCCESS (no congestion)
+ * NET_RX_DROP (packet was dropped)
+ *
+ * dev_forward_skb can be used for injecting an skb from the
+ * start_xmit function of one device into the receive queue
+ * of another device.
+ *
+ * The receiving device may be in another namespace, so
+ * we have to clear all information in the skb that could
+ * impact namespace isolation.
+ */
+int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+{
+ skb_orphan(skb);
+
+ if (!(dev->flags & IFF_UP))
+ return NET_RX_DROP;
+
+ if (skb->len > (dev->mtu + dev->hard_header_len))
+ return NET_RX_DROP;
+
+ skb_dst_drop(skb);
+ skb->tstamp.tv64 = 0;
+ skb->pkt_type = PACKET_HOST;
+ skb->protocol = eth_type_trans(skb, dev);
+ skb->mark = 0;
+ secpath_reset(skb);
+ nf_reset(skb);
+ return netif_rx(skb);
+}
+EXPORT_SYMBOL_GPL(dev_forward_skb);
+
/*
* Support routine. Sends outgoing frames to any network
* taps currently in use.
@@ -1359,7 +1483,7 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
if ((ptype->dev == dev || !ptype->dev) &&
(ptype->af_packet_priv == NULL ||
(struct sock *)ptype->af_packet_priv != skb->sk)) {
- struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC);
+ struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
break;
@@ -1527,6 +1651,7 @@ out_set_summed:
out:
return ret;
}
+EXPORT_SYMBOL(skb_checksum_help);
/**
* skb_gso_segment - Perform segmentation on skb.
@@ -1589,7 +1714,6 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features)
return segs;
}
-
EXPORT_SYMBOL(skb_gso_segment);
/* Take action when hardware reception checksum errors are detected. */
@@ -1683,7 +1807,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
const struct net_device_ops *ops = dev->netdev_ops;
- int rc;
+ int rc = NETDEV_TX_OK;
if (likely(!skb->next)) {
if (!list_empty(&ptype_all))
@@ -1704,7 +1828,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
skb_dst_drop(skb);
rc = ops->ndo_start_xmit(skb, dev);
- if (rc == 0)
+ if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
/*
* TODO: if skb_orphan() was called by
@@ -1730,7 +1854,9 @@ gso:
skb->next = nskb->next;
nskb->next = NULL;
rc = ops->ndo_start_xmit(nskb, dev);
- if (unlikely(rc)) {
+ if (unlikely(rc != NETDEV_TX_OK)) {
+ if (rc & ~NETDEV_TX_MASK)
+ goto out_kfree_gso_skb;
nskb->next = skb->next;
skb->next = nskb;
return rc;
@@ -1740,11 +1866,12 @@ gso:
return NETDEV_TX_BUSY;
} while (skb->next);
- skb->destructor = DEV_GSO_CB(skb)->destructor;
-
+out_kfree_gso_skb:
+ if (likely(skb->next == NULL))
+ skb->destructor = DEV_GSO_CB(skb)->destructor;
out_kfree_skb:
kfree_skb(skb);
- return 0;
+ return rc;
}
static u32 skb_tx_hashrnd;
@@ -1755,7 +1882,7 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
- while (unlikely (hash >= dev->real_num_tx_queues))
+ while (unlikely(hash >= dev->real_num_tx_queues))
hash -= dev->real_num_tx_queues;
return hash;
}
@@ -1771,21 +1898,82 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
}
EXPORT_SYMBOL(skb_tx_hash);
+static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index)
+{
+ if (unlikely(queue_index >= dev->real_num_tx_queues)) {
+ if (net_ratelimit()) {
+ WARN(1, "%s selects TX queue %d, but "
+ "real number of TX queues is %d\n",
+ dev->name, queue_index,
+ dev->real_num_tx_queues);
+ }
+ return 0;
+ }
+ return queue_index;
+}
+
static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
- const struct net_device_ops *ops = dev->netdev_ops;
- u16 queue_index = 0;
+ u16 queue_index;
+ struct sock *sk = skb->sk;
- if (ops->ndo_select_queue)
- queue_index = ops->ndo_select_queue(dev, skb);
- else if (dev->real_num_tx_queues > 1)
- queue_index = skb_tx_hash(dev, skb);
+ if (sk_tx_queue_recorded(sk)) {
+ queue_index = sk_tx_queue_get(sk);
+ } else {
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb);
+ queue_index = dev_cap_txqueue(dev, queue_index);
+ } else {
+ queue_index = 0;
+ if (dev->real_num_tx_queues > 1)
+ queue_index = skb_tx_hash(dev, skb);
+
+ if (sk && sk->sk_dst_cache)
+ sk_tx_queue_set(sk, queue_index);
+ }
+ }
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
}
+static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
+ struct net_device *dev,
+ struct netdev_queue *txq)
+{
+ spinlock_t *root_lock = qdisc_lock(q);
+ int rc;
+
+ spin_lock(root_lock);
+ if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+ kfree_skb(skb);
+ rc = NET_XMIT_DROP;
+ } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
+ !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {
+ /*
+ * This is a work-conserving queue; there are no old skbs
+ * waiting to be sent out; and the qdisc is not running -
+ * xmit the skb directly.
+ */
+ __qdisc_update_bstats(q, skb->len);
+ if (sch_direct_xmit(skb, q, dev, txq, root_lock))
+ __qdisc_run(q);
+ else
+ clear_bit(__QDISC_STATE_RUNNING, &q->state);
+
+ rc = NET_XMIT_SUCCESS;
+ } else {
+ rc = qdisc_enqueue_root(skb, q);
+ qdisc_run(q);
+ }
+ spin_unlock(root_lock);
+
+ return rc;
+}
+
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
@@ -1856,22 +2044,10 @@ gso:
q = rcu_dereference(txq->qdisc);
#ifdef CONFIG_NET_CLS_ACT
- skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
+ skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
#endif
if (q->enqueue) {
- spinlock_t *root_lock = qdisc_lock(q);
-
- spin_lock(root_lock);
-
- if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
- kfree_skb(skb);
- rc = NET_XMIT_DROP;
- } else {
- rc = qdisc_enqueue_root(skb, q);
- qdisc_run(q);
- }
- spin_unlock(root_lock);
-
+ rc = __dev_xmit_skb(skb, q, dev, txq);
goto out;
}
@@ -1895,8 +2071,8 @@ gso:
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_tx_queue_stopped(txq)) {
- rc = 0;
- if (!dev_hard_start_xmit(skb, dev, txq)) {
+ rc = dev_hard_start_xmit(skb, dev, txq);
+ if (dev_xmit_complete(rc)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
}
@@ -1924,6 +2100,7 @@ out:
rcu_read_unlock_bh();
return rc;
}
+EXPORT_SYMBOL(dev_queue_xmit);
/*=======================================================================
@@ -1990,6 +2167,7 @@ enqueue:
kfree_skb(skb);
return NET_RX_DROP;
}
+EXPORT_SYMBOL(netif_rx);
int netif_rx_ni(struct sk_buff *skb)
{
@@ -2003,7 +2181,6 @@ int netif_rx_ni(struct sk_buff *skb)
return err;
}
-
EXPORT_SYMBOL(netif_rx_ni);
static void net_tx_action(struct softirq_action *h)
@@ -2076,7 +2253,7 @@ static inline int deliver_skb(struct sk_buff *skb,
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
unsigned char *addr) __read_mostly;
-EXPORT_SYMBOL(br_fdb_test_addr_hook);
+EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
#endif
/*
@@ -2085,7 +2262,7 @@ EXPORT_SYMBOL(br_fdb_test_addr_hook);
*/
struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
struct sk_buff *skb) __read_mostly;
-EXPORT_SYMBOL(br_handle_frame_hook);
+EXPORT_SYMBOL_GPL(br_handle_frame_hook);
static inline struct sk_buff *handle_bridge(struct sk_buff *skb,
struct packet_type **pt_prev, int *ret,
@@ -2150,7 +2327,7 @@ static int ing_filter(struct sk_buff *skb)
if (MAX_RED_LOOP < ttl++) {
printk(KERN_WARNING
"Redir loop detected Dropping packet (%d->%d)\n",
- skb->iif, dev->ifindex);
+ skb->skb_iif, dev->ifindex);
return TC_ACT_SHOT;
}
@@ -2248,18 +2425,18 @@ int netif_receive_skb(struct sk_buff *skb)
int ret = NET_RX_DROP;
__be16 type;
- if (skb->vlan_tci && vlan_hwaccel_do_receive(skb))
+ if (!skb->tstamp.tv64)
+ net_timestamp(skb);
+
+ if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
return NET_RX_SUCCESS;
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
return NET_RX_DROP;
- if (!skb->tstamp.tv64)
- net_timestamp(skb);
-
- if (!skb->iif)
- skb->iif = skb->dev->ifindex;
+ if (!skb->skb_iif)
+ skb->skb_iif = skb->dev->ifindex;
null_or_orig = NULL;
orig_dev = skb->dev;
@@ -2336,6 +2513,7 @@ out:
rcu_read_unlock();
return ret;
}
+EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending */
static void flush_backlog(void *arg)
@@ -2398,7 +2576,7 @@ void napi_gro_flush(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_gro_flush);
-int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
struct packet_type *ptype;
@@ -2406,7 +2584,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
int same_flow;
int mac_len;
- int ret;
+ enum gro_result ret;
if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
@@ -2490,7 +2668,8 @@ normal:
}
EXPORT_SYMBOL(dev_gro_receive);
-static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+static gro_result_t
+__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff *p;
@@ -2498,33 +2677,35 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
return GRO_NORMAL;
for (p = napi->gro_list; p; p = p->next) {
- NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev)
- && !compare_ether_header(skb_mac_header(p),
- skb_gro_mac_header(skb));
+ NAPI_GRO_CB(p)->same_flow =
+ (p->dev == skb->dev) &&
+ !compare_ether_header(skb_mac_header(p),
+ skb_gro_mac_header(skb));
NAPI_GRO_CB(p)->flush = 0;
}
return dev_gro_receive(napi, skb);
}
-int napi_skb_finish(int ret, struct sk_buff *skb)
+gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
{
- int err = NET_RX_SUCCESS;
-
switch (ret) {
case GRO_NORMAL:
- return netif_receive_skb(skb);
+ if (netif_receive_skb(skb))
+ ret = GRO_DROP;
+ break;
case GRO_DROP:
- err = NET_RX_DROP;
- /* fall through */
-
case GRO_MERGED_FREE:
kfree_skb(skb);
break;
+
+ case GRO_HELD:
+ case GRO_MERGED:
+ break;
}
- return err;
+ return ret;
}
EXPORT_SYMBOL(napi_skb_finish);
@@ -2544,7 +2725,7 @@ void skb_gro_reset_offset(struct sk_buff *skb)
}
EXPORT_SYMBOL(skb_gro_reset_offset);
-int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
skb_gro_reset_offset(skb);
@@ -2563,49 +2744,41 @@ EXPORT_SYMBOL(napi_reuse_skb);
struct sk_buff *napi_get_frags(struct napi_struct *napi)
{
- struct net_device *dev = napi->dev;
struct sk_buff *skb = napi->skb;
if (!skb) {
- skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN);
- if (!skb)
- goto out;
-
- skb_reserve(skb, NET_IP_ALIGN);
-
- napi->skb = skb;
+ skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
+ if (skb)
+ napi->skb = skb;
}
-
-out:
return skb;
}
EXPORT_SYMBOL(napi_get_frags);
-int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
+gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
+ gro_result_t ret)
{
- int err = NET_RX_SUCCESS;
-
switch (ret) {
case GRO_NORMAL:
case GRO_HELD:
skb->protocol = eth_type_trans(skb, napi->dev);
- if (ret == GRO_NORMAL)
- return netif_receive_skb(skb);
-
- skb_gro_pull(skb, -ETH_HLEN);
+ if (ret == GRO_HELD)
+ skb_gro_pull(skb, -ETH_HLEN);
+ else if (netif_receive_skb(skb))
+ ret = GRO_DROP;
break;
case GRO_DROP:
- err = NET_RX_DROP;
- /* fall through */
-
case GRO_MERGED_FREE:
napi_reuse_skb(napi, skb);
break;
+
+ case GRO_MERGED:
+ break;
}
- return err;
+ return ret;
}
EXPORT_SYMBOL(napi_frags_finish);
@@ -2646,12 +2819,12 @@ out:
}
EXPORT_SYMBOL(napi_frags_skb);
-int napi_gro_frags(struct napi_struct *napi)
+gro_result_t napi_gro_frags(struct napi_struct *napi)
{
struct sk_buff *skb = napi_frags_skb(napi);
if (!skb)
- return NET_RX_DROP;
+ return GRO_DROP;
return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
}
@@ -2852,7 +3025,7 @@ softnet_break:
goto out;
}
-static gifconf_func_t * gifconf_list [NPROTO];
+static gifconf_func_t *gifconf_list[NPROTO];
/**
* register_gifconf - register a SIOCGIF handler
@@ -2863,13 +3036,14 @@ static gifconf_func_t * gifconf_list [NPROTO];
* that is passed must not be freed or reused until it has been replaced
* by another handler.
*/
-int register_gifconf(unsigned int family, gifconf_func_t * gifconf)
+int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
{
if (family >= NPROTO)
return -EINVAL;
gifconf_list[family] = gifconf;
return 0;
}
+EXPORT_SYMBOL(register_gifconf);
/*
@@ -2895,15 +3069,15 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg)
if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
return -EFAULT;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_index(net, ifr.ifr_ifindex);
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex);
if (!dev) {
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return -ENODEV;
}
strcpy(ifr.ifr_name, dev->name);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
return -EFAULT;
@@ -2973,18 +3147,18 @@ static int dev_ifconf(struct net *net, char __user *arg)
* in detail.
*/
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(dev_base_lock)
+ __acquires(RCU)
{
struct net *net = seq_file_net(seq);
loff_t off;
struct net_device *dev;
- read_lock(&dev_base_lock);
+ rcu_read_lock();
if (!*pos)
return SEQ_START_TOKEN;
off = 1;
- for_each_netdev(net, dev)
+ for_each_netdev_rcu(net, dev)
if (off++ == *pos)
return dev;
@@ -2993,16 +3167,18 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos)
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct net *net = seq_file_net(seq);
+ struct net_device *dev = (v == SEQ_START_TOKEN) ?
+ first_net_device(seq_file_net(seq)) :
+ next_net_device((struct net_device *)v);
+
++*pos;
- return v == SEQ_START_TOKEN ?
- first_net_device(net) : next_net_device((struct net_device *)v);
+ return rcu_dereference(dev);
}
void dev_seq_stop(struct seq_file *seq, void *v)
- __releases(dev_base_lock)
+ __releases(RCU)
{
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
}
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
@@ -3080,7 +3256,7 @@ static int softnet_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
s->total, s->dropped, s->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision );
+ s->cpu_collision);
return 0;
}
@@ -3316,6 +3492,7 @@ int netdev_set_master(struct net_device *slave, struct net_device *master)
rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
return 0;
}
+EXPORT_SYMBOL(netdev_set_master);
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
@@ -3394,6 +3571,7 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
dev_set_rx_mode(dev);
return err;
}
+EXPORT_SYMBOL(dev_set_promiscuity);
/**
* dev_set_allmulti - update allmulti count on a device
@@ -3437,6 +3615,7 @@ int dev_set_allmulti(struct net_device *dev, int inc)
}
return 0;
}
+EXPORT_SYMBOL(dev_set_allmulti);
/*
* Upload unicast and multicast address lists to device and
@@ -3927,6 +4106,7 @@ int __dev_addr_sync(struct dev_addr_list **to, int *to_count,
}
return err;
}
+EXPORT_SYMBOL_GPL(__dev_addr_sync);
void __dev_addr_unsync(struct dev_addr_list **to, int *to_count,
struct dev_addr_list **from, int *from_count)
@@ -3946,6 +4126,7 @@ void __dev_addr_unsync(struct dev_addr_list **to, int *to_count,
da = next;
}
}
+EXPORT_SYMBOL_GPL(__dev_addr_unsync);
/**
* dev_unicast_sync - Synchronize device's unicast list to another device
@@ -4064,6 +4245,7 @@ unsigned dev_get_flags(const struct net_device *dev)
return flags;
}
+EXPORT_SYMBOL(dev_get_flags);
/**
* dev_change_flags - change device settings
@@ -4114,12 +4296,13 @@ int dev_change_flags(struct net_device *dev, unsigned flags)
}
if (dev->flags & IFF_UP &&
- ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
+ ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
IFF_VOLATILE)))
call_netdevice_notifiers(NETDEV_CHANGE, dev);
if ((flags ^ dev->gflags) & IFF_PROMISC) {
- int inc = (flags & IFF_PROMISC) ? +1 : -1;
+ int inc = (flags & IFF_PROMISC) ? 1 : -1;
+
dev->gflags ^= IFF_PROMISC;
dev_set_promiscuity(dev, inc);
}
@@ -4129,7 +4312,8 @@ int dev_change_flags(struct net_device *dev, unsigned flags)
IFF_ALLMULTI is requested not asking us and not reporting.
*/
if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
- int inc = (flags & IFF_ALLMULTI) ? +1 : -1;
+ int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
+
dev->gflags ^= IFF_ALLMULTI;
dev_set_allmulti(dev, inc);
}
@@ -4141,6 +4325,7 @@ int dev_change_flags(struct net_device *dev, unsigned flags)
return ret;
}
+EXPORT_SYMBOL(dev_change_flags);
/**
* dev_set_mtu - Change maximum transfer unit
@@ -4174,6 +4359,7 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
return err;
}
+EXPORT_SYMBOL(dev_set_mtu);
/**
* dev_set_mac_address - Change Media Access Control Address
@@ -4198,69 +4384,70 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return err;
}
+EXPORT_SYMBOL(dev_set_mac_address);
/*
- * Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock)
+ * Perform the SIOCxIFxxx calls, inside rcu_read_lock()
*/
static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
{
int err;
- struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+ struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
if (!dev)
return -ENODEV;
switch (cmd) {
- case SIOCGIFFLAGS: /* Get interface flags */
- ifr->ifr_flags = (short) dev_get_flags(dev);
- return 0;
+ case SIOCGIFFLAGS: /* Get interface flags */
+ ifr->ifr_flags = (short) dev_get_flags(dev);
+ return 0;
- case SIOCGIFMETRIC: /* Get the metric on the interface
- (currently unused) */
- ifr->ifr_metric = 0;
- return 0;
+ case SIOCGIFMETRIC: /* Get the metric on the interface
+ (currently unused) */
+ ifr->ifr_metric = 0;
+ return 0;
- case SIOCGIFMTU: /* Get the MTU of a device */
- ifr->ifr_mtu = dev->mtu;
- return 0;
+ case SIOCGIFMTU: /* Get the MTU of a device */
+ ifr->ifr_mtu = dev->mtu;
+ return 0;
- case SIOCGIFHWADDR:
- if (!dev->addr_len)
- memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
- else
- memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- ifr->ifr_hwaddr.sa_family = dev->type;
- return 0;
+ case SIOCGIFHWADDR:
+ if (!dev->addr_len)
+ memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+ else
+ memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ ifr->ifr_hwaddr.sa_family = dev->type;
+ return 0;
- case SIOCGIFSLAVE:
- err = -EINVAL;
- break;
+ case SIOCGIFSLAVE:
+ err = -EINVAL;
+ break;
- case SIOCGIFMAP:
- ifr->ifr_map.mem_start = dev->mem_start;
- ifr->ifr_map.mem_end = dev->mem_end;
- ifr->ifr_map.base_addr = dev->base_addr;
- ifr->ifr_map.irq = dev->irq;
- ifr->ifr_map.dma = dev->dma;
- ifr->ifr_map.port = dev->if_port;
- return 0;
+ case SIOCGIFMAP:
+ ifr->ifr_map.mem_start = dev->mem_start;
+ ifr->ifr_map.mem_end = dev->mem_end;
+ ifr->ifr_map.base_addr = dev->base_addr;
+ ifr->ifr_map.irq = dev->irq;
+ ifr->ifr_map.dma = dev->dma;
+ ifr->ifr_map.port = dev->if_port;
+ return 0;
- case SIOCGIFINDEX:
- ifr->ifr_ifindex = dev->ifindex;
- return 0;
+ case SIOCGIFINDEX:
+ ifr->ifr_ifindex = dev->ifindex;
+ return 0;
- case SIOCGIFTXQLEN:
- ifr->ifr_qlen = dev->tx_queue_len;
- return 0;
+ case SIOCGIFTXQLEN:
+ ifr->ifr_qlen = dev->tx_queue_len;
+ return 0;
- default:
- /* dev_ioctl() should ensure this case
- * is never reached
- */
- WARN_ON(1);
- err = -EINVAL;
- break;
+ default:
+ /* dev_ioctl() should ensure this case
+ * is never reached
+ */
+ WARN_ON(1);
+ err = -EINVAL;
+ break;
}
return err;
@@ -4281,92 +4468,91 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
ops = dev->netdev_ops;
switch (cmd) {
- case SIOCSIFFLAGS: /* Set interface flags */
- return dev_change_flags(dev, ifr->ifr_flags);
-
- case SIOCSIFMETRIC: /* Set the metric on the interface
- (currently unused) */
- return -EOPNOTSUPP;
+ case SIOCSIFFLAGS: /* Set interface flags */
+ return dev_change_flags(dev, ifr->ifr_flags);
- case SIOCSIFMTU: /* Set the MTU of a device */
- return dev_set_mtu(dev, ifr->ifr_mtu);
+ case SIOCSIFMETRIC: /* Set the metric on the interface
+ (currently unused) */
+ return -EOPNOTSUPP;
- case SIOCSIFHWADDR:
- return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+ case SIOCSIFMTU: /* Set the MTU of a device */
+ return dev_set_mtu(dev, ifr->ifr_mtu);
- case SIOCSIFHWBROADCAST:
- if (ifr->ifr_hwaddr.sa_family != dev->type)
- return -EINVAL;
- memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
- return 0;
+ case SIOCSIFHWADDR:
+ return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
- case SIOCSIFMAP:
- if (ops->ndo_set_config) {
- if (!netif_device_present(dev))
- return -ENODEV;
- return ops->ndo_set_config(dev, &ifr->ifr_map);
- }
- return -EOPNOTSUPP;
-
- case SIOCADDMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
- if (!netif_device_present(dev))
- return -ENODEV;
- return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ case SIOCSIFHWBROADCAST:
+ if (ifr->ifr_hwaddr.sa_family != dev->type)
+ return -EINVAL;
+ memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return 0;
- case SIOCDELMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
+ case SIOCSIFMAP:
+ if (ops->ndo_set_config) {
if (!netif_device_present(dev))
return -ENODEV;
- return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ return ops->ndo_set_config(dev, &ifr->ifr_map);
+ }
+ return -EOPNOTSUPP;
- case SIOCSIFTXQLEN:
- if (ifr->ifr_qlen < 0)
- return -EINVAL;
- dev->tx_queue_len = ifr->ifr_qlen;
- return 0;
+ case SIOCADDMULTI:
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCDELMULTI:
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
- case SIOCSIFNAME:
- ifr->ifr_newname[IFNAMSIZ-1] = '\0';
- return dev_change_name(dev, ifr->ifr_newname);
+ case SIOCSIFTXQLEN:
+ if (ifr->ifr_qlen < 0)
+ return -EINVAL;
+ dev->tx_queue_len = ifr->ifr_qlen;
+ return 0;
- /*
- * Unknown or private ioctl
- */
+ case SIOCSIFNAME:
+ ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+ return dev_change_name(dev, ifr->ifr_newname);
- default:
- if ((cmd >= SIOCDEVPRIVATE &&
- cmd <= SIOCDEVPRIVATE + 15) ||
- cmd == SIOCBONDENSLAVE ||
- cmd == SIOCBONDRELEASE ||
- cmd == SIOCBONDSETHWADDR ||
- cmd == SIOCBONDSLAVEINFOQUERY ||
- cmd == SIOCBONDINFOQUERY ||
- cmd == SIOCBONDCHANGEACTIVE ||
- cmd == SIOCGMIIPHY ||
- cmd == SIOCGMIIREG ||
- cmd == SIOCSMIIREG ||
- cmd == SIOCBRADDIF ||
- cmd == SIOCBRDELIF ||
- cmd == SIOCSHWTSTAMP ||
- cmd == SIOCWANDEV) {
- err = -EOPNOTSUPP;
- if (ops->ndo_do_ioctl) {
- if (netif_device_present(dev))
- err = ops->ndo_do_ioctl(dev, ifr, cmd);
- else
- err = -ENODEV;
- }
- } else
- err = -EINVAL;
+ /*
+ * Unknown or private ioctl
+ */
+ default:
+ if ((cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15) ||
+ cmd == SIOCBONDENSLAVE ||
+ cmd == SIOCBONDRELEASE ||
+ cmd == SIOCBONDSETHWADDR ||
+ cmd == SIOCBONDSLAVEINFOQUERY ||
+ cmd == SIOCBONDINFOQUERY ||
+ cmd == SIOCBONDCHANGEACTIVE ||
+ cmd == SIOCGMIIPHY ||
+ cmd == SIOCGMIIREG ||
+ cmd == SIOCSMIIREG ||
+ cmd == SIOCBRADDIF ||
+ cmd == SIOCBRDELIF ||
+ cmd == SIOCSHWTSTAMP ||
+ cmd == SIOCWANDEV) {
+ err = -EOPNOTSUPP;
+ if (ops->ndo_do_ioctl) {
+ if (netif_device_present(dev))
+ err = ops->ndo_do_ioctl(dev, ifr, cmd);
+ else
+ err = -ENODEV;
+ }
+ } else
+ err = -EINVAL;
}
return err;
@@ -4423,135 +4609,135 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
*/
switch (cmd) {
- /*
- * These ioctl calls:
- * - can be done by all.
- * - atomic and do not require locking.
- * - return a value
- */
- case SIOCGIFFLAGS:
- case SIOCGIFMETRIC:
- case SIOCGIFMTU:
- case SIOCGIFHWADDR:
- case SIOCGIFSLAVE:
- case SIOCGIFMAP:
- case SIOCGIFINDEX:
- case SIOCGIFTXQLEN:
- dev_load(net, ifr.ifr_name);
- read_lock(&dev_base_lock);
- ret = dev_ifsioc_locked(net, &ifr, cmd);
- read_unlock(&dev_base_lock);
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ /*
+ * These ioctl calls:
+ * - can be done by all.
+ * - atomic and do not require locking.
+ * - return a value
+ */
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFHWADDR:
+ case SIOCGIFSLAVE:
+ case SIOCGIFMAP:
+ case SIOCGIFINDEX:
+ case SIOCGIFTXQLEN:
+ dev_load(net, ifr.ifr_name);
+ rcu_read_lock();
+ ret = dev_ifsioc_locked(net, &ifr, cmd);
+ rcu_read_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- case SIOCETHTOOL:
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ethtool(net, &ifr);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ case SIOCETHTOOL:
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ethtool(net, &ifr);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- /*
- * These ioctl calls:
- * - require superuser power.
- * - require strict serialization.
- * - return a value
- */
- case SIOCGMIIPHY:
- case SIOCGMIIREG:
- case SIOCSIFNAME:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(net, &ifr, cmd);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - return a value
+ */
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSIFNAME:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- /*
- * These ioctl calls:
- * - require superuser power.
- * - require strict serialization.
- * - do not return a value
- */
- case SIOCSIFFLAGS:
- case SIOCSIFMETRIC:
- case SIOCSIFMTU:
- case SIOCSIFMAP:
- case SIOCSIFHWADDR:
- case SIOCSIFSLAVE:
- case SIOCADDMULTI:
- case SIOCDELMULTI:
- case SIOCSIFHWBROADCAST:
- case SIOCSIFTXQLEN:
- case SIOCSMIIREG:
- case SIOCBONDENSLAVE:
- case SIOCBONDRELEASE:
- case SIOCBONDSETHWADDR:
- case SIOCBONDCHANGEACTIVE:
- case SIOCBRADDIF:
- case SIOCBRDELIF:
- case SIOCSHWTSTAMP:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- /* fall through */
- case SIOCBONDSLAVEINFOQUERY:
- case SIOCBONDINFOQUERY:
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - do not return a value
+ */
+ case SIOCSIFFLAGS:
+ case SIOCSIFMETRIC:
+ case SIOCSIFMTU:
+ case SIOCSIFMAP:
+ case SIOCSIFHWADDR:
+ case SIOCSIFSLAVE:
+ case SIOCADDMULTI:
+ case SIOCDELMULTI:
+ case SIOCSIFHWBROADCAST:
+ case SIOCSIFTXQLEN:
+ case SIOCSMIIREG:
+ case SIOCBONDENSLAVE:
+ case SIOCBONDRELEASE:
+ case SIOCBONDSETHWADDR:
+ case SIOCBONDCHANGEACTIVE:
+ case SIOCBRADDIF:
+ case SIOCBRDELIF:
+ case SIOCSHWTSTAMP:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ /* fall through */
+ case SIOCBONDSLAVEINFOQUERY:
+ case SIOCBONDINFOQUERY:
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ return ret;
+
+ case SIOCGIFMEM:
+ /* Get the per device memory space. We can add this but
+ * currently do not support it */
+ case SIOCSIFMEM:
+ /* Set the per device memory buffer space.
+ * Not applicable in our case */
+ case SIOCSIFLINK:
+ return -EINVAL;
+
+ /*
+ * Unknown or private ioctl.
+ */
+ default:
+ if (cmd == SIOCWANDEV ||
+ (cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15)) {
dev_load(net, ifr.ifr_name);
rtnl_lock();
ret = dev_ifsioc(net, &ifr, cmd);
rtnl_unlock();
+ if (!ret && copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
return ret;
-
- case SIOCGIFMEM:
- /* Get the per device memory space. We can add this but
- * currently do not support it */
- case SIOCSIFMEM:
- /* Set the per device memory buffer space.
- * Not applicable in our case */
- case SIOCSIFLINK:
- return -EINVAL;
-
- /*
- * Unknown or private ioctl.
- */
- default:
- if (cmd == SIOCWANDEV ||
- (cmd >= SIOCDEVPRIVATE &&
- cmd <= SIOCDEVPRIVATE + 15)) {
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(net, &ifr, cmd);
- rtnl_unlock();
- if (!ret && copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- return ret;
- }
- /* Take care of Wireless Extensions */
- if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
- return wext_handle_ioctl(net, &ifr, cmd, arg);
- return -EINVAL;
+ }
+ /* Take care of Wireless Extensions */
+ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
+ return wext_handle_ioctl(net, &ifr, cmd, arg);
+ return -EINVAL;
}
}
@@ -4583,59 +4769,80 @@ static void net_set_todo(struct net_device *dev)
list_add_tail(&dev->todo_list, &net_todo_list);
}
-static void rollback_registered(struct net_device *dev)
+static void rollback_registered_many(struct list_head *head)
{
+ struct net_device *dev;
+
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
- /* Some devices call without registering for initialization unwind. */
- if (dev->reg_state == NETREG_UNINITIALIZED) {
- printk(KERN_DEBUG "unregister_netdevice: device %s/%p never "
- "was registered\n", dev->name, dev);
+ list_for_each_entry(dev, head, unreg_list) {
+ /* Some devices call without registering
+ * for initialization unwind.
+ */
+ if (dev->reg_state == NETREG_UNINITIALIZED) {
+ pr_debug("unregister_netdevice: device %s/%p never "
+ "was registered\n", dev->name, dev);
- WARN_ON(1);
- return;
- }
+ WARN_ON(1);
+ return;
+ }
- BUG_ON(dev->reg_state != NETREG_REGISTERED);
+ BUG_ON(dev->reg_state != NETREG_REGISTERED);
- /* If device is running, close it first. */
- dev_close(dev);
+ /* If device is running, close it first. */
+ dev_close(dev);
- /* And unlink it from device chain. */
- unlist_netdevice(dev);
+ /* And unlink it from device chain. */
+ unlist_netdevice(dev);
- dev->reg_state = NETREG_UNREGISTERING;
+ dev->reg_state = NETREG_UNREGISTERING;
+ }
synchronize_net();
- /* Shutdown queueing discipline. */
- dev_shutdown(dev);
+ list_for_each_entry(dev, head, unreg_list) {
+ /* Shutdown queueing discipline. */
+ dev_shutdown(dev);
- /* Notify protocols, that we are about to destroy
- this device. They should clean all the things.
- */
- call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+ /* Notify protocols, that we are about to destroy
+ this device. They should clean all the things.
+ */
+ call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
- /*
- * Flush the unicast and multicast chains
- */
- dev_unicast_flush(dev);
- dev_addr_discard(dev);
+ /*
+ * Flush the unicast and multicast chains
+ */
+ dev_unicast_flush(dev);
+ dev_addr_discard(dev);
- if (dev->netdev_ops->ndo_uninit)
- dev->netdev_ops->ndo_uninit(dev);
+ if (dev->netdev_ops->ndo_uninit)
+ dev->netdev_ops->ndo_uninit(dev);
- /* Notifier chain MUST detach us from master device. */
- WARN_ON(dev->master);
+ /* Notifier chain MUST detach us from master device. */
+ WARN_ON(dev->master);
- /* Remove entries from kobject tree */
- netdev_unregister_kobject(dev);
+ /* Remove entries from kobject tree */
+ netdev_unregister_kobject(dev);
+ }
+
+ /* Process any work delayed until the end of the batch */
+ dev = list_entry(head->next, struct net_device, unreg_list);
+ call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
synchronize_net();
- dev_put(dev);
+ list_for_each_entry(dev, head, unreg_list)
+ dev_put(dev);
+}
+
+static void rollback_registered(struct net_device *dev)
+{
+ LIST_HEAD(single);
+
+ list_add(&dev->unreg_list, &single);
+ rollback_registered_many(&single);
}
static void __netdev_init_queue_locks_one(struct net_device *dev,
@@ -4694,6 +4901,33 @@ unsigned long netdev_fix_features(unsigned long features, const char *name)
EXPORT_SYMBOL(netdev_fix_features);
/**
+ * netif_stacked_transfer_operstate - transfer operstate
+ * @rootdev: the root or lower level device to transfer state from
+ * @dev: the device to transfer operstate to
+ *
+ * Transfer operational state from root to device. This is normally
+ * called when a stacking relationship exists between the root
+ * device and the device(a leaf device).
+ */
+void netif_stacked_transfer_operstate(const struct net_device *rootdev,
+ struct net_device *dev)
+{
+ if (rootdev->operstate == IF_OPER_DORMANT)
+ netif_dormant_on(dev);
+ else
+ netif_dormant_off(dev);
+
+ if (netif_carrier_ok(rootdev)) {
+ if (!netif_carrier_ok(dev))
+ netif_carrier_on(dev);
+ } else {
+ if (netif_carrier_ok(dev))
+ netif_carrier_off(dev);
+ }
+}
+EXPORT_SYMBOL(netif_stacked_transfer_operstate);
+
+/**
* register_netdevice - register a network device
* @dev: device to register
*
@@ -4712,8 +4946,6 @@ EXPORT_SYMBOL(netdev_fix_features);
int register_netdevice(struct net_device *dev)
{
- struct hlist_head *head;
- struct hlist_node *p;
int ret;
struct net *net = dev_net(dev);
@@ -4742,26 +4974,14 @@ int register_netdevice(struct net_device *dev)
}
}
- if (!dev_valid_name(dev->name)) {
- ret = -EINVAL;
+ ret = dev_get_valid_name(net, dev->name, dev->name, 0);
+ if (ret)
goto err_uninit;
- }
dev->ifindex = dev_new_index(net);
if (dev->iflink == -1)
dev->iflink = dev->ifindex;
- /* Check for existence of name */
- head = dev_name_hash(net, dev->name);
- hlist_for_each(p, head) {
- struct net_device *d
- = hlist_entry(p, struct net_device, name_hlist);
- if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
- ret = -EEXIST;
- goto err_uninit;
- }
- }
-
/* Fix illegal checksum combinations */
if ((dev->features & NETIF_F_HW_CSUM) &&
(dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
@@ -4784,6 +5004,12 @@ int register_netdevice(struct net_device *dev)
dev->features |= NETIF_F_GSO;
netdev_initialize_kobject(dev);
+
+ ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ goto err_uninit;
+
ret = netdev_register_kobject(dev);
if (ret)
goto err_uninit;
@@ -4816,6 +5042,7 @@ err_uninit:
dev->netdev_ops->ndo_uninit(dev);
goto out;
}
+EXPORT_SYMBOL(register_netdevice);
/**
* init_dummy_netdev - init a dummy network device for NAPI
@@ -4907,6 +5134,8 @@ static void netdev_wait_allrefs(struct net_device *dev)
{
unsigned long rebroadcast_time, warning_time;
+ linkwatch_forget_dev(dev);
+
rebroadcast_time = warning_time = jiffies;
while (atomic_read(&dev->refcnt) != 0) {
if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
@@ -4914,6 +5143,8 @@ static void netdev_wait_allrefs(struct net_device *dev)
/* Rebroadcast unregister notification */
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+ /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users
+ * should have already handle it the first time */
if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
&dev->state)) {
@@ -5009,6 +5240,32 @@ void netdev_run_todo(void)
}
/**
+ * dev_txq_stats_fold - fold tx_queues stats
+ * @dev: device to get statistics from
+ * @stats: struct net_device_stats to hold results
+ */
+void dev_txq_stats_fold(const struct net_device *dev,
+ struct net_device_stats *stats)
+{
+ unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
+ unsigned int i;
+ struct netdev_queue *txq;
+
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ txq = netdev_get_tx_queue(dev, i);
+ tx_bytes += txq->tx_bytes;
+ tx_packets += txq->tx_packets;
+ tx_dropped += txq->tx_dropped;
+ }
+ if (tx_bytes || tx_packets || tx_dropped) {
+ stats->tx_bytes = tx_bytes;
+ stats->tx_packets = tx_packets;
+ stats->tx_dropped = tx_dropped;
+ }
+}
+EXPORT_SYMBOL(dev_txq_stats_fold);
+
+/**
* dev_get_stats - get network device statistics
* @dev: device to get statistics from
*
@@ -5022,25 +5279,9 @@ const struct net_device_stats *dev_get_stats(struct net_device *dev)
if (ops->ndo_get_stats)
return ops->ndo_get_stats(dev);
- else {
- unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
- struct net_device_stats *stats = &dev->stats;
- unsigned int i;
- struct netdev_queue *txq;
-
- for (i = 0; i < dev->num_tx_queues; i++) {
- txq = netdev_get_tx_queue(dev, i);
- tx_bytes += txq->tx_bytes;
- tx_packets += txq->tx_packets;
- tx_dropped += txq->tx_dropped;
- }
- if (tx_bytes || tx_packets || tx_dropped) {
- stats->tx_bytes = tx_bytes;
- stats->tx_packets = tx_packets;
- stats->tx_dropped = tx_dropped;
- }
- return stats;
- }
+
+ dev_txq_stats_fold(dev, &dev->stats);
+ return &dev->stats;
}
EXPORT_SYMBOL(dev_get_stats);
@@ -5120,6 +5361,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
netdev_init_queues(dev);
INIT_LIST_HEAD(&dev->napi_list);
+ INIT_LIST_HEAD(&dev->unreg_list);
+ INIT_LIST_HEAD(&dev->link_watch_list);
dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
strcpy(dev->name, name);
@@ -5168,6 +5411,7 @@ void free_netdev(struct net_device *dev)
/* will free via device release */
put_device(&dev->dev);
}
+EXPORT_SYMBOL(free_netdev);
/**
* synchronize_net - Synchronize with packet receive processing
@@ -5180,26 +5424,50 @@ void synchronize_net(void)
might_sleep();
synchronize_rcu();
}
+EXPORT_SYMBOL(synchronize_net);
/**
- * unregister_netdevice - remove device from the kernel
+ * unregister_netdevice_queue - remove device from the kernel
* @dev: device
+ * @head: list
*
* This function shuts down a device interface and removes it
* from the kernel tables.
+ * If head not NULL, device is queued to be unregistered later.
*
* Callers must hold the rtnl semaphore. You may want
* unregister_netdev() instead of this.
*/
-void unregister_netdevice(struct net_device *dev)
+void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
{
ASSERT_RTNL();
- rollback_registered(dev);
- /* Finish processing unregister after unlock */
- net_set_todo(dev);
+ if (head) {
+ list_move_tail(&dev->unreg_list, head);
+ } else {
+ rollback_registered(dev);
+ /* Finish processing unregister after unlock */
+ net_set_todo(dev);
+ }
}
+EXPORT_SYMBOL(unregister_netdevice_queue);
+
+/**
+ * unregister_netdevice_many - unregister many devices
+ * @head: list of devices
+ */
+void unregister_netdevice_many(struct list_head *head)
+{
+ struct net_device *dev;
+
+ if (!list_empty(head)) {
+ rollback_registered_many(head);
+ list_for_each_entry(dev, head, unreg_list)
+ net_set_todo(dev);
+ }
+}
+EXPORT_SYMBOL(unregister_netdevice_many);
/**
* unregister_netdev - remove device from the kernel
@@ -5218,7 +5486,6 @@ void unregister_netdev(struct net_device *dev)
unregister_netdevice(dev);
rtnl_unlock();
}
-
EXPORT_SYMBOL(unregister_netdev);
/**
@@ -5237,8 +5504,6 @@ EXPORT_SYMBOL(unregister_netdev);
int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat)
{
- char buf[IFNAMSIZ];
- const char *destname;
int err;
ASSERT_RTNL();
@@ -5271,20 +5536,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
* we can use it in the destination network namespace.
*/
err = -EEXIST;
- destname = dev->name;
- if (__dev_get_by_name(net, destname)) {
+ if (__dev_get_by_name(net, dev->name)) {
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- if (!dev_valid_name(pat))
- goto out;
- if (strchr(pat, '%')) {
- if (__dev_alloc_name(net, pat, buf) < 0)
- goto out;
- destname = buf;
- } else
- destname = pat;
- if (__dev_get_by_name(net, destname))
+ if (dev_get_valid_name(net, pat, dev->name, 1))
goto out;
}
@@ -5308,6 +5564,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
this device. They should clean all the things.
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
+ call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
/*
* Flush the unicast and multicast chains
@@ -5320,10 +5577,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
/* Actually switch the network namespace */
dev_net_set(dev, net);
- /* Assign the new device name */
- if (destname != dev->name)
- strcpy(dev->name, destname);
-
/* If there is an ifindex conflict assign a new one */
if (__dev_get_by_index(net, dev->ifindex)) {
int iflink = (dev->iflink == dev->ifindex);
@@ -5347,6 +5600,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
out:
return err;
}
+EXPORT_SYMBOL_GPL(dev_change_net_namespace);
static int dev_cpu_callback(struct notifier_block *nfb,
unsigned long action,
@@ -5407,7 +5661,7 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one,
unsigned long mask)
{
/* If device needs checksumming, downgrade to it. */
- if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
+ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM);
else if (mask & NETIF_F_ALL_CSUM) {
/* If one device supports v4/v6 checksumming, set for all. */
@@ -5427,7 +5681,7 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one,
one |= NETIF_F_ALL_CSUM;
one |= all & NETIF_F_ONE_FOR_ALL;
- all &= one | NETIF_F_LLTX | NETIF_F_GSO;
+ all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO;
all |= one & mask & NETIF_F_ONE_FOR_ALL;
return all;
@@ -5509,14 +5763,13 @@ static struct pernet_operations __net_initdata netdev_net_ops = {
static void __net_exit default_device_exit(struct net *net)
{
- struct net_device *dev;
+ struct net_device *dev, *aux;
/*
- * Push all migratable of the network devices back to the
+ * Push all migratable network devices back to the
* initial network namespace
*/
rtnl_lock();
-restart:
- for_each_netdev(net, dev) {
+ for_each_netdev_safe(net, dev, aux) {
int err;
char fb_name[IFNAMSIZ];
@@ -5524,11 +5777,9 @@ restart:
if (dev->features & NETIF_F_NETNS_LOCAL)
continue;
- /* Delete virtual devices */
- if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) {
- dev->rtnl_link_ops->dellink(dev);
- goto restart;
- }
+ /* Leave virtual devices for the generic cleanup */
+ if (dev->rtnl_link_ops)
+ continue;
/* Push remaing network devices to init_net */
snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
@@ -5538,13 +5789,37 @@ restart:
__func__, dev->name, err);
BUG();
}
- goto restart;
}
rtnl_unlock();
}
+static void __net_exit default_device_exit_batch(struct list_head *net_list)
+{
+ /* At exit all network devices most be removed from a network
+ * namespace. Do this in the reverse order of registeration.
+ * Do this across as many network namespaces as possible to
+ * improve batching efficiency.
+ */
+ struct net_device *dev;
+ struct net *net;
+ LIST_HEAD(dev_kill_list);
+
+ rtnl_lock();
+ list_for_each_entry(net, net_list, exit_list) {
+ for_each_netdev_reverse(net, dev) {
+ if (dev->rtnl_link_ops)
+ dev->rtnl_link_ops->dellink(dev, &dev_kill_list);
+ else
+ unregister_netdevice_queue(dev, &dev_kill_list);
+ }
+ }
+ unregister_netdevice_many(&dev_kill_list);
+ rtnl_unlock();
+}
+
static struct pernet_operations __net_initdata default_device_ops = {
.exit = default_device_exit,
+ .exit_batch = default_device_exit_batch,
};
/*
@@ -5633,41 +5908,3 @@ static int __init initialize_hashrnd(void)
late_initcall_sync(initialize_hashrnd);
-EXPORT_SYMBOL(__dev_get_by_index);
-EXPORT_SYMBOL(__dev_get_by_name);
-EXPORT_SYMBOL(__dev_remove_pack);
-EXPORT_SYMBOL(dev_valid_name);
-EXPORT_SYMBOL(dev_add_pack);
-EXPORT_SYMBOL(dev_alloc_name);
-EXPORT_SYMBOL(dev_close);
-EXPORT_SYMBOL(dev_get_by_flags);
-EXPORT_SYMBOL(dev_get_by_index);
-EXPORT_SYMBOL(dev_get_by_name);
-EXPORT_SYMBOL(dev_open);
-EXPORT_SYMBOL(dev_queue_xmit);
-EXPORT_SYMBOL(dev_remove_pack);
-EXPORT_SYMBOL(dev_set_allmulti);
-EXPORT_SYMBOL(dev_set_promiscuity);
-EXPORT_SYMBOL(dev_change_flags);
-EXPORT_SYMBOL(dev_set_mtu);
-EXPORT_SYMBOL(dev_set_mac_address);
-EXPORT_SYMBOL(free_netdev);
-EXPORT_SYMBOL(netdev_boot_setup_check);
-EXPORT_SYMBOL(netdev_set_master);
-EXPORT_SYMBOL(netdev_state_change);
-EXPORT_SYMBOL(netif_receive_skb);
-EXPORT_SYMBOL(netif_rx);
-EXPORT_SYMBOL(register_gifconf);
-EXPORT_SYMBOL(register_netdevice);
-EXPORT_SYMBOL(register_netdevice_notifier);
-EXPORT_SYMBOL(skb_checksum_help);
-EXPORT_SYMBOL(synchronize_net);
-EXPORT_SYMBOL(unregister_netdevice);
-EXPORT_SYMBOL(unregister_netdevice_notifier);
-EXPORT_SYMBOL(net_enable_timestamp);
-EXPORT_SYMBOL(net_disable_timestamp);
-EXPORT_SYMBOL(dev_get_flags);
-
-EXPORT_SYMBOL(dev_load);
-
-EXPORT_PER_CPU_SYMBOL(softnet_data);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 9d66fa953ab7..b8e9d3a86887 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -41,7 +41,7 @@ static void send_dm_alert(struct work_struct *unused);
* netlink alerts
*/
static int trace_state = TRACE_OFF;
-static spinlock_t trace_state_lock = SPIN_LOCK_UNLOCKED;
+static DEFINE_SPINLOCK(trace_state_lock);
struct per_cpu_dm_data {
struct work_struct dm_alert_work;
@@ -52,6 +52,7 @@ struct per_cpu_dm_data {
struct dm_hw_stat_delta {
struct net_device *dev;
+ unsigned long last_rx;
struct list_head list;
struct rcu_head rcu;
unsigned long last_drop_val;
@@ -180,17 +181,25 @@ static void trace_napi_poll_hit(struct napi_struct *napi)
struct dm_hw_stat_delta *new_stat;
/*
- * Ratelimit our check time to dm_hw_check_delta jiffies
+ * Don't check napi structures with no associated device
*/
- if (!time_after(jiffies, napi->dev->last_rx + dm_hw_check_delta))
+ if (!napi->dev)
return;
rcu_read_lock();
list_for_each_entry_rcu(new_stat, &hw_stats_list, list) {
+ /*
+ * only add a note to our monitor buffer if:
+ * 1) this is the dev we received on
+ * 2) its after the last_rx delta
+ * 3) our rx_dropped count has gone up
+ */
if ((new_stat->dev == napi->dev) &&
+ (time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) &&
(napi->dev->stats.rx_dropped != new_stat->last_drop_val)) {
trace_drop_common(NULL, NULL);
new_stat->last_drop_val = napi->dev->stats.rx_dropped;
+ new_stat->last_rx = jiffies;
break;
}
}
@@ -286,6 +295,7 @@ static int dropmon_net_event(struct notifier_block *ev_block,
goto out;
new_stat->dev = dev;
+ new_stat->last_rx = jiffies;
INIT_RCU_HEAD(&new_stat->rcu);
spin_lock(&trace_state_lock);
list_add_rcu(&new_stat->list, &hw_stats_list);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index d9d5160610d5..d8aee584e8d1 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -30,10 +30,17 @@ u32 ethtool_op_get_link(struct net_device *dev)
return netif_carrier_ok(dev) ? 1 : 0;
}
+u32 ethtool_op_get_rx_csum(struct net_device *dev)
+{
+ return (dev->features & NETIF_F_ALL_CSUM) != 0;
+}
+EXPORT_SYMBOL(ethtool_op_get_rx_csum);
+
u32 ethtool_op_get_tx_csum(struct net_device *dev)
{
return (dev->features & NETIF_F_ALL_CSUM) != 0;
}
+EXPORT_SYMBOL(ethtool_op_get_tx_csum);
int ethtool_op_set_tx_csum(struct net_device *dev, u32 data)
{
@@ -191,13 +198,6 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr)
rc = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS);
if (rc >= 0)
info.n_priv_flags = rc;
- } else {
- /* code path for obsolete hooks */
-
- if (ops->self_test_count)
- info.testinfo_len = ops->self_test_count(dev);
- if (ops->get_stats_count)
- info.n_stats = ops->get_stats_count(dev);
}
if (ops->get_regs_len)
info.regdump_len = ops->get_regs_len(dev);
@@ -302,6 +302,26 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
return ret;
}
+static int ethtool_reset(struct net_device *dev, char __user *useraddr)
+{
+ struct ethtool_value reset;
+ int ret;
+
+ if (!dev->ethtool_ops->reset)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&reset, useraddr, sizeof(reset)))
+ return -EFAULT;
+
+ ret = dev->ethtool_ops->reset(dev, &reset.data);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(useraddr, &reset, sizeof(reset)))
+ return -EFAULT;
+ return 0;
+}
+
static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
{
struct ethtool_wolinfo wol = { ETHTOOL_GWOL };
@@ -677,16 +697,10 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
u64 *data;
int ret, test_len;
- if (!ops->self_test)
- return -EOPNOTSUPP;
- if (!ops->get_sset_count && !ops->self_test_count)
+ if (!ops->self_test || !ops->get_sset_count)
return -EOPNOTSUPP;
- if (ops->get_sset_count)
- test_len = ops->get_sset_count(dev, ETH_SS_TEST);
- else
- /* code path for obsolete hook */
- test_len = ops->self_test_count(dev);
+ test_len = ops->get_sset_count(dev, ETH_SS_TEST);
if (test_len < 0)
return test_len;
WARN_ON(test_len == 0);
@@ -721,36 +735,17 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
u8 *data;
int ret;
- if (!ops->get_strings)
+ if (!ops->get_strings || !ops->get_sset_count)
return -EOPNOTSUPP;
if (copy_from_user(&gstrings, useraddr, sizeof(gstrings)))
return -EFAULT;
- if (ops->get_sset_count) {
- ret = ops->get_sset_count(dev, gstrings.string_set);
- if (ret < 0)
- return ret;
-
- gstrings.len = ret;
- } else {
- /* code path for obsolete hooks */
-
- switch (gstrings.string_set) {
- case ETH_SS_TEST:
- if (!ops->self_test_count)
- return -EOPNOTSUPP;
- gstrings.len = ops->self_test_count(dev);
- break;
- case ETH_SS_STATS:
- if (!ops->get_stats_count)
- return -EOPNOTSUPP;
- gstrings.len = ops->get_stats_count(dev);
- break;
- default:
- return -EINVAL;
- }
- }
+ ret = ops->get_sset_count(dev, gstrings.string_set);
+ if (ret < 0)
+ return ret;
+
+ gstrings.len = ret;
data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER);
if (!data)
@@ -791,16 +786,10 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
u64 *data;
int ret, n_stats;
- if (!ops->get_ethtool_stats)
- return -EOPNOTSUPP;
- if (!ops->get_sset_count && !ops->get_stats_count)
+ if (!ops->get_ethtool_stats || !ops->get_sset_count)
return -EOPNOTSUPP;
- if (ops->get_sset_count)
- n_stats = ops->get_sset_count(dev, ETH_SS_STATS);
- else
- /* code path for obsolete hook */
- n_stats = ops->get_stats_count(dev);
+ n_stats = ops->get_sset_count(dev, ETH_SS_STATS);
if (n_stats < 0)
return n_stats;
WARN_ON(n_stats == 0);
@@ -891,6 +880,19 @@ static int ethtool_set_value(struct net_device *dev, char __user *useraddr,
return actor(dev, edata.data);
}
+static int ethtool_flash_device(struct net_device *dev, char __user *useraddr)
+{
+ struct ethtool_flash efl;
+
+ if (copy_from_user(&efl, useraddr, sizeof(efl)))
+ return -EFAULT;
+
+ if (!dev->ethtool_ops->flash_device)
+ return -EOPNOTSUPP;
+
+ return dev->ethtool_ops->flash_device(dev, &efl);
+}
+
/* The main entry point in this file. Called from net/core/dev.c */
int dev_ethtool(struct net *net, struct ifreq *ifr)
@@ -1004,7 +1006,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
break;
case ETHTOOL_GRXCSUM:
rc = ethtool_get_value(dev, useraddr, ethcmd,
- dev->ethtool_ops->get_rx_csum);
+ (dev->ethtool_ops->get_rx_csum ?
+ dev->ethtool_ops->get_rx_csum :
+ ethtool_op_get_rx_csum));
break;
case ETHTOOL_SRXCSUM:
rc = ethtool_set_rx_csum(dev, useraddr);
@@ -1068,7 +1072,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
break;
case ETHTOOL_GFLAGS:
rc = ethtool_get_value(dev, useraddr, ethcmd,
- dev->ethtool_ops->get_flags);
+ (dev->ethtool_ops->get_flags ?
+ dev->ethtool_ops->get_flags :
+ ethtool_op_get_flags));
break;
case ETHTOOL_SFLAGS:
rc = ethtool_set_value(dev, useraddr,
@@ -1100,6 +1106,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_SGRO:
rc = ethtool_set_gro(dev, useraddr);
break;
+ case ETHTOOL_FLASHDEV:
+ rc = ethtool_flash_device(dev, useraddr);
+ break;
+ case ETHTOOL_RESET:
+ rc = ethtool_reset(dev, useraddr);
+ break;
default:
rc = -EOPNOTSUPP;
}
@@ -1116,7 +1128,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
EXPORT_SYMBOL(ethtool_op_get_link);
EXPORT_SYMBOL(ethtool_op_get_sg);
EXPORT_SYMBOL(ethtool_op_get_tso);
-EXPORT_SYMBOL(ethtool_op_get_tx_csum);
EXPORT_SYMBOL(ethtool_op_set_sg);
EXPORT_SYMBOL(ethtool_op_set_tso);
EXPORT_SYMBOL(ethtool_op_set_tx_csum);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index bd309384f8b8..02a3b2c69c1e 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -72,7 +72,7 @@ static void flush_route_cache(struct fib_rules_ops *ops)
ops->flush_cache(ops);
}
-int fib_rules_register(struct fib_rules_ops *ops)
+static int __fib_rules_register(struct fib_rules_ops *ops)
{
int err = -EEXIST;
struct fib_rules_ops *o;
@@ -102,6 +102,28 @@ errout:
return err;
}
+struct fib_rules_ops *
+fib_rules_register(struct fib_rules_ops *tmpl, struct net *net)
+{
+ struct fib_rules_ops *ops;
+ int err;
+
+ ops = kmemdup(tmpl, sizeof (*ops), GFP_KERNEL);
+ if (ops == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ INIT_LIST_HEAD(&ops->rules_list);
+ ops->fro_net = net;
+
+ err = __fib_rules_register(ops);
+ if (err) {
+ kfree(ops);
+ ops = ERR_PTR(err);
+ }
+
+ return ops;
+}
+
EXPORT_SYMBOL_GPL(fib_rules_register);
void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
@@ -115,6 +137,15 @@ void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
}
EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops);
+static void fib_rules_put_rcu(struct rcu_head *head)
+{
+ struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu);
+ struct net *net = ops->fro_net;
+
+ release_net(net);
+ kfree(ops);
+}
+
void fib_rules_unregister(struct fib_rules_ops *ops)
{
struct net *net = ops->fro_net;
@@ -124,8 +155,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
fib_rules_cleanup_ops(ops);
spin_unlock(&net->rules_mod_lock);
- synchronize_rcu();
- release_net(net);
+ call_rcu(&ops->rcu, fib_rules_put_rcu);
}
EXPORT_SYMBOL_GPL(fib_rules_unregister);
@@ -135,7 +165,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
{
int ret = 0;
- if (rule->ifindex && (rule->ifindex != fl->iif))
+ if (rule->iifindex && (rule->iifindex != fl->iif))
+ goto out;
+
+ if (rule->oifindex && (rule->oifindex != fl->oif))
goto out;
if ((rule->mark ^ fl->mark) & rule->mark_mask)
@@ -248,14 +281,24 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
if (tb[FRA_PRIORITY])
rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
- if (tb[FRA_IFNAME]) {
+ if (tb[FRA_IIFNAME]) {
+ struct net_device *dev;
+
+ rule->iifindex = -1;
+ nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+ dev = __dev_get_by_name(net, rule->iifname);
+ if (dev)
+ rule->iifindex = dev->ifindex;
+ }
+
+ if (tb[FRA_OIFNAME]) {
struct net_device *dev;
- rule->ifindex = -1;
- nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ);
- dev = __dev_get_by_name(net, rule->ifname);
+ rule->oifindex = -1;
+ nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+ dev = __dev_get_by_name(net, rule->oifname);
if (dev)
- rule->ifindex = dev->ifindex;
+ rule->oifindex = dev->ifindex;
}
if (tb[FRA_FWMARK]) {
@@ -274,7 +317,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
rule->flags = frh->flags;
rule->table = frh_get_table(frh, tb);
- if (!rule->pref && ops->default_pref)
+ if (!tb[FRA_PRIORITY] && ops->default_pref)
rule->pref = ops->default_pref(ops);
err = -EINVAL;
@@ -388,8 +431,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
(rule->pref != nla_get_u32(tb[FRA_PRIORITY])))
continue;
- if (tb[FRA_IFNAME] &&
- nla_strcmp(tb[FRA_IFNAME], rule->ifname))
+ if (tb[FRA_IIFNAME] &&
+ nla_strcmp(tb[FRA_IIFNAME], rule->iifname))
+ continue;
+
+ if (tb[FRA_OIFNAME] &&
+ nla_strcmp(tb[FRA_OIFNAME], rule->oifname))
continue;
if (tb[FRA_FWMARK] &&
@@ -447,7 +494,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
struct fib_rule *rule)
{
size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr))
- + nla_total_size(IFNAMSIZ) /* FRA_IFNAME */
+ + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */
+ + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */
+ nla_total_size(4) /* FRA_PRIORITY */
+ nla_total_size(4) /* FRA_TABLE */
+ nla_total_size(4) /* FRA_FWMARK */
@@ -481,11 +529,18 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL)
frh->flags |= FIB_RULE_UNRESOLVED;
- if (rule->ifname[0]) {
- NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname);
+ if (rule->iifname[0]) {
+ NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname);
- if (rule->ifindex == -1)
- frh->flags |= FIB_RULE_DEV_DETACHED;
+ if (rule->iifindex == -1)
+ frh->flags |= FIB_RULE_IIF_DETACHED;
+ }
+
+ if (rule->oifname[0]) {
+ NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname);
+
+ if (rule->oifindex == -1)
+ frh->flags |= FIB_RULE_OIF_DETACHED;
}
if (rule->pref)
@@ -600,9 +655,12 @@ static void attach_rules(struct list_head *rules, struct net_device *dev)
struct fib_rule *rule;
list_for_each_entry(rule, rules, list) {
- if (rule->ifindex == -1 &&
- strcmp(dev->name, rule->ifname) == 0)
- rule->ifindex = dev->ifindex;
+ if (rule->iifindex == -1 &&
+ strcmp(dev->name, rule->iifname) == 0)
+ rule->iifindex = dev->ifindex;
+ if (rule->oifindex == -1 &&
+ strcmp(dev->name, rule->oifname) == 0)
+ rule->oifindex = dev->ifindex;
}
}
@@ -610,9 +668,12 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
{
struct fib_rule *rule;
- list_for_each_entry(rule, rules, list)
- if (rule->ifindex == dev->ifindex)
- rule->ifindex = -1;
+ list_for_each_entry(rule, rules, list) {
+ if (rule->iifindex == dev->ifindex)
+ rule->iifindex = -1;
+ if (rule->oifindex == dev->ifindex)
+ rule->oifindex = -1;
+ }
}
diff --git a/net/core/filter.c b/net/core/filter.c
index d1d779ca096d..08db7b9143a3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -303,6 +303,12 @@ load_b:
case SKF_AD_IFINDEX:
A = skb->dev->ifindex;
continue;
+ case SKF_AD_MARK:
+ A = skb->mark;
+ continue;
+ case SKF_AD_QUEUE:
+ A = skb->queue_mapping;
+ continue;
case SKF_AD_NLATTR: {
struct nlattr *nla;
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 8569310268ab..393b1d8618e2 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -127,6 +127,7 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b)
/**
* gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV
* @d: dumping handle
+ * @b: basic statistics
* @r: rate estimator statistics
*
* Appends the rate estimator statistics to the top level TLV created by
@@ -136,8 +137,13 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b)
* if the room in the socket buffer was not sufficient.
*/
int
-gnet_stats_copy_rate_est(struct gnet_dump *d, struct gnet_stats_rate_est *r)
+gnet_stats_copy_rate_est(struct gnet_dump *d,
+ const struct gnet_stats_basic_packed *b,
+ struct gnet_stats_rate_est *r)
{
+ if (b && !gen_estimator_active(b, r))
+ return 0;
+
if (d->compat_tc_stats) {
d->tc_stats.bps = r->bps;
d->tc_stats.pps = r->pps;
diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index bf8f7af699d7..5910b555a54a 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -35,7 +35,7 @@ static unsigned long linkwatch_nextevent;
static void linkwatch_event(struct work_struct *dummy);
static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event);
-static struct net_device *lweventlist;
+static LIST_HEAD(lweventlist);
static DEFINE_SPINLOCK(lweventlist_lock);
static unsigned char default_operstate(const struct net_device *dev)
@@ -89,8 +89,10 @@ static void linkwatch_add_event(struct net_device *dev)
unsigned long flags;
spin_lock_irqsave(&lweventlist_lock, flags);
- dev->link_watch_next = lweventlist;
- lweventlist = dev;
+ if (list_empty(&dev->link_watch_list)) {
+ list_add_tail(&dev->link_watch_list, &lweventlist);
+ dev_hold(dev);
+ }
spin_unlock_irqrestore(&lweventlist_lock, flags);
}
@@ -133,9 +135,35 @@ static void linkwatch_schedule_work(int urgent)
}
+static void linkwatch_do_dev(struct net_device *dev)
+{
+ /*
+ * Make sure the above read is complete since it can be
+ * rewritten as soon as we clear the bit below.
+ */
+ smp_mb__before_clear_bit();
+
+ /* We are about to handle this device,
+ * so new events can be accepted
+ */
+ clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state);
+
+ rfc2863_policy(dev);
+ if (dev->flags & IFF_UP) {
+ if (netif_carrier_ok(dev))
+ dev_activate(dev);
+ else
+ dev_deactivate(dev);
+
+ netdev_state_change(dev);
+ }
+ dev_put(dev);
+}
+
static void __linkwatch_run_queue(int urgent_only)
{
- struct net_device *next;
+ struct net_device *dev;
+ LIST_HEAD(wrk);
/*
* Limit the number of linkwatch events to one
@@ -153,46 +181,40 @@ static void __linkwatch_run_queue(int urgent_only)
clear_bit(LW_URGENT, &linkwatch_flags);
spin_lock_irq(&lweventlist_lock);
- next = lweventlist;
- lweventlist = NULL;
- spin_unlock_irq(&lweventlist_lock);
+ list_splice_init(&lweventlist, &wrk);
- while (next) {
- struct net_device *dev = next;
+ while (!list_empty(&wrk)) {
- next = dev->link_watch_next;
+ dev = list_first_entry(&wrk, struct net_device, link_watch_list);
+ list_del_init(&dev->link_watch_list);
if (urgent_only && !linkwatch_urgent_event(dev)) {
- linkwatch_add_event(dev);
+ list_add_tail(&dev->link_watch_list, &lweventlist);
continue;
}
-
- /*
- * Make sure the above read is complete since it can be
- * rewritten as soon as we clear the bit below.
- */
- smp_mb__before_clear_bit();
-
- /* We are about to handle this device,
- * so new events can be accepted
- */
- clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state);
-
- rfc2863_policy(dev);
- if (dev->flags & IFF_UP) {
- if (netif_carrier_ok(dev))
- dev_activate(dev);
- else
- dev_deactivate(dev);
-
- netdev_state_change(dev);
- }
-
- dev_put(dev);
+ spin_unlock_irq(&lweventlist_lock);
+ linkwatch_do_dev(dev);
+ spin_lock_irq(&lweventlist_lock);
}
- if (lweventlist)
+ if (!list_empty(&lweventlist))
linkwatch_schedule_work(0);
+ spin_unlock_irq(&lweventlist_lock);
+}
+
+void linkwatch_forget_dev(struct net_device *dev)
+{
+ unsigned long flags;
+ int clean = 0;
+
+ spin_lock_irqsave(&lweventlist_lock, flags);
+ if (!list_empty(&dev->link_watch_list)) {
+ list_del_init(&dev->link_watch_list);
+ clean = 1;
+ }
+ spin_unlock_irqrestore(&lweventlist_lock, flags);
+ if (clean)
+ linkwatch_do_dev(dev);
}
@@ -216,8 +238,6 @@ void linkwatch_fire_event(struct net_device *dev)
bool urgent = linkwatch_urgent_event(dev);
if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) {
- dev_hold(dev);
-
linkwatch_add_event(dev);
} else if (!urgent)
return;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 163b4f5b0365..f35377b643e4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -692,75 +692,74 @@ static void neigh_connect(struct neighbour *neigh)
hh->hh_output = neigh->ops->hh_output;
}
-static void neigh_periodic_timer(unsigned long arg)
+static void neigh_periodic_work(struct work_struct *work)
{
- struct neigh_table *tbl = (struct neigh_table *)arg;
+ struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work);
struct neighbour *n, **np;
- unsigned long expire, now = jiffies;
+ unsigned int i;
NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs);
- write_lock(&tbl->lock);
+ write_lock_bh(&tbl->lock);
/*
* periodically recompute ReachableTime from random function
*/
- if (time_after(now, tbl->last_rand + 300 * HZ)) {
+ if (time_after(jiffies, tbl->last_rand + 300 * HZ)) {
struct neigh_parms *p;
- tbl->last_rand = now;
+ tbl->last_rand = jiffies;
for (p = &tbl->parms; p; p = p->next)
p->reachable_time =
neigh_rand_reach_time(p->base_reachable_time);
}
- np = &tbl->hash_buckets[tbl->hash_chain_gc];
- tbl->hash_chain_gc = ((tbl->hash_chain_gc + 1) & tbl->hash_mask);
+ for (i = 0 ; i <= tbl->hash_mask; i++) {
+ np = &tbl->hash_buckets[i];
- while ((n = *np) != NULL) {
- unsigned int state;
+ while ((n = *np) != NULL) {
+ unsigned int state;
- write_lock(&n->lock);
+ write_lock(&n->lock);
- state = n->nud_state;
- if (state & (NUD_PERMANENT | NUD_IN_TIMER)) {
- write_unlock(&n->lock);
- goto next_elt;
- }
+ state = n->nud_state;
+ if (state & (NUD_PERMANENT | NUD_IN_TIMER)) {
+ write_unlock(&n->lock);
+ goto next_elt;
+ }
- if (time_before(n->used, n->confirmed))
- n->used = n->confirmed;
+ if (time_before(n->used, n->confirmed))
+ n->used = n->confirmed;
- if (atomic_read(&n->refcnt) == 1 &&
- (state == NUD_FAILED ||
- time_after(now, n->used + n->parms->gc_staletime))) {
- *np = n->next;
- n->dead = 1;
+ if (atomic_read(&n->refcnt) == 1 &&
+ (state == NUD_FAILED ||
+ time_after(jiffies, n->used + n->parms->gc_staletime))) {
+ *np = n->next;
+ n->dead = 1;
+ write_unlock(&n->lock);
+ neigh_cleanup_and_release(n);
+ continue;
+ }
write_unlock(&n->lock);
- neigh_cleanup_and_release(n);
- continue;
- }
- write_unlock(&n->lock);
next_elt:
- np = &n->next;
+ np = &n->next;
+ }
+ /*
+ * It's fine to release lock here, even if hash table
+ * grows while we are preempted.
+ */
+ write_unlock_bh(&tbl->lock);
+ cond_resched();
+ write_lock_bh(&tbl->lock);
}
-
/* Cycle through all hash buckets every base_reachable_time/2 ticks.
* ARP entry timeouts range from 1/2 base_reachable_time to 3/2
* base_reachable_time.
*/
- expire = tbl->parms.base_reachable_time >> 1;
- expire /= (tbl->hash_mask + 1);
- if (!expire)
- expire = 1;
-
- if (expire>HZ)
- mod_timer(&tbl->gc_timer, round_jiffies(now + expire));
- else
- mod_timer(&tbl->gc_timer, now + expire);
-
- write_unlock(&tbl->lock);
+ schedule_delayed_work(&tbl->gc_work,
+ tbl->parms.base_reachable_time >> 1);
+ write_unlock_bh(&tbl->lock);
}
static __inline__ int neigh_max_probes(struct neighbour *n)
@@ -1316,7 +1315,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
}
EXPORT_SYMBOL(pneigh_enqueue);
-static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl,
+static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl,
struct net *net, int ifindex)
{
struct neigh_parms *p;
@@ -1337,7 +1336,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
struct net *net = dev_net(dev);
const struct net_device_ops *ops = dev->netdev_ops;
- ref = lookup_neigh_params(tbl, net, 0);
+ ref = lookup_neigh_parms(tbl, net, 0);
if (!ref)
return NULL;
@@ -1442,10 +1441,8 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl)
get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd));
rwlock_init(&tbl->lock);
- setup_timer(&tbl->gc_timer, neigh_periodic_timer, (unsigned long)tbl);
- tbl->gc_timer.expires = now + 1;
- add_timer(&tbl->gc_timer);
-
+ INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work);
+ schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time);
setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl);
skb_queue_head_init_class(&tbl->proxy_queue,
&neigh_table_proxy_queue_class);
@@ -1482,7 +1479,8 @@ int neigh_table_clear(struct neigh_table *tbl)
struct neigh_table **tp;
/* It is not clean... Fix it to unload IPv6 module safely */
- del_timer_sync(&tbl->gc_timer);
+ cancel_delayed_work(&tbl->gc_work);
+ flush_scheduled_work();
del_timer_sync(&tbl->proxy_timer);
pneigh_queue_purge(&tbl->proxy_queue);
neigh_ifdown(tbl, NULL);
@@ -1752,7 +1750,6 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
.ndtc_last_rand = jiffies_to_msecs(rand_delta),
.ndtc_hash_rnd = tbl->hash_rnd,
.ndtc_hash_mask = tbl->hash_mask,
- .ndtc_hash_chain_gc = tbl->hash_chain_gc,
.ndtc_proxy_qlen = tbl->proxy_queue.qlen,
};
@@ -1906,7 +1903,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
if (tbp[NDTPA_IFINDEX])
ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]);
- p = lookup_neigh_params(tbl, net, ifindex);
+ p = lookup_neigh_parms(tbl, net, ifindex);
if (p == NULL) {
err = -ENOENT;
goto errout_tbl_lock;
@@ -2095,7 +2092,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
if (h > s_h)
s_idx = 0;
for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) {
- if (dev_net(n->dev) != net)
+ if (!net_eq(dev_net(n->dev), net))
continue;
if (idx < s_idx)
goto next;
@@ -2569,21 +2566,18 @@ static struct neigh_sysctl_table {
} neigh_sysctl_template __read_mostly = {
.neigh_vars = {
{
- .ctl_name = NET_NEIGH_MCAST_SOLICIT,
.procname = "mcast_solicit",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_NEIGH_UCAST_SOLICIT,
.procname = "ucast_solicit",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_NEIGH_APP_SOLICIT,
.procname = "app_solicit",
.maxlen = sizeof(int),
.mode = 0644,
@@ -2596,38 +2590,30 @@ static struct neigh_sysctl_table {
.proc_handler = proc_dointvec_userhz_jiffies,
},
{
- .ctl_name = NET_NEIGH_REACHABLE_TIME,
.procname = "base_reachable_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_NEIGH_DELAY_PROBE_TIME,
.procname = "delay_first_probe_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_NEIGH_GC_STALE_TIME,
.procname = "gc_stale_time",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_NEIGH_UNRES_QLEN,
.procname = "unres_qlen",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_NEIGH_PROXY_QLEN,
.procname = "proxy_qlen",
.maxlen = sizeof(int),
.mode = 0644,
@@ -2652,45 +2638,36 @@ static struct neigh_sysctl_table {
.proc_handler = proc_dointvec_userhz_jiffies,
},
{
- .ctl_name = NET_NEIGH_RETRANS_TIME_MS,
.procname = "retrans_time_ms",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
- .strategy = sysctl_ms_jiffies,
},
{
- .ctl_name = NET_NEIGH_REACHABLE_TIME_MS,
.procname = "base_reachable_time_ms",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
- .strategy = sysctl_ms_jiffies,
},
{
- .ctl_name = NET_NEIGH_GC_INTERVAL,
.procname = "gc_interval",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_NEIGH_GC_THRESH1,
.procname = "gc_thresh1",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_NEIGH_GC_THRESH2,
.procname = "gc_thresh2",
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_NEIGH_GC_THRESH3,
.procname = "gc_thresh3",
.maxlen = sizeof(int),
.mode = 0644,
@@ -2702,7 +2679,7 @@ static struct neigh_sysctl_table {
int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
int p_id, int pdev_id, char *p_name,
- proc_handler *handler, ctl_handler *strategy)
+ proc_handler *handler)
{
struct neigh_sysctl_table *t;
const char *dev_name_source = NULL;
@@ -2713,10 +2690,10 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
#define NEIGH_CTL_PATH_DEV 3
struct ctl_path neigh_path[] = {
- { .procname = "net", .ctl_name = CTL_NET, },
- { .procname = "proto", .ctl_name = 0, },
- { .procname = "neigh", .ctl_name = 0, },
- { .procname = "default", .ctl_name = NET_PROTO_CONF_DEFAULT, },
+ { .procname = "net", },
+ { .procname = "proto", },
+ { .procname = "neigh", },
+ { .procname = "default", },
{ },
};
@@ -2741,7 +2718,6 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
if (dev) {
dev_name_source = dev->name;
- neigh_path[NEIGH_CTL_PATH_DEV].ctl_name = dev->ifindex;
/* Terminate the table early */
memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14]));
} else {
@@ -2753,31 +2729,19 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
}
- if (handler || strategy) {
+ if (handler) {
/* RetransTime */
t->neigh_vars[3].proc_handler = handler;
- t->neigh_vars[3].strategy = strategy;
t->neigh_vars[3].extra1 = dev;
- if (!strategy)
- t->neigh_vars[3].ctl_name = CTL_UNNUMBERED;
/* ReachableTime */
t->neigh_vars[4].proc_handler = handler;
- t->neigh_vars[4].strategy = strategy;
t->neigh_vars[4].extra1 = dev;
- if (!strategy)
- t->neigh_vars[4].ctl_name = CTL_UNNUMBERED;
/* RetransTime (in milliseconds)*/
t->neigh_vars[12].proc_handler = handler;
- t->neigh_vars[12].strategy = strategy;
t->neigh_vars[12].extra1 = dev;
- if (!strategy)
- t->neigh_vars[12].ctl_name = CTL_UNNUMBERED;
/* ReachableTime (in milliseconds) */
t->neigh_vars[13].proc_handler = handler;
- t->neigh_vars[13].strategy = strategy;
t->neigh_vars[13].extra1 = dev;
- if (!strategy)
- t->neigh_vars[13].ctl_name = CTL_UNNUMBERED;
}
t->dev_name = kstrdup(dev_name_source, GFP_KERNEL);
@@ -2785,9 +2749,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
goto free;
neigh_path[NEIGH_CTL_PATH_DEV].procname = t->dev_name;
- neigh_path[NEIGH_CTL_PATH_NEIGH].ctl_name = pdev_id;
neigh_path[NEIGH_CTL_PATH_PROTO].procname = p_name;
- neigh_path[NEIGH_CTL_PATH_PROTO].ctl_name = p_id;
t->sysctl_header =
register_net_sysctl_table(neigh_parms_net(p), neigh_path, t->neigh_vars);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 3994680c08b9..fbc1c7472c5e 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -16,7 +16,7 @@
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/wireless.h>
-#include <net/iw_handler.h>
+#include <net/wext.h>
#include "net-sysfs.h"
@@ -130,6 +130,48 @@ static ssize_t show_carrier(struct device *dev,
return -EINVAL;
}
+static ssize_t show_speed(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct net_device *netdev = to_net_dev(dev);
+ int ret = -EINVAL;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ if (netif_running(netdev) &&
+ netdev->ethtool_ops &&
+ netdev->ethtool_ops->get_settings) {
+ struct ethtool_cmd cmd = { ETHTOOL_GSET };
+
+ if (!netdev->ethtool_ops->get_settings(netdev, &cmd))
+ ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd));
+ }
+ rtnl_unlock();
+ return ret;
+}
+
+static ssize_t show_duplex(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct net_device *netdev = to_net_dev(dev);
+ int ret = -EINVAL;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+ if (netif_running(netdev) &&
+ netdev->ethtool_ops &&
+ netdev->ethtool_ops->get_settings) {
+ struct ethtool_cmd cmd = { ETHTOOL_GSET };
+
+ if (!netdev->ethtool_ops->get_settings(netdev, &cmd))
+ ret = sprintf(buf, "%s\n", cmd.duplex ? "full" : "half");
+ }
+ rtnl_unlock();
+ return ret;
+}
+
static ssize_t show_dormant(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -141,7 +183,7 @@ static ssize_t show_dormant(struct device *dev,
return -EINVAL;
}
-static const char *operstates[] = {
+static const char *const operstates[] = {
"unknown",
"notpresent", /* currently unused */
"down",
@@ -259,6 +301,8 @@ static struct device_attribute net_class_attributes[] = {
__ATTR(address, S_IRUGO, show_address, NULL),
__ATTR(broadcast, S_IRUGO, show_broadcast, NULL),
__ATTR(carrier, S_IRUGO, show_carrier, NULL),
+ __ATTR(speed, S_IRUGO, show_speed, NULL),
+ __ATTR(duplex, S_IRUGO, show_duplex, NULL),
__ATTR(dormant, S_IRUGO, show_dormant, NULL),
__ATTR(operstate, S_IRUGO, show_operstate, NULL),
__ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu),
@@ -363,18 +407,16 @@ static ssize_t wireless_show(struct device *d, char *buf,
char *))
{
struct net_device *dev = to_net_dev(d);
- const struct iw_statistics *iw = NULL;
+ const struct iw_statistics *iw;
ssize_t ret = -EINVAL;
- read_lock(&dev_base_lock);
+ rtnl_lock();
if (dev_isalive(dev)) {
- if (dev->wireless_handlers &&
- dev->wireless_handlers->get_wireless_stats)
- iw = dev->wireless_handlers->get_wireless_stats(dev);
- if (iw != NULL)
+ iw = get_wireless_stats(dev);
+ if (iw)
ret = (*format)(iw, buf);
}
- read_unlock(&dev_base_lock);
+ rtnl_unlock();
return ret;
}
@@ -483,7 +525,7 @@ void netdev_unregister_kobject(struct net_device * net)
kobject_get(&dev->kobj);
- if (dev_net(net) != &init_net)
+ if (!net_eq(dev_net(net), &init_net))
return;
device_del(dev);
@@ -493,7 +535,7 @@ void netdev_unregister_kobject(struct net_device * net)
int netdev_register_kobject(struct net_device *net)
{
struct device *dev = &(net->dev);
- struct attribute_group **groups = net->sysfs_groups;
+ const struct attribute_group **groups = net->sysfs_groups;
dev->class = &net_class;
dev->platform_data = net;
@@ -502,15 +544,22 @@ int netdev_register_kobject(struct net_device *net)
dev_set_name(dev, "%s", net->name);
#ifdef CONFIG_SYSFS
- *groups++ = &netstat_group;
+ /* Allow for a device specific group */
+ if (*groups)
+ groups++;
+ *groups++ = &netstat_group;
#ifdef CONFIG_WIRELESS_EXT_SYSFS
- if (net->wireless_handlers && net->wireless_handlers->get_wireless_stats)
+ if (net->ieee80211_ptr)
*groups++ = &wireless_group;
+#ifdef CONFIG_WIRELESS_EXT
+ else if (net->wireless_handlers)
+ *groups++ = &wireless_group;
+#endif
#endif
#endif /* CONFIG_SYSFS */
- if (dev_net(net) != &init_net)
+ if (!net_eq(dev_net(net), &init_net))
return 0;
return device_add(dev);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 197283072cc8..bd8c4712ea24 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -6,6 +6,8 @@
#include <linux/delay.h>
#include <linux/sched.h>
#include <linux/idr.h>
+#include <linux/rculist.h>
+#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
@@ -25,14 +27,64 @@ EXPORT_SYMBOL(init_net);
#define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */
+static int ops_init(const struct pernet_operations *ops, struct net *net)
+{
+ int err;
+ if (ops->id && ops->size) {
+ void *data = kzalloc(ops->size, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ err = net_assign_generic(net, *ops->id, data);
+ if (err) {
+ kfree(data);
+ return err;
+ }
+ }
+ if (ops->init)
+ return ops->init(net);
+ return 0;
+}
+
+static void ops_free(const struct pernet_operations *ops, struct net *net)
+{
+ if (ops->id && ops->size) {
+ int id = *ops->id;
+ kfree(net_generic(net, id));
+ }
+}
+
+static void ops_exit_list(const struct pernet_operations *ops,
+ struct list_head *net_exit_list)
+{
+ struct net *net;
+ if (ops->exit) {
+ list_for_each_entry(net, net_exit_list, exit_list)
+ ops->exit(net);
+ }
+ if (ops->exit_batch)
+ ops->exit_batch(net_exit_list);
+}
+
+static void ops_free_list(const struct pernet_operations *ops,
+ struct list_head *net_exit_list)
+{
+ struct net *net;
+ if (ops->size && ops->id) {
+ list_for_each_entry(net, net_exit_list, exit_list)
+ ops_free(ops, net);
+ }
+}
+
/*
* setup_net runs the initializers for the network namespace object.
*/
static __net_init int setup_net(struct net *net)
{
/* Must be called with net_mutex held */
- struct pernet_operations *ops;
+ const struct pernet_operations *ops, *saved_ops;
int error = 0;
+ LIST_HEAD(net_exit_list);
atomic_set(&net->count, 1);
@@ -41,11 +93,9 @@ static __net_init int setup_net(struct net *net)
#endif
list_for_each_entry(ops, &pernet_list, list) {
- if (ops->init) {
- error = ops->init(net);
- if (error < 0)
- goto out_undo;
- }
+ error = ops_init(ops, net);
+ if (error < 0)
+ goto out_undo;
}
out:
return error;
@@ -54,10 +104,14 @@ out_undo:
/* Walk through the list backwards calling the exit functions
* for the pernet modules whose init functions did not fail.
*/
- list_for_each_entry_continue_reverse(ops, &pernet_list, list) {
- if (ops->exit)
- ops->exit(net);
- }
+ list_add(&net->exit_list, &net_exit_list);
+ saved_ops = ops;
+ list_for_each_entry_continue_reverse(ops, &pernet_list, list)
+ ops_exit_list(ops, &net_exit_list);
+
+ ops = saved_ops;
+ list_for_each_entry_continue_reverse(ops, &pernet_list, list)
+ ops_free_list(ops, &net_exit_list);
rcu_barrier();
goto out;
@@ -127,7 +181,7 @@ static struct net *net_create(void)
rv = setup_net(net);
if (rv == 0) {
rtnl_lock();
- list_add_tail(&net->list, &net_namespace_list);
+ list_add_tail_rcu(&net->list, &net_namespace_list);
rtnl_unlock();
}
mutex_unlock(&net_mutex);
@@ -145,25 +199,45 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
return net_create();
}
+static DEFINE_SPINLOCK(cleanup_list_lock);
+static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */
+
static void cleanup_net(struct work_struct *work)
{
- struct pernet_operations *ops;
- struct net *net;
+ const struct pernet_operations *ops;
+ struct net *net, *tmp;
+ LIST_HEAD(net_kill_list);
+ LIST_HEAD(net_exit_list);
- net = container_of(work, struct net, work);
+ /* Atomically snapshot the list of namespaces to cleanup */
+ spin_lock_irq(&cleanup_list_lock);
+ list_replace_init(&cleanup_list, &net_kill_list);
+ spin_unlock_irq(&cleanup_list_lock);
mutex_lock(&net_mutex);
/* Don't let anyone else find us. */
rtnl_lock();
- list_del(&net->list);
+ list_for_each_entry(net, &net_kill_list, cleanup_list) {
+ list_del_rcu(&net->list);
+ list_add_tail(&net->exit_list, &net_exit_list);
+ }
rtnl_unlock();
+ /*
+ * Another CPU might be rcu-iterating the list, wait for it.
+ * This needs to be before calling the exit() notifiers, so
+ * the rcu_barrier() below isn't sufficient alone.
+ */
+ synchronize_rcu();
+
/* Run all of the network namespace exit methods */
- list_for_each_entry_reverse(ops, &pernet_list, list) {
- if (ops->exit)
- ops->exit(net);
- }
+ list_for_each_entry_reverse(ops, &pernet_list, list)
+ ops_exit_list(ops, &net_exit_list);
+
+ /* Free the net generic variables */
+ list_for_each_entry_reverse(ops, &pernet_list, list)
+ ops_free_list(ops, &net_exit_list);
mutex_unlock(&net_mutex);
@@ -173,14 +247,23 @@ static void cleanup_net(struct work_struct *work)
rcu_barrier();
/* Finally it is safe to free my network namespace structure */
- net_free(net);
+ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
+ list_del_init(&net->exit_list);
+ net_free(net);
+ }
}
+static DECLARE_WORK(net_cleanup_work, cleanup_net);
void __put_net(struct net *net)
{
/* Cleanup the network namespace in process context */
- INIT_WORK(&net->work, cleanup_net);
- queue_work(netns_wq, &net->work);
+ unsigned long flags;
+
+ spin_lock_irqsave(&cleanup_list_lock, flags);
+ list_add(&net->cleanup_list, &cleanup_list);
+ spin_unlock_irqrestore(&cleanup_list_lock, flags);
+
+ queue_work(netns_wq, &net_cleanup_work);
}
EXPORT_SYMBOL_GPL(__put_net);
@@ -193,6 +276,26 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
}
#endif
+struct net *get_net_ns_by_pid(pid_t pid)
+{
+ struct task_struct *tsk;
+ struct net *net;
+
+ /* Lookup the network namespace */
+ net = ERR_PTR(-ESRCH);
+ rcu_read_lock();
+ tsk = find_task_by_vpid(pid);
+ if (tsk) {
+ struct nsproxy *nsproxy;
+ nsproxy = task_nsproxy(tsk);
+ if (nsproxy)
+ net = get_net(nsproxy->net_ns);
+ }
+ rcu_read_unlock();
+ return net;
+}
+EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
+
static int __init net_ns_init(void)
{
struct net_generic *ng;
@@ -219,7 +322,7 @@ static int __init net_ns_init(void)
panic("Could not setup the initial network namespace");
rtnl_lock();
- list_add_tail(&init_net.list, &net_namespace_list);
+ list_add_tail_rcu(&init_net.list, &net_namespace_list);
rtnl_unlock();
mutex_unlock(&net_mutex);
@@ -230,18 +333,20 @@ static int __init net_ns_init(void)
pure_initcall(net_ns_init);
#ifdef CONFIG_NET_NS
-static int register_pernet_operations(struct list_head *list,
- struct pernet_operations *ops)
+static int __register_pernet_operations(struct list_head *list,
+ struct pernet_operations *ops)
{
- struct net *net, *undo_net;
+ struct net *net;
int error;
+ LIST_HEAD(net_exit_list);
list_add_tail(&ops->list, list);
- if (ops->init) {
+ if (ops->init || (ops->id && ops->size)) {
for_each_net(net) {
- error = ops->init(net);
+ error = ops_init(ops, net);
if (error)
goto out_undo;
+ list_add_tail(&net->exit_list, &net_exit_list);
}
}
return 0;
@@ -249,45 +354,82 @@ static int register_pernet_operations(struct list_head *list,
out_undo:
/* If I have an error cleanup all namespaces I initialized */
list_del(&ops->list);
- if (ops->exit) {
- for_each_net(undo_net) {
- if (undo_net == net)
- goto undone;
- ops->exit(undo_net);
- }
- }
-undone:
+ ops_exit_list(ops, &net_exit_list);
+ ops_free_list(ops, &net_exit_list);
return error;
}
-static void unregister_pernet_operations(struct pernet_operations *ops)
+static void __unregister_pernet_operations(struct pernet_operations *ops)
{
struct net *net;
+ LIST_HEAD(net_exit_list);
list_del(&ops->list);
- if (ops->exit)
- for_each_net(net)
- ops->exit(net);
+ for_each_net(net)
+ list_add_tail(&net->exit_list, &net_exit_list);
+ ops_exit_list(ops, &net_exit_list);
+ ops_free_list(ops, &net_exit_list);
}
#else
+static int __register_pernet_operations(struct list_head *list,
+ struct pernet_operations *ops)
+{
+ int err = 0;
+ err = ops_init(ops, &init_net);
+ if (err)
+ ops_free(ops, &init_net);
+ return err;
+
+}
+
+static void __unregister_pernet_operations(struct pernet_operations *ops)
+{
+ LIST_HEAD(net_exit_list);
+ list_add(&init_net.exit_list, &net_exit_list);
+ ops_exit_list(ops, &net_exit_list);
+ ops_free_list(ops, &net_exit_list);
+}
+
+#endif /* CONFIG_NET_NS */
+
+static DEFINE_IDA(net_generic_ids);
+
static int register_pernet_operations(struct list_head *list,
struct pernet_operations *ops)
{
- if (ops->init == NULL)
- return 0;
- return ops->init(&init_net);
+ int error;
+
+ if (ops->id) {
+again:
+ error = ida_get_new_above(&net_generic_ids, 1, ops->id);
+ if (error < 0) {
+ if (error == -EAGAIN) {
+ ida_pre_get(&net_generic_ids, GFP_KERNEL);
+ goto again;
+ }
+ return error;
+ }
+ }
+ error = __register_pernet_operations(list, ops);
+ if (error) {
+ rcu_barrier();
+ if (ops->id)
+ ida_remove(&net_generic_ids, *ops->id);
+ }
+
+ return error;
}
static void unregister_pernet_operations(struct pernet_operations *ops)
{
- if (ops->exit)
- ops->exit(&init_net);
+
+ __unregister_pernet_operations(ops);
+ rcu_barrier();
+ if (ops->id)
+ ida_remove(&net_generic_ids, *ops->id);
}
-#endif
-
-static DEFINE_IDA(net_generic_ids);
/**
* register_pernet_subsys - register a network namespace subsystem
@@ -335,38 +477,6 @@ void unregister_pernet_subsys(struct pernet_operations *module)
}
EXPORT_SYMBOL_GPL(unregister_pernet_subsys);
-int register_pernet_gen_subsys(int *id, struct pernet_operations *ops)
-{
- int rv;
-
- mutex_lock(&net_mutex);
-again:
- rv = ida_get_new_above(&net_generic_ids, 1, id);
- if (rv < 0) {
- if (rv == -EAGAIN) {
- ida_pre_get(&net_generic_ids, GFP_KERNEL);
- goto again;
- }
- goto out;
- }
- rv = register_pernet_operations(first_device, ops);
- if (rv < 0)
- ida_remove(&net_generic_ids, *id);
-out:
- mutex_unlock(&net_mutex);
- return rv;
-}
-EXPORT_SYMBOL_GPL(register_pernet_gen_subsys);
-
-void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops)
-{
- mutex_lock(&net_mutex);
- unregister_pernet_operations(ops);
- ida_remove(&net_generic_ids, id);
- mutex_unlock(&net_mutex);
-}
-EXPORT_SYMBOL_GPL(unregister_pernet_gen_subsys);
-
/**
* register_pernet_device - register a network namespace device
* @ops: pernet operations structure for the subsystem
@@ -398,30 +508,6 @@ int register_pernet_device(struct pernet_operations *ops)
}
EXPORT_SYMBOL_GPL(register_pernet_device);
-int register_pernet_gen_device(int *id, struct pernet_operations *ops)
-{
- int error;
- mutex_lock(&net_mutex);
-again:
- error = ida_get_new_above(&net_generic_ids, 1, id);
- if (error) {
- if (error == -EAGAIN) {
- ida_pre_get(&net_generic_ids, GFP_KERNEL);
- goto again;
- }
- goto out;
- }
- error = register_pernet_operations(&pernet_list, ops);
- if (error)
- ida_remove(&net_generic_ids, *id);
- else if (first_device == &pernet_list)
- first_device = &ops->list;
-out:
- mutex_unlock(&net_mutex);
- return error;
-}
-EXPORT_SYMBOL_GPL(register_pernet_gen_device);
-
/**
* unregister_pernet_device - unregister a network namespace netdevice
* @ops: pernet operations structure to manipulate
@@ -441,17 +527,6 @@ void unregister_pernet_device(struct pernet_operations *ops)
}
EXPORT_SYMBOL_GPL(unregister_pernet_device);
-void unregister_pernet_gen_device(int id, struct pernet_operations *ops)
-{
- mutex_lock(&net_mutex);
- if (&ops->list == first_device)
- first_device = first_device->next;
- unregister_pernet_operations(ops);
- ida_remove(&net_generic_ids, id);
- mutex_unlock(&net_mutex);
-}
-EXPORT_SYMBOL_GPL(unregister_pernet_gen_device);
-
static void net_generic_release(struct rcu_head *rcu)
{
struct net_generic *ng;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 1b76eb11deb4..0b4d0d35ef40 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -9,6 +9,7 @@
* Copyright (C) 2002 Red Hat, Inc.
*/
+#include <linux/moduleparam.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
@@ -50,6 +51,9 @@ static atomic_t trapped;
static void zap_completion_queue(void);
static void arp_reply(struct sk_buff *skb);
+static unsigned int carrier_timeout = 4;
+module_param(carrier_timeout, uint, 0644);
+
static void queue_process(struct work_struct *work)
{
struct netpoll_info *npinfo =
@@ -737,7 +741,7 @@ int netpoll_setup(struct netpoll *np)
}
atleast = jiffies + HZ/10;
- atmost = jiffies + 4*HZ;
+ atmost = jiffies + carrier_timeout * HZ;
while (!netif_carrier_ok(ndev)) {
if (time_after(jiffies, atmost)) {
printk(KERN_NOTICE
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 19b8c20e98a4..a23b45f08ec9 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -131,6 +131,7 @@
#include <linux/ioport.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
+#include <linux/hrtimer.h>
#include <linux/freezer.h>
#include <linux/delay.h>
#include <linux/timer.h>
@@ -162,14 +163,13 @@
#include <asm/byteorder.h>
#include <linux/rcupdate.h>
#include <linux/bitops.h>
-#include <asm/io.h>
+#include <linux/io.h>
+#include <linux/timex.h>
+#include <linux/uaccess.h>
#include <asm/dma.h>
-#include <asm/uaccess.h>
#include <asm/div64.h> /* do_div */
-#include <asm/timex.h>
-
-#define VERSION "pktgen v2.70: Packet Generator for packet performance testing.\n"
+#define VERSION "2.72"
#define IP_NAME_SZ 32
#define MAX_MPLS_LABELS 16 /* This is the max label stack depth */
#define MPLS_STACK_BOTTOM htonl(0x00000100)
@@ -192,11 +192,10 @@
#define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */
/* Thread control flag bits */
-#define T_TERMINATE (1<<0)
-#define T_STOP (1<<1) /* Stop run */
-#define T_RUN (1<<2) /* Start run */
-#define T_REMDEVALL (1<<3) /* Remove all devs */
-#define T_REMDEV (1<<4) /* Remove one dev */
+#define T_STOP (1<<0) /* Stop run */
+#define T_RUN (1<<1) /* Start run */
+#define T_REMDEVALL (1<<2) /* Remove all devs */
+#define T_REMDEV (1<<3) /* Remove one dev */
/* If lock -- can be removed after some work */
#define if_lock(t) spin_lock(&(t->if_lock));
@@ -206,7 +205,7 @@
#define PKTGEN_MAGIC 0xbe9be955
#define PG_PROC_DIR "pktgen"
#define PGCTRL "pgctrl"
-static struct proc_dir_entry *pg_proc_dir = NULL;
+static struct proc_dir_entry *pg_proc_dir;
#define MAX_CFLOWS 65536
@@ -231,9 +230,9 @@ struct pktgen_dev {
*/
struct proc_dir_entry *entry; /* proc file */
struct pktgen_thread *pg_thread;/* the owner */
- struct list_head list; /* Used for chaining in the thread's run-queue */
+ struct list_head list; /* chaining in the thread's run-queue */
- int running; /* if this changes to false, the test will stop */
+ int running; /* if false, the test will stop */
/* If min != max, then we will either do a linear iteration, or
* we will do a random selection from within the range.
@@ -246,33 +245,37 @@ struct pktgen_dev {
int max_pkt_size; /* = ETH_ZLEN; */
int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */
int nfrags;
- __u32 delay_us; /* Default delay */
- __u32 delay_ns;
+ u64 delay; /* nano-seconds */
+
__u64 count; /* Default No packets to send */
__u64 sofar; /* How many pkts we've sent so far */
__u64 tx_bytes; /* How many bytes we've transmitted */
- __u64 errors; /* Errors when trying to transmit, pkts will be re-sent */
+ __u64 errors; /* Errors when trying to transmit,
+ pkts will be re-sent */
/* runtime counters relating to clone_skb */
- __u64 next_tx_us; /* timestamp of when to tx next */
- __u32 next_tx_ns;
__u64 allocated_skbs;
__u32 clone_count;
int last_ok; /* Was last skb sent?
- * Or a failed transmit of some sort? This will keep
- * sequence numbers in order, for example.
+ * Or a failed transmit of some sort?
+ * This will keep sequence numbers in order
*/
- __u64 started_at; /* micro-seconds */
- __u64 stopped_at; /* micro-seconds */
- __u64 idle_acc; /* micro-seconds */
+ ktime_t next_tx;
+ ktime_t started_at;
+ ktime_t stopped_at;
+ u64 idle_acc; /* nano-seconds */
+
__u32 seq_num;
- int clone_skb; /* Use multiple SKBs during packet gen. If this number
- * is greater than 1, then that many copies of the same
- * packet will be sent before a new packet is allocated.
- * For instance, if you want to send 1024 identical packets
- * before creating a new packet, set clone_skb to 1024.
+ int clone_skb; /*
+ * Use multiple SKBs during packet gen.
+ * If this number is greater than 1, then
+ * that many copies of the same packet will be
+ * sent before a new packet is allocated.
+ * If you want to send 1024 identical packets
+ * before creating a new packet,
+ * set clone_skb to 1024.
*/
char dst_min[IP_NAME_SZ]; /* IP, ie 1.2.3.4 */
@@ -304,8 +307,10 @@ struct pktgen_dev {
__u16 udp_dst_max; /* exclusive, dest UDP port */
/* DSCP + ECN */
- __u8 tos; /* six most significant bits of (former) IPv4 TOS are for dscp codepoint */
- __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 (see RFC 3260, sec. 4) */
+ __u8 tos; /* six MSB of (former) IPv4 TOS
+ are for dscp codepoint */
+ __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6
+ (see RFC 3260, sec. 4) */
/* MPLS */
unsigned nr_labels; /* Depth of stack, 0 = no MPLS */
@@ -330,10 +335,12 @@ struct pktgen_dev {
__u32 cur_src_mac_offset;
__be32 cur_saddr;
__be32 cur_daddr;
+ __u16 ip_id;
__u16 cur_udp_dst;
__u16 cur_udp_src;
__u16 cur_queue_map;
__u32 cur_pkt_size;
+ __u32 last_pkt_size;
__u8 hh[14];
/* = {
@@ -346,15 +353,18 @@ struct pktgen_dev {
*/
__u16 pad; /* pad out the hh struct to an even 16 bytes */
- struct sk_buff *skb; /* skb we are to transmit next, mainly used for when we
+ struct sk_buff *skb; /* skb we are to transmit next, used for when we
* are transmitting the same one multiple times
*/
- struct net_device *odev; /* The out-going device. Note that the device should
- * have it's pg_info pointer pointing back to this
- * device. This will be set when the user specifies
- * the out-going device name (not when the inject is
- * started as it used to do.)
- */
+ struct net_device *odev; /* The out-going device.
+ * Note that the device should have it's
+ * pg_info pointer pointing back to this
+ * device.
+ * Set when the user specifies the out-going
+ * device name (not when the inject is
+ * started as it used to do.)
+ */
+ char odevname[32];
struct flow_state *flows;
unsigned cflows; /* Concurrent flows (config) */
unsigned lflow; /* Flow length (config) */
@@ -379,13 +389,14 @@ struct pktgen_hdr {
};
struct pktgen_thread {
- spinlock_t if_lock;
+ spinlock_t if_lock; /* for list of devices */
struct list_head if_list; /* All device here */
struct list_head th_list;
struct task_struct *tsk;
char result[512];
- /* Field for thread to receive "posted" events terminate, stop ifs etc. */
+ /* Field for thread to receive "posted" events terminate,
+ stop ifs etc. */
u32 control;
int cpu;
@@ -397,34 +408,32 @@ struct pktgen_thread {
#define REMOVE 1
#define FIND 0
-/** Convert to micro-seconds */
-static inline __u64 tv_to_us(const struct timeval *tv)
+static inline ktime_t ktime_now(void)
{
- __u64 us = tv->tv_usec;
- us += (__u64) tv->tv_sec * (__u64) 1000000;
- return us;
+ struct timespec ts;
+ ktime_get_ts(&ts);
+
+ return timespec_to_ktime(ts);
}
-static __u64 getCurUs(void)
+/* This works even if 32 bit because of careful byte order choice */
+static inline int ktime_lt(const ktime_t cmp1, const ktime_t cmp2)
{
- struct timeval tv;
- do_gettimeofday(&tv);
- return tv_to_us(&tv);
+ return cmp1.tv64 < cmp2.tv64;
}
-/* old include end */
-
-static char version[] __initdata = VERSION;
+static const char version[] =
+ "pktgen " VERSION ": Packet Generator for packet performance testing.\n";
static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i);
static int pktgen_add_device(struct pktgen_thread *t, const char *ifname);
static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
- const char *ifname);
+ const char *ifname, bool exact);
static int pktgen_device_event(struct notifier_block *, unsigned long, void *);
static void pktgen_run_all_threads(void);
static void pktgen_reset_all_threads(void);
static void pktgen_stop_all_threads_ifs(void);
-static int pktgen_stop_device(struct pktgen_dev *pkt_dev);
+
static void pktgen_stop(struct pktgen_thread *t);
static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);
@@ -432,10 +441,10 @@ static unsigned int scan_ip6(const char *s, char ip[16]);
static unsigned int fmt_ip6(char *s, const char ip[16]);
/* Module parameters, defaults. */
-static int pg_count_d = 1000; /* 1000 pkts by default */
-static int pg_delay_d;
-static int pg_clone_skb_d;
-static int debug;
+static int pg_count_d __read_mostly = 1000;
+static int pg_delay_d __read_mostly;
+static int pg_clone_skb_d __read_mostly;
+static int debug __read_mostly;
static DEFINE_MUTEX(pktgen_thread_lock);
static LIST_HEAD(pktgen_threads);
@@ -451,12 +460,12 @@ static struct notifier_block pktgen_notifier_block = {
static int pgctrl_show(struct seq_file *seq, void *v)
{
- seq_puts(seq, VERSION);
+ seq_puts(seq, version);
return 0;
}
-static ssize_t pgctrl_write(struct file *file, const char __user * buf,
- size_t count, loff_t * ppos)
+static ssize_t pgctrl_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
{
int err = 0;
char data[128];
@@ -509,10 +518,9 @@ static const struct file_operations pktgen_fops = {
static int pktgen_if_show(struct seq_file *seq, void *v)
{
- struct pktgen_dev *pkt_dev = seq->private;
- __u64 sa;
- __u64 stopped;
- __u64 now = getCurUs();
+ const struct pktgen_dev *pkt_dev = seq->private;
+ ktime_t stopped;
+ u64 idle;
seq_printf(seq,
"Params: count %llu min_pkt_size: %u max_pkt_size: %u\n",
@@ -520,10 +528,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
pkt_dev->max_pkt_size);
seq_printf(seq,
- " frags: %d delay: %u clone_skb: %d ifname: %s\n",
- pkt_dev->nfrags,
- 1000 * pkt_dev->delay_us + pkt_dev->delay_ns,
- pkt_dev->clone_skb, pkt_dev->odev->name);
+ " frags: %d delay: %llu clone_skb: %d ifname: %s\n",
+ pkt_dev->nfrags, (unsigned long long) pkt_dev->delay,
+ pkt_dev->clone_skb, pkt_dev->odevname);
seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows,
pkt_dev->lflow);
@@ -549,11 +556,14 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
" daddr: %s min_daddr: %s max_daddr: %s\n", b1,
b2, b3);
- } else
+ } else {
seq_printf(seq,
- " dst_min: %s dst_max: %s\n src_min: %s src_max: %s\n",
- pkt_dev->dst_min, pkt_dev->dst_max, pkt_dev->src_min,
- pkt_dev->src_max);
+ " dst_min: %s dst_max: %s\n",
+ pkt_dev->dst_min, pkt_dev->dst_max);
+ seq_printf(seq,
+ " src_min: %s src_max: %s\n",
+ pkt_dev->src_min, pkt_dev->src_max);
+ }
seq_puts(seq, " src_mac: ");
@@ -565,7 +575,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
seq_printf(seq, "%pM\n", pkt_dev->dst_mac);
seq_printf(seq,
- " udp_src_min: %d udp_src_max: %d udp_dst_min: %d udp_dst_max: %d\n",
+ " udp_src_min: %d udp_src_max: %d"
+ " udp_dst_min: %d udp_dst_max: %d\n",
pkt_dev->udp_src_min, pkt_dev->udp_src_max,
pkt_dev->udp_dst_min, pkt_dev->udp_dst_max);
@@ -581,23 +592,21 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
i == pkt_dev->nr_labels-1 ? "\n" : ", ");
}
- if (pkt_dev->vlan_id != 0xffff) {
+ if (pkt_dev->vlan_id != 0xffff)
seq_printf(seq, " vlan_id: %u vlan_p: %u vlan_cfi: %u\n",
- pkt_dev->vlan_id, pkt_dev->vlan_p, pkt_dev->vlan_cfi);
- }
+ pkt_dev->vlan_id, pkt_dev->vlan_p,
+ pkt_dev->vlan_cfi);
- if (pkt_dev->svlan_id != 0xffff) {
+ if (pkt_dev->svlan_id != 0xffff)
seq_printf(seq, " svlan_id: %u vlan_p: %u vlan_cfi: %u\n",
- pkt_dev->svlan_id, pkt_dev->svlan_p, pkt_dev->svlan_cfi);
- }
+ pkt_dev->svlan_id, pkt_dev->svlan_p,
+ pkt_dev->svlan_cfi);
- if (pkt_dev->tos) {
+ if (pkt_dev->tos)
seq_printf(seq, " tos: 0x%02x\n", pkt_dev->tos);
- }
- if (pkt_dev->traffic_class) {
+ if (pkt_dev->traffic_class)
seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class);
- }
seq_printf(seq, " Flags: ");
@@ -654,17 +663,21 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
seq_puts(seq, "\n");
- sa = pkt_dev->started_at;
- stopped = pkt_dev->stopped_at;
- if (pkt_dev->running)
- stopped = now; /* not really stopped, more like last-running-at */
+ /* not really stopped, more like last-running-at */
+ stopped = pkt_dev->running ? ktime_now() : pkt_dev->stopped_at;
+ idle = pkt_dev->idle_acc;
+ do_div(idle, NSEC_PER_USEC);
seq_printf(seq,
- "Current:\n pkts-sofar: %llu errors: %llu\n started: %lluus stopped: %lluus idle: %lluus\n",
+ "Current:\n pkts-sofar: %llu errors: %llu\n",
(unsigned long long)pkt_dev->sofar,
- (unsigned long long)pkt_dev->errors, (unsigned long long)sa,
- (unsigned long long)stopped,
- (unsigned long long)pkt_dev->idle_acc);
+ (unsigned long long)pkt_dev->errors);
+
+ seq_printf(seq,
+ " started: %lluus stopped: %lluus idle: %lluus\n",
+ (unsigned long long) ktime_to_us(pkt_dev->started_at),
+ (unsigned long long) ktime_to_us(stopped),
+ (unsigned long long) idle);
seq_printf(seq,
" seq_num: %d cur_dst_mac_offset: %d cur_src_mac_offset: %d\n",
@@ -696,7 +709,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
}
-static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, __u32 *num)
+static int hex32_arg(const char __user *user_buffer, unsigned long maxlen,
+ __u32 *num)
{
int i = 0;
*num = 0;
@@ -846,9 +860,9 @@ static ssize_t pktgen_if_write(struct file *file,
/* Read variable name */
len = strn_len(&user_buffer[i], sizeof(name) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
memset(name, 0, sizeof(name));
if (copy_from_user(name, &user_buffer[i], len))
return -EFAULT;
@@ -872,9 +886,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "min_pkt_size")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value < 14 + 20 + 8)
value = 14 + 20 + 8;
@@ -889,9 +903,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "max_pkt_size")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value < 14 + 20 + 8)
value = 14 + 20 + 8;
@@ -908,9 +922,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "pkt_size")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value < 14 + 20 + 8)
value = 14 + 20 + 8;
@@ -925,9 +939,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "debug")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
debug = value;
sprintf(pg_result, "OK: debug=%u", debug);
@@ -936,9 +950,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "frags")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->nfrags = value;
sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags);
@@ -946,26 +960,24 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "delay")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
- if (value == 0x7FFFFFFF) {
- pkt_dev->delay_us = 0x7FFFFFFF;
- pkt_dev->delay_ns = 0;
- } else {
- pkt_dev->delay_us = value / 1000;
- pkt_dev->delay_ns = value % 1000;
- }
- sprintf(pg_result, "OK: delay=%u",
- 1000 * pkt_dev->delay_us + pkt_dev->delay_ns);
+ if (value == 0x7FFFFFFF)
+ pkt_dev->delay = ULLONG_MAX;
+ else
+ pkt_dev->delay = (u64)value;
+
+ sprintf(pg_result, "OK: delay=%llu",
+ (unsigned long long) pkt_dev->delay);
return count;
}
if (!strcmp(name, "udp_src_min")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_src_min) {
pkt_dev->udp_src_min = value;
@@ -976,9 +988,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "udp_dst_min")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_dst_min) {
pkt_dev->udp_dst_min = value;
@@ -989,9 +1001,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "udp_src_max")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_src_max) {
pkt_dev->udp_src_max = value;
@@ -1002,9 +1014,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "udp_dst_max")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value != pkt_dev->udp_dst_max) {
pkt_dev->udp_dst_max = value;
@@ -1015,9 +1027,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "clone_skb")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->clone_skb = value;
@@ -1026,9 +1038,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "count")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->count = value;
sprintf(pg_result, "OK: count=%llu",
@@ -1037,9 +1049,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "src_mac_count")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (pkt_dev->src_mac_count != value) {
pkt_dev->src_mac_count = value;
@@ -1051,9 +1063,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "dst_mac_count")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (pkt_dev->dst_mac_count != value) {
pkt_dev->dst_mac_count = value;
@@ -1067,9 +1079,9 @@ static ssize_t pktgen_if_write(struct file *file,
char f[32];
memset(f, 0, 32);
len = strn_len(&user_buffer[i], sizeof(f) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(f, &user_buffer[i], len))
return -EFAULT;
i += len;
@@ -1168,9 +1180,8 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
@@ -1190,9 +1201,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "dst_max")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
@@ -1303,9 +1314,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "src_min")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
buf[len] = 0;
@@ -1324,9 +1335,9 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "src_max")) {
len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
if (copy_from_user(buf, &user_buffer[i], len))
return -EFAULT;
buf[len] = 0;
@@ -1350,9 +1361,9 @@ static ssize_t pktgen_if_write(struct file *file,
memcpy(old_dmac, pkt_dev->dst_mac, ETH_ALEN);
len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
memset(valstr, 0, sizeof(valstr));
if (copy_from_user(valstr, &user_buffer[i], len))
return -EFAULT;
@@ -1392,9 +1403,9 @@ static ssize_t pktgen_if_write(struct file *file,
memcpy(old_smac, pkt_dev->src_mac, ETH_ALEN);
len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
memset(valstr, 0, sizeof(valstr));
if (copy_from_user(valstr, &user_buffer[i], len))
return -EFAULT;
@@ -1435,9 +1446,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "flows")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value > MAX_CFLOWS)
value = MAX_CFLOWS;
@@ -1449,9 +1460,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "flowlen")) {
len = num_arg(&user_buffer[i], 10, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->lflow = value;
sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow);
@@ -1460,9 +1471,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "queue_map_min")) {
len = num_arg(&user_buffer[i], 5, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->queue_map_min = value;
sprintf(pg_result, "OK: queue_map_min=%u", pkt_dev->queue_map_min);
@@ -1471,9 +1482,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "queue_map_max")) {
len = num_arg(&user_buffer[i], 5, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
pkt_dev->queue_map_max = value;
sprintf(pg_result, "OK: queue_map_max=%u", pkt_dev->queue_map_max);
@@ -1505,9 +1516,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "vlan_id")) {
len = num_arg(&user_buffer[i], 4, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (value <= 4095) {
pkt_dev->vlan_id = value; /* turn on VLAN */
@@ -1532,9 +1543,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "vlan_p")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) {
pkt_dev->vlan_p = value;
@@ -1547,9 +1558,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "vlan_cfi")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) {
pkt_dev->vlan_cfi = value;
@@ -1562,9 +1573,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "svlan_id")) {
len = num_arg(&user_buffer[i], 4, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) {
pkt_dev->svlan_id = value; /* turn on SVLAN */
@@ -1589,9 +1600,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "svlan_p")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) {
pkt_dev->svlan_p = value;
@@ -1604,9 +1615,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "svlan_cfi")) {
len = num_arg(&user_buffer[i], 1, &value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) {
pkt_dev->svlan_cfi = value;
@@ -1620,9 +1631,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "tos")) {
__u32 tmp_value = 0;
len = hex32_arg(&user_buffer[i], 2, &tmp_value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (len == 2) {
pkt_dev->tos = tmp_value;
@@ -1636,9 +1647,9 @@ static ssize_t pktgen_if_write(struct file *file,
if (!strcmp(name, "traffic_class")) {
__u32 tmp_value = 0;
len = hex32_arg(&user_buffer[i], 2, &tmp_value);
- if (len < 0) {
+ if (len < 0)
return len;
- }
+
i += len;
if (len == 2) {
pkt_dev->traffic_class = tmp_value;
@@ -1670,7 +1681,7 @@ static const struct file_operations pktgen_if_fops = {
static int pktgen_thread_show(struct seq_file *seq, void *v)
{
struct pktgen_thread *t = seq->private;
- struct pktgen_dev *pkt_dev;
+ const struct pktgen_dev *pkt_dev;
BUG_ON(!t);
@@ -1679,13 +1690,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v)
if_lock(t);
list_for_each_entry(pkt_dev, &t->if_list, list)
if (pkt_dev->running)
- seq_printf(seq, "%s ", pkt_dev->odev->name);
+ seq_printf(seq, "%s ", pkt_dev->odevname);
seq_printf(seq, "\nStopped: ");
list_for_each_entry(pkt_dev, &t->if_list, list)
if (!pkt_dev->running)
- seq_printf(seq, "%s ", pkt_dev->odev->name);
+ seq_printf(seq, "%s ", pkt_dev->odevname);
if (t->result[0])
seq_printf(seq, "\nResult: %s\n", t->result);
@@ -1808,9 +1819,10 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove)
{
struct pktgen_thread *t;
struct pktgen_dev *pkt_dev = NULL;
+ bool exact = (remove == FIND);
list_for_each_entry(t, &pktgen_threads, th_list) {
- pkt_dev = pktgen_find_dev(t, ifname);
+ pkt_dev = pktgen_find_dev(t, ifname, exact);
if (pkt_dev) {
if (remove) {
if_lock(t);
@@ -1873,8 +1885,10 @@ static void pktgen_change_name(struct net_device *dev)
remove_proc_entry(pkt_dev->entry->name, pg_proc_dir);
- pkt_dev->entry = create_proc_entry(dev->name, 0600,
- pg_proc_dir);
+ pkt_dev->entry = proc_create_data(dev->name, 0600,
+ pg_proc_dir,
+ &pktgen_if_fops,
+ pkt_dev);
if (!pkt_dev->entry)
printk(KERN_ERR "pktgen: can't move proc "
" entry for '%s'\n", dev->name);
@@ -1908,13 +1922,14 @@ static int pktgen_device_event(struct notifier_block *unused,
return NOTIFY_DONE;
}
-static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, const char *ifname)
+static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev,
+ const char *ifname)
{
char b[IFNAMSIZ+5];
int i = 0;
- for(i=0; ifname[i] != '@'; i++) {
- if(i == IFNAMSIZ)
+ for (i = 0; ifname[i] != '@'; i++) {
+ if (i == IFNAMSIZ)
break;
b[i] = ifname[i];
@@ -1981,16 +1996,16 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
printk(KERN_WARNING "pktgen: WARNING: Requested "
"queue_map_min (zero-based) (%d) exceeds valid range "
"[0 - %d] for (%d) queues on %s, resetting\n",
- pkt_dev->queue_map_min, (ntxq ?: 1)- 1, ntxq,
- pkt_dev->odev->name);
+ pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq,
+ pkt_dev->odevname);
pkt_dev->queue_map_min = ntxq - 1;
}
if (pkt_dev->queue_map_max >= ntxq) {
printk(KERN_WARNING "pktgen: WARNING: Requested "
"queue_map_max (zero-based) (%d) exceeds valid range "
"[0 - %d] for (%d) queues on %s, resetting\n",
- pkt_dev->queue_map_max, (ntxq ?: 1)- 1, ntxq,
- pkt_dev->odev->name);
+ pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq,
+ pkt_dev->odevname);
pkt_dev->queue_map_max = ntxq - 1;
}
@@ -2030,15 +2045,15 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
*/
rcu_read_lock();
- if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) {
+ idev = __in6_dev_get(pkt_dev->odev);
+ if (idev) {
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
for (ifp = idev->addr_list; ifp;
ifp = ifp->if_next) {
- if (ifp->scope == IFA_LINK
- && !(ifp->
- flags & IFA_F_TENTATIVE)) {
+ if (ifp->scope == IFA_LINK &&
+ !(ifp->flags & IFA_F_TENTATIVE)) {
ipv6_addr_copy(&pkt_dev->
cur_in6_saddr,
&ifp->addr);
@@ -2089,27 +2104,45 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
pkt_dev->nflows = 0;
}
-static void spin(struct pktgen_dev *pkt_dev, __u64 spin_until_us)
+
+static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until)
{
- __u64 start;
- __u64 now;
+ ktime_t start_time, end_time;
+ s64 remaining;
+ struct hrtimer_sleeper t;
- start = now = getCurUs();
- while (now < spin_until_us) {
- /* TODO: optimize sleeping behavior */
- if (spin_until_us - now > jiffies_to_usecs(1) + 1)
- schedule_timeout_interruptible(1);
- else if (spin_until_us - now > 100) {
- if (!pkt_dev->running)
- return;
- if (need_resched())
+ hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_set_expires(&t.timer, spin_until);
+
+ remaining = ktime_to_us(hrtimer_expires_remaining(&t.timer));
+ if (remaining <= 0) {
+ pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay);
+ return;
+ }
+
+ start_time = ktime_now();
+ if (remaining < 100)
+ udelay(remaining); /* really small just spin */
+ else {
+ /* see do_nanosleep */
+ hrtimer_init_sleeper(&t, current);
+ do {
+ set_current_state(TASK_INTERRUPTIBLE);
+ hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS);
+ if (!hrtimer_active(&t.timer))
+ t.task = NULL;
+
+ if (likely(t.task))
schedule();
- }
- now = getCurUs();
+ hrtimer_cancel(&t.timer);
+ } while (t.task && pkt_dev->running && !signal_pending(current));
+ __set_current_state(TASK_RUNNING);
}
+ end_time = ktime_now();
- pkt_dev->idle_acc += now - start;
+ pkt_dev->idle_acc += ktime_to_ns(ktime_sub(end_time, start_time));
+ pkt_dev->next_tx = ktime_add_ns(end_time, pkt_dev->delay);
}
static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
@@ -2120,13 +2153,9 @@ static inline void set_pkt_overhead(struct pktgen_dev *pkt_dev)
pkt_dev->pkt_overhead += SVLAN_TAG_SIZE(pkt_dev);
}
-static inline int f_seen(struct pktgen_dev *pkt_dev, int flow)
+static inline int f_seen(const struct pktgen_dev *pkt_dev, int flow)
{
-
- if (pkt_dev->flows[flow].flags & F_INIT)
- return 1;
- else
- return 0;
+ return !!(pkt_dev->flows[flow].flags & F_INIT);
}
static inline int f_pick(struct pktgen_dev *pkt_dev)
@@ -2174,7 +2203,7 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
if (x) {
pkt_dev->flows[flow].x = x;
set_pkt_overhead(pkt_dev);
- pkt_dev->pkt_overhead+=x->props.header_len;
+ pkt_dev->pkt_overhead += x->props.header_len;
}
}
@@ -2186,7 +2215,7 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev)
if (pkt_dev->flags & F_QUEUE_MAP_CPU)
pkt_dev->cur_queue_map = smp_processor_id();
- else if (pkt_dev->queue_map_min < pkt_dev->queue_map_max) {
+ else if (pkt_dev->queue_map_min <= pkt_dev->queue_map_max) {
__u16 t;
if (pkt_dev->flags & F_QUEUE_MAP_RND) {
t = random32() %
@@ -2313,18 +2342,18 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
if (!(pkt_dev->flags & F_IPV6)) {
- if ((imn = ntohl(pkt_dev->saddr_min)) < (imx =
- ntohl(pkt_dev->
- saddr_max))) {
+ imn = ntohl(pkt_dev->saddr_min);
+ imx = ntohl(pkt_dev->saddr_max);
+ if (imn < imx) {
__u32 t;
if (pkt_dev->flags & F_IPSRC_RND)
t = random32() % (imx - imn) + imn;
else {
t = ntohl(pkt_dev->cur_saddr);
t++;
- if (t > imx) {
+ if (t > imx)
t = imn;
- }
+
}
pkt_dev->cur_saddr = htonl(t);
}
@@ -2435,14 +2464,14 @@ static int pktgen_output_ipsec(struct sk_buff *skb, struct pktgen_dev *pkt_dev)
if (err)
goto error;
- x->curlft.bytes +=skb->len;
+ x->curlft.bytes += skb->len;
x->curlft.packets++;
error:
spin_unlock(&x->lock);
return err;
}
-static inline void free_SAs(struct pktgen_dev *pkt_dev)
+static void free_SAs(struct pktgen_dev *pkt_dev)
{
if (pkt_dev->cflows) {
/* let go of the SAs if we have them */
@@ -2457,7 +2486,7 @@ static inline void free_SAs(struct pktgen_dev *pkt_dev)
}
}
-static inline int process_ipsec(struct pktgen_dev *pkt_dev,
+static int process_ipsec(struct pktgen_dev *pkt_dev,
struct sk_buff *skb, __be16 protocol)
{
if (pkt_dev->flags & F_IPSEC_ON) {
@@ -2467,11 +2496,11 @@ static inline int process_ipsec(struct pktgen_dev *pkt_dev,
int ret;
__u8 *eth;
nhead = x->props.header_len - skb_headroom(skb);
- if (nhead >0) {
+ if (nhead > 0) {
ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC);
if (ret < 0) {
printk(KERN_ERR "Error expanding "
- "ipsec packet %d\n",ret);
+ "ipsec packet %d\n", ret);
goto err;
}
}
@@ -2481,13 +2510,13 @@ static inline int process_ipsec(struct pktgen_dev *pkt_dev,
ret = pktgen_output_ipsec(skb, pkt_dev);
if (ret) {
printk(KERN_ERR "Error creating ipsec "
- "packet %d\n",ret);
+ "packet %d\n", ret);
goto err;
}
/* restore ll */
eth = (__u8 *) skb_push(skb, ETH_HLEN);
memcpy(eth, pkt_dev->hh, 12);
- *(u16 *) & eth[12] = protocol;
+ *(u16 *) &eth[12] = protocol;
}
}
return 1;
@@ -2500,9 +2529,9 @@ err:
static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev)
{
unsigned i;
- for (i = 0; i < pkt_dev->nr_labels; i++) {
+ for (i = 0; i < pkt_dev->nr_labels; i++)
*mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM;
- }
+
mpls--;
*mpls |= MPLS_STACK_BOTTOM;
}
@@ -2543,8 +2572,9 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
mod_cur_headers(pkt_dev);
datalen = (odev->hard_header_len + 16) & ~0xf;
- skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + datalen +
- pkt_dev->pkt_overhead, GFP_ATOMIC);
+ skb = __netdev_alloc_skb(odev,
+ pkt_dev->cur_pkt_size + 64
+ + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
@@ -2603,6 +2633,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
iph->protocol = IPPROTO_UDP; /* UDP */
iph->saddr = pkt_dev->cur_saddr;
iph->daddr = pkt_dev->cur_daddr;
+ iph->id = htons(pkt_dev->ip_id);
+ pkt_dev->ip_id++;
iph->frag_off = 0;
iplen = 20 + 8 + datalen;
iph->tot_len = htons(iplen);
@@ -2614,24 +2646,26 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
skb->dev = odev;
skb->pkt_type = PACKET_HOST;
- if (pkt_dev->nfrags <= 0)
+ if (pkt_dev->nfrags <= 0) {
pgh = (struct pktgen_hdr *)skb_put(skb, datalen);
- else {
+ memset(pgh + 1, 0, datalen - sizeof(struct pktgen_hdr));
+ } else {
int frags = pkt_dev->nfrags;
- int i;
+ int i, len;
pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8);
if (frags > MAX_SKB_FRAGS)
frags = MAX_SKB_FRAGS;
if (datalen > frags * PAGE_SIZE) {
- skb_put(skb, datalen - frags * PAGE_SIZE);
+ len = datalen - frags * PAGE_SIZE;
+ memset(skb_put(skb, len), 0, len);
datalen = frags * PAGE_SIZE;
}
i = 0;
while (datalen > 0) {
- struct page *page = alloc_pages(GFP_KERNEL, 0);
+ struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
skb_shinfo(skb)->frags[i].page = page;
skb_shinfo(skb)->frags[i].page_offset = 0;
skb_shinfo(skb)->frags[i].size =
@@ -2668,8 +2702,9 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
}
}
- /* Stamp the time, and sequence number, convert them to network byte order */
-
+ /* Stamp the time, and sequence number,
+ * convert them to network byte order
+ */
if (pgh) {
struct timeval timestamp;
@@ -2882,8 +2917,9 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
queue_map = pkt_dev->cur_queue_map;
mod_cur_headers(pkt_dev);
- skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16 +
- pkt_dev->pkt_overhead, GFP_ATOMIC);
+ skb = __netdev_alloc_skb(odev,
+ pkt_dev->cur_pkt_size + 64
+ + 16 + pkt_dev->pkt_overhead, GFP_NOWAIT);
if (!skb) {
sprintf(pkt_dev->result, "No memory");
return NULL;
@@ -2922,7 +2958,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
udph = udp_hdr(skb);
memcpy(eth, pkt_dev->hh, 12);
- *(__be16 *) & eth[12] = protocol;
+ *(__be16 *) &eth[12] = protocol;
/* Eth + IPh + UDPh + mpls */
datalen = pkt_dev->cur_pkt_size - 14 -
@@ -3016,8 +3052,10 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
}
}
- /* Stamp the time, and sequence number, convert them to network byte order */
- /* should we update cloned packets too ? */
+ /* Stamp the time, and sequence number,
+ * convert them to network byte order
+ * should we update cloned packets too ?
+ */
if (pgh) {
struct timeval timestamp;
@@ -3033,8 +3071,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
return skb;
}
-static inline struct sk_buff *fill_packet(struct net_device *odev,
- struct pktgen_dev *pkt_dev)
+static struct sk_buff *fill_packet(struct net_device *odev,
+ struct pktgen_dev *pkt_dev)
{
if (pkt_dev->flags & F_IPV6)
return fill_packet_ipv6(odev, pkt_dev);
@@ -3072,9 +3110,9 @@ static void pktgen_run(struct pktgen_thread *t)
pktgen_clear_counters(pkt_dev);
pkt_dev->running = 1; /* Cranke yeself! */
pkt_dev->skb = NULL;
- pkt_dev->started_at = getCurUs();
- pkt_dev->next_tx_us = getCurUs(); /* Transmit immediately */
- pkt_dev->next_tx_ns = 0;
+ pkt_dev->started_at =
+ pkt_dev->next_tx = ktime_now();
+
set_pkt_overhead(pkt_dev);
strcpy(pkt_dev->result, "Starting");
@@ -3101,17 +3139,14 @@ static void pktgen_stop_all_threads_ifs(void)
mutex_unlock(&pktgen_thread_lock);
}
-static int thread_is_running(struct pktgen_thread *t)
+static int thread_is_running(const struct pktgen_thread *t)
{
- struct pktgen_dev *pkt_dev;
- int res = 0;
+ const struct pktgen_dev *pkt_dev;
list_for_each_entry(pkt_dev, &t->if_list, list)
- if (pkt_dev->running) {
- res = 1;
- break;
- }
- return res;
+ if (pkt_dev->running)
+ return 1;
+ return 0;
}
static int pktgen_wait_thread_run(struct pktgen_thread *t)
@@ -3168,7 +3203,8 @@ static void pktgen_run_all_threads(void)
mutex_unlock(&pktgen_thread_lock);
- schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */
+ /* Propagate thread->control */
+ schedule_timeout_interruptible(msecs_to_jiffies(125));
pktgen_wait_all_threads_run();
}
@@ -3186,35 +3222,29 @@ static void pktgen_reset_all_threads(void)
mutex_unlock(&pktgen_thread_lock);
- schedule_timeout_interruptible(msecs_to_jiffies(125)); /* Propagate thread->control */
+ /* Propagate thread->control */
+ schedule_timeout_interruptible(msecs_to_jiffies(125));
pktgen_wait_all_threads_run();
}
static void show_results(struct pktgen_dev *pkt_dev, int nr_frags)
{
- __u64 total_us, bps, mbps, pps, idle;
+ __u64 bps, mbps, pps;
char *p = pkt_dev->result;
-
- total_us = pkt_dev->stopped_at - pkt_dev->started_at;
-
- idle = pkt_dev->idle_acc;
-
- p += sprintf(p, "OK: %llu(c%llu+d%llu) usec, %llu (%dbyte,%dfrags)\n",
- (unsigned long long)total_us,
- (unsigned long long)(total_us - idle),
- (unsigned long long)idle,
+ ktime_t elapsed = ktime_sub(pkt_dev->stopped_at,
+ pkt_dev->started_at);
+ ktime_t idle = ns_to_ktime(pkt_dev->idle_acc);
+
+ p += sprintf(p, "OK: %llu(c%llu+d%llu) nsec, %llu (%dbyte,%dfrags)\n",
+ (unsigned long long)ktime_to_us(elapsed),
+ (unsigned long long)ktime_to_us(ktime_sub(elapsed, idle)),
+ (unsigned long long)ktime_to_us(idle),
(unsigned long long)pkt_dev->sofar,
pkt_dev->cur_pkt_size, nr_frags);
- pps = pkt_dev->sofar * USEC_PER_SEC;
-
- while ((total_us >> 32) != 0) {
- pps >>= 1;
- total_us >>= 1;
- }
-
- do_div(pps, total_us);
+ pps = div64_u64(pkt_dev->sofar * NSEC_PER_SEC,
+ ktime_to_ns(elapsed));
bps = pps * 8 * pkt_dev->cur_pkt_size;
@@ -3228,18 +3258,19 @@ static void show_results(struct pktgen_dev *pkt_dev, int nr_frags)
}
/* Set stopped-at timer, remove from running list, do counters & statistics */
-
static int pktgen_stop_device(struct pktgen_dev *pkt_dev)
{
int nr_frags = pkt_dev->skb ? skb_shinfo(pkt_dev->skb)->nr_frags : -1;
if (!pkt_dev->running) {
printk(KERN_WARNING "pktgen: interface: %s is already "
- "stopped\n", pkt_dev->odev->name);
+ "stopped\n", pkt_dev->odevname);
return -EINVAL;
}
- pkt_dev->stopped_at = getCurUs();
+ kfree_skb(pkt_dev->skb);
+ pkt_dev->skb = NULL;
+ pkt_dev->stopped_at = ktime_now();
pkt_dev->running = 0;
show_results(pkt_dev, nr_frags);
@@ -3258,7 +3289,7 @@ static struct pktgen_dev *next_to_run(struct pktgen_thread *t)
continue;
if (best == NULL)
best = pkt_dev;
- else if (pkt_dev->next_tx_us < best->next_tx_us)
+ else if (ktime_lt(pkt_dev->next_tx, best->next_tx))
best = pkt_dev;
}
if_unlock(t);
@@ -3275,9 +3306,6 @@ static void pktgen_stop(struct pktgen_thread *t)
list_for_each_entry(pkt_dev, &t->if_list, list) {
pktgen_stop_device(pkt_dev);
- kfree_skb(pkt_dev->skb);
-
- pkt_dev->skb = NULL;
}
if_unlock(t);
@@ -3348,156 +3376,117 @@ static void pktgen_rem_thread(struct pktgen_thread *t)
mutex_unlock(&pktgen_thread_lock);
}
-static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
+static void pktgen_resched(struct pktgen_dev *pkt_dev)
+{
+ ktime_t idle_start = ktime_now();
+ schedule();
+ pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start));
+}
+
+static void pktgen_wait_for_skb(struct pktgen_dev *pkt_dev)
+{
+ ktime_t idle_start = ktime_now();
+
+ while (atomic_read(&(pkt_dev->skb->users)) != 1) {
+ if (signal_pending(current))
+ break;
+
+ if (need_resched())
+ pktgen_resched(pkt_dev);
+ else
+ cpu_relax();
+ }
+ pkt_dev->idle_acc += ktime_to_ns(ktime_sub(ktime_now(), idle_start));
+}
+
+static void pktgen_xmit(struct pktgen_dev *pkt_dev)
{
struct net_device *odev = pkt_dev->odev;
- int (*xmit)(struct sk_buff *, struct net_device *)
+ netdev_tx_t (*xmit)(struct sk_buff *, struct net_device *)
= odev->netdev_ops->ndo_start_xmit;
struct netdev_queue *txq;
- __u64 idle_start = 0;
u16 queue_map;
int ret;
- if (pkt_dev->delay_us || pkt_dev->delay_ns) {
- u64 now;
-
- now = getCurUs();
- if (now < pkt_dev->next_tx_us)
- spin(pkt_dev, pkt_dev->next_tx_us);
-
- /* This is max DELAY, this has special meaning of
- * "never transmit"
- */
- if (pkt_dev->delay_us == 0x7FFFFFFF) {
- pkt_dev->next_tx_us = getCurUs() + pkt_dev->delay_us;
- pkt_dev->next_tx_ns = pkt_dev->delay_ns;
- goto out;
- }
+ /* If device is offline, then don't send */
+ if (unlikely(!netif_running(odev) || !netif_carrier_ok(odev))) {
+ pktgen_stop_device(pkt_dev);
+ return;
}
- if (!pkt_dev->skb) {
- set_cur_queue_map(pkt_dev);
- queue_map = pkt_dev->cur_queue_map;
- } else {
- queue_map = skb_get_queue_mapping(pkt_dev->skb);
+ /* This is max DELAY, this has special meaning of
+ * "never transmit"
+ */
+ if (unlikely(pkt_dev->delay == ULLONG_MAX)) {
+ pkt_dev->next_tx = ktime_add_ns(ktime_now(), ULONG_MAX);
+ return;
}
- txq = netdev_get_tx_queue(odev, queue_map);
- if (netif_tx_queue_stopped(txq) ||
- netif_tx_queue_frozen(txq) ||
- need_resched()) {
- idle_start = getCurUs();
-
- if (!netif_running(odev)) {
- pktgen_stop_device(pkt_dev);
- kfree_skb(pkt_dev->skb);
- pkt_dev->skb = NULL;
- goto out;
- }
- if (need_resched())
- schedule();
-
- pkt_dev->idle_acc += getCurUs() - idle_start;
+ /* If no skb or clone count exhausted then get new one */
+ if (!pkt_dev->skb || (pkt_dev->last_ok &&
+ ++pkt_dev->clone_count >= pkt_dev->clone_skb)) {
+ /* build a new pkt */
+ kfree_skb(pkt_dev->skb);
- if (netif_tx_queue_stopped(txq) ||
- netif_tx_queue_frozen(txq)) {
- pkt_dev->next_tx_us = getCurUs(); /* TODO */
- pkt_dev->next_tx_ns = 0;
- goto out; /* Try the next interface */
+ pkt_dev->skb = fill_packet(odev, pkt_dev);
+ if (pkt_dev->skb == NULL) {
+ printk(KERN_ERR "pktgen: ERROR: couldn't "
+ "allocate skb in fill_packet.\n");
+ schedule();
+ pkt_dev->clone_count--; /* back out increment, OOM */
+ return;
}
+ pkt_dev->last_pkt_size = pkt_dev->skb->len;
+ pkt_dev->allocated_skbs++;
+ pkt_dev->clone_count = 0; /* reset counter */
}
- if (pkt_dev->last_ok || !pkt_dev->skb) {
- if ((++pkt_dev->clone_count >= pkt_dev->clone_skb)
- || (!pkt_dev->skb)) {
- /* build a new pkt */
- kfree_skb(pkt_dev->skb);
+ if (pkt_dev->delay && pkt_dev->last_ok)
+ spin(pkt_dev, pkt_dev->next_tx);
- pkt_dev->skb = fill_packet(odev, pkt_dev);
- if (pkt_dev->skb == NULL) {
- printk(KERN_ERR "pktgen: ERROR: couldn't "
- "allocate skb in fill_packet.\n");
- schedule();
- pkt_dev->clone_count--; /* back out increment, OOM */
- goto out;
- }
- pkt_dev->allocated_skbs++;
- pkt_dev->clone_count = 0; /* reset counter */
- }
- }
-
- /* fill_packet() might have changed the queue */
queue_map = skb_get_queue_mapping(pkt_dev->skb);
txq = netdev_get_tx_queue(odev, queue_map);
__netif_tx_lock_bh(txq);
- if (!netif_tx_queue_stopped(txq) &&
- !netif_tx_queue_frozen(txq)) {
-
- atomic_inc(&(pkt_dev->skb->users));
- retry_now:
- ret = (*xmit)(pkt_dev->skb, odev);
- if (likely(ret == NETDEV_TX_OK)) {
- txq_trans_update(txq);
- pkt_dev->last_ok = 1;
- pkt_dev->sofar++;
- pkt_dev->seq_num++;
- pkt_dev->tx_bytes += pkt_dev->cur_pkt_size;
-
- } else if (ret == NETDEV_TX_LOCKED
- && (odev->features & NETIF_F_LLTX)) {
- cpu_relax();
- goto retry_now;
- } else { /* Retry it next time */
-
- atomic_dec(&(pkt_dev->skb->users));
-
- if (debug && net_ratelimit())
- printk(KERN_INFO "pktgen: Hard xmit error\n");
-
- pkt_dev->errors++;
- pkt_dev->last_ok = 0;
- }
-
- pkt_dev->next_tx_us = getCurUs();
- pkt_dev->next_tx_ns = 0;
-
- pkt_dev->next_tx_us += pkt_dev->delay_us;
- pkt_dev->next_tx_ns += pkt_dev->delay_ns;
-
- if (pkt_dev->next_tx_ns > 1000) {
- pkt_dev->next_tx_us++;
- pkt_dev->next_tx_ns -= 1000;
- }
- }
- else { /* Retry it next time */
+ if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) {
+ ret = NETDEV_TX_BUSY;
+ pkt_dev->last_ok = 0;
+ goto unlock;
+ }
+ atomic_inc(&(pkt_dev->skb->users));
+ ret = (*xmit)(pkt_dev->skb, odev);
+
+ switch (ret) {
+ case NETDEV_TX_OK:
+ txq_trans_update(txq);
+ pkt_dev->last_ok = 1;
+ pkt_dev->sofar++;
+ pkt_dev->seq_num++;
+ pkt_dev->tx_bytes += pkt_dev->last_pkt_size;
+ break;
+ default: /* Drivers are not supposed to return other values! */
+ if (net_ratelimit())
+ pr_info("pktgen: %s xmit error: %d\n",
+ pkt_dev->odevname, ret);
+ pkt_dev->errors++;
+ /* fallthru */
+ case NETDEV_TX_LOCKED:
+ case NETDEV_TX_BUSY:
+ /* Retry it next time */
+ atomic_dec(&(pkt_dev->skb->users));
pkt_dev->last_ok = 0;
- pkt_dev->next_tx_us = getCurUs(); /* TODO */
- pkt_dev->next_tx_ns = 0;
}
-
+unlock:
__netif_tx_unlock_bh(txq);
/* If pkt_dev->count is zero, then run forever */
if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) {
- if (atomic_read(&(pkt_dev->skb->users)) != 1) {
- idle_start = getCurUs();
- while (atomic_read(&(pkt_dev->skb->users)) != 1) {
- if (signal_pending(current)) {
- break;
- }
- schedule();
- }
- pkt_dev->idle_acc += getCurUs() - idle_start;
- }
+ pktgen_wait_for_skb(pkt_dev);
/* Done with this */
pktgen_stop_device(pkt_dev);
- kfree_skb(pkt_dev->skb);
- pkt_dev->skb = NULL;
}
-out:;
}
/*
@@ -3516,7 +3505,8 @@ static int pktgen_thread_worker(void *arg)
init_waitqueue_head(&t->queue);
complete(&t->start_done);
- pr_debug("pktgen: starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current));
+ pr_debug("pktgen: starting pktgen/%d: pid=%d\n",
+ cpu, task_pid_nr(current));
set_current_state(TASK_INTERRUPTIBLE);
@@ -3525,20 +3515,24 @@ static int pktgen_thread_worker(void *arg)
while (!kthread_should_stop()) {
pkt_dev = next_to_run(t);
- if (!pkt_dev &&
- (t->control & (T_STOP | T_RUN | T_REMDEVALL | T_REMDEV))
- == 0) {
- prepare_to_wait(&(t->queue), &wait,
- TASK_INTERRUPTIBLE);
- schedule_timeout(HZ / 10);
- finish_wait(&(t->queue), &wait);
+ if (unlikely(!pkt_dev && t->control == 0)) {
+ wait_event_interruptible_timeout(t->queue,
+ t->control != 0,
+ HZ/10);
+ continue;
}
__set_current_state(TASK_RUNNING);
- if (pkt_dev)
+ if (likely(pkt_dev)) {
pktgen_xmit(pkt_dev);
+ if (need_resched())
+ pktgen_resched(pkt_dev);
+ else
+ cpu_relax();
+ }
+
if (t->control & T_STOP) {
pktgen_stop(t);
t->control &= ~(T_STOP);
@@ -3577,13 +3571,18 @@ static int pktgen_thread_worker(void *arg)
}
static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t,
- const char *ifname)
+ const char *ifname, bool exact)
{
struct pktgen_dev *p, *pkt_dev = NULL;
- if_lock(t);
+ size_t len = strlen(ifname);
+ if_lock(t);
list_for_each_entry(p, &t->if_list, list)
- if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) {
+ if (strncmp(p->odevname, ifname, len) == 0) {
+ if (p->odevname[len]) {
+ if (exact || p->odevname[len] != '@')
+ continue;
+ }
pkt_dev = p;
break;
}
@@ -3626,6 +3625,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
{
struct pktgen_dev *pkt_dev;
int err;
+ int node = cpu_to_node(t->cpu);
/* We don't allow a device to be on several threads */
@@ -3635,11 +3635,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
return -EBUSY;
}
- pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL);
+ pkt_dev = kzalloc_node(sizeof(struct pktgen_dev), GFP_KERNEL, node);
if (!pkt_dev)
return -ENOMEM;
- pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state));
+ strcpy(pkt_dev->odevname, ifname);
+ pkt_dev->flows = vmalloc_node(MAX_CFLOWS * sizeof(struct flow_state),
+ node);
if (pkt_dev->flows == NULL) {
kfree(pkt_dev);
return -ENOMEM;
@@ -3651,8 +3653,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
pkt_dev->max_pkt_size = ETH_ZLEN;
pkt_dev->nfrags = 0;
pkt_dev->clone_skb = pg_clone_skb_d;
- pkt_dev->delay_us = pg_delay_d / 1000;
- pkt_dev->delay_ns = pg_delay_d % 1000;
+ pkt_dev->delay = pg_delay_d;
pkt_dev->count = pg_count_d;
pkt_dev->sofar = 0;
pkt_dev->udp_src_min = 9; /* sink port */
@@ -3702,7 +3703,8 @@ static int __init pktgen_create_thread(int cpu)
struct proc_dir_entry *pe;
struct task_struct *p;
- t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL);
+ t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL,
+ cpu_to_node(cpu));
if (!t) {
printk(KERN_ERR "pktgen: ERROR: out of memory, can't "
"create new thread.\n");
@@ -3864,10 +3866,15 @@ static void __exit pg_cleanup(void)
module_init(pg_init);
module_exit(pg_cleanup);
-MODULE_AUTHOR("Robert Olsson <[email protected]");
+MODULE_AUTHOR("Robert Olsson <[email protected]>");
MODULE_DESCRIPTION("Packet Generator tool");
MODULE_LICENSE("GPL");
+MODULE_VERSION(VERSION);
module_param(pg_count_d, int, 0);
+MODULE_PARM_DESC(pg_count_d, "Default number of packets to inject");
module_param(pg_delay_d, int, 0);
+MODULE_PARM_DESC(pg_delay_d, "Default delay between packets (nanoseconds)");
module_param(pg_clone_skb_d, int, 0);
+MODULE_PARM_DESC(pg_clone_skb_d, "Default number of copies of the same packet");
module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Enable debugging of pktgen module");
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index d78030f88bd0..33148a568199 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -35,11 +35,9 @@
#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/if_addr.h>
-#include <linux/nsproxy.h>
#include <asm/uaccess.h>
#include <asm/system.h>
-#include <asm/string.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
@@ -52,9 +50,9 @@
#include <net/pkt_sched.h>
#include <net/fib_rules.h>
#include <net/rtnetlink.h>
+#include <net/net_namespace.h>
-struct rtnl_link
-{
+struct rtnl_link {
rtnl_doit_func doit;
rtnl_dumpit_func dumpit;
};
@@ -65,6 +63,7 @@ void rtnl_lock(void)
{
mutex_lock(&rtnl_mutex);
}
+EXPORT_SYMBOL(rtnl_lock);
void __rtnl_unlock(void)
{
@@ -76,16 +75,19 @@ void rtnl_unlock(void)
/* This fellow will unlock it for us. */
netdev_run_todo();
}
+EXPORT_SYMBOL(rtnl_unlock);
int rtnl_trylock(void)
{
return mutex_trylock(&rtnl_mutex);
}
+EXPORT_SYMBOL(rtnl_trylock);
int rtnl_is_locked(void)
{
return mutex_is_locked(&rtnl_mutex);
}
+EXPORT_SYMBOL(rtnl_is_locked);
static struct rtnl_link *rtnl_msg_handlers[NPROTO];
@@ -168,7 +170,6 @@ int __rtnl_register(int protocol, int msgtype,
return 0;
}
-
EXPORT_SYMBOL_GPL(__rtnl_register);
/**
@@ -188,7 +189,6 @@ void rtnl_register(int protocol, int msgtype,
"protocol = %d, message type = %d\n",
protocol, msgtype);
}
-
EXPORT_SYMBOL_GPL(rtnl_register);
/**
@@ -213,7 +213,6 @@ int rtnl_unregister(int protocol, int msgtype)
return 0;
}
-
EXPORT_SYMBOL_GPL(rtnl_unregister);
/**
@@ -230,7 +229,6 @@ void rtnl_unregister_all(int protocol)
kfree(rtnl_msg_handlers[protocol]);
rtnl_msg_handlers[protocol] = NULL;
}
-
EXPORT_SYMBOL_GPL(rtnl_unregister_all);
static LIST_HEAD(link_ops);
@@ -248,12 +246,11 @@ static LIST_HEAD(link_ops);
int __rtnl_link_register(struct rtnl_link_ops *ops)
{
if (!ops->dellink)
- ops->dellink = unregister_netdevice;
+ ops->dellink = unregister_netdevice_queue;
list_add_tail(&ops->list, &link_ops);
return 0;
}
-
EXPORT_SYMBOL_GPL(__rtnl_link_register);
/**
@@ -271,19 +268,18 @@ int rtnl_link_register(struct rtnl_link_ops *ops)
rtnl_unlock();
return err;
}
-
EXPORT_SYMBOL_GPL(rtnl_link_register);
static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
{
struct net_device *dev;
-restart:
+ LIST_HEAD(list_kill);
+
for_each_netdev(net, dev) {
- if (dev->rtnl_link_ops == ops) {
- ops->dellink(dev);
- goto restart;
- }
+ if (dev->rtnl_link_ops == ops)
+ ops->dellink(dev, &list_kill);
}
+ unregister_netdevice_many(&list_kill);
}
void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops)
@@ -309,7 +305,6 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
}
list_del(&ops->list);
}
-
EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
/**
@@ -322,7 +317,6 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops)
__rtnl_link_unregister(ops);
rtnl_unlock();
}
-
EXPORT_SYMBOL_GPL(rtnl_link_unregister);
static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
@@ -427,12 +421,13 @@ void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data
struct rtattr *rta;
int size = RTA_LENGTH(attrlen);
- rta = (struct rtattr*)skb_put(skb, RTA_ALIGN(size));
+ rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size));
rta->rta_type = attrtype;
rta->rta_len = size;
memcpy(RTA_DATA(rta), data, attrlen);
memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size);
}
+EXPORT_SYMBOL(__rta_fill);
int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo)
{
@@ -454,6 +449,7 @@ int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid)
return nlmsg_unicast(rtnl, skb, pid);
}
+EXPORT_SYMBOL(rtnl_unicast);
void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
struct nlmsghdr *nlh, gfp_t flags)
@@ -466,6 +462,7 @@ void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
nlmsg_notify(rtnl, skb, pid, group, report, flags);
}
+EXPORT_SYMBOL(rtnl_notify);
void rtnl_set_sk_err(struct net *net, u32 group, int error)
{
@@ -473,6 +470,7 @@ void rtnl_set_sk_err(struct net *net, u32 group, int error)
netlink_set_err(rtnl, 0, group, error);
}
+EXPORT_SYMBOL(rtnl_set_sk_err);
int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
{
@@ -501,6 +499,7 @@ nla_put_failure:
nla_nest_cancel(skb, mx);
return -EMSGSIZE;
}
+EXPORT_SYMBOL(rtnetlink_put_metrics);
int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
u32 ts, u32 tsage, long expires, u32 error)
@@ -520,14 +519,13 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci);
}
-
EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo);
static void set_operstate(struct net_device *dev, unsigned char transition)
{
unsigned char operstate = dev->operstate;
- switch(transition) {
+ switch (transition) {
case IF_OPER_UP:
if ((operstate == IF_OPER_DORMANT ||
operstate == IF_OPER_UNKNOWN) &&
@@ -606,7 +604,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags)
{
- struct netdev_queue *txq;
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
const struct net_device_stats *stats;
@@ -637,9 +634,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
if (dev->master)
NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex);
- txq = netdev_get_tx_queue(dev, 0);
- if (txq->qdisc_sleeping)
- NLA_PUT_STRING(skb, IFLA_QDISC, txq->qdisc_sleeping->ops->id);
+ if (dev->qdisc)
+ NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc->ops->id);
if (dev->ifalias)
NLA_PUT_STRING(skb, IFLA_IFALIAS, dev->ifalias);
@@ -684,22 +680,33 @@ nla_put_failure:
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
- int idx;
- int s_idx = cb->args[0];
+ int h, s_h;
+ int idx = 0, s_idx;
struct net_device *dev;
-
- idx = 0;
- for_each_netdev(net, dev) {
- if (idx < s_idx)
- goto cont;
- if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
- NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0)
- break;
+ struct hlist_head *head;
+ struct hlist_node *node;
+
+ s_h = cb->args[0];
+ s_idx = cb->args[1];
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ idx = 0;
+ head = &net->dev_index_head[h];
+ hlist_for_each_entry(dev, node, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ NETLINK_CB(cb->skb).pid,
+ cb->nlh->nlmsg_seq, 0,
+ NLM_F_MULTI) <= 0)
+ goto out;
cont:
- idx++;
+ idx++;
+ }
}
- cb->args[0] = idx;
+out:
+ cb->args[1] = idx;
+ cb->args[0] = h;
return skb->len;
}
@@ -719,30 +726,26 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_NET_NS_PID] = { .type = NLA_U32 },
[IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 },
};
+EXPORT_SYMBOL(ifla_policy);
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
[IFLA_INFO_KIND] = { .type = NLA_STRING },
[IFLA_INFO_DATA] = { .type = NLA_NESTED },
};
-static struct net *get_net_ns_by_pid(pid_t pid)
+struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[])
{
- struct task_struct *tsk;
struct net *net;
-
- /* Lookup the network namespace */
- net = ERR_PTR(-ESRCH);
- rcu_read_lock();
- tsk = find_task_by_vpid(pid);
- if (tsk) {
- struct nsproxy *nsproxy;
- nsproxy = task_nsproxy(tsk);
- if (nsproxy)
- net = get_net(nsproxy->net_ns);
- }
- rcu_read_unlock();
+ /* Examine the link attributes and figure out which
+ * network namespace we are talking about.
+ */
+ if (tb[IFLA_NET_NS_PID])
+ net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID]));
+ else
+ net = get_net(src_net);
return net;
}
+EXPORT_SYMBOL(rtnl_link_get_net);
static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[])
{
@@ -767,8 +770,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
int err;
if (tb[IFLA_NET_NS_PID]) {
- struct net *net;
- net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID]));
+ struct net *net = rtnl_link_get_net(dev_net(dev), tb);
if (IS_ERR(net)) {
err = PTR_ERR(net);
goto errout;
@@ -931,9 +933,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
err = -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
- dev = dev_get_by_index(net, ifm->ifi_index);
+ dev = __dev_get_by_index(net, ifm->ifi_index);
else if (tb[IFLA_IFNAME])
- dev = dev_get_by_name(net, ifname);
+ dev = __dev_get_by_name(net, ifname);
else
goto errout;
@@ -942,12 +944,11 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
goto errout;
}
- if ((err = validate_linkmsg(dev, tb)) < 0)
- goto errout_dev;
+ err = validate_linkmsg(dev, tb);
+ if (err < 0)
+ goto errout;
err = do_setlink(dev, ifm, tb, ifname, 0);
-errout_dev:
- dev_put(dev);
errout:
return err;
}
@@ -984,30 +985,39 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
if (!ops)
return -EOPNOTSUPP;
- ops->dellink(dev);
+ ops->dellink(dev, NULL);
return 0;
}
-struct net_device *rtnl_create_link(struct net *net, char *ifname,
- const struct rtnl_link_ops *ops, struct nlattr *tb[])
+struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
+ char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[])
{
int err;
struct net_device *dev;
+ unsigned int num_queues = 1;
+ unsigned int real_num_queues = 1;
+ if (ops->get_tx_queues) {
+ err = ops->get_tx_queues(src_net, tb, &num_queues,
+ &real_num_queues);
+ if (err)
+ goto err;
+ }
err = -ENOMEM;
- dev = alloc_netdev(ops->priv_size, ifname, ops->setup);
+ dev = alloc_netdev_mq(ops->priv_size, ifname, ops->setup, num_queues);
if (!dev)
goto err;
+ dev_net_set(dev, net);
+ dev->rtnl_link_ops = ops;
+ dev->real_num_tx_queues = real_num_queues;
+
if (strchr(dev->name, '%')) {
err = dev_alloc_name(dev, dev->name);
if (err < 0)
goto err_free;
}
- dev_net_set(dev, net);
- dev->rtnl_link_ops = ops;
-
if (tb[IFLA_MTU])
dev->mtu = nla_get_u32(tb[IFLA_MTU]);
if (tb[IFLA_ADDRESS])
@@ -1030,6 +1040,7 @@ err_free:
err:
return ERR_PTR(err);
}
+EXPORT_SYMBOL(rtnl_create_link);
static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
@@ -1063,7 +1074,8 @@ replay:
else
dev = NULL;
- if ((err = validate_linkmsg(dev, tb)) < 0)
+ err = validate_linkmsg(dev, tb);
+ if (err < 0)
return err;
if (tb[IFLA_LINKINFO]) {
@@ -1084,6 +1096,7 @@ replay:
if (1) {
struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL;
+ struct net *dest_net;
if (ops) {
if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
@@ -1148,17 +1161,19 @@ replay:
if (!ifname[0])
snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
- dev = rtnl_create_link(net, ifname, ops, tb);
+ dest_net = rtnl_link_get_net(net, tb);
+ dev = rtnl_create_link(net, dest_net, ifname, ops, tb);
if (IS_ERR(dev))
err = PTR_ERR(dev);
else if (ops->newlink)
- err = ops->newlink(dev, tb, data);
+ err = ops->newlink(net, dev, tb, data);
else
err = register_netdevice(dev);
-
if (err < 0 && !IS_ERR(dev))
free_netdev(dev);
+
+ put_net(dest_net);
return err;
}
}
@@ -1167,6 +1182,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
+ char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
struct net_device *dev = NULL;
struct sk_buff *nskb;
@@ -1176,19 +1192,23 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
if (err < 0)
return err;
+ if (tb[IFLA_IFNAME])
+ nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+
ifm = nlmsg_data(nlh);
- if (ifm->ifi_index > 0) {
- dev = dev_get_by_index(net, ifm->ifi_index);
- if (dev == NULL)
- return -ENODEV;
- } else
+ if (ifm->ifi_index > 0)
+ dev = __dev_get_by_index(net, ifm->ifi_index);
+ else if (tb[IFLA_IFNAME])
+ dev = __dev_get_by_name(net, ifname);
+ else
return -EINVAL;
+ if (dev == NULL)
+ return -ENODEV;
+
nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
- if (nskb == NULL) {
- err = -ENOBUFS;
- goto errout;
- }
+ if (nskb == NULL)
+ return -ENOBUFS;
err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid,
nlh->nlmsg_seq, 0, 0);
@@ -1196,11 +1216,8 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
kfree_skb(nskb);
- goto errout;
- }
- err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid);
-errout:
- dev_put(dev);
+ } else
+ err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid);
return err;
}
@@ -1212,7 +1229,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
if (s_idx == 0)
s_idx = 1;
- for (idx=1; idx<NPROTO; idx++) {
+ for (idx = 1; idx < NPROTO; idx++) {
int type = cb->nlh->nlmsg_type-RTM_BASE;
if (idx < s_idx || idx == PF_PACKET)
continue;
@@ -1279,7 +1296,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg)))
return 0;
- family = ((struct rtgenmsg*)NLMSG_DATA(nlh))->rtgen_family;
+ family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family;
if (family >= NPROTO)
return -EAFNOSUPPORT;
@@ -1312,7 +1329,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
if (nlh->nlmsg_len > min_len) {
int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len);
- struct rtattr *attr = (void*)nlh + NLMSG_ALIGN(min_len);
+ struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len);
while (RTA_OK(attr, attrlen)) {
unsigned flavor = attr->rta_type;
@@ -1418,14 +1435,3 @@ void __init rtnetlink_init(void)
rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all);
}
-EXPORT_SYMBOL(__rta_fill);
-EXPORT_SYMBOL(rtnetlink_put_metrics);
-EXPORT_SYMBOL(rtnl_lock);
-EXPORT_SYMBOL(rtnl_trylock);
-EXPORT_SYMBOL(rtnl_unlock);
-EXPORT_SYMBOL(rtnl_is_locked);
-EXPORT_SYMBOL(rtnl_unicast);
-EXPORT_SYMBOL(rtnl_notify);
-EXPORT_SYMBOL(rtnl_set_sk_err);
-EXPORT_SYMBOL(rtnl_create_link);
-EXPORT_SYMBOL(ifla_policy);
diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c
deleted file mode 100644
index 79687dfd6957..000000000000
--- a/net/core/skb_dma_map.c
+++ /dev/null
@@ -1,65 +0,0 @@
-/* skb_dma_map.c: DMA mapping helpers for socket buffers.
- *
- * Copyright (C) David S. Miller <[email protected]>
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/skbuff.h>
-
-int skb_dma_map(struct device *dev, struct sk_buff *skb,
- enum dma_data_direction dir)
-{
- struct skb_shared_info *sp = skb_shinfo(skb);
- dma_addr_t map;
- int i;
-
- map = dma_map_single(dev, skb->data,
- skb_headlen(skb), dir);
- if (dma_mapping_error(dev, map))
- goto out_err;
-
- sp->dma_head = map;
- for (i = 0; i < sp->nr_frags; i++) {
- skb_frag_t *fp = &sp->frags[i];
-
- map = dma_map_page(dev, fp->page, fp->page_offset,
- fp->size, dir);
- if (dma_mapping_error(dev, map))
- goto unwind;
- sp->dma_maps[i] = map;
- }
-
- return 0;
-
-unwind:
- while (--i >= 0) {
- skb_frag_t *fp = &sp->frags[i];
-
- dma_unmap_page(dev, sp->dma_maps[i],
- fp->size, dir);
- }
- dma_unmap_single(dev, sp->dma_head,
- skb_headlen(skb), dir);
-out_err:
- return -ENOMEM;
-}
-EXPORT_SYMBOL(skb_dma_map);
-
-void skb_dma_unmap(struct device *dev, struct sk_buff *skb,
- enum dma_data_direction dir)
-{
- struct skb_shared_info *sp = skb_shinfo(skb);
- int i;
-
- dma_unmap_single(dev, sp->dma_head,
- skb_headlen(skb), dir);
- for (i = 0; i < sp->nr_frags; i++) {
- skb_frag_t *fp = &sp->frags[i];
-
- dma_unmap_page(dev, sp->dma_maps[i],
- fp->size, dir);
- }
-}
-EXPORT_SYMBOL(skb_dma_unmap);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9e0597d189b0..bfa3e7865a8c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -493,6 +493,9 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size)
{
struct skb_shared_info *shinfo;
+ if (irqs_disabled())
+ return 0;
+
if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE)
return 0;
@@ -546,7 +549,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
#endif
new->protocol = old->protocol;
new->mark = old->mark;
- new->iif = old->iif;
+ new->skb_iif = old->skb_iif;
__nf_copy(new, old);
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
@@ -559,9 +562,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
#endif
#endif
new->vlan_tci = old->vlan_tci;
-#if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE)
- new->do_not_encrypt = old->do_not_encrypt;
-#endif
skb_copy_secmark(new, old);
}
@@ -2704,7 +2704,8 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
NAPI_GRO_CB(skb)->free = 1;
goto done;
- }
+ } else if (skb_gro_len(p) != pinfo->gso_size)
+ return -E2BIG;
headroom = skb_headroom(p);
nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p));
diff --git a/net/core/sock.c b/net/core/sock.c
index bbb25be7ddfe..76ff58d43e26 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -142,7 +142,7 @@ static struct lock_class_key af_family_slock_keys[AF_MAX];
* strings build-time, so that runtime initialization of socket
* locks is fast):
*/
-static const char *af_family_key_strings[AF_MAX+1] = {
+static const char *const af_family_key_strings[AF_MAX+1] = {
"sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" ,
"sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK",
"sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" ,
@@ -158,7 +158,7 @@ static const char *af_family_key_strings[AF_MAX+1] = {
"sk_lock-AF_IEEE802154",
"sk_lock-AF_MAX"
};
-static const char *af_family_slock_key_strings[AF_MAX+1] = {
+static const char *const af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" ,
"slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK",
"slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" ,
@@ -174,7 +174,7 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = {
"slock-AF_IEEE802154",
"slock-AF_MAX"
};
-static const char *af_family_clock_key_strings[AF_MAX+1] = {
+static const char *const af_family_clock_key_strings[AF_MAX+1] = {
"clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" ,
"clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK",
"clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" ,
@@ -274,25 +274,27 @@ static void sock_disable_timestamp(struct sock *sk, int flag)
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
- int err = 0;
+ int err;
int skb_len;
+ unsigned long flags;
+ struct sk_buff_head *list = &sk->sk_receive_queue;
/* Cast sk->rcvbuf to unsigned... It's pointless, but reduces
number of warnings when compiling with -W --ANK
*/
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
(unsigned)sk->sk_rcvbuf) {
- err = -ENOMEM;
- goto out;
+ atomic_inc(&sk->sk_drops);
+ return -ENOMEM;
}
err = sk_filter(sk, skb);
if (err)
- goto out;
+ return err;
if (!sk_rmem_schedule(sk, skb->truesize)) {
- err = -ENOBUFS;
- goto out;
+ atomic_inc(&sk->sk_drops);
+ return -ENOBUFS;
}
skb->dev = NULL;
@@ -305,12 +307,14 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
*/
skb_len = skb->len;
- skb_queue_tail(&sk->sk_receive_queue, skb);
+ spin_lock_irqsave(&list->lock, flags);
+ skb->dropcount = atomic_read(&sk->sk_drops);
+ __skb_queue_tail(list, skb);
+ spin_unlock_irqrestore(&list->lock, flags);
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_data_ready(sk, skb_len);
-out:
- return err;
+ return 0;
}
EXPORT_SYMBOL(sock_queue_rcv_skb);
@@ -348,11 +352,18 @@ discard_and_relse:
}
EXPORT_SYMBOL(sk_receive_skb);
+void sk_reset_txq(struct sock *sk)
+{
+ sk_tx_queue_clear(sk);
+}
+EXPORT_SYMBOL(sk_reset_txq);
+
struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
struct dst_entry *dst = sk->sk_dst_cache;
if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
+ sk_tx_queue_clear(sk);
sk->sk_dst_cache = NULL;
dst_release(dst);
return NULL;
@@ -406,17 +417,18 @@ static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen)
if (copy_from_user(devname, optval, optlen))
goto out;
- if (devname[0] == '\0') {
- index = 0;
- } else {
- struct net_device *dev = dev_get_by_name(net, devname);
+ index = 0;
+ if (devname[0] != '\0') {
+ struct net_device *dev;
+ rcu_read_lock();
+ dev = dev_get_by_name_rcu(net, devname);
+ if (dev)
+ index = dev->ifindex;
+ rcu_read_unlock();
ret = -ENODEV;
if (!dev)
goto out;
-
- index = dev->ifindex;
- dev_put(dev);
}
lock_sock(sk);
@@ -446,7 +458,7 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
*/
int sock_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
int val;
@@ -482,6 +494,8 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
sk->sk_reuse = valbool;
break;
case SO_TYPE:
+ case SO_PROTOCOL:
+ case SO_DOMAIN:
case SO_ERROR:
ret = -ENOPROTOOPT;
break;
@@ -700,6 +714,12 @@ set_rcvbuf:
/* We implement the SO_SNDLOWAT etc to
not be settable (1003.1g 5.3) */
+ case SO_RXQ_OVFL:
+ if (valbool)
+ sock_set_flag(sk, SOCK_RXQ_OVFL);
+ else
+ sock_reset_flag(sk, SOCK_RXQ_OVFL);
+ break;
default:
ret = -ENOPROTOOPT;
break;
@@ -764,6 +784,14 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_type;
break;
+ case SO_PROTOCOL:
+ v.val = sk->sk_protocol;
+ break;
+
+ case SO_DOMAIN:
+ v.val = sk->sk_family;
+ break;
+
case SO_ERROR:
v.val = -sock_error(sk);
if (v.val == 0)
@@ -891,6 +919,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_mark;
break;
+ case SO_RXQ_OVFL:
+ v.val = !!sock_flag(sk, SOCK_RXQ_OVFL);
+ break;
+
default:
return -ENOPROTOOPT;
}
@@ -929,7 +961,8 @@ static void sock_copy(struct sock *nsk, const struct sock *osk)
void *sptr = nsk->sk_security;
#endif
BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) !=
- sizeof(osk->sk_node) + sizeof(osk->sk_refcnt));
+ sizeof(osk->sk_node) + sizeof(osk->sk_refcnt) +
+ sizeof(osk->sk_tx_queue_mapping));
memcpy(&nsk->sk_copy_start, &osk->sk_copy_start,
osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start));
#ifdef CONFIG_SECURITY_NETWORK
@@ -973,6 +1006,7 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority,
if (!try_module_get(prot->owner))
goto out_free_sec;
+ sk_tx_queue_clear(sk);
}
return sk;
@@ -1025,6 +1059,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
sk->sk_prot = sk->sk_prot_creator = prot;
sock_lock_init(sk);
sock_net_set(sk, get_net(net));
+ atomic_set(&sk->sk_wmem_alloc, 1);
}
return sk;
@@ -1195,12 +1230,12 @@ EXPORT_SYMBOL_GPL(sk_setup_caps);
void __init sk_init(void)
{
- if (num_physpages <= 4096) {
+ if (totalram_pages <= 4096) {
sysctl_wmem_max = 32767;
sysctl_rmem_max = 32767;
sysctl_wmem_default = 32767;
sysctl_rmem_default = 32767;
- } else if (num_physpages >= 131072) {
+ } else if (totalram_pages >= 131072) {
sysctl_wmem_max = 131071;
sysctl_rmem_max = 131071;
}
@@ -1217,17 +1252,22 @@ void __init sk_init(void)
void sock_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
- int res;
+ unsigned int len = skb->truesize;
- /* In case it might be waiting for more memory. */
- res = atomic_sub_return(skb->truesize, &sk->sk_wmem_alloc);
- if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE))
+ if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) {
+ /*
+ * Keep a reference on sk_wmem_alloc, this will be released
+ * after sk_write_space() call
+ */
+ atomic_sub(len - 1, &sk->sk_wmem_alloc);
sk->sk_write_space(sk);
+ len = 1;
+ }
/*
- * if sk_wmem_alloc reached 0, we are last user and should
- * free this sock, as sk_free() call could not do it.
+ * if sk_wmem_alloc reaches 0, we must finish what sk_free()
+ * could not do because of in-flight packets
*/
- if (res == 0)
+ if (atomic_sub_and_test(len, &sk->sk_wmem_alloc))
__sk_free(sk);
}
EXPORT_SYMBOL(sock_wfree);
@@ -1686,7 +1726,7 @@ int sock_no_shutdown(struct socket *sock, int how)
EXPORT_SYMBOL(sock_no_shutdown);
int sock_no_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
return -EOPNOTSUPP;
}
@@ -1872,7 +1912,6 @@ void sock_init_data(struct socket *sock, struct sock *sk)
*/
smp_wmb();
atomic_set(&sk->sk_refcnt, 1);
- atomic_set(&sk->sk_wmem_alloc, 1);
atomic_set(&sk->sk_drops, 0);
}
EXPORT_SYMBOL(sock_init_data);
@@ -2008,7 +2047,7 @@ EXPORT_SYMBOL(sock_common_recvmsg);
* Set socket options on an inet socket.
*/
int sock_common_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
@@ -2018,7 +2057,7 @@ EXPORT_SYMBOL(sock_common_setsockopt);
#ifdef CONFIG_COMPAT
int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
- char __user *optval, int optlen)
+ char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 7db1de0497c6..06124872af5b 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -10,14 +10,15 @@
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/netdevice.h>
+#include <linux/ratelimit.h>
#include <linux/init.h>
+
#include <net/ip.h>
#include <net/sock.h>
static struct ctl_table net_core_table[] = {
#ifdef CONFIG_NET
{
- .ctl_name = NET_CORE_WMEM_MAX,
.procname = "wmem_max",
.data = &sysctl_wmem_max,
.maxlen = sizeof(int),
@@ -25,7 +26,6 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec
},
{
- .ctl_name = NET_CORE_RMEM_MAX,
.procname = "rmem_max",
.data = &sysctl_rmem_max,
.maxlen = sizeof(int),
@@ -33,7 +33,6 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec
},
{
- .ctl_name = NET_CORE_WMEM_DEFAULT,
.procname = "wmem_default",
.data = &sysctl_wmem_default,
.maxlen = sizeof(int),
@@ -41,7 +40,6 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec
},
{
- .ctl_name = NET_CORE_RMEM_DEFAULT,
.procname = "rmem_default",
.data = &sysctl_rmem_default,
.maxlen = sizeof(int),
@@ -49,7 +47,6 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec
},
{
- .ctl_name = NET_CORE_DEV_WEIGHT,
.procname = "dev_weight",
.data = &weight_p,
.maxlen = sizeof(int),
@@ -57,7 +54,6 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec
},
{
- .ctl_name = NET_CORE_MAX_BACKLOG,
.procname = "netdev_max_backlog",
.data = &netdev_max_backlog,
.maxlen = sizeof(int),
@@ -65,16 +61,13 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec
},
{
- .ctl_name = NET_CORE_MSG_COST,
.procname = "message_cost",
.data = &net_ratelimit_state.interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
- .strategy = sysctl_jiffies,
},
{
- .ctl_name = NET_CORE_MSG_BURST,
.procname = "message_burst",
.data = &net_ratelimit_state.burst,
.maxlen = sizeof(int),
@@ -82,7 +75,6 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec,
},
{
- .ctl_name = NET_CORE_OPTMEM_MAX,
.procname = "optmem_max",
.data = &sysctl_optmem_max,
.maxlen = sizeof(int),
@@ -91,7 +83,6 @@ static struct ctl_table net_core_table[] = {
},
#endif /* CONFIG_NET */
{
- .ctl_name = NET_CORE_BUDGET,
.procname = "netdev_budget",
.data = &netdev_budget,
.maxlen = sizeof(int),
@@ -99,31 +90,29 @@ static struct ctl_table net_core_table[] = {
.proc_handler = proc_dointvec
},
{
- .ctl_name = NET_CORE_WARNINGS,
.procname = "warnings",
.data = &net_msg_warn,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
- { .ctl_name = 0 }
+ { }
};
static struct ctl_table netns_core_table[] = {
{
- .ctl_name = NET_CORE_SOMAXCONN,
.procname = "somaxconn",
.data = &init_net.core.sysctl_somaxconn,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec
},
- { .ctl_name = 0 }
+ { }
};
__net_initdata struct ctl_path net_core_path[] = {
- { .procname = "net", .ctl_name = CTL_NET, },
- { .procname = "core", .ctl_name = NET_CORE, },
+ { .procname = "net", },
+ { .procname = "core", },
{ },
};
@@ -134,7 +123,7 @@ static __net_init int sysctl_core_net_init(struct net *net)
net->core.sysctl_somaxconn = SOMAXCONN;
tbl = netns_core_table;
- if (net != &init_net) {
+ if (!net_eq(net, &init_net)) {
tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL);
if (tbl == NULL)
goto err_dup;
diff --git a/net/core/utils.c b/net/core/utils.c
index 83221aee7084..838250241d26 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -24,6 +24,8 @@
#include <linux/types.h>
#include <linux/percpu.h>
#include <linux/init.h>
+#include <linux/ratelimit.h>
+
#include <net/sock.h>
#include <asm/byteorder.h>
Powered by cgit, Gruvboxed by Blaster4385.