#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
+#include <linux/hashtable.h>
+#include <linux/vmalloc.h>
#include "net-sysfs.h"
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base_lock);
+/* protects napi_hash addition/deletion and napi_gen_id */
+static DEFINE_SPINLOCK(napi_hash_lock);
+
+static unsigned int napi_gen_id;
+static DEFINE_HASHTABLE(napi_hash, 8);
+
seqcount_t devnet_rename_seq;
static inline void dev_base_seq_inc(struct net *net)
}
/* Device list insertion */
-static int list_netdevice(struct net_device *dev)
+static void list_netdevice(struct net_device *dev)
{
struct net *net = dev_net(dev);
write_unlock_bh(&dev_base_lock);
dev_base_seq_inc(net);
-
- return 0;
}
/* Device list removal
* If we don't do this there is a chance ndo_poll_controller
* or ndo_poll may be running while we open the device
*/
- ret = netpoll_rx_disable(dev);
- if (ret)
- return ret;
+ netpoll_rx_disable(dev);
ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev);
ret = notifier_to_errno(ret);
LIST_HEAD(single);
/* Temporarily disable netpoll until the interface is down */
- retval = netpoll_rx_disable(dev);
- if (retval)
- return retval;
+ netpoll_rx_disable(dev);
list_add(&dev->unreg_list, &single);
retval = __dev_close_many(&single);
*/
int dev_close(struct net_device *dev)
{
- int ret = 0;
if (dev->flags & IFF_UP) {
LIST_HEAD(single);
/* Block netpoll rx while the interface is going down */
- ret = netpoll_rx_disable(dev);
- if (ret)
- return ret;
+ netpoll_rx_disable(dev);
list_add(&dev->unreg_list, &single);
dev_close_many(&single);
netpoll_rx_enable(dev);
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL(dev_close);
}
EXPORT_SYMBOL(dev_disable_lro);
+static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val,
+ struct net_device *dev)
+{
+ struct netdev_notifier_info info;
+
+ netdev_notifier_info_init(&info, dev);
+ return nb->notifier_call(nb, val, &info);
+}
static int dev_boot_phase = 1;
goto unlock;
for_each_net(net) {
for_each_netdev(net, dev) {
- err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
+ err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev);
err = notifier_to_errno(err);
if (err)
goto rollback;
if (!(dev->flags & IFF_UP))
continue;
- nb->notifier_call(nb, NETDEV_UP, dev);
+ call_netdevice_notifier(nb, NETDEV_UP, dev);
}
}
goto outroll;
if (dev->flags & IFF_UP) {
- nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
- nb->notifier_call(nb, NETDEV_DOWN, dev);
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
}
- nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
}
}
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);
+ call_netdevice_notifier(nb, NETDEV_GOING_DOWN,
+ dev);
+ call_netdevice_notifier(nb, NETDEV_DOWN, dev);
}
- nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev);
}
}
unlock:
}
EXPORT_SYMBOL(unregister_netdevice_notifier);
+/**
+ * call_netdevice_notifiers_info - call all network notifier blocks
+ * @val: value passed unmodified to notifier function
+ * @dev: net_device pointer passed unmodified to notifier function
+ * @info: notifier information data
+ *
+ * Call all network notifier blocks. Parameters and return value
+ * are as for raw_notifier_call_chain().
+ */
+
+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
* @val: value passed unmodified to notifier function
int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
{
- ASSERT_RTNL();
- return raw_notifier_call_chain(&netdev_chain, val, dev);
+ struct netdev_notifier_info info;
+
+ return call_netdevice_notifiers_info(val, dev, &info);
}
EXPORT_SYMBOL(call_netdevice_notifiers);
}
}
- skb_orphan(skb);
-
if (unlikely(!is_skb_forwardable(dev, skb))) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
}
- skb->skb_iif = 0;
- skb->dev = dev;
- skb_dst_drop(skb);
- skb->tstamp.tv64 = 0;
- skb->pkt_type = PACKET_HOST;
+ skb_scrub_packet(skb);
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);
skb_reset_mac_header(skb2);
if (skb_network_header(skb2) < skb2->data ||
- skb2->network_header > skb2->tail) {
+ skb_network_header(skb2) > skb_tail_pointer(skb2)) {
net_crit_ratelimited("protocol %04x is buggy, dev %s\n",
ntohs(skb2->protocol),
dev->name);
struct net_device *dev = skb->dev;
const char *driver = "";
+ if (!net_ratelimit())
+ return;
+
if (dev && dev->dev.parent)
driver = dev_driver_string(dev->dev.parent);
}
EXPORT_SYMBOL(skb_checksum_help);
-/**
- * skb_mac_gso_segment - mac layer segmentation handler.
- * @skb: buffer to segment
- * @features: features for the output path (see dev->features)
- */
-struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
- netdev_features_t features)
+__be16 skb_network_protocol(struct sk_buff *skb)
{
- struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
- struct packet_offload *ptype;
__be16 type = skb->protocol;
int vlan_depth = ETH_HLEN;
- while (type == htons(ETH_P_8021Q)) {
+ /* Tunnel gso handlers can set protocol to ethernet. */
+ if (type == htons(ETH_P_TEB)) {
+ struct ethhdr *eth;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr))))
+ return 0;
+
+ eth = (struct ethhdr *)skb_mac_header(skb);
+ type = eth->h_proto;
+ }
+
+ while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
struct vlan_hdr *vh;
if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN)))
- return ERR_PTR(-EINVAL);
+ return 0;
vh = (struct vlan_hdr *)(skb->data + vlan_depth);
type = vh->h_vlan_encapsulated_proto;
vlan_depth += VLAN_HLEN;
}
+ return type;
+}
+
+/**
+ * skb_mac_gso_segment - mac layer segmentation handler.
+ * @skb: buffer to segment
+ * @features: features for the output path (see dev->features)
+ */
+struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
+ struct packet_offload *ptype;
+ __be16 type = skb_network_protocol(skb);
+
+ if (unlikely(!type))
+ return ERR_PTR(-EINVAL);
+
__skb_pull(skb, skb->mac_len);
rcu_read_lock();
return 0;
}
-static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
-{
- return ((features & NETIF_F_GEN_CSUM) ||
- ((features & NETIF_F_V4_CSUM) &&
- protocol == htons(ETH_P_IP)) ||
- ((features & NETIF_F_V6_CSUM) &&
- protocol == htons(ETH_P_IPV6)) ||
- ((features & NETIF_F_FCOE_CRC) &&
- protocol == htons(ETH_P_FCOE)));
-}
-
static netdev_features_t harmonize_features(struct sk_buff *skb,
__be16 protocol, netdev_features_t features)
{
if (skb->ip_summed != CHECKSUM_NONE &&
!can_checksum_protocol(features, protocol)) {
features &= ~NETIF_F_ALL_CSUM;
- features &= ~NETIF_F_SG;
} else if (illegal_highdma(skb->dev, skb)) {
features &= ~NETIF_F_SG;
}
if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
features &= ~NETIF_F_GSO_MASK;
- if (protocol == htons(ETH_P_8021Q)) {
+ if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
} else if (!vlan_tx_tag_present(skb)) {
return harmonize_features(skb, protocol, features);
}
- features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX);
+ features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX);
- if (protocol != htons(ETH_P_8021Q)) {
+ if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) {
return harmonize_features(skb, protocol, features);
} else {
features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST |
- NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX;
+ NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
+ NETIF_F_HW_VLAN_STAG_TX;
return harmonize_features(skb, protocol, features);
}
}
* 2. skb is fragmented and the device does not support SG.
*/
static inline int skb_needs_linearize(struct sk_buff *skb,
- int features)
+ netdev_features_t features)
{
return skb_is_nonlinear(skb) &&
((skb_has_frag_list(skb) &&
features = netif_skb_features(skb);
if (vlan_tx_tag_present(skb) &&
- !(features & NETIF_F_HW_VLAN_TX)) {
- skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb));
+ !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+ skb = __vlan_put_tag(skb, skb->vlan_proto,
+ vlan_tx_tag_get(skb));
if (unlikely(!skb))
goto out;
skb->next = nskb->next;
nskb->next = NULL;
- /*
- * If device doesn't need nskb->dst, release it right now while
- * its hot in this cpu cache
- */
- if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
- skb_dst_drop(nskb);
-
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(nskb, dev);
} while (skb->next);
out_kfree_gso_skb:
- if (likely(skb->next == NULL))
+ if (likely(skb->next == NULL)) {
skb->destructor = DEV_GSO_CB(skb)->destructor;
+ consume_skb(skb);
+ return rc;
+ }
out_kfree_skb:
kfree_skb(skb);
out:
*/
if (shinfo->gso_size) {
unsigned int hdr_len;
+ u16 gso_segs = shinfo->gso_segs;
/* mac layer + network layer */
hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
hdr_len += tcp_hdrlen(skb);
else
hdr_len += sizeof(struct udphdr);
- qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len;
+
+ if (shinfo->gso_type & SKB_GSO_DODGY)
+ gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
+ shinfo->gso_size);
+
+ qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len;
}
}
return 0;
}
+#ifdef CONFIG_NET_FLOW_LIMIT
+int netdev_flow_limit_table_len __read_mostly = (1 << 12);
+#endif
+
+static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
+{
+#ifdef CONFIG_NET_FLOW_LIMIT
+ struct sd_flow_limit *fl;
+ struct softnet_data *sd;
+ unsigned int old_flow, new_flow;
+
+ if (qlen < (netdev_max_backlog >> 1))
+ return false;
+
+ sd = &__get_cpu_var(softnet_data);
+
+ rcu_read_lock();
+ fl = rcu_dereference(sd->flow_limit);
+ if (fl) {
+ new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+ old_flow = fl->history[fl->history_head];
+ fl->history[fl->history_head] = new_flow;
+
+ fl->history_head++;
+ fl->history_head &= FLOW_LIMIT_HISTORY - 1;
+
+ if (likely(fl->buckets[old_flow]))
+ fl->buckets[old_flow]--;
+
+ if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) {
+ fl->count++;
+ rcu_read_unlock();
+ return true;
+ }
+ }
+ rcu_read_unlock();
+#endif
+ return false;
+}
+
/*
* enqueue_to_backlog is called to queue an skb to a per CPU backlog
* queue (may be a remote CPU queue).
{
struct softnet_data *sd;
unsigned long flags;
+ unsigned int qlen;
sd = &per_cpu(softnet_data, cpu);
local_irq_save(flags);
rps_lock(sd);
- if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
+ qlen = skb_queue_len(&sd->input_pkt_queue);
+ if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
* netdev_rx_handler_unregister - unregister receive handler
* @dev: device to unregister a handler from
*
- * Unregister a receive hander from a device.
+ * Unregister a receive handler from a device.
*
* The caller must hold the rtnl_mutex.
*/
case __constant_htons(ETH_P_IP):
case __constant_htons(ETH_P_IPV6):
case __constant_htons(ETH_P_8021Q):
+ case __constant_htons(ETH_P_8021AD):
return true;
default:
return false;
__this_cpu_inc(softnet_data.processed);
- if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
+ if (skb->protocol == cpu_to_be16(ETH_P_8021Q) ||
+ skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
skb = vlan_untag(skb);
if (unlikely(!skb))
goto unlock;
NAPI_GRO_CB(skb)->frag0 = NULL;
NAPI_GRO_CB(skb)->frag0_len = 0;
- if (skb->mac_header == skb->tail &&
+ 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);
}
EXPORT_SYMBOL(napi_complete);
+/* must be called under rcu_read_lock(), as we dont take a reference */
+struct napi_struct *napi_by_id(unsigned int napi_id)
+{
+ unsigned int hash = napi_id % HASH_SIZE(napi_hash);
+ struct napi_struct *napi;
+
+ hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node)
+ if (napi->napi_id == napi_id)
+ return napi;
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(napi_by_id);
+
+void napi_hash_add(struct napi_struct *napi)
+{
+ if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) {
+
+ spin_lock(&napi_hash_lock);
+
+ /* 0 is not a valid id, we also skip an id that is taken
+ * we expect both events to be extremely rare
+ */
+ napi->napi_id = 0;
+ while (!napi->napi_id) {
+ napi->napi_id = ++napi_gen_id;
+ if (napi_by_id(napi->napi_id))
+ napi->napi_id = 0;
+ }
+
+ hlist_add_head_rcu(&napi->napi_hash_node,
+ &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+
+ spin_unlock(&napi_hash_lock);
+ }
+}
+EXPORT_SYMBOL_GPL(napi_hash_add);
+
+/* Warning : caller is responsible to make sure rcu grace period
+ * is respected before freeing memory containing @napi
+ */
+void napi_hash_del(struct napi_struct *napi)
+{
+ spin_lock(&napi_hash_lock);
+
+ if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state))
+ hlist_del_rcu(&napi->napi_hash_node);
+
+ spin_unlock(&napi_hash_lock);
+}
+EXPORT_SYMBOL_GPL(napi_hash_del);
+
void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
int (*poll)(struct napi_struct *, int), int weight)
{
napi->gro_list = NULL;
napi->skb = NULL;
napi->poll = poll;
+ if (weight > NAPI_POLL_WEIGHT)
+ pr_err_once("netif_napi_add() called with weight %d on device %s\n",
+ weight, dev->name);
napi->weight = weight;
list_add(&napi->dev_list, &dev->napi_list);
napi->dev = dev;
else
list_add_tail_rcu(&upper->list, &dev->upper_dev_list);
dev_hold(upper_dev);
-
+ call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
return 0;
}
list_del_rcu(&upper->list);
dev_put(upper_dev);
kfree_rcu(upper, rcu);
+ call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev);
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
}
if (dev->flags & IFF_UP &&
- (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE)))
- call_netdevice_notifiers(NETDEV_CHANGE, dev);
+ (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) {
+ struct netdev_notifier_change_info change_info;
+
+ change_info.flags_changed = changes;
+ call_netdevice_notifiers_info(NETDEV_CHANGE, dev,
+ &change_info.info);
+ }
}
/**
features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
}
- /* Fix illegal SG+CSUM combinations. */
- if ((features & NETIF_F_SG) &&
- !(features & NETIF_F_ALL_CSUM)) {
- netdev_dbg(dev,
- "Dropping NETIF_F_SG since no checksum feature.\n");
- features &= ~NETIF_F_SG;
- }
-
/* TSO requires that SG is present as well. */
if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) {
netdev_dbg(dev, "Dropping TSO features since no SG feature.\n");
features &= ~NETIF_F_ALL_TSO;
}
+ if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) &&
+ !(features & NETIF_F_IP_CSUM)) {
+ netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n");
+ features &= ~NETIF_F_TSO;
+ features &= ~NETIF_F_TSO_ECN;
+ }
+
+ if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) &&
+ !(features & NETIF_F_IPV6_CSUM)) {
+ netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n");
+ features &= ~NETIF_F_TSO6;
+ }
+
/* TSO ECN requires that TSO is present as well. */
if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN)
features &= ~NETIF_F_TSO_ECN;
#endif
}
+static void netif_free_tx_queues(struct net_device *dev)
+{
+ if (is_vmalloc_addr(dev->_tx))
+ vfree(dev->_tx);
+ else
+ kfree(dev->_tx);
+}
+
static int netif_alloc_netdev_queues(struct net_device *dev)
{
unsigned int count = dev->num_tx_queues;
struct netdev_queue *tx;
+ size_t sz = count * sizeof(*tx);
- BUG_ON(count < 1);
-
- tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
- if (!tx)
- return -ENOMEM;
+ BUG_ON(count < 1 || count > 0xffff);
+ tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+ if (!tx) {
+ tx = vzalloc(sz);
+ if (!tx)
+ return -ENOMEM;
+ }
dev->_tx = tx;
netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
}
}
- if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_FILTER) &&
+ if (((dev->hw_features | dev->features) &
+ NETIF_F_HW_VLAN_CTAG_FILTER) &&
(!dev->netdev_ops->ndo_vlan_rx_add_vid ||
!dev->netdev_ops->ndo_vlan_rx_kill_vid)) {
netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n");
*/
dev->vlan_features |= NETIF_F_HIGHDMA;
+ /* Make NETIF_F_SG inheritable to tunnel devices.
+ */
+ dev->hw_enc_features |= NETIF_F_SG;
+
+ /* Make NETIF_F_SG inheritable to MPLS.
+ */
+ dev->mpls_features |= NETIF_F_SG;
+
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
free_pcpu:
free_percpu(dev->pcpu_refcnt);
- kfree(dev->_tx);
+ netif_free_tx_queues(dev);
#ifdef CONFIG_RPS
kfree(dev->_rx);
#endif
release_net(dev_net(dev));
- kfree(dev->_tx);
+ netif_free_tx_queues(dev);
#ifdef CONFIG_RPS
kfree(dev->_rx);
#endif
}
EXPORT_SYMBOL(netdev_increment_features);
-static struct hlist_head *netdev_create_hash(void)
+static struct hlist_head * __net_init netdev_create_hash(void)
{
int i;
struct hlist_head *hash;
sd->backlog.weight = weight_p;
sd->backlog.gro_list = NULL;
sd->backlog.gro_count = 0;
+
+#ifdef CONFIG_NET_FLOW_LIMIT
+ sd->flow_limit = NULL;
+#endif
}
dev_boot_phase = 0;
projects / ~andy / linux / blobdiff