aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c1
-rw-r--r--net/core/dev.c408
-rw-r--r--net/core/drop_monitor.c2
-rw-r--r--net/core/ethtool.c81
-rw-r--r--net/core/filter.c6
-rw-r--r--net/core/gen_stats.c8
-rw-r--r--net/core/net-sysfs.c55
-rw-r--r--net/core/pktgen.c16
-rw-r--r--net/core/rtnetlink.c179
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/core/sock.c58
11 files changed, 523 insertions, 294 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 4ade3011bb3..95c2e0840d0 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -271,6 +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;
diff --git a/net/core/dev.c b/net/core/dev.c
index fe10551d367..d867522290b 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>
@@ -175,7 +176,7 @@ 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
@@ -193,18 +194,15 @@ static struct list_head ptype_all __read_mostly; /* Taps */
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 */
@@ -215,23 +213,26 @@ 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);
}
@@ -587,18 +588,44 @@ __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
* @net: the applicable net namespace
* @name: name to find
@@ -614,11 +641,11 @@ 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);
@@ -638,17 +665,42 @@ EXPORT_SYMBOL(dev_get_by_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);
+
/**
* dev_get_by_index - find a device by its ifindex
@@ -665,11 +717,11 @@ 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);
@@ -748,15 +800,15 @@ struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags,
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);
@@ -935,7 +987,12 @@ 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);
@@ -1038,9 +1095,9 @@ 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_NET_ADMIN))
request_module("%s", name);
@@ -1701,7 +1758,7 @@ 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))
@@ -1749,6 +1806,8 @@ gso:
nskb->next = NULL;
rc = ops->ndo_start_xmit(nskb, dev);
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;
@@ -1758,11 +1817,12 @@ 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 NETDEV_TX_OK;
+ return rc;
}
static u32 skb_tx_hashrnd;
@@ -1789,16 +1849,43 @@ 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 (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 (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 && 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);
@@ -1935,8 +2022,8 @@ gso:
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_tx_queue_stopped(txq)) {
- rc = NET_XMIT_SUCCESS;
- 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;
}
@@ -2292,7 +2379,7 @@ int netif_receive_skb(struct sk_buff *skb)
if (!skb->tstamp.tv64)
net_timestamp(skb);
- if (skb->vlan_tci && vlan_hwaccel_do_receive(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 */
@@ -2440,7 +2527,7 @@ 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;
@@ -2448,7 +2535,7 @@ 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;
@@ -2532,7 +2619,8 @@ 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;
@@ -2549,24 +2637,25 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
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);
@@ -2586,7 +2675,7 @@ 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);
@@ -2605,49 +2694,41 @@ 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);
@@ -2688,12 +2769,12 @@ 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));
}
@@ -2938,15 +3019,15 @@ 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;
@@ -3016,18 +3097,18 @@ 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;
@@ -3036,16 +3117,18 @@ 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)
@@ -4254,12 +4337,12 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
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;
@@ -4491,9 +4574,9 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
case SIOCGIFINDEX:
case SIOCGIFTXQLEN:
dev_load(net, ifr.ifr_name);
- read_lock(&dev_base_lock);
+ rcu_read_lock();
ret = dev_ifsioc_locked(net, &ifr, cmd);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
if (!ret) {
if (colon)
*colon = ':';
@@ -4636,59 +4719,76 @@ 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);
+ }
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,
@@ -4837,6 +4937,12 @@ 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;
@@ -5174,6 +5280,7 @@ 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);
dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
strcpy(dev->name, name);
@@ -5238,25 +5345,48 @@ void synchronize_net(void)
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);
+EXPORT_SYMBOL(unregister_netdevice_many);
/**
* unregister_netdev - remove device from the kernel
@@ -5484,7 +5614,7 @@ 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;
@@ -5583,7 +5713,7 @@ restart:
/* Delete virtual devices */
if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) {
- dev->rtnl_link_ops->dellink(dev);
+ dev->rtnl_link_ops->dellink(dev, NULL);
goto restart;
}
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 0a113f26bc9..b8e9d3a8688 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;
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 4c12ddb5f5e..d8aee584e8d 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -198,13 +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);
@@ -309,6 +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 };
@@ -684,16 +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);
@@ -728,36 +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)
@@ -798,16 +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);
@@ -1127,6 +1109,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_FLASHDEV:
rc = ethtool_flash_device(dev, useraddr);
break;
+ case ETHTOOL_RESET:
+ rc = ethtool_reset(dev, useraddr);
+ break;
default:
rc = -EOPNOTSUPP;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index d1d779ca096..08db7b9143a 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 8569310268a..393b1d8618e 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/net-sysfs.c b/net/core/net-sysfs.c
index 427ded84122..157645c0da7 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -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)
{
@@ -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),
@@ -500,12 +544,19 @@ int netdev_register_kobject(struct net_device *net)