summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c6
-rw-r--r--net/core/dev.c177
-rw-r--r--net/core/dev_addr_lists.c100
-rw-r--r--net/core/drop_monitor.c145
-rw-r--r--net/core/ethtool.c130
-rw-r--r--net/core/fib_rules.c32
-rw-r--r--net/core/filter.c87
-rw-r--r--net/core/gen_stats.c3
-rw-r--r--net/core/kmap_skb.h19
-rw-r--r--net/core/neighbour.c128
-rw-r--r--net/core/net-sysfs.c13
-rw-r--r--net/core/net_namespace.c39
-rw-r--r--net/core/netprio_cgroup.c6
-rw-r--r--net/core/pktgen.c78
-rw-r--r--net/core/rtnetlink.c359
-rw-r--r--net/core/skbuff.c454
-rw-r--r--net/core/sock.c95
-rw-r--r--net/core/sock_diag.c12
-rw-r--r--net/core/sysctl_net_core.c15
-rw-r--r--net/core/utils.c9
20 files changed, 1289 insertions, 618 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index e4fbfd6..ae6acf6 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -65,7 +65,7 @@ static inline int connection_based(struct sock *sk)
return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
}
-static int receiver_wake_function(wait_queue_t *wait, unsigned mode, int sync,
+static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync,
void *key)
{
unsigned long bits = (unsigned long)key;
@@ -158,7 +158,7 @@ out_noerr:
* quite explicitly by POSIX 1003.1g, don't change them without having
* the standard around please.
*/
-struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
+struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
int *peeked, int *off, int *err)
{
struct sk_buff *skb;
@@ -216,7 +216,7 @@ no_packet:
}
EXPORT_SYMBOL(__skb_recv_datagram);
-struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
+struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
int noblock, int *err)
{
int peeked, off = 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index 5d59155..cd09819 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -208,7 +208,8 @@ static inline void dev_base_seq_inc(struct net *net)
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
{
- unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
+ unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
+
return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)];
}
@@ -299,10 +300,9 @@ static const unsigned short netdev_lock_type[] =
ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
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_VOID, ARPHRD_NONE};
+ ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
+ ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
+ ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
static const char *const netdev_lock_name[] =
{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
@@ -317,10 +317,9 @@ static const char *const netdev_lock_name[] =
"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
"_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_VOID", "_xmit_NONE"};
+ "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
+ "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
+ "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
@@ -1409,14 +1408,34 @@ EXPORT_SYMBOL(register_netdevice_notifier);
* register_netdevice_notifier(). The notifier is unlinked into the
* kernel structures and may then be reused. A negative errno code
* is returned on a failure.
+ *
+ * After unregistering unregister and down device events are synthesized
+ * for all devices on the device list to the removed notifier to remove
+ * the need for special case cleanup code.
*/
int unregister_netdevice_notifier(struct notifier_block *nb)
{
+ struct net_device *dev;
+ struct net *net;
int err;
rtnl_lock();
err = raw_notifier_chain_unregister(&netdev_chain, nb);
+ if (err)
+ goto unlock;
+
+ for_each_net(net) {
+ for_each_netdev(net, dev) {
+ if (dev->flags & IFF_UP) {
+ nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
+ nb->notifier_call(nb, NETDEV_DOWN, dev);
+ }
+ nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev);
+ }
+ }
+unlock:
rtnl_unlock();
return err;
}
@@ -1596,10 +1615,15 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
kfree_skb(skb);
return NET_RX_DROP;
}
- skb_set_dev(skb, dev);
+ skb->skb_iif = 0;
+ skb->dev = dev;
+ 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);
@@ -1651,10 +1675,9 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
if (skb_network_header(skb2) < skb2->data ||
skb2->network_header > skb2->tail) {
- if (net_ratelimit())
- pr_crit("protocol %04x is buggy, dev %s\n",
- ntohs(skb2->protocol),
- dev->name);
+ net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
+ ntohs(skb2->protocol),
+ dev->name);
skb_reset_network_header(skb2);
}
@@ -1848,36 +1871,6 @@ void netif_device_attach(struct net_device *dev)
}
EXPORT_SYMBOL(netif_device_attach);
-/**
- * skb_dev_set -- assign a new device to a buffer
- * @skb: buffer for the new device
- * @dev: network device
- *
- * If an skb is owned by a device already, we have to reset
- * all data private to the namespace a device belongs to
- * before assigning it a new device.
- */
-#ifdef CONFIG_NET_NS
-void skb_set_dev(struct sk_buff *skb, struct net_device *dev)
-{
- skb_dst_drop(skb);
- if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) {
- secpath_reset(skb);
- nf_reset(skb);
- skb_init_secmark(skb);
- skb->mark = 0;
- skb->priority = 0;
- skb->nf_trace = 0;
- skb->ipvs_property = 0;
-#ifdef CONFIG_NET_SCHED
- skb->tc_index = 0;
-#endif
- }
- skb->dev = dev;
-}
-EXPORT_SYMBOL(skb_set_dev);
-#endif /* CONFIG_NET_NS */
-
static void skb_warn_bad_offload(const struct sk_buff *skb)
{
static const netdev_features_t null_features = 0;
@@ -2321,11 +2314,9 @@ 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()) {
- pr_warn("%s selects TX queue %d, but real number of TX queues is %d\n",
- dev->name, queue_index,
- dev->real_num_tx_queues);
- }
+ net_warn_ratelimited("%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;
@@ -2567,17 +2558,15 @@ int dev_queue_xmit(struct sk_buff *skb)
}
}
HARD_TX_UNLOCK(dev, txq);
- if (net_ratelimit())
- pr_crit("Virtual device %s asks to queue packet!\n",
- dev->name);
+ net_crit_ratelimited("Virtual device %s asks to queue packet!\n",
+ dev->name);
} else {
/* Recursion is detected! It is possible,
* unfortunately
*/
recursion_alert:
- if (net_ratelimit())
- pr_crit("Dead loop on virtual device %s, fix it urgently!\n",
- dev->name);
+ net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n",
+ dev->name);
}
}
@@ -3058,9 +3047,8 @@ static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq)
struct Qdisc *q;
if (unlikely(MAX_RED_LOOP < ttl++)) {
- if (net_ratelimit())
- pr_warn("Redir loop detected Dropping packet (%d->%d)\n",
- skb->skb_iif, dev->ifindex);
+ net_warn_ratelimited("Redir loop detected Dropping packet (%d->%d)\n",
+ skb->skb_iif, dev->ifindex);
return TC_ACT_SHOT;
}
@@ -3520,10 +3508,16 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
break;
case GRO_DROP:
- case GRO_MERGED_FREE:
kfree_skb(skb);
break;
+ case GRO_MERGED_FREE:
+ if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
+ kmem_cache_free(skbuff_head_cache, skb);
+ else
+ __kfree_skb(skb);
+ break;
+
case GRO_HELD:
case GRO_MERGED:
break;
@@ -3608,7 +3602,7 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
}
EXPORT_SYMBOL(napi_frags_finish);
-struct sk_buff *napi_frags_skb(struct napi_struct *napi)
+static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
{
struct sk_buff *skb = napi->skb;
struct ethhdr *eth;
@@ -3643,7 +3637,6 @@ struct sk_buff *napi_frags_skb(struct napi_struct *napi)
out:
return skb;
}
-EXPORT_SYMBOL(napi_frags_skb);
gro_result_t napi_gro_frags(struct napi_struct *napi)
{
@@ -4027,54 +4020,41 @@ static int dev_ifconf(struct net *net, char __user *arg)
#ifdef CONFIG_PROC_FS
-#define BUCKET_SPACE (32 - NETDEV_HASHBITS)
-
-struct dev_iter_state {
- struct seq_net_private p;
- unsigned int pos; /* bucket << BUCKET_SPACE + offset */
-};
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
#define get_bucket(x) ((x) >> BUCKET_SPACE)
#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
-static inline struct net_device *dev_from_same_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
{
- struct dev_iter_state *state = seq->private;
struct net *net = seq_file_net(seq);
struct net_device *dev;
struct hlist_node *p;
struct hlist_head *h;
- unsigned int count, bucket, offset;
+ unsigned int count = 0, offset = get_offset(*pos);
- bucket = get_bucket(state->pos);
- offset = get_offset(state->pos);
- h = &net->dev_name_head[bucket];
- count = 0;
+ h = &net->dev_name_head[get_bucket(*pos)];
hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
- if (count++ == offset) {
- state->pos = set_bucket_offset(bucket, count);
+ if (++count == offset)
return dev;
- }
}
return NULL;
}
-static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
{
- struct dev_iter_state *state = seq->private;
struct net_device *dev;
unsigned int bucket;
- bucket = get_bucket(state->pos);
do {
- dev = dev_from_same_bucket(seq);
+ dev = dev_from_same_bucket(seq, pos);
if (dev)
return dev;
- bucket++;
- state->pos = set_bucket_offset(bucket, 0);
+ bucket = get_bucket(*pos) + 1;
+ *pos = set_bucket_offset(bucket, 1);
} while (bucket < NETDEV_HASHENTRIES);
return NULL;
@@ -4087,33 +4067,20 @@ static inline struct net_device *dev_from_new_bucket(struct seq_file *seq)
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
- struct dev_iter_state *state = seq->private;
-
rcu_read_lock();
if (!*pos)
return SEQ_START_TOKEN;
- /* check for end of the hash */
- if (state->pos == 0 && *pos > 1)
+ if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
return NULL;
- return dev_from_new_bucket(seq);
+ return dev_from_bucket(seq, pos);
}
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct net_device *dev;
-
++*pos;
-
- if (v == SEQ_START_TOKEN)
- return dev_from_new_bucket(seq);
-
- dev = dev_from_same_bucket(seq);
- if (dev)
- return dev;
-
- return dev_from_new_bucket(seq);
+ return dev_from_bucket(seq, pos);
}
void dev_seq_stop(struct seq_file *seq, void *v)
@@ -4212,13 +4179,7 @@ static const struct seq_operations dev_seq_ops = {
static int dev_seq_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &dev_seq_ops,
- sizeof(struct dev_iter_state));
-}
-
-int dev_seq_open_ops(struct inode *inode, struct file *file,
- const struct seq_operations *ops)
-{
- return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+ sizeof(struct seq_net_private));
}
static const struct file_operations dev_seq_fops = {
@@ -4629,9 +4590,9 @@ void dev_set_rx_mode(struct net_device *dev)
*
* Get the combination of flag bits exported through APIs to userspace.
*/
-unsigned dev_get_flags(const struct net_device *dev)
+unsigned int dev_get_flags(const struct net_device *dev)
{
- unsigned flags;
+ unsigned int flags;
flags = (dev->flags & ~(IFF_PROMISC |
IFF_ALLMULTI |
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 29c07fe..c4cc2bc 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -21,12 +21,35 @@
* General list handling functions
*/
+static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
+ unsigned char *addr, int addr_len,
+ unsigned char addr_type, bool global)
+{
+ struct netdev_hw_addr *ha;
+ int alloc_size;
+
+ alloc_size = sizeof(*ha);
+ if (alloc_size < L1_CACHE_BYTES)
+ alloc_size = L1_CACHE_BYTES;
+ ha = kmalloc(alloc_size, GFP_ATOMIC);
+ if (!ha)
+ return -ENOMEM;
+ memcpy(ha->addr, addr, addr_len);
+ ha->type = addr_type;
+ ha->refcount = 1;
+ ha->global_use = global;
+ ha->synced = false;
+ list_add_tail_rcu(&ha->list, &list->list);
+ list->count++;
+
+ return 0;
+}
+
static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
unsigned char *addr, int addr_len,
unsigned char addr_type, bool global)
{
struct netdev_hw_addr *ha;
- int alloc_size;
if (addr_len > MAX_ADDR_LEN)
return -EINVAL;
@@ -46,21 +69,7 @@ static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
}
}
-
- alloc_size = sizeof(*ha);
- if (alloc_size < L1_CACHE_BYTES)
- alloc_size = L1_CACHE_BYTES;
- ha = kmalloc(alloc_size, GFP_ATOMIC);
- if (!ha)
- return -ENOMEM;
- memcpy(ha->addr, addr, addr_len);
- ha->type = addr_type;
- ha->refcount = 1;
- ha->global_use = global;
- ha->synced = false;
- list_add_tail_rcu(&ha->list, &list->list);
- list->count++;
- return 0;
+ return __hw_addr_create_ex(list, addr, addr_len, addr_type, global);
}
static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr,
@@ -377,6 +386,34 @@ EXPORT_SYMBOL(dev_addr_del_multiple);
*/
/**
+ * dev_uc_add_excl - Add a global secondary unicast address
+ * @dev: device
+ * @addr: address to add
+ */
+int dev_uc_add_excl(struct net_device *dev, unsigned char *addr)
+{
+ struct netdev_hw_addr *ha;
+ int err;
+
+ netif_addr_lock_bh(dev);
+ list_for_each_entry(ha, &dev->uc.list, list) {
+ if (!memcmp(ha->addr, addr, dev->addr_len) &&
+ ha->type == NETDEV_HW_ADDR_T_UNICAST) {
+ err = -EEXIST;
+ goto out;
+ }
+ }
+ err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len,
+ NETDEV_HW_ADDR_T_UNICAST, true);
+ if (!err)
+ __dev_set_rx_mode(dev);
+out:
+ netif_addr_unlock_bh(dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_uc_add_excl);
+
+/**
* dev_uc_add - Add a secondary unicast address
* @dev: device
* @addr: address to add
@@ -501,6 +538,34 @@ EXPORT_SYMBOL(dev_uc_init);
* Multicast list handling functions
*/
+/**
+ * dev_mc_add_excl - Add a global secondary multicast address
+ * @dev: device
+ * @addr: address to add
+ */
+int dev_mc_add_excl(struct net_device *dev, unsigned char *addr)
+{
+ struct netdev_hw_addr *ha;
+ int err;
+
+ netif_addr_lock_bh(dev);
+ list_for_each_entry(ha, &dev->mc.list, list) {
+ if (!memcmp(ha->addr, addr, dev->addr_len) &&
+ ha->type == NETDEV_HW_ADDR_T_MULTICAST) {
+ err = -EEXIST;
+ goto out;
+ }
+ }
+ err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len,
+ NETDEV_HW_ADDR_T_MULTICAST, true);
+ if (!err)
+ __dev_set_rx_mode(dev);
+out:
+ netif_addr_unlock_bh(dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_mc_add_excl);
+
static int __dev_mc_add(struct net_device *dev, unsigned char *addr,
bool global)
{
@@ -696,7 +761,8 @@ static const struct seq_operations dev_mc_seq_ops = {
static int dev_mc_seq_open(struct inode *inode, struct file *file)
{
- return dev_seq_open_ops(inode, file, &dev_mc_seq_ops);
+ return seq_open_net(inode, file, &dev_mc_seq_ops,
+ sizeof(struct seq_net_private));
}
static const struct file_operations dev_mc_seq_fops = {
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 7f36b38..3252e7e 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -4,6 +4,8 @@
* Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
@@ -22,6 +24,7 @@
#include <linux/timer.h>
#include <linux/bitops.h>
#include <linux/slab.h>
+#include <linux/module.h>
#include <net/genetlink.h>
#include <net/netevent.h>
@@ -42,13 +45,14 @@ static void send_dm_alert(struct work_struct *unused);
* netlink alerts
*/
static int trace_state = TRACE_OFF;
-static DEFINE_SPINLOCK(trace_state_lock);
+static DEFINE_MUTEX(trace_state_mutex);
struct per_cpu_dm_data {
struct work_struct dm_alert_work;
- struct sk_buff *skb;
+ struct sk_buff __rcu *skb;
atomic_t dm_hit_count;
struct timer_list send_timer;
+ int cpu;
};
struct dm_hw_stat_delta {
@@ -79,29 +83,53 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data)
size_t al;
struct net_dm_alert_msg *msg;
struct nlattr *nla;
+ struct sk_buff *skb;
+ struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1);
al = sizeof(struct net_dm_alert_msg);
al += dm_hit_limit * sizeof(struct net_dm_drop_point);
al += sizeof(struct nlattr);
- data->skb = genlmsg_new(al, GFP_KERNEL);
- genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family,
- 0, NET_DM_CMD_ALERT);
- nla = nla_reserve(data->skb, NLA_UNSPEC, sizeof(struct net_dm_alert_msg));
- msg = nla_data(nla);
- memset(msg, 0, al);
- atomic_set(&data->dm_hit_count, dm_hit_limit);
+ skb = genlmsg_new(al, GFP_KERNEL);
+
+ if (skb) {
+ genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+ 0, NET_DM_CMD_ALERT);
+ nla = nla_reserve(skb, NLA_UNSPEC,
+ sizeof(struct net_dm_alert_msg));
+ msg = nla_data(nla);
+ memset(msg, 0, al);
+ } else
+ schedule_work_on(data->cpu, &data->dm_alert_work);
+
+ /*
+ * Don't need to lock this, since we are guaranteed to only
+ * run this on a single cpu at a time.
+ * Note also that we only update data->skb if the old and new skb
+ * pointers don't match. This ensures that we don't continually call
+ * synchornize_rcu if we repeatedly fail to alloc a new netlink message.
+ */
+ if (skb != oskb) {
+ rcu_assign_pointer(data->skb, skb);
+
+ synchronize_rcu();
+
+ atomic_set(&data->dm_hit_count, dm_hit_limit);
+ }
+
}
static void send_dm_alert(struct work_struct *unused)
{
struct sk_buff *skb;
- struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+ struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+
+ WARN_ON_ONCE(data->cpu != smp_processor_id());
/*
* Grab the skb we're about to send
*/
- skb = data->skb;
+ skb = rcu_dereference_protected(data->skb, 1);
/*
* Replace it with a new one
@@ -111,8 +139,10 @@ static void send_dm_alert(struct work_struct *unused)
/*
* Ship it!
*/
- genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+ if (skb)
+ genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL);
+ put_cpu_var(dm_cpu_data);
}
/*
@@ -123,9 +153,11 @@ static void send_dm_alert(struct work_struct *unused)
*/
static void sched_send_work(unsigned long unused)
{
- struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+ struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+
+ schedule_work_on(smp_processor_id(), &data->dm_alert_work);
- schedule_work(&data->dm_alert_work);
+ put_cpu_var(dm_cpu_data);
}
static void trace_drop_common(struct sk_buff *skb, void *location)
@@ -134,9 +166,16 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
struct nlmsghdr *nlh;
struct nlattr *nla;
int i;
- struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data);
+ struct sk_buff *dskb;
+ struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data);
+ rcu_read_lock();
+ dskb = rcu_dereference(data->skb);
+
+ if (!dskb)
+ goto out;
+
if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) {
/*
* we're already at zero, discard this hit
@@ -144,12 +183,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
goto out;
}
- nlh = (struct nlmsghdr *)data->skb->data;
+ nlh = (struct nlmsghdr *)dskb->data;
nla = genlmsg_data(nlmsg_data(nlh));
msg = nla_data(nla);
for (i = 0; i < msg->entries; i++) {
if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
msg->points[i].count++;
+ atomic_inc(&data->dm_hit_count);
goto out;
}
}
@@ -157,7 +197,7 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
/*
* We need to create a new entry
*/
- __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point));
+ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
msg->points[msg->entries].count = 1;
@@ -169,6 +209,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location)
}
out:
+ rcu_read_unlock();
+ put_cpu_var(dm_cpu_data);
return;
}
@@ -213,7 +255,7 @@ static int set_all_monitor_traces(int state)
struct dm_hw_stat_delta *new_stat = NULL;
struct dm_hw_stat_delta *temp;
- spin_lock(&trace_state_lock);
+ mutex_lock(&trace_state_mutex);
if (state == trace_state) {
rc = -EAGAIN;
@@ -222,9 +264,15 @@ static int set_all_monitor_traces(int state)
switch (state) {
case TRACE_ON:
+ if (!try_module_get(THIS_MODULE)) {
+ rc = -ENODEV;
+ break;
+ }
+
rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
break;
+
case TRACE_OFF:
rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
@@ -240,6 +288,9 @@ static int set_all_monitor_traces(int state)
kfree_rcu(new_stat, rcu);
}
}
+
+ module_put(THIS_MODULE);
+
break;
default:
rc = 1;
@@ -252,7 +303,7 @@ static int set_all_monitor_traces(int state)
rc = -EINPROGRESS;
out_unlock:
- spin_unlock(&trace_state_lock);
+ mutex_unlock(&trace_state_mutex);
return rc;
}
@@ -295,12 +346,12 @@ static int dropmon_net_event(struct notifier_block *ev_block,
new_stat->dev = dev;
new_stat->last_rx = jiffies;
- spin_lock(&trace_state_lock);
+ mutex_lock(&trace_state_mutex);
list_add_rcu(&new_stat->list, &hw_stats_list);
- spin_unlock(&trace_state_lock);
+ mutex_unlock(&trace_state_mutex);
break;
case NETDEV_UNREGISTER:
- spin_lock(&trace_state_lock);
+ mutex_lock(&trace_state_mutex);
list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
if (new_stat->dev == dev) {
new_stat->dev = NULL;
@@ -311,7 +362,7 @@ static int dropmon_net_event(struct notifier_block *ev_block,
}
}
}
- spin_unlock(&trace_state_lock);
+ mutex_unlock(&trace_state_mutex);
break;
}
out:
@@ -342,10 +393,10 @@ static int __init init_net_drop_monitor(void)
struct per_cpu_dm_data *data;
int cpu, rc;
- printk(KERN_INFO "Initializing network drop monitor service\n");
+ pr_info("Initializing network drop monitor service\n");
if (sizeof(void *) > 8) {
- printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n");
+ pr_err("Unable to store program counters on this arch, Drop monitor failed\n");
return -ENOSPC;
}
@@ -353,27 +404,29 @@ static int __init init_net_drop_monitor(void)
dropmon_ops,
ARRAY_SIZE(dropmon_ops));
if (rc) {
- printk(KERN_ERR "Could not create drop monitor netlink family\n");
+ pr_err("Could not create drop monitor netlink family\n");
return rc;
}
rc = register_netdevice_notifier(&dropmon_net_notifier);
if (rc < 0) {
- printk(KERN_CRIT "Failed to register netdevice notifier\n");
+ pr_crit("Failed to register netdevice notifier\n");
goto out_unreg;
}
rc = 0;
- for_each_present_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
data = &per_cpu(dm_cpu_data, cpu);
- reset_per_cpu_data(data);
+ data->cpu = cpu;
INIT_WORK(&data->dm_alert_work, send_dm_alert);
init_timer(&data->send_timer);
data->send_timer.data = cpu;
data->send_timer.function = sched_send_work;
+ reset_per_cpu_data(data);
}
+
goto out;
out_unreg:
@@ -382,4 +435,36 @@ out:
return rc;
}
-late_initcall(init_net_drop_monitor);
+static void exit_net_drop_monitor(void)
+{
+ struct per_cpu_dm_data *data;
+ int cpu;
+
+ BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier));
+
+ /*
+ * Because of the module_get/put we do in the trace state change path
+ * we are guarnateed not to have any current users when we get here
+ * all we need to do is make sure that we don't have any running timers
+ * or pending schedule calls
+ */
+
+ for_each_possible_cpu(cpu) {
+ data = &per_cpu(dm_cpu_data, cpu);
+ del_timer_sync(&data->send_timer);
+ cancel_work_sync(&data->dm_alert_work);
+ /*
+ * At this point, we should have exclusive access
+ * to this struct and can free the skb inside it
+ */
+ kfree_skb(data->skb);
+ }
+
+ BUG_ON(genl_unregister_family(&net_drop_monitor_family));
+}
+
+module_init(init_net_drop_monitor);
+module_exit(exit_net_drop_monitor);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 6d6d7d2..9c2afb4 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -17,6 +17,8 @@
#include <linux/errno.h>
#include <linux/ethtool.h>
#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+#include <linux/phy.h>
#include <linux/bitops.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
@@ -36,6 +38,17 @@ u32 ethtool_op_get_link(struct net_device *dev)
}
EXPORT_SYMBOL(ethtool_op_get_link);
+int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info)
+{
+ info->so_timestamping =
+ SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+ info->phc_index = -1;
+ return 0;
+}
+EXPORT_SYMBOL(ethtool_op_get_ts_info);
+
/* Handlers for each ethtool command */
#define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32)
@@ -738,18 +751,17 @@ static int ethtool_get_link(struct net_device *dev, char __user *useraddr)
return 0;
}
-static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr)
+static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr,
+ int (*getter)(struct net_device *,
+ struct ethtool_eeprom *, u8 *),
+ u32 total_len)
{
struct ethtool_eeprom eeprom;
- const struct ethtool_ops *ops = dev->ethtool_ops;
void __user *userbuf = useraddr + sizeof(eeprom);
u32 bytes_remaining;
u8 *data;
int ret = 0;
- if (!ops->get_eeprom || !ops->get_eeprom_len)
- return -EOPNOTSUPP;
-
if (copy_from_user(&eeprom, useraddr, sizeof(eeprom)))
return -EFAULT;
@@ -758,7 +770,7 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr)
return -EINVAL;
/* Check for exceeding total eeprom len */
- if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev))
+ if (eeprom.offset + eeprom.len > total_len)
return -EINVAL;
data = kmalloc(PAGE_SIZE, GFP_USER);
@@ -769,7 +781,7 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr)
while (bytes_remaining > 0) {
eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE);
- ret = ops->get_eeprom(dev, &eeprom, data);
+ ret = getter(dev, &eeprom, data);
if (ret)
break;
if (copy_to_user(userbuf, data, eeprom.len)) {
@@ -790,6 +802,17 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr)
return ret;
}
+static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr)
+{
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+
+ if (!ops->get_eeprom || !ops->get_eeprom_len)
+ return -EOPNOTSUPP;
+
+ return ethtool_get_any_eeprom(dev, useraddr, ops->get_eeprom,
+ ops->get_eeprom_len(dev));
+}
+
static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr)
{
struct ethtool_eeprom eeprom;
@@ -1278,6 +1301,81 @@ out:
return ret;
}
+static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr)
+{
+ int err = 0;
+ struct ethtool_ts_info info;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+ struct phy_device *phydev = dev->phydev;
+
+ memset(&info, 0, sizeof(info));
+ info.cmd = ETHTOOL_GET_TS_INFO;
+
+ if (phydev && phydev->drv && phydev->drv->ts_info) {
+
+ err = phydev->drv->ts_info(phydev, &info);
+
+ } else if (dev->ethtool_ops && dev->ethtool_ops->get_ts_info) {
+
+ err = ops->get_ts_info(dev, &info);
+
+ } else {
+ info.so_timestamping =
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+ info.phc_index = -1;
+ }
+
+ if (err)
+ return err;
+
+ if (copy_to_user(useraddr, &info, sizeof(info)))
+ err = -EFAULT;
+
+ return err;
+}
+
+static int ethtool_get_module_info(struct net_device *dev,
+ void __user *useraddr)
+{
+ int ret;
+ struct ethtool_modinfo modinfo;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+
+ if (!ops->get_module_info)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&modinfo, useraddr, sizeof(modinfo)))
+ return -EFAULT;
+
+ ret = ops->get_module_info(dev, &modinfo);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(useraddr, &modinfo, sizeof(modinfo)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int ethtool_get_module_eeprom(struct net_device *dev,
+ void __user *useraddr)
+{
+ int ret;
+ struct ethtool_modinfo modinfo;
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+
+ if (!ops->get_module_info || !ops->get_module_eeprom)
+ return -EOPNOTSUPP;
+
+ ret = ops->get_module_info(dev, &modinfo);
+ if (ret)
+ return ret;
+
+ return ethtool_get_any_eeprom(dev, useraddr, ops->get_module_eeprom,
+ modinfo.eeprom_len);
+}
+
/* The main entry point in this file. Called from net/core/dev.c */
int dev_ethtool(struct net *net, struct ifreq *ifr)
@@ -1295,11 +1393,13 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
return -EFAULT;
if (!dev->ethtool_ops) {
- /* ETHTOOL_GDRVINFO does not require any driver support.
- * It is also unprivileged and does not change anything,
- * so we can take a shortcut to it. */
+ /* A few commands do not require any driver support,
+ * are unprivileged, and do not change anything, so we
+ * can take a shortcut to them. */
if (ethcmd == ETHTOOL_GDRVINFO)
return ethtool_get_drvinfo(dev, useraddr);
+ else if (ethcmd == ETHTOOL_GET_TS_INFO)
+ return ethtool_get_ts_info(dev, useraddr);
else
return -EOPNOTSUPP;
}
@@ -1330,6 +1430,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GRXCLSRULE:
case ETHTOOL_GRXCLSRLALL:
case ETHTOOL_GFEATURES:
+ case ETHTOOL_GET_TS_INFO:
break;
default:
if (!capable(CAP_NET_ADMIN))
@@ -1496,6 +1597,15 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
case ETHTOOL_GET_DUMP_DATA:
rc = ethtool_get_dump_data(dev, useraddr);
break;
+ case ETHTOOL_GET_TS_INFO:
+ rc = ethtool_get_ts_info(dev, useraddr);
+ break;
+ case ETHTOOL_GMODULEINFO:
+ rc = ethtool_get_module_info(dev, useraddr);
+ break;
+ case ETHTOOL_GMODULEEEPROM:
+ rc = ethtool_get_module_eeprom(dev, useraddr);
+ break;
default:
rc = -EOPNOTSUPP;
}
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index c02e63c..72cceb7 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -542,7 +542,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
frh = nlmsg_data(nlh);
frh->family = ops->family;
frh->table = rule->table;
- NLA_PUT_U32(skb, FRA_TABLE, rule->table);
+ if (nla_put_u32(skb, FRA_TABLE, rule->table))
+ goto nla_put_failure;
frh->res1 = 0;
frh->res2 = 0;
frh->action = rule->action;
@@ -553,31 +554,28 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
frh->flags |= FIB_RULE_UNRESOLVED;
if (rule->iifname[0]) {
- NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname);
-
+ if (nla_put_string(skb, FRA_IIFNAME, rule->iifname))
+ goto nla_put_failure;
if (rule->iifindex == -1)
frh->flags |= FIB_RULE_IIF_DETACHED;
}
if (rule->oifname[0]) {
- NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname);
-
+ if (nla_put_string(skb, FRA_OIFNAME, rule->oifname))
+ goto nla_put_failure;
if (rule->oifindex == -1)
frh->flags |= FIB_RULE_OIF_DETACHED;
}
- if (rule->pref)
- NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref);
-
- if (rule->mark)
- NLA_PUT_U32(skb, FRA_FWMARK, rule->mark);
-
- if (rule->mark_mask || rule->mark)
- NLA_PUT_U32(skb, FRA_FWMASK, rule->mark_mask);
-
- if (rule->target)
- NLA_PUT_U32(skb, FRA_GOTO, rule->target);
-
+ if ((rule->pref &&
+ nla_put_u32(skb, FRA_PRIORITY, rule->pref)) ||
+ (rule->mark &&
+ nla_put_u32(skb, FRA_FWMARK, rule->mark)) ||
+ ((rule->mark_mask || rule->mark) &&
+ nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
+ (rule->target &&
+ nla_put_u32(skb, FRA_GOTO, rule->target)))
+ goto nla_put_failure;
if (ops->fill(rule, skb, frh) < 0)
goto nla_put_failure;
diff --git a/net/core/filter.c b/net/core/filter.c
index cf4989a..a3eddb5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -38,9 +38,13 @@
#include <linux/filter.h>
#include <linux/reciprocal_div.h>
#include <linux/ratelimit.h>
+#include <linux/seccomp.h>
-/* No hurry in this branch */
-static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size)
+/* No hurry in this branch
+ *
+ * Exported for the bpf jit load helper.
+ */
+void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size)
{
u8 *ptr = NULL;
@@ -59,7 +63,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k,
{
if (k >= 0)
return skb_header_pointer(skb, k, size, buffer);
- return __load_pointer(skb, k, size);
+ return bpf_internal_load_pointer_neg_helper(skb, k, size);
}
/**
@@ -314,6 +318,9 @@ load_b:
case BPF_S_ANC_CPU:
A = raw_smp_processor_id();
continue;
+ case BPF_S_ANC_ALU_XOR_X:
+ A ^= X;
+ continue;
case BPF_S_ANC_NLATTR: {
struct nlattr *nla;
@@ -349,6 +356,11 @@ load_b:
A = 0;
continue;
}
+#ifdef CONFIG_SECCOMP_FILTER
+ case BPF_S_ANC_SECCOMP_LD_W:
+ A = seccomp_bpf_load(fentry->k);
+ continue;
+#endif
default:
WARN_RATELIMIT(1, "Unknown code:%u jt:%u tf:%u k:%u\n",
fentry->code, fentry->jt,
@@ -525,7 +537,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
* Compare this with conditional jumps below,
* where offsets are limited. --ANK (981016)
*/
- if (ftest->k >= (unsigned)(flen-pc-1))
+ if (ftest->k >= (unsigned int)(flen-pc-1))
return -EINVAL;
break;
case BPF_S_JMP_JEQ_K:
@@ -558,6 +570,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen)
ANCILLARY(HATYPE);
ANCILLARY(RXHASH);
ANCILLARY(CPU);
+ ANCILLARY(ALU_XOR_X);
}
}
ftest->code = code;
@@ -586,6 +599,67 @@ void sk_filter_release_rcu(struct rcu_head *rcu)
}
EXPORT_SYMBOL(sk_filter_release_rcu);
+static int __sk_prepare_filter(struct sk_filter *fp)
+{
+ int err;
+
+ fp->bpf_func = sk_run_filter;
+
+ err = sk_chk_filter(fp->insns, fp->len);
+ if (err)
+ return err;
+
+ bpf_jit_compile(fp);
+ return 0;
+}
+
+/**
+ * sk_unattached_filter_create - create an unattached filter
+ * @fprog: the filter program
+ * @sk: the socket to use
+ *
+ * Create a filter independent ofr any socket. We first run some
+ * sanity checks on it to make sure it does not explode on us later.
+ * If an error occurs or there is insufficient memory for the filter
+ * a negative errno code is returned. On success the return is zero.
+ */
+int sk_unattached_filter_create(struct sk_filter **pfp,
+ struct sock_fprog *fprog)
+{
+ struct sk_filter *fp;
+ unsigned int fsize = sizeof(struct sock_filter) * fprog->len;
+ int err;
+
+ /* Make sure new filter is there and in the right amounts. */
+ if (fprog->filter == NULL)
+ return -EINVAL;
+
+ fp = kmalloc(fsize + sizeof(*fp), GFP_KERNEL);
+ if (!fp)
+ return -ENOMEM;
+ memcpy(fp->insns, fprog->filter, fsize);
+
+ atomic_set(&fp->refcnt, 1);
+ fp->len = fprog->len;
+
+ err = __sk_prepare_filter(fp);
+ if (err)
+ goto free_mem;
+
+ *pfp = fp;
+ return 0;
+free_mem:
+ kfree(fp);
+ return err;
+}
+EXPORT_SYMBOL_GPL(sk_unattached_filter_create);
+
+void sk_unattached_filter_destroy(struct sk_filter *fp)
+{
+ sk_filter_release(fp);
+}
+EXPORT_SYMBOL_GPL(sk_unattached_filter_destroy);
+
/**
* sk_attach_filter - attach a socket filter
* @fprog: the filter program
@@ -616,16 +690,13 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
atomic_set(&fp->refcnt, 1);
fp->len = fprog->len;
- fp->bpf_func = sk_run_filter;
- err = sk_chk_filter(fp->insns, fp->len);
+ err = __sk_prepare_filter(fp);
if (err) {
sk_filter_uncharge(sk, fp);
return err;
}
- bpf_jit_compile(fp);
-
old_fp = rcu_dereference_protected(sk->sk_filter,
sock_owned_by_user(sk));
rcu_assign_pointer(sk->sk_filter, fp);
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index 0452eb2..ddedf21 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -27,7 +27,8 @@
static inline int
gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size)
{
- NLA_PUT(d->skb, type, size, buf);
+ if (nla_put(d->skb, type, size, buf))
+ goto nla_put_failure;
return 0;
nla_put_failure:
diff --git a/net/core/kmap_skb.h b/net/core/kmap_skb.h
deleted file mode 100644
index 52d0a44..0000000
--- a/net/core/kmap_skb.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#include <linux/highmem.h>
-
-static inline void *kmap_skb_frag(const skb_frag_t *frag)
-{
-#ifdef CONFIG_HIGHMEM
- BUG_ON(in_irq());
-
- local_bh_disable();
-#endif
- return kmap_atomic(skb_frag_page(frag));
-}
-
-static inline void kunmap_skb_frag(void *vaddr)
-{
- kunmap_atomic(vaddr);
-#ifdef CONFIG_HIGHMEM
- local_bh_enable();
-#endif
-}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 0a68045..eb09f8b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -15,6 +15,8 @@
* Harald Welte Add neighbour cache statistics like rtstat
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/kernel.h>
@@ -712,14 +714,13 @@ void neigh_destroy(struct neighbour *neigh)
NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);
if (!neigh->dead) {
- printk(KERN_WARNING
- "Destroying alive neighbour %p\n", neigh);
+ pr_warn("Destroying alive neighbour %p\n", neigh);
dump_stack();
return;
}
if (neigh_del_timer(neigh))
- printk(KERN_WARNING "Impossible event.\n");
+ pr_warn("Impossible event\n");
skb_queue_purge(&neigh->arp_queue);
neigh->arp_queue_len_bytes = 0;
@@ -890,7 +891,7 @@ static void neigh_timer_handler(unsigned long arg)
{
unsigned long now, next;
struct neighbour *neigh = (struct neighbour *)arg;
- unsigned state;
+ unsigned int state;
int notify = 0;
write_lock(&neigh->lock);
@@ -1500,7 +1501,7 @@ static void neigh_parms_destroy(struct neigh_parms *parms)
static struct lock_class_key neigh_table_proxy_queue_class;
-void neigh_table_init_no_netlink(struct neigh_table *tbl)
+static void neigh_table_init_no_netlink(struct neigh_table *tbl)
{
unsigned long now = jiffies;
unsigned long phsize;
@@ -1538,7 +1539,6 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl)
tbl->last_flush = now;
tbl->last_rand = now + tbl->parms.reachable_time * 20;
}
-EXPORT_SYMBOL(neigh_table_init_no_netlink);
void neigh_table_init(struct neigh_table *tbl)
{
@@ -1555,8 +1555,8 @@ void neigh_table_init(struct neigh_table *tbl)
write_unlock(&neigh_tbl_lock);
if (unlikely(tmp)) {
- printk(KERN_ERR "NEIGH: Registering multiple tables for "
- "family %d\n", tbl->family);
+ pr_err("Registering multiple tables for family %d\n",
+ tbl->family);
dump_stack();
}
}
@@ -1572,7 +1572,7 @@ int neigh_table_clear(struct neigh_table *tbl)
pneigh_queue_purge(&tbl->proxy_queue);
neigh_ifdown(tbl, NULL);
if (atomic_read(&tbl->entries))
- printk(KERN_CRIT "neighbour leakage\n");
+ pr_crit("neighbour leakage\n");
write_lock(&neigh_tbl_lock);
for (tp = &neigh_tables; *tp; tp = &(*tp)->next) {
if (*tp == tbl) {
@@ -1768,29 +1768,29 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
if (nest == NULL)
return -ENOBUFS;
- if (parms->dev)
- NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex);
-
- NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt));
- NLA_PUT_U32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes);
- /* approximative value for deprecated QUEUE_LEN (in packets) */
- NLA_PUT_U32(skb, NDTPA_QUEUE_LEN,
- DIV_ROUND_UP(parms->queue_len_bytes,
- SKB_TRUESIZE(ETH_FRAME_LEN)));
- NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen);
- NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes);
- NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes);
- NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes);
- NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time);
- NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME,
- parms->base_reachable_time);
- NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime);
- NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time);
- NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time);
- NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay);
- NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay);
- NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime);
-
+ if ((parms->dev &&
+ nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) ||
+ nla_put_u32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)) ||
+ nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes) ||
+ /* approximative value for deprecated QUEUE_LEN (in packets) */
+ nla_put_u32(skb, NDTPA_QUEUE_LEN,
+ DIV_ROUND_UP(parms->queue_len_bytes,
+ SKB_TRUESIZE(ETH_FRAME_LEN))) ||
+ nla_put_u32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen) ||
+ nla_put_u32(skb, NDTPA_APP_PROBES, parms->app_probes) ||
+ nla_put_u32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes) ||
+ nla_put_u32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes) ||
+ nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time) ||
+ nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME,
+ parms->base_reachable_time) ||
+ nla_put_msecs(skb, NDTPA_GC_STALETIME, parms->gc_staletime) ||
+ nla_put_msecs(skb, NDTPA_DELAY_PROBE_TIME,
+ parms->delay_probe_time) ||
+ nla_put_msecs(skb, NDTPA_RETRANS_TIME, parms->retrans_time) ||
+ nla_put_msecs(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay) ||
+ nla_put_msecs(skb, NDTPA_PROXY_DELAY, parms->proxy_delay) ||
+ nla_put_msecs(skb, NDTPA_LOCKTIME, parms->locktime))
+ goto nla_put_failure;
return nla_nest_end(skb, nest);
nla_put_failure:
@@ -1815,12 +1815,12 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
ndtmsg->ndtm_pad1 = 0;
ndtmsg->ndtm_pad2 = 0;
- NLA_PUT_STRING(skb, NDTA_NAME, tbl->id);
- NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval);
- NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1);
- NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2);
- NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3);
-
+ if (nla_put_string(skb, NDTA_NAME, tbl->id) ||
+ nla_put_msecs(skb, NDTA_GC_INTERVAL, tbl->gc_interval) ||
+ nla_put_u32(skb, NDTA_THRESH1, tbl->gc_thresh1) ||
+ nla_put_u32(skb, NDTA_THRESH2, tbl->gc_thresh2) ||
+ nla_put_u32(skb, NDTA_THRESH3, tbl->gc_thresh3))
+ goto nla_put_failure;
{
unsigned long now = jiffies;
unsigned int flush_delta = now - tbl->last_flush;
@@ -1841,7 +1841,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1);
rcu_read_unlock_bh();
- NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc);
+ if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc))
+ goto nla_put_failure;
}
{
@@ -1866,7 +1867,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl,
ndst.ndts_forced_gc_runs += st->forced_gc_runs;
}
- NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst);
+ if (nla_put(skb, NDTA_STATS, sizeof(ndst), &ndst))
+ goto nla_put_failure;
}
BUG_ON(tbl->parms.dev);
@@ -2137,7 +2139,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
ndm->ndm_type = neigh->type;
ndm->ndm_ifindex = neigh->dev->ifindex;
- NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key);
+ if (nla_put(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key))
+ goto nla_put_failure;
read_lock_bh(&neigh->lock);
ndm->ndm_state = neigh->nud_state;
@@ -2157,8 +2160,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh,
ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1;
read_unlock_bh(&neigh->lock);
- NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes));
- NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci);
+ if (nla_put_u32(skb, NDA_PROBES, atomic_read(&neigh->probes)) ||
+ nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
+ goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -2187,7 +2191,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn,
ndm->ndm_ifindex = pn->dev->ifindex;
ndm->ndm_state = NUD_NONE;
- NLA_PUT(skb, NDA_DST, tbl->key_len, pn->key);
+ if (nla_put(skb, NDA_DST, tbl->key_len, pn->key))
+ goto nla_put_failure;
return nlmsg_end(skb, nlh);
@@ -2795,7 +2800,6 @@ enum {
static struct neigh_sysctl_table {
struct ctl_table_header *sysctl_header;
struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1];
- char *dev_name;
} neigh_sysctl_template __read_mostly = {
.neigh_vars = {
[NEIGH_VAR_MCAST_PROBE] = {
@@ -2921,19 +2925,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
{
struct neigh_sysctl_table *t;
const char *dev_name_source = NULL;
-
-#define NEIGH_CTL_PATH_ROOT 0
-#define NEIGH_CTL_PATH_PROTO 1
-#define NEIGH_CTL_PATH_NEIGH 2
-#define NEIGH_CTL_PATH_DEV 3
-
- struct ctl_path neigh_path[] = {
- { .procname = "net", },
- { .procname = "proto", },
- { .procname = "neigh", },
- { .procname = "default", },
- { },
- };
+ char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ];
t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL);
if (!t)
@@ -2961,7 +2953,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0,
sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL]));
} else {
- dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname;
+ dev_name_source = "default";
t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1);
t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1;
t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2;
@@ -2984,23 +2976,16 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev;
}
- t->dev_name = kstrdup(dev_name_source, GFP_KERNEL);
- if (!t->dev_name)
- goto free;
-
- neigh_path[NEIGH_CTL_PATH_DEV].procname = t->dev_name;
- neigh_path[NEIGH_CTL_PATH_PROTO].procname = p_name;
-
+ snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s",
+ p_name, dev_name_source);
t->sysctl_header =
- register_net_sysctl_table(neigh_parms_net(p), neigh_path, t->neigh_vars);
+ register_net_sysctl(neigh_parms_net(p), neigh_path, t->neigh_vars);
if (!t->sysctl_header)
- goto free_procname;
+ goto free;
p->sysctl_table = t;
return 0;
-free_procname:
- kfree(t->dev_name);
free:
kfree(t);
err:
@@ -3013,8 +2998,7 @@ void neigh_sysctl_unregister(struct neigh_parms *p)
if (p->sysctl_table) {
struct neigh_sysctl_table *t = p->sysctl_table;
p->sysctl_table = NULL;
- unregister_sysctl_table(t->sysctl_header);
- kfree(t->dev_name);
+ unregister_net_sysctl_table(t->sysctl_header);
kfree(t);
}
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 4955862..fdf9e61 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -74,15 +74,14 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
int (*set)(struct net_device *, unsigned long))
{
struct net_device *net = to_net_dev(dev);
- char *endp;
unsigned long new;
int ret = -EINVAL;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
- new = simple_strtoul(buf, &endp, 0);
- if (endp == buf)
+ ret = kstrtoul(buf, 0, &new);
+ if (ret)
goto err;
if (!rtnl_trylock())
@@ -232,7 +231,7 @@ NETDEVICE_SHOW(flags, fmt_hex);
static int change_flags(struct net_device *net, unsigned long new_flags)
{
- return dev_change_flags(net, (unsigned) new_flags);
+ return dev_change_flags(net, (unsigned int) new_flags);
}
static ssize_t store_flags(struct device *dev, struct device_attribute *attr,
@@ -582,7 +581,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
return err;
}
- map = kzalloc(max_t(unsigned,
+ map = kzalloc(max_t(unsigned int,
RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES),
GFP_KERNEL);
if (!map) {
@@ -903,7 +902,7 @@ static ssize_t bql_set_hold_time(struct netdev_queue *queue,
const char *buf, size_t len)
{
struct dql *dql = &queue->dql;
- unsigned value;
+ unsigned int value;
int err;
err = kstrtouint(buf, 10, &value);
@@ -1107,7 +1106,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
return err;
}
- new_dev_maps = kzalloc(max_t(unsigned,
+ new_dev_maps = kzalloc(max_t(unsigned int,
XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL);
if (!new_dev_maps) {
free_cpumask_var(mask);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 0e950fd..dddbacb 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -1,3 +1,5 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/workqueue.h>
#include <linux/rtnetlink.h>
#include <linux/cache.h>
@@ -83,21 +85,29 @@ assign:
static int ops_init(const struct pernet_operations *ops, struct net *net)
{
- int err;
+ int err = -ENOMEM;
+ void *data = NULL;
+
if (ops->id && ops->size) {
- void *data = kzalloc(ops->size, GFP_KERNEL);
+ data = kzalloc(ops->size, GFP_KERNEL);
if (!data)
- return -ENOMEM;
+ goto out;
err = net_assign_generic(net, *ops->id, data);
- if (err) {
- kfree(data);
- return err;
- }
+ if (err)
+ goto cleanup;
}
+ err = 0;
if (ops->init)
- return ops->init(net);
- return 0;
+ err = ops->init(net);
+ if (!err)
+ return 0;
+
+cleanup:
+ kfree(data);
+
+out:
+ return err;
}
static void ops_free(const struct pernet_operations *ops, struct net *net)
@@ -204,8 +214,8 @@ static void net_free(struct net *net)
{
#ifdef NETNS_REFCNT_DEBUG
if (unlikely(atomic_read(&net->use_count) != 0)) {
- printk(KERN_EMERG "network namespace not free! Usage: %d\n",
- atomic_read(&net->use_count));
+ pr_emerg("network namespace not free! Usage: %d\n",
+ atomic_read(&net->use_count));
return;
}
#endif
@@ -448,12 +458,7 @@ static void __unregister_pernet_operations(struct pernet_operations *ops)
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;
-
+ return ops_init(ops, &init_net);
}
static void __unregister_pernet_operations(struct pernet_operations *ops)
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index b2a5986..5b8aa2f 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -9,6 +9,8 @@
* Authors: Neil Horman <nhorman@tuxdriver.com>
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
@@ -73,7 +75,7 @@ static void extend_netdev_table(struct net_device *dev, u32 new_len)
old_priomap = rtnl_dereference(dev->priomap);
if (!new_priomap) {
- printk(KERN_WARNING "Unable to alloc new priomap!\n");
+ pr_warn("Unable to alloc new priomap!\n");
return;
}
@@ -121,7 +123,7 @@ static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
ret = get_prioidx(&cs->prioidx);
if (ret != 0) {
- printk(KERN_WARNING "No space in priority index array\n");
+ pr_warn("No space in priority index array\n");
kfree(cs);
return ERR_PTR(ret);
}
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 4d8ce93..cce9e53 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -320,7 +320,7 @@ struct pktgen_dev {
(see RFC 3260, sec. 4) */
/* MPLS */
- unsigned nr_labels; /* Depth of stack, 0 = no MPLS */
+ unsigned int nr_labels; /* Depth of stack, 0 = no MPLS */
__be32 labels[MAX_MPLS_LABELS];
/* VLAN/SVLAN (802.1Q/Q-in-Q) */
@@ -373,10 +373,10 @@ struct pktgen_dev {
*/
char odevname[32];
struct flow_state *flows;
- unsigned cflows; /* Concurrent flows (config) */
- unsigned lflow; /* Flow length (config) */
- unsigned nflows; /* accumulated flows (stats) */
- unsigned curfl; /* current sequenced flow (state)*/
+ unsigned int cflows; /* Concurrent flows (config) */
+ unsigned int lflow; /* Flow length (config) */
+ unsigned int nflows; /* accumulated flows (stats) */
+ unsigned int curfl; /* current sequenced flow (state)*/
u16 queue_map_min;
u16 queue_map_max;
@@ -592,7 +592,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
pkt_dev->src_mac_count, pkt_dev->dst_mac_count);
if (pkt_dev->nr_labels) {
- unsigned i;
+ unsigned int i;
seq_printf(seq, " mpls: ");
for (i = 0; i < pkt_dev->nr_labels; i++)
seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]),
@@ -812,7 +812,7 @@ done_str:
static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
{
- unsigned n = 0;
+ unsigned int n = 0;
char c;
ssize_t i = 0;
int len;
@@ -891,8 +891,8 @@ static ssize_t pktgen_if_write(struct file *file,
if (copy_from_user(tb, user_buffer, copy))
return -EFAULT;
tb[copy] = 0;
- printk(KERN_DEBUG "pktgen: %s,%lu buffer -:%s:-\n", name,
- (unsigned long)count, tb);
+ pr_debug("%s,%lu buffer -:%s:-\n",
+ name, (unsigned long)count, tb);
}
if (!strcmp(name, "min_pkt_size")) {
@@ -1261,8 +1261,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->cur_daddr = pkt_dev->daddr_min;
}
if (debug)
- printk(KERN_DEBUG "pktgen: dst_min set to: %s\n",
- pkt_dev->dst_min);
+ pr_debug("dst_min set to: %s\n", pkt_dev->dst_min);
i += len;
sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min);
return count;
@@ -1284,8 +1283,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->cur_daddr = pkt_dev->daddr_max;
}
if (debug)
- printk(KERN_DEBUG "pktgen: dst_max set to: %s\n",
- pkt_dev->dst_max);
+ pr_debug("dst_max set to: %s\n", pkt_dev->dst_max);
i += len;
sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max);
return count;
@@ -1307,7 +1305,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr;
if (debug)
- printk(KERN_DEBUG "pktgen: dst6 set to: %s\n", buf);
+ pr_debug("dst6 set to: %s\n", buf);
i += len;
sprintf(pg_result, "OK: dst6=%s", buf);
@@ -1329,7 +1327,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr;
if (debug)
- printk(KERN_DEBUG "pktgen: dst6_min set to: %s\n", buf);
+ pr_debug("dst6_min set to: %s\n", buf);
i += len;
sprintf(pg_result, "OK: dst6_min=%s", buf);
@@ -1350,7 +1348,7 @@ static ssize_t pktgen_if_write(struct file *file,
snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr);
if (debug)
- printk(KERN_DEBUG "pktgen: dst6_max set to: %s\n", buf);
+ pr_debug("dst6_max set to: %s\n", buf);
i += len;
sprintf(pg_result, "OK: dst6_max=%s", buf);
@@ -1373,7 +1371,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr;
if (debug)
- printk(KERN_DEBUG "pktgen: src6 set to: %s\n", buf);
+ pr_debug("src6 set to: %s\n", buf);
i += len;
sprintf(pg_result, "OK: src6=%s", buf);
@@ -1394,8 +1392,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->cur_saddr = pkt_dev->saddr_min;
}
if (debug)
- printk(KERN_DEBUG "pktgen: src_min set to: %s\n",
- pkt_dev->src_min);
+ pr_debug("src_min set to: %s\n", pkt_dev->src_min);
i += len;
sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min);
return count;
@@ -1415,8 +1412,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->cur_saddr = pkt_dev->saddr_max;
}
if (debug)
- printk(KERN_DEBUG "pktgen: src_max set to: %s\n",
- pkt_dev->src_max);
+ pr_debug("src_max set to: %s\n", pkt_dev->src_max);
i += len;
sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max);
return count;
@@ -1510,7 +1506,7 @@ static ssize_t pktgen_if_write(struct file *file,
}
if (!strcmp(name, "mpls")) {
- unsigned n, cnt;
+ unsigned int n, cnt;
len = get_labels(&user_buffer[i], pkt_dev);
if (len < 0)
@@ -1527,7 +1523,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->svlan_id = 0xffff;
if (debug)
- printk(KERN_DEBUG "pktgen: VLAN/SVLAN auto turned off\n");
+ pr_debug("VLAN/SVLAN auto turned off\n");
}
return count;
}
@@ -1542,10 +1538,10 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->vlan_id = value; /* turn on VLAN */
if (debug)
- printk(KERN_DEBUG "pktgen: VLAN turned on\n");
+ pr_debug("VLAN turned on\n");
if (debug && pkt_dev->nr_labels)
- printk(KERN_DEBUG "pktgen: MPLS auto turned off\n");
+ pr_debug("MPLS auto turned off\n");
pkt_dev->nr_labels = 0; /* turn off MPLS */
sprintf(pg_result, "OK: vlan_id=%u", pkt_dev->vlan_id);
@@ -1554,7 +1550,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->svlan_id = 0xffff;
if (debug)
- printk(KERN_DEBUG "pktgen: VLAN/SVLAN turned off\n");
+ pr_debug("VLAN/SVLAN turned off\n");
}
return count;
}
@@ -1599,10 +1595,10 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->svlan_id = value; /* turn on SVLAN */
if (debug)
- printk(KERN_DEBUG "pktgen: SVLAN turned on\n");
+ pr_debug("SVLAN turned on\n");
if (debug && pkt_dev->nr_labels)
- printk(KERN_DEBUG "pktgen: MPLS auto turned off\n");
+ pr_debug("MPLS auto turned off\n");
pkt_dev->nr_labels = 0; /* turn off MPLS */
sprintf(pg_result, "OK: svlan_id=%u", pkt_dev->svlan_id);
@@ -1611,7 +1607,7 @@ static ssize_t pktgen_if_write(struct file *file,
pkt_dev->svlan_id = 0xffff;
if (debug)
- printk(KERN_DEBUG "pktgen: VLAN/SVLAN turned off\n");
+ pr_debug("VLAN/SVLAN turned off\n");
}
return count;
}
@@ -1779,8 +1775,7 @@ static ssize_t pktgen_thread_write(struct file *file,
i += len;
if (debug)
- printk(KERN_DEBUG "pktgen: t=%s, count=%lu\n",
- name, (unsigned long)count);
+ pr_debug("t=%s, count=%lu\n", name, (unsigned long)count);
if (!t) {
pr_err("ERROR: No thread\n");
@@ -1931,7 +1926,7 @@ static int pktgen_device_event(struct notifier_block *unused,
{
struct net_device *dev = ptr;
- if (!net_eq(dev_net(dev), &init_net))
+ if (!net_eq(dev_net(dev), &init_net) || pktgen_exiting)
return NOTIFY_DONE;
/* It is OK that we do not hold the group lock right now,
@@ -2324,7 +2319,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
}
if (pkt_dev->flags & F_MPLS_RND) {
- unsigned i;
+ unsigned int i;
for (i = 0; i < pkt_dev->nr_labels; i++)
if (pkt_dev->labels[i] & MPLS_STACK_BOTTOM)
pkt_dev->labels[i] = MPLS_STACK_BOTTOM |
@@ -2550,7 +2545,7 @@ err:
static void mpls_push(__be32 *mpls, struct pktgen_dev *pkt_dev)
{
- unsigned i;
+ unsigned int i;
for (i = 0; i < pkt_dev->nr_labels; i++)
*mpls++ = pkt_dev->labels[i] & ~MPLS_STACK_BOTTOM;
@@ -2934,8 +2929,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
if (datalen < sizeof(struct pktgen_hdr)) {
datalen = sizeof(struct pktgen_hdr);
- if (net_ratelimit())
- pr_info("increased datalen to %d\n", datalen);
+ net_info_ratelimited("increased datalen to %d\n", datalen);
}
udph->source = htons(pkt_dev->cur_udp_src);
@@ -3365,8 +3359,8 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
pkt_dev->errors++;
break;
default: /* Drivers are not supposed to return other values! */
- if (net_ratelimit())
- pr_info("%s xmit error: %d\n", pkt_dev->odevname, ret);
+ net_info_ratelimited("%s xmit error: %d\n",
+ pkt_dev->odevname, ret);
pkt_dev->errors++;
/* fallthru */
case NETDEV_TX_LOCKED:
@@ -3755,12 +3749,18 @@ static void __exit pg_cleanup(void)
{
struct pktgen_thread *t;
struct list_head *q, *n;
+ LIST_HEAD(list);
/* Stop all interfaces & threads */
pktgen_exiting = true;
- list_for_each_safe(q, n, &pktgen_threads) {
+ mutex_lock(&pktgen_thread_lock);
+ list_splice_init(&pktgen_threads, &list);
+ mutex_unlock(&pktgen_thread_lock);
+
+ list_for_each_safe(q, n, &list) {
t = list_entry(q, struct pktgen_thread, th_list);
+ list_del(&t->th_list);
kthread_stop(t->tsk);
kfree(t);
}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 90430b7..21318d1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -35,7 +35,9 @@
#include <linux/security.h>
#include <linux/mutex.h>
#include <linux/if_addr.h>
+#include <linux/if_bridge.h>
#include <linux/pci.h>
+#include <linux/etherdevice.h>
#include <asm/uaccess.h>
@@ -552,7 +554,7 @@ void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data
}
EXPORT_SYMBOL(__rta_fill);
-int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo)
+int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned int group, int echo)
{
struct sock *rtnl = net->rtnl;
int err = 0;
@@ -607,7 +609,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics)
for (i = 0; i < RTAX_MAX; i++) {
if (metrics[i]) {
valid++;
- NLA_PUT_U32(skb, i+1, metrics[i]);
+ if (nla_put_u32(skb, i+1, metrics[i]))
+ goto nla_put_failure;
}
}
@@ -782,6 +785,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_MTU */
+ nla_total_size(4) /* IFLA_LINK */
+ nla_total_size(4) /* IFLA_MASTER */
+ + nla_total_size(4) /* IFLA_PROMISCUITY */
+ nla_total_size(1) /* IFLA_OPERSTATE */
+ nla_total_size(1) /* IFLA_LINKMODE */
+ nla_total_size(ext_filter_mask
@@ -807,7 +811,8 @@ static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
vf_port = nla_nest_start(skb, IFLA_VF_PORT);
if (!vf_port)
goto nla_put_failure;
- NLA_PUT_U32(skb, IFLA_PORT_VF, vf);
+ if (nla_put_u32(skb, IFLA_PORT_VF, vf))
+ goto nla_put_failure;
err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb);
if (err == -EMSGSIZE)
goto nla_put_failure;
@@ -891,25 +896,23 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
ifm->ifi_flags = dev_get_flags(dev);
ifm->ifi_change = change;
- NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name);
- NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len);
- NLA_PUT_U8(skb, IFLA_OPERSTATE,
- netif_running(dev) ? dev->operstate : IF_OPER_DOWN);
- NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode);
- NLA_PUT_U32(skb, IFLA_MTU, dev->mtu);
- NLA_PUT_U32(skb, IFLA_GROUP, dev->group);
-
- if (dev->ifindex != dev->iflink)
- NLA_PUT_U32(skb, IFLA_LINK, dev->iflink);
-
- if (dev->master)
- NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex);
-
- if (dev->qdisc)
- NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc->ops->id);
-
- if (dev->ifalias)
- NLA_PUT_STRING(skb, IFLA_IFALIAS, dev->ifalias);
+ if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
+ nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) ||
+ nla_put_u8(skb, IFLA_OPERSTATE,
+ netif_running(dev) ? dev->operstate : IF_OPER_DOWN) ||
+ nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) ||
+ nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
+ nla_put_u32(skb, IFLA_GROUP, dev->group) ||
+ nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) ||
+ (dev->ifindex != dev->iflink &&
+ nla_put_u32(skb, IFLA_LINK, dev->iflink)) ||
+ (dev->master &&
+ nla_put_u32(skb, IFLA_MASTER, dev->master->ifindex)) ||
+ (dev->qdisc &&
+ nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) ||
+ (dev->ifalias &&
+ nla_put_string(skb, IFLA_IFALIAS, dev->ifalias)))
+ goto nla_put_failure;
if (1) {
struct rtnl_link_ifmap map = {
@@ -920,12 +923,14 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
.dma = dev->dma,
.port = dev->if_port,
};
- NLA_PUT(skb, IFLA_MAP, sizeof(map), &map);
+ if (nla_put(skb, IFLA_MAP, sizeof(map), &map))
+ goto nla_put_failure;
}
if (dev->addr_len) {
- NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr);
- NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast);
+ if (nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr) ||
+ nla_put(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast))
+ goto nla_put_failure;
}
attr = nla_reserve(skb, IFLA_STATS,
@@ -942,8 +947,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
goto nla_put_failure;
copy_rtnl_link_stats64(nla_data(attr), stats);
- if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF))
- NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent));
+ if (dev->dev.parent && (ext_filter_mask & RTEXT_FILTER_VF) &&
+ nla_put_u32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)))
+ goto nla_put_failure;
if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent
&& (ext_filter_mask & RTEXT_FILTER_VF)) {
@@ -986,12 +992,13 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
nla_nest_cancel(skb, vfinfo);
goto nla_put_failure;
}
- NLA_PUT(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac);
- NLA_PUT(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan);
- NLA_PUT(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
- &vf_tx_rate);
- NLA_PUT(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
- &vf_spoofchk);
+ if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) ||
+ nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) ||
+ nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate),
+ &vf_tx_rate) ||
+ nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk),
+ &vf_spoofchk))
+ goto nla_put_failure;
nla_nest_end(skb, vf);
}
nla_nest_end(skb, vfinfo);
@@ -1113,6 +1120,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_PORT_SELF] = { .type = NLA_NESTED },
[IFLA_AF_SPEC] = { .type = NLA_NESTED },
[IFLA_EXT_MASK] = { .type = NLA_U32 },
+ [IFLA_PROMISCUITY] = { .type = NLA_U32 },
};
EXPORT_SYMBOL(ifla_policy);
@@ -1516,11 +1524,9 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
err = 0;
errout:
- if (err < 0 && modified && net_ratelimit())
- printk(KERN_WARNING "A link change request failed with "
- "some changes committed already. Interface %s may "
- "have been left with an inconsistent configuration, "
- "please check.\n", dev->name);
+ if (err < 0 && modified)
+ net_warn_ratelimited("A link change request failed with some changes committed already. Interface %s may have been left with an inconsistent configuration, please check.\n",
+ dev->name);
if (send_addr_notify)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
@@ -1634,14 +1640,14 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net,
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)
+ err = ops->get_tx_queues(src_net, tb);
+ if (err < 0)
goto err;
+ num_queues = err;
}
+
err = -ENOMEM;
dev = alloc_netdev_mq(ops->priv_size, ifname, ops->setup, num_queues);
if (!dev)
@@ -1947,7 +1953,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
return skb->len;
}
-void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
+void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change)
{
struct net *net = dev_net(dev);
struct sk_buff *skb;
@@ -1972,6 +1978,267 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_LINK, err);
}
+static int nlmsg_populate_fdb_fill(struct sk_buff *skb,
+ struct net_device *dev,
+ u8 *addr, u32 pid, u32 seq,
+ int type, unsigned int flags)
+{
+ struct nlmsghdr *nlh;
+ struct ndmsg *ndm;
+
+ nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), NLM_F_MULTI);
+ if (!nlh)
+ return -EMSGSIZE;
+
+ ndm = nlmsg_data(nlh);
+ ndm->ndm_family = AF_BRIDGE;
+ ndm->ndm_pad1 = 0;
+ ndm->ndm_pad2 = 0;
+ ndm->ndm_flags = flags;
+ ndm->ndm_type = 0;
+ ndm->ndm_ifindex = dev->ifindex;
+ ndm->ndm_state = NUD_PERMANENT;
+
+ if (nla_put(skb, NDA_LLADDR, ETH_ALEN, addr))
+ goto nla_put_failure;
+
+ return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+ return -EMSGSIZE;
+}
+
+static inline size_t rtnl_fdb_nlmsg_size(void)
+{
+ return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN);
+}
+
+static void rtnl_fdb_notify(struct net_device *dev, u8 *addr, int type)
+{
+ struct net *net = dev_net(dev);
+ struct sk_buff *skb;
+ int err = -ENOBUFS;
+
+ skb = nlmsg_new(rtnl_fdb_nlmsg_size(), GFP_ATOMIC);
+ if (!skb)
+ goto errout;
+
+ err = nlmsg_populate_fdb_fill(skb, dev, addr, 0, 0, type, NTF_SELF);
+ if (err < 0) {
+ kfree_skb(skb);
+ goto errout;
+ }
+
+ rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
+ return;
+errout:
+ rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
+}
+
+static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+ struct net *net = sock_net(skb->sk);
+ struct net_device *master = NULL;
+ struct ndmsg *ndm;
+ struct nlattr *tb[NDA_MAX+1];
+ struct net_device *dev;
+ u8 *addr;
+ int err;
+
+ err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL);
+ if (err < 0)
+ return err;
+
+ ndm = nlmsg_data(nlh);
+ if (ndm->ndm_ifindex == 0) {
+ pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ifindex\n");
+ return -EINVAL;
+ }
+
+ dev = __dev_get_by_index(net, ndm->ndm_ifindex);
+ if (dev == NULL) {
+ pr_info("PF_BRIDGE: RTM_NEWNEIGH with unknown ifindex\n");
+ return -ENODEV;
+ }
+
+ if (!tb[NDA_LLADDR] || nla_len(tb[NDA_LLADDR]) != ETH_ALEN) {
+ pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid address\n");
+ return -EINVAL;
+ }
+
+ addr = nla_data(tb[NDA_LLADDR]);
+ if (!is_valid_ether_addr(addr)) {
+ pr_info("PF_BRIDGE: RTM_NEWNEIGH with invalid ether address\n");
+ return -EINVAL;
+ }
+
+ err = -EOPNOTSUPP;
+
+ /* Support fdb on master device the net/bridge default case */
+ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
+ (dev->priv_flags & IFF_BRIDGE_PORT)) {
+ master = dev->master;
+ err = master->netdev_ops->ndo_fdb_add(ndm, dev, addr,
+ nlh->nlmsg_flags);
+ if (err)
+ goto out;
+ else
+ ndm->ndm_flags &= ~NTF_MASTER;
+ }
+
+ /* Embedded bridge, macvlan, and any other device support */
+ if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_add) {
+ err = dev->netdev_ops->ndo_fdb_add(ndm, dev, addr,
+ nlh->nlmsg_flags);
+
+ if (!err) {
+ rtnl_fdb_notify(dev, addr, RTM_NEWNEIGH);
+ ndm->ndm_flags &= ~NTF_SELF;
+ }
+ }
+out:
+ return err;
+}
+
+static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+ struct net *net = sock_net(skb->sk);
+ struct ndmsg *ndm;
+ struct nlattr *llattr;
+ struct net_device *dev;
+ int err = -EINVAL;
+ __u8 *addr;
+
+ if (nlmsg_len(nlh) < sizeof(*ndm))
+ return -EINVAL;
+
+ ndm = nlmsg_data(nlh);
+ if (ndm->ndm_ifindex == 0) {
+ pr_info("PF_BRIDGE: RTM_DELNEIGH with invalid ifindex\n");
+ return -EINVAL;
+ }
+
+ dev = __dev_get_by_index(net, ndm->ndm_ifindex);
+ if (dev == NULL) {
+ pr_info("PF_BRIDGE: RTM_DELNEIGH with unknown ifindex\n");
+ return -ENODEV;
+ }
+
+ llattr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_LLADDR);
+ if (llattr == NULL || nla_len(llattr) != ETH_ALEN) {
+ pr_info("PF_BRIGDE: RTM_DELNEIGH with invalid address\n");
+ return -EINVAL;
+ }
+
+ addr = nla_data(llattr);
+ err = -EOPNOTSUPP;
+
+ /* Support fdb on master device the net/bridge default case */
+ if ((!ndm->ndm_flags || ndm->ndm_flags & NTF_MASTER) &&
+ (dev->priv_flags & IFF_BRIDGE_PORT)) {
+ struct net_device *master = dev->master;
+
+ if (master->netdev_ops->ndo_fdb_del)
+ err = master->netdev_ops->ndo_fdb_del(ndm, dev, addr);
+
+ if (err)
+ goto out;
+ else
+ ndm->ndm_flags &= ~NTF_MASTER;
+ }
+
+ /* Embedded bridge, macvlan, and any other device support */
+ if ((ndm->ndm_flags & NTF_SELF) && dev->netdev_ops->ndo_fdb_del) {
+ err = dev->netdev_ops->ndo_fdb_del(ndm, dev, addr);
+
+ if (!err) {
+ rtnl_fdb_notify(dev, addr, RTM_DELNEIGH);
+ ndm->ndm_flags &= ~NTF_SELF;
+ }
+ }
+out:
+ return err;
+}
+
+static int nlmsg_populate_fdb(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct net_device *dev,
+ int *idx,
+ struct netdev_hw_addr_list *list)
+{
+ struct netdev_hw_addr *ha;
+ int err;
+ u32 pid, seq;
+
+ pid = NETLINK_CB(cb->skb).pid;
+ seq = cb->nlh->nlmsg_seq;
+
+ list_for_each_entry(ha, &list->list, list) {
+ if (*idx < cb->args[0])
+ goto skip;
+
+ err = nlmsg_populate_fdb_fill(skb, dev, ha->addr,
+ pid, seq, 0, NTF_SELF);
+ if (err < 0)
+ return err;
+skip:
+ *idx += 1;
+ }
+ return 0;
+}
+
+/**
+ * ndo_dflt_fdb_dump: default netdevice operation to dump an FDB table.
+ * @nlh: netlink message header
+ * @dev: netdevice
+ *
+ * Default netdevice operation to dump the existing unicast address list.
+ * Returns zero on success.
+ */
+int ndo_dflt_fdb_dump(struct sk_buff *skb,
+ struct netlink_callback *cb,
+ struct net_device *dev,
+ int idx)
+{
+ int err;
+
+ netif_addr_lock_bh(dev);
+ err = nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->uc);
+ if (err)
+ goto out;
+ nlmsg_populate_fdb(skb, cb, dev, &idx, &dev->mc);
+out:
+ netif_addr_unlock_bh(dev);
+ return idx;
+}
+EXPORT_SYMBOL(ndo_dflt_fdb_dump);
+
+static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ int idx = 0;
+ struct net *net = sock_net(skb->sk);
+ struct net_device *dev;
+
+ rcu_read_lock();
+ for_each_netdev_rcu(net, dev) {
+ if (dev->priv_flags & IFF_BRIDGE_PORT) {
+ struct net_device *master = dev->master;
+ const struct net_device_ops *ops = master->netdev_ops;
+
+ if (ops->ndo_fdb_dump)
+ idx = ops->ndo_fdb_dump(skb, cb, dev, idx);
+ }
+
+ if (dev->netdev_ops->ndo_fdb_dump)
+ idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx);
+ }
+ rcu_read_unlock();
+
+ cb->args[0] = idx;
+ return skb->len;
+}
+
/* Protected by RTNL sempahore. */
static struct rtattr **rta_buf;
static int rtattr_max;
@@ -2042,7 +2309,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len);
while (RTA_OK(attr, attrlen)) {
- unsigned flavor = attr->rta_type;
+ unsigned int flavor = attr->rta_type;
if (flavor) {
if (flavor > rta_max[sz_idx])
return -EINVAL;
@@ -2144,5 +2411,9 @@ void __init rtnetlink_init(void)
rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL);
rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL);
+
+ rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, NULL);
+ rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, NULL);
+ rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, rtnl_fdb_dump, NULL);
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f223cdc..016694d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -36,6 +36,8 @@
* The functions in this file will not compile correctly with gcc 2.4.x
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
@@ -67,10 +69,9 @@
#include <asm/uaccess.h>
#include <trace/events/skb.h>
+#include <linux/highmem.h>
-#include "kmap_skb.h"
-
-static struct kmem_cache *skbuff_head_cache __read_mostly;
+struct kmem_cache *skbuff_head_cache __read_mostly;
static struct kmem_cache *skbuff_fclone_cache __read_mostly;
static void sock_pipe_buf_release(struct pipe_inode_info *pipe,
@@ -119,11 +120,10 @@ static const struct pipe_buf_operations sock_pipe_buf_ops = {
*/
static void skb_over_panic(struct sk_buff *skb, int sz, void *here)
{
- printk(KERN_EMERG "skb_over_panic: text:%p len:%d put:%d head:%p "
- "data:%p tail:%#lx end:%#lx dev:%s\n",
- here, skb->len, sz, skb->head, skb->data,
- (unsigned long)skb->tail, (unsigned long)skb->end,
- skb->dev ? skb->dev->name : "<NULL>");
+ pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n",
+ __func__, here, skb->len, sz, skb->head, skb->data,
+ (unsigned long)skb->tail, (unsigned long)skb->end,
+ skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
@@ -138,11 +138,10 @@ static void skb_over_panic(struct sk_buff *skb, int sz, void *here)
static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
{
- printk(KERN_EMERG "skb_under_panic: text:%p len:%d put:%d head:%p "
- "data:%p tail:%#lx end:%#lx dev:%s\n",
- here, skb->len, sz, skb->head, skb->data,
- (unsigned long)skb->tail, (unsigned long)skb->end,
- skb->dev ? skb->dev->name : "<NULL>");
+ pr_emerg("%s: text:%p len:%d put:%d head:%p data:%p tail:%#lx end:%#lx dev:%s\n",
+ __func__, here, skb->len, sz, skb->head, skb->data,
+ (unsigned long)skb->tail, (unsigned long)skb->end,
+ skb->dev ? skb->dev->name : "<NULL>");
BUG();
}
@@ -246,6 +245,7 @@ EXPORT_SYMBOL(__alloc_skb);
/**
* build_skb - build a network buffer
* @data: data buffer provided by caller
+ * @frag_size: size of fragment, or 0 if head was kmalloced
*
* Allocate a new &sk_buff. Caller provides space holding head and
* skb_shared_info. @data must have been allocated by kmalloc()
@@ -259,20 +259,21 @@ EXPORT_SYMBOL(__alloc_skb);
* before giving packet to stack.
* RX rings only contains data buffers, not full skbs.
*/
-struct sk_buff *build_skb(void *data)
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
{
struct skb_shared_info *shinfo;
struct sk_buff *skb;
- unsigned int size;
+ unsigned int size = frag_size ? : ksize(data);
skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
if (!skb)
return NULL;
- size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ size -= SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
memset(skb, 0, offsetof(struct sk_buff, tail));
skb->truesize = SKB_TRUESIZE(size);
+ skb->head_frag = frag_size != 0;
atomic_set(&skb->users, 1);
skb->head = data;
skb->data = data;
@@ -292,6 +293,46 @@ struct sk_buff *build_skb(void *data)
}
EXPORT_SYMBOL(build_skb);
+struct netdev_alloc_cache {
+ struct page *page;
+ unsigned int offset;
+};
+static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
+
+/**
+ * netdev_alloc_frag - allocate a page fragment
+ * @fragsz: fragment size
+ *
+ * Allocates a frag from a page for receive buffer.
+ * Uses GFP_ATOMIC allocations.
+ */
+void *netdev_alloc_frag(unsigned int fragsz)
+{
+ struct netdev_alloc_cache *nc;
+ void *data = NULL;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ nc = &__get_cpu_var(netdev_alloc_cache);
+ if (unlikely(!nc->page)) {
+refill:
+ nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+ nc->offset = 0;
+ }
+ if (likely(nc->page)) {
+ if (nc->offset + fragsz > PAGE_SIZE) {
+ put_page(nc->page);
+ goto refill;
+ }
+ data = page_address(nc->page) + nc->offset;
+ nc->offset += fragsz;
+ get_page(nc->page);
+ }
+ local_irq_restore(flags);
+ return data;
+}
+EXPORT_SYMBOL(netdev_alloc_frag);
+
/**
* __netdev_alloc_skb - allocate an skbuff for rx on a specific device
* @dev: network device to receive on
@@ -306,11 +347,23 @@ EXPORT_SYMBOL(build_skb);
* %NULL is returned if there is no free memory.
*/
struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
- unsigned int length, gfp_t gfp_mask)
+ unsigned int length, gfp_t gfp_mask)
{
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
+ unsigned int fragsz = SKB_DATA_ALIGN(length + NET_SKB_PAD) +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ if (fragsz <= PAGE_SIZE && !(gfp_mask & __GFP_WAIT)) {
+ void *data = netdev_alloc_frag(fragsz);
- skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+ if (likely(data)) {
+ skb = build_skb(data, fragsz);
+ if (unlikely(!skb))
+ put_page(virt_to_head_page(data));
+ }
+ } else {
+ skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE);
+ }
if (likely(skb)) {
skb_reserve(skb, NET_SKB_PAD);
skb->dev = dev;
@@ -329,28 +382,6 @@ void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
}
EXPORT_SYMBOL(skb_add_rx_frag);
-/**
- * dev_alloc_skb - allocate an skbuff for receiving
- * @length: length to allocate
- *
- * Allocate a new &sk_buff and assign it a usage count of one. The
- * buffer has unspecified headroom built in. Users should allocate
- * the headroom they think they need without accounting for the
- * built in space. The built in space is used for optimisations.
- *
- * %NULL is returned if there is no free memory. Although this function
- * allocates memory it can be called from an interrupt.
- */
-struct sk_buff *dev_alloc_skb(unsigned int length)
-{
- /*
- * There is more code here than it seems:
- * __dev_alloc_skb is an inline
- */
- return __dev_alloc_skb(length, GFP_ATOMIC);
-}
-EXPORT_SYMBOL(dev_alloc_skb);
-
static void skb_drop_list(struct sk_buff **listp)
{
struct sk_buff *list = *listp;
@@ -377,6 +408,14 @@ static void skb_clone_fraglist(struct sk_buff *skb)
skb_get(list);
}
+static void skb_free_head(struct sk_buff *skb)
+{
+ if (skb->head_frag)
+ put_page(virt_to_head_page(skb->head));
+ else
+ kfree(skb->head);
+}
+
static void skb_release_data(struct sk_buff *skb)
{
if (!skb->cloned ||
@@ -403,7 +442,7 @@ static void skb_release_data(struct sk_buff *skb)
if (skb_has_frag_list(skb))
skb_drop_fraglist(skb);
- kfree(skb->head);
+ skb_free_head(skb);
}
}
@@ -645,6 +684,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
C(tail);
C(end);
C(head);
+ C(head_frag);
C(data);
C(truesize);
atomic_set(&n->users, 1);
@@ -707,10 +747,10 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
}
return -ENOMEM;
}
- vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
+ vaddr = kmap_atomic(skb_frag_page(f));
memcpy(page_address(page),
vaddr + f->page_offset, skb_frag_size(f));
- kunmap_skb_frag(vaddr);
+ kunmap_atomic(vaddr);
page->private = (unsigned long)head;
head = page;
}
@@ -819,7 +859,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
{
int headerlen = skb_headroom(skb);
- unsigned int size = (skb_end_pointer(skb) - skb->head) + skb->data_len;
+ unsigned int size = skb_end_offset(skb) + skb->data_len;
struct sk_buff *n = alloc_skb(size, gfp_mask);
if (!n)
@@ -920,9 +960,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
{
int i;
u8 *data;
- int size = nhead + (skb_end_pointer(skb) - skb->head) + ntail;
+ int size = nhead + skb_end_offset(skb) + ntail;
long off;
- bool fastpath;
BUG_ON(nhead < 0);
@@ -931,30 +970,11 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
size = SKB_DATA_ALIGN(size);
- /* Check if we can avoid taking references on fragments if we own
- * the last reference on skb->head. (see skb_release_data())
- */
- if (!skb->cloned)
- fastpath = true;
- else {
- int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1;
- fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta;
- }
-
- if (fastpath &&
- size + sizeof(struct skb_shared_info) <= ksize(skb->head)) {
- memmove(skb->head + size, skb_shinfo(skb),
- offsetof(struct skb_shared_info,
- frags[skb_shinfo(skb)->nr_frags]));
- memmove(skb->head + nhead, skb->head,
- skb_tail_pointer(skb) - skb->head);
- off = nhead;
- goto adjust_others;
- }
-
- data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
+ data = kmalloc(size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)),
+ gfp_mask);
if (!data)
goto nodata;
+ size = SKB_WITH_OVERHEAD(ksize(data));
/* Copy only real data... and, alas, header. This should be
* optimized for the cases when header is void.
@@ -965,9 +985,12 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
skb_shinfo(skb),
offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags]));
- if (fastpath) {
- kfree(skb->head);
- } else {
+ /*
+ * if shinfo is shared we must drop the old head gracefully, but if it
+ * is not we can just drop the old head and let the existing refcount
+ * be since all we did is relocate the values
+ */
+ if (skb_cloned(skb)) {
/* copy this zero copy skb frags */
if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
if (skb_copy_ubufs(skb, gfp_mask))
@@ -980,11 +1003,13 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
skb_clone_fraglist(skb);
skb_release_data(skb);
+ } else {
+ skb_free_head(skb);
}
off = (data + nhead) - skb->head;
skb->head = data;
-adjust_others:
+ skb->head_frag = 0;
skb->data += off;
#ifdef NET_SKBUFF_DATA_USES_OFFSET
skb->end = size;
@@ -1273,7 +1298,7 @@ drop_pages:
return -ENOMEM;
nfrag->next = frag->next;
- kfree_skb(frag);
+ consume_skb(frag);
frag = nfrag;
*fragp = frag;
}
@@ -1485,21 +1510,22 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len)
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
+ skb_frag_t *f = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
- end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
+ end = start + skb_frag_size(f);
if ((copy = end - offset) > 0) {
u8 *vaddr;
if (copy > len)
copy = len;
- vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]);
+ vaddr = kmap_atomic(skb_frag_page(f));
memcpy(to,
- vaddr + skb_shinfo(skb)->frags[i].page_offset+
- offset - start, copy);
- kunmap_skb_frag(vaddr);
+ vaddr + f->page_offset + offset - start,
+ copy);
+ kunmap_atomic(vaddr);
if ((len -= copy) == 0)
return 0;
@@ -1545,9 +1571,9 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i)
put_page(spd->pages[i]);
}
-static inline struct page *linear_to_page(struct page *page, unsigned int *len,
- unsigned int *offset,
- struct sk_buff *skb, struct sock *sk)
+static struct page *linear_to_page(struct page *page, unsigned int *len,
+ unsigned int *offset,
+ struct sk_buff *skb, struct sock *sk)
{
struct page *p = sk->sk_sndmsg_page;
unsigned int off;
@@ -1563,6 +1589,9 @@ new_page:
} else {
unsigned int mlen;
+ /* If we are the only user of the page, we can reset offset */
+ if (page_count(p) == 1)
+ sk->sk_sndmsg_off = 0;
off = sk->sk_sndmsg_off;
mlen = PAGE_SIZE - off;
if (mlen < 64 && mlen < *len) {
@@ -1576,36 +1605,48 @@ new_page:
memcpy(page_address(p) + off, page_address(page) + *offset, *len);
sk->sk_sndmsg_off += *len;
*offset = off;
- get_page(p);
return p;
}
+static bool spd_can_coalesce(const struct splice_pipe_desc *spd,
+ struct page *page,
+ unsigned int offset)
+{
+ return spd->nr_pages &&
+ spd->pages[spd->nr_pages - 1] == page &&
+ (spd->partial[spd->nr_pages - 1].offset +
+ spd->partial[spd->nr_pages - 1].len == offset);
+}
+
/*
* Fill page/offset/length into spd, if it can hold more pages.
*/
-static inline int spd_fill_page(struct splice_pipe_desc *spd,
- struct pipe_inode_info *pipe, struct page *page,
- unsigned int *len, unsigned int offset,
- struct sk_buff *skb, int linear,
- struct sock *sk)
+static bool spd_fill_page(struct splice_pipe_desc *spd,
+ struct pipe_inode_info *pipe, struct page *page,
+ unsigned int *len, unsigned int offset,
+ struct sk_buff *skb, bool linear,
+ struct sock *sk)
{
- if (unlikely(spd->nr_pages == pipe->buffers))
- return 1;
+ if (unlikely(spd->nr_pages == MAX_SKB_FRAGS))
+ return true;
if (linear) {
page = linear_to_page(page, len, &offset, skb, sk);
if (!page)
- return 1;
- } else
- get_page(page);
-
+ return true;
+ }
+ if (spd_can_coalesce(spd, page, offset)) {
+ spd->partial[spd->nr_pages - 1].len += *len;
+ return false;
+ }
+ get_page(page);
spd->pages[spd->nr_pages] = page;
spd->partial[spd->nr_pages].len = *len;
spd->partial[spd->nr_pages].offset = offset;
spd->nr_pages++;
- return 0;
+ return false;
}
static inline void __segment_seek(struct page **page, unsigned int *poff,
@@ -1622,20 +1663,20 @@ static inline void __segment_seek(struct page **page, unsigned int *poff,
*plen -= off;
}
-static inline int __splice_segment(struct page *page, unsigned int poff,
- unsigned int plen, unsigned int *off,
- unsigned int *len, struct sk_buff *skb,
- struct splice_pipe_desc *spd, int linear,
- struct sock *sk,
- struct pipe_inode_info *pipe)
+static bool __splice_segment(struct page *page, unsigned int poff,
+ unsigned int plen, unsigned int *off,
+ unsigned int *len, struct sk_buff *skb,
+ struct splice_pipe_desc *spd, bool linear,
+ struct sock *sk,
+ struct pipe_inode_info *pipe)
{
if (!*len)
- return 1;
+ return true;
/* skip this segment if already processed */
if (*off >= plen) {
*off -= plen;
- return 0;
+ return false;
}
/* ignore any bits we already processed */
@@ -1651,34 +1692,38 @@ static inline int __splice_segment(struct page *page, unsigned int poff,
flen = min_t(unsigned int, flen, PAGE_SIZE - poff);
if (spd_fill_page(spd, pipe, page, &flen, poff, skb, linear, sk))
- return 1;
+ return true;
__segment_seek(&page, &poff, &plen, flen);
*len -= flen;
} while (*len && plen);
- return 0;
+ return false;
}
/*
- * Map linear and fragment data from the skb to spd. It reports failure if the
+ * Map linear and fragment data from the skb to spd. It reports true if the
* pipe is full or if we already spliced the requested length.
*/
-static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
- unsigned int *offset, unsigned int *len,
- struct splice_pipe_desc *spd, struct sock *sk)
+static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
+ unsigned int *offset, unsigned int *len,
+ struct splice_pipe_desc *spd, struct sock *sk)
{
int seg;
- /*
- * map the linear part
+ /* map the linear part :
+ * If skb->head_frag is set, this 'linear' part is backed by a
+ * fragment, and if the head is not shared with any clones then
+ * we can avoid a copy since we own the head portion of this page.
*/
if (__splice_segment(virt_to_page(skb->data),
(unsigned long) skb->data & (PAGE_SIZE - 1),
skb_headlen(skb),
- offset, len, skb, spd, 1, sk, pipe))
- return 1;
+ offset, len, skb, spd,
+ skb_head_is_locked(skb),
+ sk, pipe))
+ return true;
/*
* then map the fragments
@@ -1688,11 +1733,11 @@ static int __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
if (__splice_segment(skb_frag_page(f),
f->page_offset, skb_frag_size(f),
- offset, len, skb, spd, 0, sk, pipe))
- return 1;
+ offset, len, skb, spd, false, sk, pipe))
+ return true;
}
- return 0;
+ return false;
}
/*
@@ -1705,8 +1750,8 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
struct pipe_inode_info *pipe, unsigned int tlen,
unsigned int flags)
{
- struct partial_page partial[PIPE_DEF_BUFFERS];
- struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[MAX_SKB_FRAGS];
+ struct page *pages[MAX_SKB_FRAGS];
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
@@ -1718,9 +1763,6 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset,
struct sock *sk = skb->sk;
int ret = 0;
- if (splice_grow_spd(pipe, &spd))
- return -ENOMEM;
-
/*
* __skb_splice_bits() only fails if the output has no room left,
* so no point in going over the frag_list for the error case.
@@ -1756,7 +1798,6 @@ done:
lock_sock(sk);
}
- splice_shrink_spd(pipe, &spd);
return ret;
}
@@ -1804,10 +1845,10 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len)
if (copy > len)
copy = len;
- vaddr = kmap_skb_frag(frag);
+ vaddr = kmap_atomic(skb_frag_page(frag));
memcpy(vaddr + frag->page_offset + offset - start,
from, copy);
- kunmap_skb_frag(vaddr);
+ kunmap_atomic(vaddr);
if ((len -= copy) == 0)
return 0;
@@ -1867,21 +1908,21 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset,
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
int end;
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
WARN_ON(start > offset + len);
- end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]);
+ end = start + skb_frag_size(frag);
if ((copy = end - offset) > 0) {
__wsum csum2;
u8 *vaddr;
- skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
if (copy > len)
copy = len;
- vaddr = kmap_skb_frag(frag);
+ vaddr = kmap_atomic(skb_frag_page(frag));
csum2 = csum_partial(vaddr + frag->page_offset +
offset - start, copy, 0);
- kunmap_skb_frag(vaddr);
+ kunmap_atomic(vaddr);
csum = csum_block_add(csum, csum2, pos);
if (!(len -= copy))
return csum;
@@ -1953,12 +1994,12 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
if (copy > len)
copy = len;
- vaddr = kmap_skb_frag(frag);
+ vaddr = kmap_atomic(skb_frag_page(frag));
csum2 = csum_partial_copy_nocheck(vaddr +
frag->page_offset +
offset - start, to,
copy, 0);
- kunmap_skb_frag(vaddr);
+ kunmap_atomic(vaddr);
csum = csum_block_add(csum, csum2, pos);
if (!(len -= copy))
return csum;
@@ -2478,7 +2519,7 @@ next_skb:
if (abs_offset < block_limit) {
if (!st->frag_data)
- st->frag_data = kmap_skb_frag(frag);
+ st->frag_data = kmap_atomic(skb_frag_page(frag));
*data = (u8 *) st->frag_data + frag->page_offset +
(abs_offset - st->stepped_offset);
@@ -2487,7 +2528,7 @@ next_skb:
}
if (st->frag_data) {
- kunmap_skb_frag(st->frag_data);
+ kunmap_atomic(st->frag_data);
st->frag_data = NULL;
}
@@ -2496,7 +2537,7 @@ next_skb:
}
if (st->frag_data) {
- kunmap_skb_frag(st->frag_data);
+ kunmap_atomic(st->frag_data);
st->frag_data = NULL;
}
@@ -2524,7 +2565,7 @@ EXPORT_SYMBOL(skb_seq_read);
void skb_abort_seq_read(struct skb_seq_state *st)
{
if (st->frag_data)
- kunmap_skb_frag(st->frag_data);
+ kunmap_atomic(st->frag_data);
}
EXPORT_SYMBOL(skb_abort_seq_read);
@@ -2716,14 +2757,13 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
if (unlikely(!nskb))
goto err;
- hsize = skb_end_pointer(nskb) - nskb->head;
+ hsize = skb_end_offset(nskb);
if (skb_cow_head(nskb, doffset + headroom)) {
kfree_skb(nskb);
goto err;
}
- nskb->truesize += skb_end_pointer(nskb) - nskb->head -
- hsize;
+ nskb->truesize += skb_end_offset(nskb) - hsize;
skb_release_head_state(nskb);
__skb_push(nskb, doffset);
} else {
@@ -2841,6 +2881,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
unsigned int len = skb_gro_len(skb);
unsigned int offset = skb_gro_offset(skb);
unsigned int headlen = skb_headlen(skb);
+ unsigned int delta_truesize;
if (p->len + len >= 65536)
return -E2BIG;
@@ -2870,11 +2911,41 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
frag->page_offset += offset;
skb_frag_size_sub(frag, offset);
+ /* all fragments truesize : remove (head size + sk_buff) */
+ delta_truesize = skb->truesize -
+ SKB_TRUESIZE(skb_end_offset(skb));
+
skb->truesize -= skb->data_len;
skb->len -= skb->data_len;
skb->data_len = 0;
- NAPI_GRO_CB(skb)->free = 1;
+ NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE;
+ goto done;
+ } else if (skb->head_frag) {
+ int nr_frags = pinfo->nr_frags;
+ skb_frag_t *frag = pinfo->frags + nr_frags;
+ struct page *page = virt_to_head_page(skb->head);
+ unsigned int first_size = headlen - offset;
+ unsigned int first_offset;
+
+ if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS)
+ return -E2BIG;
+
+ first_offset = skb->data -
+ (unsigned char *)page_address(page) +
+ offset;
+
+ pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags;
+
+ frag->page.p = page;
+ frag->page_offset = first_offset;
+ skb_frag_size_set(frag, first_size);
+
+ memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags);
+ /* We dont need to clear skbinfo->nr_frags here */
+
+ delta_truesize = skb->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
+ NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD;
goto done;
} else if (skb_gro_len(p) != pinfo->gso_size)
return -E2BIG;
@@ -2916,7 +2987,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
p = nskb;
merge:
- p->truesize += skb->truesize - len;
+ delta_truesize = skb->truesize;
if (offset > headlen) {
unsigned int eat = offset - headlen;
@@ -2936,7 +3007,7 @@ merge:
done:
NAPI_GRO_CB(p)->count++;
p->data_len += len;
- p->truesize += len;
+ p->truesize += delta_truesize;
p->len += len;
NAPI_GRO_CB(skb)->same_flow = 1;
@@ -3161,8 +3232,10 @@ static void sock_rmem_free(struct sk_buff *skb)
*/
int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
+ int len = skb->len;
+
if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
- (unsigned)sk->sk_rcvbuf)
+ (unsigned int)sk->sk_rcvbuf)
return -ENOMEM;
skb_orphan(skb);
@@ -3175,7 +3248,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
skb_queue_tail(&sk->sk_error_queue, skb);
if (!sock_flag(sk, SOCK_DEAD))
- sk->sk_data_ready(sk, skb->len);
+ sk->sk_data_ready(sk, len);
return 0;
}
EXPORT_SYMBOL(sock_queue_err_skb);
@@ -3256,10 +3329,8 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off)
{
if (unlikely(start > skb_headlen(skb)) ||
unlikely((int)start + off > skb_headlen(skb) - 2)) {
- if (net_ratelimit())
- printk(KERN_WARNING
- "bad partial csum: csum=%u/%u len=%u\n",
- start, off, skb_headlen(skb));
+ net_warn_ratelimited("bad partial csum: csum=%u/%u len=%u\n",
+ start, off, skb_headlen(skb));
return false;
}
skb->ip_summed = CHECKSUM_PARTIAL;
@@ -3271,8 +3342,93 @@ EXPORT_SYMBOL_GPL(skb_partial_csum_set);
void __skb_warn_lro_forwarding(const struct sk_buff *skb)
{
- if (net_ratelimit())
- pr_warning("%s: received packets cannot be forwarded"
- " while LRO is enabled\n", skb->dev->name);
+ net_warn_ratelimited("%s: received packets cannot be forwarded while LRO is enabled\n",
+ skb->dev->name);
}
EXPORT_SYMBOL(__skb_warn_lro_forwarding);
+
+void kfree_skb_partial(struct sk_buff *skb, bool head_stolen)
+{
+ if (head_stolen)
+ kmem_cache_free(skbuff_head_cache, skb);
+ else
+ __kfree_skb(skb);
+}
+EXPORT_SYMBOL(kfree_skb_partial);
+
+/**
+ * skb_try_coalesce - try to merge skb to prior one
+ * @to: prior buffer
+ * @from: buffer to add
+ * @fragstolen: pointer to boolean
+ *
+ */
+bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from,
+ bool *fragstolen, int *delta_truesize)
+{
+ int i, delta, len = from->len;
+
+ *fragstolen = false;
+
+ if (skb_cloned(to))
+ return false;
+
+ if (len <= skb_tailroom(to)) {
+ BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
+ *delta_truesize = 0;
+ return true;
+ }
+
+ if (skb_has_frag_list(to) || skb_has_frag_list(from))
+ return false;
+
+ if (skb_headlen(from) != 0) {
+ struct page *page;
+ unsigned int offset;
+
+ if (skb_shinfo(to)->nr_frags +
+ skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ return false;
+
+ if (skb_head_is_locked(from))
+ return false;
+
+ delta = from->truesize - SKB_DATA_ALIGN(sizeof(struct sk_buff));
+
+ page = virt_to_head_page(from->head);
+ offset = from->data - (unsigned char *)page_address(page);
+
+ skb_fill_page_desc(to, skb_shinfo(to)->nr_frags,
+ page, offset, skb_headlen(from));
+ *fragstolen = true;
+ } else {
+ if (skb_shinfo(to)->nr_frags +
+ skb_shinfo(from)->nr_frags > MAX_SKB_FRAGS)
+ return false;
+
+ delta = from->truesize -
+ SKB_TRUESIZE(skb_end_pointer(from) - from->head);
+ }
+
+ WARN_ON_ONCE(delta < len);
+
+ memcpy(skb_shinfo(to)->frags + skb_shinfo(to)->nr_frags,
+ skb_shinfo(from)->frags,
+ skb_shinfo(from)->nr_frags * sizeof(skb_frag_t));
+ skb_shinfo(to)->nr_frags += skb_shinfo(from)->nr_frags;
+
+ if (!skb_cloned(from))
+ skb_shinfo(from)->nr_frags = 0;
+
+ /* if the skb is cloned this does nothing since we set nr_frags to 0 */
+ for (i = 0; i < skb_shinfo(from)->nr_frags; i++)
+ skb_frag_ref(from, i);
+
+ to->truesize += delta;
+ to->len += len;
+ to->data_len += len;
+
+ *delta_truesize = delta;
+ return true;
+}
+EXPORT_SYMBOL(skb_try_coalesce);
diff --git a/net/core/sock.c b/net/core/sock.c
index 878f744..f372d9b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -89,6 +89,8 @@
* 2 of the License, or (at your option) any later version.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
@@ -113,6 +115,7 @@
#include <linux/user_namespace.h>
#include <linux/static_key.h>
#include <linux/memcontrol.h>
+#include <linux/prefetch.h>
#include <asm/uaccess.h>
@@ -258,7 +261,9 @@ static struct lock_class_key af_callback_keys[AF_MAX];
/* Run time adjustable parameters. */
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
+EXPORT_SYMBOL(sysctl_wmem_max);
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
+EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
@@ -294,9 +299,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
*timeo_p = 0;
if (warned < 10 && net_ratelimit()) {
warned++;
- printk(KERN_INFO "sock_set_timeout: `%s' (pid %d) "
- "tries to set negative timeout\n",
- current->comm, task_pid_nr(current));
+ pr_info("%s: `%s' (pid %d) tries to set negative timeout\n",
+ __func__, current->comm, task_pid_nr(current));
}
return 0;
}
@@ -314,8 +318,8 @@ static void sock_warn_obsolete_bsdism(const char *name)
static char warncomm[TASK_COMM_LEN];
if (strcmp(warncomm, current->comm) && warned < 5) {
strcpy(warncomm, current->comm);
- printk(KERN_WARNING "process `%s' is using obsolete "
- "%s SO_BSDCOMPAT\n", warncomm, name);
+ pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n",
+ warncomm, name);
warned++;
}
}
@@ -389,7 +393,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
skb->dev = NULL;
- if (sk_rcvqueues_full(sk, skb)) {
+ if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
}
@@ -406,7 +410,7 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested)
rc = sk_backlog_rcv(sk, skb);
mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
- } else if (sk_add_backlog(sk, skb)) {
+ } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
bh_unlock_sock(sk);
atomic_inc(&sk->sk_drops);
goto discard_and_relse;
@@ -561,7 +565,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
sock_valbool_flag(sk, SOCK_DBG, valbool);
break;
case SO_REUSEADDR:
- sk->sk_reuse = valbool;
+ sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
break;
case SO_TYPE:
case SO_PROTOCOL:
@@ -577,23 +581,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
break;
case SO_SNDBUF:
/* Don't error on this BSD doesn't and if you think
- about it this is right. Otherwise apps have to
- play 'guess the biggest size' games. RCVBUF/SNDBUF
- are treated in BSD as hints */
-
- if (val > sysctl_wmem_max)
- val = sysctl_wmem_max;
+ * about it this is right. Otherwise apps have to
+ * play 'guess the biggest size' games. RCVBUF/SNDBUF
+ * are treated in BSD as hints
+ */
+ val = min_t(u32, val, sysctl_wmem_max);
set_sndbuf:
sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
- if ((val * 2) < SOCK_MIN_SNDBUF)
- sk->sk_sndbuf = SOCK_MIN_SNDBUF;
- else
- sk->sk_sndbuf = val * 2;
-
- /*
- * Wake up sending tasks if we
- * upped the value.
- */
+ sk->sk_sndbuf = max_t(u32, val * 2, SOCK_MIN_SNDBUF);
+ /* Wake up sending tasks if we upped the value. */
sk->sk_write_space(sk);
break;
@@ -606,12 +602,11 @@ set_sndbuf:
case SO_RCVBUF:
/* Don't error on this BSD doesn't and if you think
- about it this is right. Otherwise apps have to
- play 'guess the biggest size' games. RCVBUF/SNDBUF
- are treated in BSD as hints */
-
- if (val > sysctl_rmem_max)
- val = sysctl_rmem_max;
+ * about it this is right. Otherwise apps have to
+ * play 'guess the biggest size' games. RCVBUF/SNDBUF
+ * are treated in BSD as hints
+ */
+ val = min_t(u32, val, sysctl_rmem_max);
set_rcvbuf:
sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
/*
@@ -629,10 +624,7 @@ set_rcvbuf:
* returning the value we actually used in getsockopt
* is the most desirable behavior.
*/
- if ((val * 2) < SOCK_MIN_RCVBUF)
- sk->sk_rcvbuf = SOCK_MIN_RCVBUF;
- else
- sk->sk_rcvbuf = val * 2;
+ sk->sk_rcvbuf = max_t(u32, val * 2, SOCK_MIN_RCVBUF);
break;
case SO_RCVBUFFORCE:
@@ -858,7 +850,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_BROADCAST:
- v.val = !!sock_flag(sk, SOCK_BROADCAST);
+ v.val = sock_flag(sk, SOCK_BROADCAST);
break;
case SO_SNDBUF:
@@ -874,7 +866,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_KEEPALIVE:
- v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
+ v.val = sock_flag(sk, SOCK_KEEPOPEN);
break;
case SO_TYPE:
@@ -896,7 +888,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_OOBINLINE:
- v.val = !!sock_flag(sk, SOCK_URGINLINE);
+ v.val = sock_flag(sk, SOCK_URGINLINE);
break;
case SO_NO_CHECK:
@@ -909,7 +901,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
case SO_LINGER:
lv = sizeof(v.ling);
- v.ling.l_onoff = !!sock_flag(sk, SOCK_LINGER);
+ v.ling.l_onoff = sock_flag(sk, SOCK_LINGER);
v.ling.l_linger = sk->sk_lingertime / HZ;
break;
@@ -975,7 +967,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_PASSCRED:
- v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0;
+ v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
break;
case SO_PEERCRED:
@@ -1010,7 +1002,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_PASSSEC:
- v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0;
+ v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
break;
case SO_PEERSEC:
@@ -1021,11 +1013,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
break;
case SO_RXQ_OVFL:
- v.val = !!sock_flag(sk, SOCK_RXQ_OVFL);
+ v.val = sock_flag(sk, SOCK_RXQ_OVFL);
break;
case SO_WIFI_STATUS:
- v.val = !!sock_flag(sk, SOCK_WIFI_STATUS);
+ v.val = sock_flag(sk, SOCK_WIFI_STATUS);
break;
case SO_PEEK_OFF:
@@ -1035,7 +1027,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = sk->sk_peek_off;
break;
case SO_NOFCS:
- v.val = !!sock_flag(sk, SOCK_NOFCS);
+ v.val = sock_flag(sk, SOCK_NOFCS);
break;
default:
return -ENOPROTOOPT;
@@ -1247,8 +1239,8 @@ static void __sk_free(struct sock *sk)
sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
if (atomic_read(&sk->sk_omem_alloc))
- printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
- __func__, atomic_read(&sk->sk_omem_alloc));
+ pr_debug("%s: optmem leakage (%d bytes) detected\n",
+ __func__, atomic_read(&sk->sk_omem_alloc));
if (sk->sk_peer_cred)
put_cred(sk->sk_peer_cred);
@@ -1534,7 +1526,7 @@ struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
*/
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
{
- if ((unsigned)size <= sysctl_optmem_max &&
+ if ((unsigned int)size <= sysctl_optmem_max &&
atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
void *mem;
/* First do the add, to avoid the race if kmalloc
@@ -1712,6 +1704,7 @@ static void __release_sock(struct sock *sk)
do {
struct sk_buff *next = skb->next;
+ prefetch(next);
WARN_ON_ONCE(skb_dst_is_noref(skb));
skb->next = NULL;
sk_backlog_rcv(sk, skb);
@@ -2432,7 +2425,7 @@ static void assign_proto_idx(struct proto *prot)
prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
- printk(KERN_ERR "PROTO_INUSE_NR exhausted\n");
+ pr_err("PROTO_INUSE_NR exhausted\n");
return;
}
@@ -2462,8 +2455,8 @@ int proto_register(struct proto *prot, int alloc_slab)
NULL);
if (prot->slab == NULL) {
- printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n",
- prot->name);
+ pr_crit("%s: Can't create sock SLAB cache!\n",
+ prot->name);
goto out;
}
@@ -2477,8 +2470,8 @@ int proto_register(struct proto *prot, int alloc_slab)
SLAB_HWCACHE_ALIGN, NULL);
if (prot->rsk_prot->slab == NULL) {
- printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n",
- prot->name);
+ pr_crit("%s: Can't create request sock SLAB cache!\n",
+ prot->name);
goto out_free_request_sock_slab_name;
}
}
@@ -2576,7 +2569,7 @@ static char proto_method_implemented(const void *method)
}
static long sock_prot_memory_allocated(struct proto *proto)
{
- return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L;
+ return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L;
}
static char *sock_prot_memory_pressure(struct proto *proto)
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index b9868e1..5fd1467 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -10,7 +10,7 @@
#include <linux/inet_diag.h>
#include <linux/sock_diag.h>
-static struct sock_diag_handler *sock_diag_handlers[AF_MAX];
+static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
static DEFINE_MUTEX(sock_diag_table_mutex);
@@ -70,7 +70,7 @@ void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlms
}
EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat);
-int sock_diag_register(struct sock_diag_handler *hndl)
+int sock_diag_register(const struct sock_diag_handler *hndl)
{
int err = 0;
@@ -88,7 +88,7 @@ int sock_diag_register(struct sock_diag_handler *hndl)
}
EXPORT_SYMBOL_GPL(sock_diag_register);
-void sock_diag_unregister(struct sock_diag_handler *hnld)
+void sock_diag_unregister(const struct sock_diag_handler *hnld)
{
int family = hnld->family;
@@ -102,7 +102,7 @@ void sock_diag_unregister(struct sock_diag_handler *hnld)
}
EXPORT_SYMBOL_GPL(sock_diag_unregister);
-static inline struct sock_diag_handler *sock_diag_lock_handler(int family)
+static const inline struct sock_diag_handler *sock_diag_lock_handler(int family)
{
if (sock_diag_handlers[family] == NULL)
request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
@@ -112,7 +112,7 @@ static inline struct sock_diag_handler *sock_diag_lock_handler(int family)
return sock_diag_handlers[family];
}
-static inline void sock_diag_unlock_handler(struct sock_diag_handler *h)
+static inline void sock_diag_unlock_handler(const struct sock_diag_handler *h)
{
mutex_unlock(&sock_diag_table_mutex);
}
@@ -121,7 +121,7 @@ static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
int err;
struct sock_diag_req *req = NLMSG_DATA(nlh);
- struct sock_diag_handler *hndl;
+ const struct sock_diag_handler *hndl;
if (nlmsg_len(nlh) < sizeof(*req))
return -EINVAL;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 0c28508..a7c3684 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -14,6 +14,7 @@
#include <linux/vmalloc.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/kmemleak.h>
#include <net/ip.h>
#include <net/sock.h>
@@ -202,12 +203,6 @@ static struct ctl_table netns_core_table[] = {
{ }
};
-__net_initdata struct ctl_path net_core_path[] = {
- { .procname = "net", },
- { .procname = "core", },
- { },
-};
-
static __net_init int sysctl_core_net_init(struct net *net)
{
struct ctl_table *tbl;
@@ -223,8 +218,7 @@ static __net_init int sysctl_core_net_init(struct net *net)
tbl[0].data = &net->core.sysctl_somaxconn;
}
- net->core.sysctl_hdr = register_net_sysctl_table(net,
- net_core_path, tbl);
+ net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl);
if (net->core.sysctl_hdr == NULL)
goto err_reg;
@@ -254,10 +248,7 @@ static __net_initdata struct pernet_operations sysctl_core_ops = {
static __init int sysctl_core_init(void)
{
- static struct ctl_table empty[1];
-
- register_sysctl_paths(net_core_path, empty);
- register_net_sysctl_rotable(net_core_path, net_core_table);
+ register_net_sysctl(&init_net, "net/core", net_core_table);
return register_pernet_subsys(&sysctl_core_ops);
}
diff --git a/net/core/utils.c b/net/core/utils.c
index dc3c3fa..39895a6 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -58,14 +58,11 @@ __be32 in_aton(const char *str)
int i;
l = 0;
- for (i = 0; i < 4; i++)
- {
+ for (i = 0; i < 4; i++) {
l <<= 8;
- if (*str != '\0')
- {
+ if (*str != '\0') {
val = 0;
- while (*str != '\0' && *str != '.' && *str != '\n')
- {
+ while (*str != '\0' && *str != '.' && *str != '\n') {
val *= 10;
val += *str - '0';
str++;
generated by cgit v0.10.2 at 2024-10-03 18:06:12 (GMT)