summaryrefslogtreecommitdiffstats
path: root/net/core/dev.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/dev.c')
-rw-r--r--net/core/dev.c111
1 files changed, 97 insertions, 14 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 84f01ba81a34..0cb3fe8d8e72 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1172,6 +1172,7 @@ static int __dev_open(struct net_device *dev)
net_dmaengine_get();
dev_set_rx_mode(dev);
dev_activate(dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
}
return ret;
@@ -1632,6 +1633,8 @@ static inline int deliver_skb(struct sk_buff *skb,
struct packet_type *pt_prev,
struct net_device *orig_dev)
{
+ if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+ return -ENOMEM;
atomic_inc(&skb->users);
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
@@ -1691,7 +1694,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
rcu_read_unlock();
}
-/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
+/**
+ * netif_setup_tc - Handle tc mappings on real_num_tx_queues change
* @dev: Network device
* @txq: number of queues available
*
@@ -1793,6 +1797,18 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
EXPORT_SYMBOL(netif_set_real_num_rx_queues);
#endif
+/**
+ * netif_get_num_default_rss_queues - default number of RSS queues
+ *
+ * This routine should set an upper limit on the number of RSS queues
+ * used by default by multiqueue devices.
+ */
+int netif_get_num_default_rss_queues(void)
+{
+ return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+}
+EXPORT_SYMBOL(netif_get_num_default_rss_queues);
+
static inline void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
@@ -2444,8 +2460,12 @@ static void skb_update_prio(struct sk_buff *skb)
{
struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
- if ((!skb->priority) && (skb->sk) && map)
- skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx];
+ if (!skb->priority && skb->sk && map) {
+ unsigned int prioidx = skb->sk->sk_cgrp_prioidx;
+
+ if (prioidx < map->priomap_len)
+ skb->priority = map->priomap[prioidx];
+ }
}
#else
#define skb_update_prio(skb)
@@ -2455,6 +2475,23 @@ static DEFINE_PER_CPU(int, xmit_recursion);
#define RECURSION_LIMIT 10
/**
+ * dev_loopback_xmit - loop back @skb
+ * @skb: buffer to transmit
+ */
+int dev_loopback_xmit(struct sk_buff *skb)
+{
+ skb_reset_mac_header(skb);
+ __skb_pull(skb, skb_network_offset(skb));
+ skb->pkt_type = PACKET_LOOPBACK;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ WARN_ON(!skb_dst(skb));
+ skb_dst_force(skb);
+ netif_rx_ni(skb);
+ return 0;
+}
+EXPORT_SYMBOL(dev_loopback_xmit);
+
+/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
*
@@ -3119,6 +3156,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+ switch (skb->protocol) {
+ case __constant_htons(ETH_P_ARP):
+ case __constant_htons(ETH_P_IP):
+ case __constant_htons(ETH_P_IPV6):
+ case __constant_htons(ETH_P_8021Q):
+ return true;
+ default:
+ return false;
+ }
+}
+
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
@@ -3128,17 +3182,28 @@ static int __netif_receive_skb(struct sk_buff *skb)
bool deliver_exact = false;
int ret = NET_RX_DROP;
__be16 type;
+ unsigned long pflags = current->flags;
net_timestamp_check(!netdev_tstamp_prequeue, skb);
trace_netif_receive_skb(skb);
+ /*
+ * PFMEMALLOC skbs are special, they should
+ * - be delivered to SOCK_MEMALLOC sockets only
+ * - stay away from userspace
+ * - have bounded memory usage
+ *
+ * Use PF_MEMALLOC as this saves us from propagating the allocation
+ * context down to all allocation sites.
+ */
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+ current->flags |= PF_MEMALLOC;
+
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
- return NET_RX_DROP;
+ goto out;
- if (!skb->skb_iif)
- skb->skb_iif = skb->dev->ifindex;
orig_dev = skb->dev;
skb_reset_network_header(skb);
@@ -3150,13 +3215,14 @@ static int __netif_receive_skb(struct sk_buff *skb)
rcu_read_lock();
another_round:
+ skb->skb_iif = skb->dev->ifindex;
__this_cpu_inc(softnet_data.processed);
if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
- goto out;
+ goto unlock;
}
#ifdef CONFIG_NET_CLS_ACT
@@ -3166,6 +3232,9 @@ another_round:
}
#endif
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+ goto skip_taps;
+
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
@@ -3174,13 +3243,18 @@ another_round:
}
}
+skip_taps:
#ifdef CONFIG_NET_CLS_ACT
skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
if (!skb)
- goto out;
+ goto unlock;
ncls:
#endif
+ if (sk_memalloc_socks() && skb_pfmemalloc(skb)
+ && !skb_pfmemalloc_protocol(skb))
+ goto drop;
+
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (vlan_tx_tag_present(skb)) {
if (pt_prev) {
@@ -3190,7 +3264,7 @@ ncls:
if (vlan_do_receive(&skb, !rx_handler))
goto another_round;
else if (unlikely(!skb))
- goto out;
+ goto unlock;
}
if (rx_handler) {
@@ -3200,7 +3274,7 @@ ncls:
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
- goto out;
+ goto unlock;
case RX_HANDLER_ANOTHER:
goto another_round;
case RX_HANDLER_EXACT:
@@ -3228,8 +3302,12 @@ ncls:
}
if (pt_prev) {
- ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+ if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+ ret = -ENOMEM;
+ else
+ ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
+drop:
atomic_long_inc(&skb->dev->rx_dropped);
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
@@ -3238,8 +3316,10 @@ ncls:
ret = NET_RX_DROP;
}
-out:
+unlock:
rcu_read_unlock();
+out:
+ tsk_restore_flags(current, pflags, PF_MEMALLOC);
return ret;
}
@@ -4763,6 +4843,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
err = ops->ndo_set_mac_address(dev, sa);
if (!err)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
return err;
}
EXPORT_SYMBOL(dev_set_mac_address);
@@ -5541,6 +5622,7 @@ int register_netdevice(struct net_device *dev)
dev_init_scheduler(dev);
dev_hold(dev);
list_netdevice(dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
/* Notify protocols, that a new device appeared. */
ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
@@ -5642,7 +5724,7 @@ int netdev_refcnt_read(const struct net_device *dev)
}
EXPORT_SYMBOL(netdev_refcnt_read);
-/*
+/**
* netdev_wait_allrefs - wait until all references are gone.
*
* This is called when unregistering network devices.
@@ -6279,7 +6361,8 @@ static struct hlist_head *netdev_create_hash(void)
/* Initialize per network namespace state */
static int __net_init netdev_init(struct net *net)
{
- INIT_LIST_HEAD(&net->dev_base_head);
+ if (net != &init_net)
+ INIT_LIST_HEAD(&net->dev_base_head);
net->dev_name_head = netdev_create_hash();
if (net->dev_name_head == NULL)
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-09-18 10:55:56 +0200