summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile3
-rw-r--r--net/core/dev.c268
-rw-r--r--net/core/dev_addr_lists.c97
-rw-r--r--net/core/dev_ioctl.c2
-rw-r--r--net/core/flow_dissector.c6
-rw-r--r--net/core/neighbour.c466
-rw-r--r--net/core/net-sysfs.c6
-rw-r--r--net/core/net-sysfs.h2
-rw-r--r--net/core/netclassid_cgroup.c120
-rw-r--r--net/core/netprio_cgroup.c2
-rw-r--r--net/core/rtnetlink.c22
-rw-r--r--net/core/skbuff.c8
-rw-r--r--net/core/sock.c35
-rw-r--r--net/core/sysctl_net_core.c3
14 files changed, 523 insertions, 517 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index b33b996f5dd6..9628c20acff6 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -21,4 +21,5 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o
obj-$(CONFIG_TRACEPOINTS) += net-traces.o
obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
-obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o
+obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
+obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 4fc17221545d..e5e23d785454 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -480,7 +480,7 @@ EXPORT_SYMBOL(dev_add_offload);
* and must not be freed until after all the CPU's have gone
* through a quiescent state.
*/
-void __dev_remove_offload(struct packet_offload *po)
+static void __dev_remove_offload(struct packet_offload *po)
{
struct list_head *head = &offload_base;
struct packet_offload *po1;
@@ -498,7 +498,6 @@ void __dev_remove_offload(struct packet_offload *po)
out:
spin_unlock(&offload_lock);
}
-EXPORT_SYMBOL(__dev_remove_offload);
/**
* dev_remove_offload - remove packet offload handler
@@ -1566,14 +1565,14 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
* are as for raw_notifier_call_chain().
*/
-int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
- struct netdev_notifier_info *info)
+static int call_netdevice_notifiers_info(unsigned long val,
+ struct net_device *dev,
+ struct netdev_notifier_info *info)
{
ASSERT_RTNL();
netdev_notifier_info_init(info, dev);
return raw_notifier_call_chain(&netdev_chain, val, info);
}
-EXPORT_SYMBOL(call_netdevice_notifiers_info);
/**
* call_netdevice_notifiers - call all network notifier blocks
@@ -2145,30 +2144,42 @@ void __netif_schedule(struct Qdisc *q)
}
EXPORT_SYMBOL(__netif_schedule);
-void dev_kfree_skb_irq(struct sk_buff *skb)
+struct dev_kfree_skb_cb {
+ enum skb_free_reason reason;
+};
+
+static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
+{
+ return (struct dev_kfree_skb_cb *)skb->cb;
+}
+
+void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
{
- if (atomic_dec_and_test(&skb->users)) {
- struct softnet_data *sd;
- unsigned long flags;
+ unsigned long flags;
- local_irq_save(flags);
- sd = &__get_cpu_var(softnet_data);
- skb->next = sd->completion_queue;
- sd->completion_queue = skb;
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_restore(flags);
+ if (likely(atomic_read(&skb->users) == 1)) {
+ smp_rmb();
+ atomic_set(&skb->users, 0);
+ } else if (likely(!atomic_dec_and_test(&skb->users))) {
+ return;
}
+ get_kfree_skb_cb(skb)->reason = reason;
+ local_irq_save(flags);
+ skb->next = __this_cpu_read(softnet_data.completion_queue);
+ __this_cpu_write(softnet_data.completion_queue, skb);
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_restore(flags);
}
-EXPORT_SYMBOL(dev_kfree_skb_irq);
+EXPORT_SYMBOL(__dev_kfree_skb_irq);
-void dev_kfree_skb_any(struct sk_buff *skb)
+void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason)
{
if (in_irq() || irqs_disabled())
- dev_kfree_skb_irq(skb);
+ __dev_kfree_skb_irq(skb, reason);
else
dev_kfree_skb(skb);
}
-EXPORT_SYMBOL(dev_kfree_skb_any);
+EXPORT_SYMBOL(__dev_kfree_skb_any);
/**
@@ -2442,13 +2453,8 @@ static void dev_gso_skb_destructor(struct sk_buff *skb)
{
struct dev_gso_cb *cb;
- do {
- struct sk_buff *nskb = skb->next;
-
- skb->next = nskb->next;
- nskb->next = NULL;
- kfree_skb(nskb);
- } while (skb->next);
+ kfree_skb_list(skb->next);
+ skb->next = NULL;
cb = DEV_GSO_CB(skb);
if (cb->destructor)
@@ -2523,21 +2529,6 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
}
EXPORT_SYMBOL(netif_skb_features);
-/*
- * Returns true if either:
- * 1. skb has frag_list and the device doesn't support FRAGLIST, or
- * 2. skb is fragmented and the device does not support SG.
- */
-static inline int skb_needs_linearize(struct sk_buff *skb,
- netdev_features_t features)
-{
- return skb_is_nonlinear(skb) &&
- ((skb_has_frag_list(skb) &&
- !(features & NETIF_F_FRAGLIST)) ||
- (skb_shinfo(skb)->nr_frags &&
- !(features & NETIF_F_SG)));
-}
-
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, void *accel_priv)
{
@@ -2750,7 +2741,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
return rc;
}
-#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
static void skb_update_prio(struct sk_buff *skb)
{
struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
@@ -3009,7 +3000,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
}
skb_reset_network_header(skb);
- if (!skb_get_rxhash(skb))
+ if (!skb_get_hash(skb))
goto done;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3154,7 +3145,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
rcu_read_lock();
fl = rcu_dereference(sd->flow_limit);
if (fl) {
- new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+ new_flow = skb_get_hash(skb) & (fl->num_buckets - 1);
old_flow = fl->history[fl->history_head];
fl->history[fl->history_head] = new_flow;
@@ -3306,7 +3297,10 @@ static void net_tx_action(struct softirq_action *h)
clist = clist->next;
WARN_ON(atomic_read(&skb->users));
- trace_kfree_skb(skb, net_tx_action);
+ if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED))
+ trace_consume_skb(skb);
+ else
+ trace_kfree_skb(skb, net_tx_action);
__kfree_skb(skb);
}
}
@@ -3752,7 +3746,7 @@ static int napi_gro_complete(struct sk_buff *skb)
if (ptype->type != type || !ptype->callbacks.gro_complete)
continue;
- err = ptype->callbacks.gro_complete(skb);
+ err = ptype->callbacks.gro_complete(skb, 0);
break;
}
rcu_read_unlock();
@@ -3818,6 +3812,23 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
}
}
+static void skb_gro_reset_offset(struct sk_buff *skb)
+{
+ const struct skb_shared_info *pinfo = skb_shinfo(skb);
+ const skb_frag_t *frag0 = &pinfo->frags[0];
+
+ NAPI_GRO_CB(skb)->data_offset = 0;
+ NAPI_GRO_CB(skb)->frag0 = NULL;
+ NAPI_GRO_CB(skb)->frag0_len = 0;
+
+ if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
+ pinfo->nr_frags &&
+ !PageHighMem(skb_frag_page(frag0))) {
+ NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+ NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
+ }
+}
+
static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
@@ -3833,6 +3844,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
if (skb_is_gso(skb) || skb_has_frag_list(skb))
goto normal;
+ skb_gro_reset_offset(skb);
gro_list_prepare(napi, skb);
rcu_read_lock();
@@ -3938,27 +3950,8 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
return ret;
}
-static void skb_gro_reset_offset(struct sk_buff *skb)
-{
- const struct skb_shared_info *pinfo = skb_shinfo(skb);
- const skb_frag_t *frag0 = &pinfo->frags[0];
-
- NAPI_GRO_CB(skb)->data_offset = 0;
- NAPI_GRO_CB(skb)->frag0 = NULL;
- NAPI_GRO_CB(skb)->frag0_len = 0;
-
- if (skb_mac_header(skb) == skb_tail_pointer(skb) &&
- pinfo->nr_frags &&
- !PageHighMem(skb_frag_page(frag0))) {
- NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
- NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
- }
-}
-
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
- skb_gro_reset_offset(skb);
-
return napi_skb_finish(dev_gro_receive(napi, skb), skb);
}
EXPORT_SYMBOL(napi_gro_receive);
@@ -3981,8 +3974,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
if (!skb) {
skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
- if (skb)
- napi->skb = skb;
+ napi->skb = skb;
}
return skb;
}
@@ -3993,12 +3985,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
{
switch (ret) {
case GRO_NORMAL:
- case GRO_HELD:
- skb->protocol = eth_type_trans(skb, skb->dev);
-
- if (ret == GRO_HELD)
- skb_gro_pull(skb, -ETH_HLEN);
- else if (netif_receive_skb(skb))
+ if (netif_receive_skb(skb))
ret = GRO_DROP;
break;
@@ -4007,6 +3994,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
napi_reuse_skb(napi, skb);
break;
+ case GRO_HELD:
case GRO_MERGED:
break;
}
@@ -4017,36 +4005,15 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
static struct sk_buff *napi_frags_skb(struct napi_struct *napi)
{
struct sk_buff *skb = napi->skb;
- struct ethhdr *eth;
- unsigned int hlen;
- unsigned int off;
napi->skb = NULL;
- skb_reset_mac_header(skb);
- skb_gro_reset_offset(skb);
-
- off = skb_gro_offset(skb);
- hlen = off + sizeof(*eth);
- eth = skb_gro_header_fast(skb, off);
- if (skb_gro_header_hard(skb, hlen)) {
- eth = skb_gro_header_slow(skb, hlen, off);
- if (unlikely(!eth)) {
- napi_reuse_skb(napi, skb);
- skb = NULL;
- goto out;
- }
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) {
+ napi_reuse_skb(napi, skb);
+ return NULL;
}
+ skb->protocol = eth_type_trans(skb, skb->dev);
- skb_gro_pull(skb, sizeof(*eth));
-
- /*
- * This works because the only protocols we care about don't require
- * special handling. We'll fix it up properly at the end.
- */
- skb->protocol = eth->h_proto;
-
-out:
return skb;
}
@@ -4062,7 +4029,7 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
EXPORT_SYMBOL(napi_gro_frags);
/*
- * net_rps_action sends any pending IPI's for rps.
+ * net_rps_action_and_irq_enable sends any pending IPI's for rps.
* Note: called with local irq disabled, but exits with local irq enabled.
*/
static void net_rps_action_and_irq_enable(struct softnet_data *sd)
@@ -4267,17 +4234,10 @@ EXPORT_SYMBOL(netif_napi_add);
void netif_napi_del(struct napi_struct *napi)
{
- struct sk_buff *skb, *next;
-
list_del_init(&napi->dev_list);
napi_free_frags(napi);
- for (skb = napi->gro_list; skb; skb = next) {
- next = skb->next;
- skb->next = NULL;
- kfree_skb(skb);
- }
-
+ kfree_skb_list(napi->gro_list);
napi->gro_list = NULL;
napi->gro_count = 0;
}
@@ -4394,19 +4354,6 @@ struct netdev_adjacent {
struct rcu_head rcu;
};
-static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev,
- struct net_device *adj_dev,
- struct list_head *adj_list)
-{
- struct netdev_adjacent *adj;
-
- list_for_each_entry_rcu(adj, adj_list, list) {
- if (adj->dev == adj_dev)
- return adj;
- }
- return NULL;
-}
-
static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *adj_list)
@@ -4445,13 +4392,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
* Find out if a device is linked to an upper device and return true in case
* it is. The caller must hold the RTNL lock.
*/
-bool netdev_has_any_upper_dev(struct net_device *dev)
+static bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
return !list_empty(&dev->all_adj_list.upper);
}
-EXPORT_SYMBOL(netdev_has_any_upper_dev);
/**
* netdev_master_upper_dev_get - Get master upper device
@@ -4571,6 +4517,27 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
/**
+ * netdev_lower_get_first_private_rcu - Get the first ->private from the
+ * lower neighbour list, RCU
+ * variant
+ * @dev: device
+ *
+ * Gets the first netdev_adjacent->private from the dev's lower neighbour
+ * list. The caller must hold RCU read lock.
+ */
+void *netdev_lower_get_first_private_rcu(struct net_device *dev)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_first_or_null_rcu(&dev->adj_list.lower,
+ struct netdev_adjacent, list);
+ if (lower)
+ return lower->private;
+ return NULL;
+}
+EXPORT_SYMBOL(netdev_lower_get_first_private_rcu);
+
+/**
* netdev_master_upper_dev_get_rcu - Get master upper device
* @dev: device
*
@@ -4662,9 +4629,9 @@ free_adj:
return ret;
}
-void __netdev_adjacent_dev_remove(struct net_device *dev,
- struct net_device *adj_dev,
- struct list_head *dev_list)
+static void __netdev_adjacent_dev_remove(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *dev_list)
{
struct netdev_adjacent *adj;
char linkname[IFNAMSIZ+7];
@@ -4702,11 +4669,11 @@ void __netdev_adjacent_dev_remove(struct net_device *dev,
kfree_rcu(adj, rcu);
}
-int __netdev_adjacent_dev_link_lists(struct net_device *dev,
- struct net_device *upper_dev,
- struct list_head *up_list,
- struct list_head *down_list,
- void *private, bool master)
+static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list,
+ void *private, bool master)
{
int ret;
@@ -4725,8 +4692,8 @@ int __netdev_adjacent_dev_link_lists(struct net_device *dev,
return 0;
}
-int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
+static int __netdev_adjacent_dev_link(struct net_device *dev,
+ struct net_device *upper_dev)
{
return __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->all_adj_list.upper,
@@ -4734,26 +4701,26 @@ int __netdev_adjacent_dev_link(struct net_device *dev,
NULL, false);
}
-void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
- struct net_device *upper_dev,
- struct list_head *up_list,
- struct list_head *down_list)
+static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list)
{
__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
}
-void __netdev_adjacent_dev_unlink(struct net_device *dev,
- struct net_device *upper_dev)
+static void __netdev_adjacent_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev)
{
__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
&dev->all_adj_list.upper,
&upper_dev->all_adj_list.lower);
}
-int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
- struct net_device *upper_dev,
- void *private, bool master)
+static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+ struct net_device *upper_dev,
+ void *private, bool master)
{
int ret = __netdev_adjacent_dev_link(dev, upper_dev);
@@ -4772,8 +4739,8 @@ int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
return 0;
}
-void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
- struct net_device *upper_dev)
+static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
+ struct net_device *upper_dev)
{
__netdev_adjacent_dev_unlink(dev, upper_dev);
__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
@@ -4962,21 +4929,6 @@ void netdev_upper_dev_unlink(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
-void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
- struct net_device *lower_dev)
-{
- struct netdev_adjacent *lower;
-
- if (!lower_dev)
- return NULL;
- lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower);
- if (!lower)
- return NULL;
-
- return lower->private;
-}
-EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu);
-
void *netdev_lower_dev_get_private(struct net_device *dev,
struct net_device *lower_dev)
{
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index ec40a849fc42..bb504a919e33 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -186,47 +186,6 @@ static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list,
return err;
}
-int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list,
- struct netdev_hw_addr_list *from_list,
- int addr_len, unsigned char addr_type)
-{
- int err;
- struct netdev_hw_addr *ha, *ha2;
- unsigned char type;
-
- list_for_each_entry(ha, &from_list->list, list) {
- type = addr_type ? addr_type : ha->type;
- err = __hw_addr_add(to_list, ha->addr, addr_len, type);
- if (err)
- goto unroll;
- }
- return 0;
-
-unroll:
- list_for_each_entry(ha2, &from_list->list, list) {
- if (ha2 == ha)
- break;
- type = addr_type ? addr_type : ha2->type;
- __hw_addr_del(to_list, ha2->addr, addr_len, type);
- }
- return err;
-}
-EXPORT_SYMBOL(__hw_addr_add_multiple);
-
-void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list,
- struct netdev_hw_addr_list *from_list,
- int addr_len, unsigned char addr_type)
-{
- struct netdev_hw_addr *ha;
- unsigned char type;
-
- list_for_each_entry(ha, &from_list->list, list) {
- type = addr_type ? addr_type : ha->type;
- __hw_addr_del(to_list, ha->addr, addr_len, type);
- }
-}
-EXPORT_SYMBOL(__hw_addr_del_multiple);
-
/* This function only works where there is a strict 1-1 relationship
* between source and destionation of they synch. If you ever need to
* sync addresses to more then 1 destination, you need to use
@@ -264,7 +223,7 @@ void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
}
EXPORT_SYMBOL(__hw_addr_unsync);
-void __hw_addr_flush(struct netdev_hw_addr_list *list)
+static void __hw_addr_flush(struct netdev_hw_addr_list *list)
{
struct netdev_hw_addr *ha, *tmp;
@@ -274,7 +233,6 @@ void __hw_addr_flush(struct netdev_hw_addr_list *list)
}
list->count = 0;
}
-EXPORT_SYMBOL(__hw_addr_flush);
void __hw_addr_init(struct netdev_hw_addr_list *list)
{
@@ -400,59 +358,6 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr,
}
EXPORT_SYMBOL(dev_addr_del);
-/**
- * dev_addr_add_multiple - Add device addresses from another device
- * @to_dev: device to which addresses will be added
- * @from_dev: device from which addresses will be added
- * @addr_type: address type - 0 means type will be used from from_dev
- *
- * Add device addresses of the one device to another.
- **
- * The caller must hold the rtnl_mutex.
- */
-int dev_addr_add_multiple(struct net_device *to_dev,
- struct net_device *from_dev,
- unsigned char addr_type)
-{
- int err;
-
- ASSERT_RTNL();
-
- if (from_dev->addr_len != to_dev->addr_len)
- return -EINVAL;
- err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
- to_dev->addr_len, addr_type);
- if (!err)
- call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
- return err;
-}
-EXPORT_SYMBOL(dev_addr_add_multiple);
-
-/**
- * dev_addr_del_multiple - Delete device addresses by another device
- * @to_dev: device where the addresses will be deleted
- * @from_dev: device supplying the addresses to be deleted
- * @addr_type: address type - 0 means type will be used from from_dev
- *
- * Deletes addresses in to device by the list of addresses in from device.
- *
- * The caller must hold the rtnl_mutex.
- */
-int dev_addr_del_multiple(struct net_device *to_dev,
- struct net_device *from_dev,
- unsigned char addr_type)
-{
- ASSERT_RTNL();
-
- if (from_dev->addr_len != to_dev->addr_len)
- return -EINVAL;
- __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs,
- to_dev->addr_len, addr_type);
- call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
- return 0;
-}
-EXPORT_SYMBOL(dev_addr_del_multiple);
-
/*
* Unicast list handling functions
*/
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 5b7d0e1d0664..cf999e09bcd2 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -327,6 +327,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
cmd == SIOCBRADDIF ||
cmd == SIOCBRDELIF ||
cmd == SIOCSHWTSTAMP ||
+ cmd == SIOCGHWTSTAMP ||
cmd == SIOCWANDEV) {
err = -EOPNOTSUPP;
if (ops->ndo_do_ioctl) {
@@ -546,6 +547,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
*/
default:
if (cmd == SIOCWANDEV ||
+ cmd == SIOCGHWTSTAMP ||
(cmd >= SIOCDEVPRIVATE &&
cmd <= SIOCDEVPRIVATE + 15)) {
dev_load(net, ifr.ifr_name);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d6ef17322500..b324bfa3485c 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -202,12 +202,12 @@ static __always_inline u32 __flow_hash_1word(u32 a)
}
/*
- * __skb_get_rxhash: calculate a flow hash based on src/dst addresses
+ * __skb_get_hash: calculate a flow hash based on src/dst addresses
* and src/dst port numbers. Sets rxhash in skb to non-zero hash value
* on success, zero indicates no valid hash. Also, sets l4_rxhash in skb
* if hash is a canonical 4-tuple hash over transport ports.
*/
-void __skb_get_rxhash(struct sk_buff *skb)
+void __skb_get_hash(struct sk_buff *skb)
{
struct flow_keys keys;
u32 hash;
@@ -234,7 +234,7 @@ void __skb_get_rxhash(struct sk_buff *skb)
skb->rxhash = hash;
}
-EXPORT_SYMBOL(__skb_get_rxhash);
+EXPORT_SYMBOL(__skb_get_hash);
/*
* Returns a Tx hash based on the given packet descriptor a Tx queues' number
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 932c6d7cf666..ea97361f0e9b 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -38,6 +38,8 @@
#include <linux/random.h>
#include <linux/string.h>
#include <linux/log2.h>
+#include <linux/inetdevice.h>
+#include <net/addrconf.h>
#define DEBUG
#define NEIGH_DEBUG 1
@@ -497,7 +499,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey,
goto out_neigh_release;
}
- n->confirmed = jiffies - (n->parms->base_reachable_time << 1);
+ n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1);
write_lock_bh(&tbl->lock);
nht = rcu_dereference_protected(tbl->nht,
@@ -776,7 +778,7 @@ static void neigh_periodic_work(struct work_struct *work)
tbl->last_rand = jiffies;
for (p = &tbl->parms; p; p = p->next)
p->reachable_time =
- neigh_rand_reach_time(p->base_reachable_time);
+ neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
}
for (i = 0 ; i < (1 << nht->hash_shift); i++) {
@@ -799,7 +801,7 @@ static void neigh_periodic_work(struct work_struct *work)
if (atomic_read(&n->refcnt) == 1 &&
(state == NUD_FAILED ||
- time_after(jiffies, n->used + n->parms->gc_staletime))) {
+ time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) {
*np = n->next;
n->dead = 1;
write_unlock(&n->lock);
@@ -822,12 +824,12 @@ next_elt:
lockdep_is_held(&tbl->lock));
}
out:
- /* Cycle through all hash buckets every base_reachable_time/2 ticks.
- * ARP entry timeouts range from 1/2 base_reachable_time to 3/2
- * base_reachable_time.
+ /* Cycle through all hash buckets every BASE_REACHABLE_TIME/2 ticks.
+ * ARP entry timeouts range from 1/2 BASE_REACHABLE_TIME to 3/2
+ * BASE_REACHABLE_TIME.
*/
schedule_delayed_work(&tbl->gc_work,
- tbl->parms.base_reachable_time >> 1);
+ NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1);
write_unlock_bh(&tbl->lock);
}
@@ -835,8 +837,9 @@ static __inline__ int neigh_max_probes(struct neighbour *n)
{
struct neigh_parms *p = n->parms;
return (n->nud_state & NUD_PROBE) ?
- p->ucast_probes :
- p->ucast_probes + p->app_probes + p->mcast_probes;
+ NEIGH_VAR(p, UCAST_PROBES) :
+ NEIGH_VAR(p, UCAST_PROBES) + NEIGH_VAR(p, APP_PROBES) +
+ NEIGH_VAR(p, MCAST_PROBES);
}
static void neigh_invalidate(struct neighbour *neigh)
@@ -901,12 +904,13 @@ static void neigh_timer_handler(unsigned long arg)
neigh_dbg(2, "neigh %p is still alive\n", neigh);
next = neigh->confirmed + neigh->parms->reachable_time;
} else if (time_before_eq(now,
- neigh->used + neigh->parms->delay_probe_time)) {
+ neigh->used +
+ NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) {
neigh_dbg(2, "neigh %p is delayed\n", neigh);
neigh->nud_state = NUD_DELAY;
neigh->updated = jiffies;
neigh_suspect(neigh);
- next = now + neigh->parms->delay_probe_time;
+ next = now + NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME);
} else {
neigh_dbg(2, "neigh %p is suspected\n", neigh);
neigh->nud_state = NUD_STALE;
@@ -916,7 +920,8 @@ static void neigh_timer_handler(unsigned long arg)
}
} else if (state & NUD_DELAY) {
if (time_before_eq(now,
- neigh->confirmed + neigh->parms->delay_probe_time)) {
+ neigh->confirmed +
+ NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME))) {
neigh_dbg(2, "neigh %p is now reachable\n", neigh);
neigh->nud_state = NUD_REACHABLE;
neigh->updated = jiffies;
@@ -928,11 +933,11 @@ static void neigh_timer_handler(unsigned long arg)
neigh->nud_state = NUD_PROBE;
neigh->updated = jiffies;
atomic_set(&neigh->probes, 0);
- next = now + neigh->parms->retrans_time;
+ next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME);
}
} else {
/* NUD_PROBE|NUD_INCOMPLETE */
- next = now + neigh->parms->retrans_time;
+ next = now + NEIGH_VAR(neigh->parms, RETRANS_TIME);
}
if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) &&
@@ -973,13 +978,16 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
goto out_unlock_bh;
if (!(neigh->nud_state & (NUD_STALE | NUD_INCOMPLETE))) {
- if (neigh->parms->mcast_probes + neigh->parms->app_probes) {
+ if (NEIGH_VAR(neigh->parms, MCAST_PROBES) +
+ NEIGH_VAR(neigh->parms, APP_PROBES)) {
unsigned long next, now = jiffies;
- atomic_set(&neigh->probes, neigh->parms->ucast_probes);
+ atomic_set(&neigh->probes,
+ NEIGH_VAR(neigh->parms, UCAST_PROBES));
neigh->nud_state = NUD_INCOMPLETE;
neigh->updated = now;
- next = now + max(neigh->parms->retrans_time, HZ/2);
+ next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME),
+ HZ/2);
neigh_add_timer(neigh, next);
immediate_probe = true;
} else {
@@ -994,14 +1002,14 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
neigh_dbg(2, "neigh %p is delayed\n", neigh);
neigh->nud_state = NUD_DELAY;
neigh->updated = jiffies;
- neigh_add_timer(neigh,
- jiffies + neigh->parms->delay_probe_time);
+ neigh_add_timer(neigh, jiffies +
+ NEIGH_VAR(neigh->parms, DELAY_PROBE_TIME));
}
if (neigh->nud_state == NUD_INCOMPLETE) {
if (skb) {
while (neigh->arp_queue_len_bytes + skb->truesize >
- neigh->parms->queue_len_bytes) {
+ NEIGH_VAR(neigh->parms, QUEUE_LEN_BYTES)) {
struct sk_buff *buff;
buff = __skb_dequeue(&neigh->arp_queue);
@@ -1171,7 +1179,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
neigh_update_hhs(neigh);
if (!(new & NUD_CONNECTED))
neigh->confirmed = jiffies -
- (neigh->parms->base_reachable_time << 1);
+ (NEIGH_VAR(neigh->parms, BASE_REACHABLE_TIME) << 1);
notify = 1;
}
if (new == old)
@@ -1231,6 +1239,21 @@ out:
}
EXPORT_SYMBOL(neigh_update);
+/* Update the neigh to listen temporarily for probe responses, even if it is
+ * in a NUD_FAILED state. The caller has to hold neigh->lock for writing.
+ */
+void __neigh_set_probe_once(struct neighbour *neigh)
+{
+ neigh->updated = jiffies;
+ if (!(neigh->nud_state & NUD_FAILED))
+ return;
+ neigh->nud_state = NUD_PROBE;
+ atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+ neigh_add_timer(neigh,
+ jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
+}
+EXPORT_SYMBOL(__neigh_set_probe_once);
+
struct neighbour *neigh_event_ns(struct neigh_table *tbl,
u8 *lladdr, void *saddr,
struct net_device *dev)
@@ -1392,9 +1415,10 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
struct sk_buff *skb)
{
unsigned long now = jiffies;
- unsigned long sched_next = now + (net_random() % p->proxy_delay);
+ unsigned long sched_next = now + (net_random() %
+ NEIGH_VAR(p, PROXY_DELAY));
- if (tbl->proxy_queue.qlen > p->proxy_qlen) {
+ if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
kfree_skb(skb);
return;
}
@@ -1441,7 +1465,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
p->tbl = tbl;
atomic_set(&p->refcnt, 1);
p->reachable_time =
- neigh_rand_reach_time(p->base_reachable_time);
+ neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME));
dev_hold(dev);
p->dev = dev;
write_pnet(&p->net, hold_net(net));
@@ -1458,6 +1482,8 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev,
p->next = tbl->parms.next;
tbl->parms.next = p;
write_unlock_bh(&tbl->lock);
+
+ neigh_parms_data_state_cleanall(p);
}
return p;
}
@@ -1510,7 +1536,7 @@ static void neigh_table_init_no_netlink(struct neigh_table *tbl)
write_pnet(&tbl->parms.net, &init_net);
atomic_set(&tbl->parms.refcnt, 1);
tbl->parms.reachable_time =
- neigh_rand_reach_time(tbl->parms.base_reachable_time);
+ neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME));
tbl->stats = alloc_percpu(struct neigh_statistics);
if (!tbl->stats)
@@ -1778,24 +1804,32 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
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) ||
+ nla_put_u32(skb, NDTPA_QUEUE_LENBYTES,
+ NEIGH_VAR(parms, QUEUE_LEN_BYTES)) ||
/* approximative value for deprecated QUEUE_LEN (in packets) */
nla_put_u32(skb, NDTPA_QUEUE_LEN,
- 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) ||
+ NEIGH_VAR(parms, QUEUE_LEN_BYTES) / SKB_TRUESIZE(ETH_FRAME_LEN)) ||
+ nla_put_u32(skb, NDTPA_PROXY_QLEN, NEIGH_VAR(parms, PROXY_QLEN)) ||
+ nla_put_u32(skb, NDTPA_APP_PROBES, NEIGH_VAR(parms, APP_PROBES)) ||
+ nla_put_u32(skb, NDTPA_UCAST_PROBES,
+ NEIGH_VAR(parms, UCAST_PROBES)) ||
+ nla_put_u32(skb, NDTPA_MCAST_PROBES,
+ NEIGH_VAR(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) ||
+ NEIGH_VAR(parms, BASE_REACHABLE_TIME)) ||
+ nla_put_msecs(skb, NDTPA_GC_STALETIME,
+ NEIGH_VAR(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))
+ NEIGH_VAR(parms, DELAY_PROBE_TIME)) ||
+ nla_put_msecs(skb, NDTPA_RETRANS_TIME,
+ NEIGH_VAR(parms, RETRANS_TIME)) ||
+ nla_put_msecs(skb, NDTPA_ANYCAST_DELAY,
+ NEIGH_VAR(parms, ANYCAST_DELAY)) ||
+ nla_put_msecs(skb, NDTPA_PROXY_DELAY,
+ NEIGH_VAR(parms, PROXY_DELAY)) ||
+ nla_put_msecs(skb, NDTPA_LOCKTIME,
+ NEIGH_VAR(parms, LOCKTIME)))
goto nla_put_failure;
return nla_nest_end(skb, nest);
@@ -2011,44 +2045,54 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh)
switch (i) {
case NDTPA_QUEUE_LEN:
- p->queue_len_bytes = nla_get_u32(tbp[i]) *
- SKB_TRUESIZE(ETH_FRAME_LEN);
+ NEIGH_VAR_SET(p, QUEUE_LEN_BYTES,
+ nla_get_u32(tbp[i]) *
+ SKB_TRUESIZE(ETH_FRAME_LEN));
break;
case NDTPA_QUEUE_LENBYTES:
- p->queue_len_bytes = nla_get_u32(tbp[i]);
+ NEIGH_VAR_SET(p, QUEUE_LEN_BYTES,
+ nla_get_u32(tbp[i]));
break;
case NDTPA_PROXY_QLEN:
- p->proxy_qlen = nla_get_u32(tbp[i]);
+ NEIGH_VAR_SET(p, PROXY_QLEN,
+ nla_get_u32(tbp[i]));
break;
case NDTPA_APP_PROBES:
- p->app_probes = nla_get_u32(tbp[i]);
+ NEIGH_VAR_SET(p, APP_PROBES,
+ nla_get_u32(tbp[i]));
break;
case NDTPA_UCAST_PROBES:
- p->ucast_probes = nla_get_u32(tbp[i]);
+ NEIGH_VAR_SET(p, UCAST_PROBES,
+ nla_get_u32(tbp[i]));
break;
case NDTPA_MCAST_PROBES:
- p->mcast_probes = nla_get_u32(tbp[i]);
+ NEIGH_VAR_SET(p, MCAST_PROBES,
+ nla_get_u32(tbp[i]));
break;
case NDTPA_BASE_REACHABLE_TIME:
- p->base_reachable_time = nla_get_msecs(tbp[i]);
+ NEIGH_VAR_SET(p, BASE_REACHABLE_TIME,
+ nla_get_msecs(tbp[i]));
break;
case NDTPA_GC_STALETIME:
- p->gc_staletime = nla_get_msecs(tbp[i]);
+ NEIGH_VAR_SET(p, GC_STALETIME,
+ nla_get_msecs(tbp[i]));
break;
case NDTPA_DELAY_PROBE_TIME:
- p->delay_probe_time = nla_get_msecs(tbp[i]);
+ NEIGH_VAR_SET(p, DELAY_PROBE_TIME,
+ nla_get_msecs(tbp[i]));
break;
case NDTPA_RETRANS_TIME:
- p->retrans_time = nla_get_msecs(tbp[i]);
+ NEIGH_VAR_SET(p, RETRANS_TIME,
+ nla_get_msecs(tbp[i]));
break;
case NDTPA_ANYCAST_DELAY:
- p->anycast_delay = nla_get_msecs(tbp[i]);
+ NEIGH_VAR_SET(p, ANYCAST_DELAY, nla_get_msecs(tbp[i]));
break;
case NDTPA_PROXY_DELAY:
- p->proxy_delay = nla_get_msecs(tbp[i]);
+ NEIGH_VAR_SET(p, PROXY_DELAY, nla_get_msecs(tbp[i]));
break;
case NDTPA_LOCKTIME:
- p->locktime = nla_get_msecs(tbp[i]);
+ NEIGH_VAR_SET(p, LOCKTIME, nla_get_msecs(tbp[i]));
break;
}
}
@@ -2789,133 +2833,167 @@ static int proc_unres_qlen(struct ctl_table *ctl, int write,
return ret;
}
-enum {
- NEIGH_VAR_MCAST_PROBE,
- NEIGH_VAR_UCAST_PROBE,
- NEIGH_VAR_APP_PROBE,
- NEIGH_VAR_RETRANS_TIME,
- NEIGH_VAR_BASE_REACHABLE_TIME,
- NEIGH_VAR_DELAY_PROBE_TIME,
- NEIGH_VAR_GC_STALETIME,
- NEIGH_VAR_QUEUE_LEN,
- NEIGH_VAR_QUEUE_LEN_BYTES,
- NEIGH_VAR_PROXY_QLEN,
- NEIGH_VAR_ANYCAST_DELAY,
- NEIGH_VAR_PROXY_DELAY,
- NEIGH_VAR_LOCKTIME,
- NEIGH_VAR_RETRANS_TIME_MS,
- NEIGH_VAR_BASE_REACHABLE_TIME_MS,
- NEIGH_VAR_GC_INTERVAL,
- NEIGH_VAR_GC_THRESH1,
- NEIGH_VAR_GC_THRESH2,
- NEIGH_VAR_GC_THRESH3,
- NEIGH_VAR_MAX
-};
+static struct neigh_parms *neigh_get_dev_parms_rcu(struct net_device *dev,
+ int family)
+{
+ switch (family) {
+ case AF_INET:
+ return __in_dev_arp_parms_get_rcu(dev);
+ case AF_INET6:
+ return __in6_dev_nd_parms_get_rcu(dev);
+ }
+ return NULL;
+}
+
+static void neigh_copy_dflt_parms(struct net *net, struct neigh_parms *p,
+ int index)
+{
+ struct net_device *dev;
+ int family = neigh_parms_family(p);
+
+ rcu_read_lock();
+ for_each_netdev_rcu(net, dev) {
+ struct neigh_parms *dst_p =
+ neigh_get_dev_parms_rcu(dev, family);
+
+ if (dst_p && !test_bit(index, dst_p->data_state))
+ dst_p->data[index] = p->data[index];
+ }
+ rcu_read_unlock();
+}
+
+static void neigh_proc_update(struct ctl_table *ctl, int write)
+{
+ struct net_device *dev = ctl->extra1;
+ struct neigh_parms *p = ctl->extra2;
+ struct net *net = neigh_parms_net(p);
+ int index = (int *) ctl->data - p->data;
+
+ if (!write)
+ return;
+
+ set_bit(index, p->data_state);
+ if (!dev) /* NULL dev means this is default value */
+ neigh_copy_dflt_parms(net, p, index);
+}
+
+static int neigh_proc_dointvec_zero_intmax(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table tmp = *ctl;
+ int ret;
+
+ tmp.extra1 = &zero;
+ tmp.extra2 = &int_max;
+
+ ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+ neigh_proc_update(ctl, write);
+ return ret;
+}
+
+int neigh_proc_dointvec(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+
+ neigh_proc_update(ctl, write);
+ return ret;
+}
+EXPORT_SYMBOL(neigh_proc_dointvec);
+
+int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int ret = proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos);
+
+ neigh_proc_update(ctl, write);
+ return ret;
+}
+EXPORT_SYMBOL(neigh_proc_dointvec_jiffies);
+
+static int neigh_proc_dointvec_userhz_jiffies(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int ret = proc_dointvec_userhz_jiffies(ctl, write, buffer, lenp, ppos);
+
+ neigh_proc_update(ctl, write);
+ return ret;
+}
+
+int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int ret = proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos);
+
+ neigh_proc_update(ctl, write);
+ return ret;
+}
+EXPORT_SYMBOL(neigh_proc_dointvec_ms_jiffies);
+
+static int neigh_proc_dointvec_unres_qlen(struct ctl_table *ctl, int write,
+ void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ int ret = proc_unres_qlen(ctl, write, buffer, lenp, ppos);
+
+ neigh_proc_update(ctl, write);
+ return ret;
+}
+
+#define NEIGH_PARMS_DATA_OFFSET(index) \
+ (&((struct neigh_parms *) 0)->data[index])
+
+#define NEIGH_SYSCTL_ENTRY(attr, data_attr, name, mval, proc) \
+ [NEIGH_VAR_ ## attr] = { \
+ .procname = name, \
+ .data = NEIGH_PARMS_DATA_OFFSET(NEIGH_VAR_ ## data_attr), \
+ .maxlen = sizeof(int), \
+ .mode = mval, \
+ .proc_handler = proc, \
+ }
+
+#define NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(attr, name) \
+ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_zero_intmax)
+
+#define NEIGH_SYSCTL_JIFFIES_ENTRY(attr, name) \
+ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_jiffies)
+
+#define NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(attr, name) \
+ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_userhz_jiffies)
+
+#define NEIGH_SYSCTL_MS_JIFFIES_ENTRY(attr, name) \
+ NEIGH_SYSCTL_ENTRY(attr, attr, name, 0644, neigh_proc_dointvec_ms_jiffies)
+
+#define NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(attr, data_attr, name) \
+ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_ms_jiffies)
+
+#define NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(attr, data_attr, name) \
+ NEIGH_SYSCTL_ENTRY(attr, data_attr, name, 0644, neigh_proc_dointvec_unres_qlen)
static struct neigh_sysctl_table {
struct ctl_table_header *sysctl_header;
struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1];
} neigh_sysctl_template __read_mostly = {
.neigh_vars = {
- [NEIGH_VAR_MCAST_PROBE] = {
- .procname = "mcast_solicit",
- .maxlen = sizeof(int),
- .mode = 0644,
- .extra1 = &zero,
- .extra2 = &int_max,
- .proc_handler = proc_dointvec_minmax,
- },
- [NEIGH_VAR_UCAST_PROBE] = {
- .procname = "ucast_solicit",
- .maxlen = sizeof(int),
- .mode = 0644,
- .extra1 = &zero,
- .extra2 = &int_max,
- .proc_handler = proc_dointvec_minmax,
- },
- [NEIGH_VAR_APP_PROBE] = {
- .procname = "app_solicit",
- .maxlen = sizeof(int),
- .mode = 0644,
- .extra1 = &zero,
- .extra2 = &int_max,
- .proc_handler = proc_dointvec_minmax,
- },
- [NEIGH_VAR_RETRANS_TIME] = {
- .procname = "retrans_time",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_userhz_jiffies,
- },
- [NEIGH_VAR_BASE_REACHABLE_TIME] = {
- .procname = "base_reachable_time",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
- [NEIGH_VAR_DELAY_PROBE_TIME] = {
- .procname = "delay_first_probe_time",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
- [NEIGH_VAR_GC_STALETIME] = {
- .procname = "gc_stale_time",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
- },
- [NEIGH_VAR_QUEUE_LEN] = {
- .procname = "unres_qlen",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_unres_qlen,
- },
- [NEIGH_VAR_QUEUE_LEN_BYTES] = {
- .procname = "unres_qlen_bytes",
- .maxlen = sizeof(int),
- .mode = 0644,
- .extra1 = &zero,
- .proc_handler = proc_dointvec_minmax,
- },
- [NEIGH_VAR_PROXY_QLEN] = {
- .procname = "proxy_qlen",
- .maxlen = sizeof(int),
- .mode = 0644,
- .extra1 = &zero,
- .extra2 = &int_max,
- .proc_handler = proc_dointvec_minmax,
- },
- [NEIGH_VAR_ANYCAST_DELAY] = {
- .procname = "anycast_delay",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_userhz_jiffies,
- },
- [NEIGH_VAR_PROXY_DELAY] = {
- .procname = "proxy_delay",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_userhz_jiffies,
- },
- [NEIGH_VAR_LOCKTIME] = {
- .procname = "locktime",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_userhz_jiffies,
- },
- [NEIGH_VAR_RETRANS_TIME_MS] = {
- .procname = "retrans_time_ms",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_ms_jiffies,
- },
- [NEIGH_VAR_BASE_REACHABLE_TIME_MS] = {
- .procname = "base_reachable_time_ms",
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_ms_jiffies,
- },
+ NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(MCAST_PROBES, "mcast_solicit"),
+ NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(UCAST_PROBES, "ucast_solicit"),
+ NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(APP_PROBES, "app_solicit"),
+ NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(RETRANS_TIME, "retrans_time"),
+ NEIGH_SYSCTL_JIFFIES_ENTRY(BASE_REACHABLE_TIME, "base_reachable_time"),
+ NEIGH_SYSCTL_JIFFIES_ENTRY(DELAY_PROBE_TIME, "delay_first_probe_time"),
+ NEIGH_SYSCTL_JIFFIES_ENTRY(GC_STALETIME, "gc_stale_time"),
+ NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(QUEUE_LEN_BYTES, "unres_qlen_bytes"),
+ NEIGH_SYSCTL_ZERO_INTMAX_ENTRY(PROXY_QLEN, "proxy_qlen"),
+ NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(ANYCAST_DELAY, "anycast_delay"),
+ NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(PROXY_DELAY, "proxy_delay"),
+ NEIGH_SYSCTL_USERHZ_JIFFIES_ENTRY(LOCKTIME, "locktime"),
+ NEIGH_SYSCTL_UNRES_QLEN_REUSED_ENTRY(QUEUE_LEN, QUEUE_LEN_BYTES, "unres_qlen"),
+ NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(RETRANS_TIME_MS, RETRANS_TIME, "retrans_time_ms"),
+ NEIGH_SYSCTL_MS_JIFFIES_REUSED_ENTRY(BASE_REACHABLE_TIME_MS, BASE_REACHABLE_TIME, "base_reachable_time_ms"),
[NEIGH_VAR_GC_INTERVAL] = {
.procname = "gc_interval",
.maxlen = sizeof(int),
@@ -2951,31 +3029,23 @@ static struct neigh_sysctl_table {
};
int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
- char *p_name, proc_handler *handler)
+ proc_handler *handler)
{
+ int i;
struct neigh_sysctl_table *t;
- const char *dev_name_source = NULL;
+ const char *dev_name_source;
char neigh_path[ sizeof("net//neigh/") + IFNAMSIZ + IFNAMSIZ ];
+ char *p_name;
t = kmemdup(&neigh_sysctl_template, sizeof(*t), GFP_KERNEL);
if (!t)
goto err;
- t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data = &p->mcast_probes;
- t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data = &p->ucast_probes;
- t->neigh_vars[NEIGH_VAR_APP_PROBE].data = &p->app_probes;
- t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data = &p->retrans_time;
- t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data = &p->base_reachable_time;
- t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data = &p->delay_probe_time;
- t->neigh_vars[NEIGH_VAR_GC_STALETIME].data = &p->gc_staletime;
- t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data = &p->queue_len_bytes;
- t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data = &p->queue_len_bytes;
- t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data = &p->proxy_qlen;
- t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data = &p->anycast_delay;
- t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay;
- t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime;
- t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data = &p->retrans_time;
- t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data = &p->base_reachable_time;
+ for (i = 0; i < ARRAY_SIZE(t->neigh_vars); i++) {
+ t->neigh_vars[i].data += (long) p;
+ t->neigh_vars[i].extra1 = dev;
+ t->neigh_vars[i].extra2 = p;
+ }
if (dev) {
dev_name_source = dev->name;
@@ -2990,26 +3060,32 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3;
}
-
if (handler) {
/* RetransTime */
t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler;
- t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev;
/* ReachableTime */
t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler;
- t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev;
/* RetransTime (in milliseconds)*/
t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler;
- t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev;
/* ReachableTime (in milliseconds) */
t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler;
- t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev;
}
/* Don't export sysctls to unprivileged users */
if (neigh_parms_net(p)->user_ns != &init_user_ns)
t->neigh_vars[0].procname = NULL;
+ switch (neigh_parms_family(p)) {
+ case AF_INET:
+ p_name = "ipv4";
+ break;
+ case AF_INET6:
+ p_name = "ipv6";
+ break;
+ default:
+ BUG();
+ }
+
snprintf(neigh_path, sizeof(neigh_path), "net/%s/neigh/%s",
p_name, dev_name_source);
t->sysctl_header =
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f3edf9635e02..49843bf7e43e 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -676,8 +676,8 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
while ((mask | (mask >> 1)) != mask)
mask |= (mask >> 1);
/* On 64 bit arches, must check mask fits in table->mask (u32),
- * and on 32bit arches, must check RPS_DEV_FLOW_TABLE_SIZE(mask + 1)
- * doesnt overflow.
+ * and on 32bit arches, must check
+ * RPS_DEV_FLOW_TABLE_SIZE(mask + 1) doesn't overflow.
*/
#if BITS_PER_LONG > 32
if (mask > (unsigned long)(u32)mask)
@@ -1358,7 +1358,7 @@ void netdev_class_remove_file_ns(struct class_attribute *class_attr,
}
EXPORT_SYMBOL(netdev_class_remove_file_ns);
-int netdev_kobject_init(void)
+int __init netdev_kobject_init(void)
{
kobj_ns_type_register(&net_ns_type_operations);
return class_register(&net_class);
diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h
index bd7751ec1c4d..2745a1b51e03 100644
--- a/net/core/net-sysfs.h
+++ b/net/core/net-sysfs.h
@@ -1,7 +1,7 @@
#ifndef __NET_SYSFS_H__
#define __NET_SYSFS_H__
-int netdev_kobject_init(void);
+int __init netdev_kobject_init(void);
int netdev_register_kobject(struct net_device *);
void netdev_unregister_kobject(struct net_device *);
int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num);
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
new file mode 100644
index 000000000000..719efd541668
--- /dev/null
+++ b/net/core/netclassid_cgroup.c
@@ -0,0 +1,120 @@
+/*
+ * net/core/netclassid_cgroup.c Classid Cgroupfs Handling
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/cgroup.h>
+#include <linux/fdtable.h>
+#include <net/cls_cgroup.h>
+#include <net/sock.h>
+
+static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css)
+{
+ return css ? container_of(css, struct cgroup_cls_state, css) : NULL;
+}
+
+struct cgroup_cls_state *task_cls_state(struct task_struct *p)
+{
+ return css_cls_state(task_css(p, net_cls_subsys_id));
+}
+EXPORT_SYMBOL_GPL(task_cls_state);
+
+static struct cgroup_subsys_state *
+cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+ struct cgroup_cls_state *cs;
+
+ cs = kzalloc(sizeof(*cs), GFP_KERNEL);
+ if (!cs)
+ return ERR_PTR(-ENOMEM);
+
+ return &cs->css;
+}
+
+static int cgrp_css_online(struct cgroup_subsys_state *css)
+{
+ struct cgroup_cls_state *cs = css_cls_state(css);
+ struct cgroup_cls_state *parent = css_cls_state(css_parent(css));
+
+ if (parent)
+ cs->classid = parent->classid;
+
+ return 0;
+}
+
+static void cgrp_css_free(struct cgroup_subsys_state *css)
+{
+ kfree(css_cls_state(css));
+}
+
+static int update_classid(const void *v, struct file *file, unsigned n)
+{
+ int err;
+ struct socket *sock = sock_from_file(file, &err);
+
+ if (sock)
+ sock->sk->sk_classid = (u32)(unsigned long)v;
+
+ return 0;
+}
+
+static void cgrp_attach(struct cgroup_subsys_state *css,
+ struct cgroup_taskset *tset)
+{
+ struct cgroup_cls_state *cs = css_cls_state(css);
+ void *v = (void *)(unsigned long)cs->classid;
+ struct task_struct *p;
+
+ cgroup_taskset_for_each(p, css, tset) {
+ task_lock(p);
+ iterate_fd(p->files, 0, update_classid, v);
+ task_unlock(p);
+ }
+}
+
+static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+ return css_cls_state(css)->classid;
+}
+
+static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
+ u64 value)
+{
+ css_cls_state(css)->classid = (u32) value;
+
+ return 0;
+}
+
+static struct cftype ss_files[] = {
+ {
+ .name = "classid",
+ .read_u64 = read_classid,
+ .write_u64 = write_classid,
+ },
+ { } /* terminate */
+};
+
+struct cgroup_subsys net_cls_subsys = {
+ .name = "net_cls",
+ .css_alloc = cgrp_css_alloc,
+ .css_online = cgrp_css_online,
+ .css_free = cgrp_css_free,
+ .attach = cgrp_attach,
+ .subsys_id = net_cls_subsys_id,
+ .base_cftypes = ss_files,
+ .module = THIS_MODULE,
+};
+
+static int __init init_netclassid_cgroup(void)
+{
+ return cgroup_load_subsys(&net_cls_subsys);
+}
+__initcall(init_netclassid_cgroup);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 9b7cf6c85f82..1dda50c2e705 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -30,7 +30,7 @@
#define PRIOMAP_MIN_SZ 128
/*
- * Extend @dev->priomap so that it's large enough to accomodate
+ * Extend @dev->priomap so that it's large enough to accommodate
* @target_idx. @dev->priomap.priomap_len > @target_idx after successful
* return. Must be called under rtnl lock.
*/
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cf67144d3e3c..e6e7d582f901 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -403,34 +403,16 @@ static const struct rtnl_af_ops *rtnl_af_lookup(const int family)
}
/**
- * __rtnl_af_register - Register rtnl_af_ops with rtnetlink.
- * @ops: struct rtnl_af_ops * to register
- *
- * The caller must hold the rtnl_mutex.
- *
- * Returns 0 on success or a negative error code.
- */
-int __rtnl_af_register(struct rtnl_af_ops *ops)
-{
- list_add_tail(&ops->list, &rtnl_af_ops);
- return 0;
-}
-EXPORT_SYMBOL_GPL(__rtnl_af_register);
-
-/**
* rtnl_af_register - Register rtnl_af_ops with rtnetlink.
* @ops: struct rtnl_af_ops * to register
*
* Returns 0 on success or a negative error code.
*/
-int rtnl_af_register(struct rtnl_af_ops *ops)
+void rtnl_af_register(struct rtnl_af_ops *ops)
{
- int err;
-
rtnl_lock();
- err = __rtnl_af_register(ops);
+ list_add_tail(&ops->list, &rtnl_af_ops);
rtnl_unlock();
- return err;
}
EXPORT_SYMBOL_GPL(rtnl_af_register);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 06e72d3cdf60..eb96c2c22400 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -712,9 +712,8 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
new->inner_network_header = old->inner_network_header;
new->inner_mac_header = old->inner_mac_header;
skb_dst_copy(new, old);
- new->rxhash = old->rxhash;
+ skb_copy_hash(new, old);
new->ooo_okay = old->ooo_okay;
- new->l4_rxhash = old->l4_rxhash;
new->no_fcs = old->no_fcs;
new->encapsulation = old->encapsulation;
#ifdef CONFIG_XFRM
@@ -2982,10 +2981,7 @@ perform_csum_check:
return segs;
err:
- while ((skb = segs)) {
- segs = skb->next;
- kfree_skb(skb);
- }
+ kfree_skb_list(segs);
return ERR_PTR(err);
}
EXPORT_SYMBOL_GPL(skb_segment);
diff --git a/net/core/sock.c b/net/core/sock.c
index 5393b4b719d7..85ad6f0d3898 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -925,8 +925,8 @@ set_rcvbuf:
EXPORT_SYMBOL(sock_setsockopt);
-void cred_to_ucred(struct pid *pid, const struct cred *cred,
- struct ucred *ucred)
+static void cred_to_ucred(struct pid *pid, const struct cred *cred,
+ struct ucred *ucred)
{
ucred->pid = pid_vnr(pid);
ucred->uid = ucred->gid = -1;
@@ -937,7 +937,6 @@ void cred_to_ucred(struct pid *pid, const struct cred *cred,
ucred->gid = from_kgid_munged(current_ns, cred->egid);
}
}
-EXPORT_SYMBOL_GPL(cred_to_ucred);
int sock_getsockopt(struct socket *sock, int level, int optname,
char __user *optval, int __user *optlen)
@@ -1308,19 +1307,7 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
module_put(owner);
}
-#if IS_ENABLED(CONFIG_NET_CLS_CGROUP)
-void sock_update_classid(struct sock *sk)
-{
- u32 classid;
-
- classid = task_cls_classid(current);
- if (classid != sk->sk_classid)
- sk->sk_classid = classid;
-}
-EXPORT_SYMBOL(sock_update_classid);
-#endif
-
-#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
void sock_update_netprioidx(struct sock *sk)
{
if (in_interrupt())
@@ -1666,22 +1653,6 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
EXPORT_SYMBOL(sock_wmalloc);
/*
- * Allocate a skb from the socket's receive buffer.
- */
-struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
- gfp_t priority)
-{
- if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
- struct sk_buff *skb = alloc_skb(size, priority);
- if (skb) {
- skb_set_owner_r(skb, sk);
- return skb;
- }
- }
- return NULL;
-}
-
-/*
* Allocate a memory block from the socket's option memory buffer.
*/
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index cca444190907..cf9cd13509a7 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -122,7 +122,8 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
synchronize_rcu();
kfree(cur);
} else if (!cur && cpumask_test_cpu(i, mask)) {
- cur = kzalloc(len, GFP_KERNEL);
+ cur = kzalloc_node(len, GFP_KERNEL,
+ cpu_to_node(i));
if (!cur) {
/* not unwinding previous changes */
ret = -ENOMEM;
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-02 09:24:16 +0000