#include <linux/pci.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
+#include <linux/if_tunnel.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
+#include <linux/net_tstamp.h>
#include "net-sysfs.h"
return 0;
while (*name) {
- if (*name == '/' || isspace(*name))
+ if (*name == '/' || *name == ':' || isspace(*name))
return 0;
name++;
}
*/
int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
{
+ char *new_ifalias;
+
ASSERT_RTNL();
if (len >= IFALIASZ)
return 0;
}
- dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
- if (!dev->ifalias)
+ new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
+ if (!new_ifalias)
return -ENOMEM;
+ dev->ifalias = new_ifalias;
strlcpy(dev->ifalias, alias, len+1);
return len;
net_dmaengine_get();
dev_set_rx_mode(dev);
dev_activate(dev);
+ add_device_randomness(dev->dev_addr, dev->addr_len);
}
return ret;
for_each_net(net) {
for_each_netdev(net, dev) {
if (dev == last)
- break;
+ goto outroll;
if (dev->flags & IFF_UP) {
nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
}
}
+outroll:
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
* 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;
}
__net_timestamp(skb);
}
+static int net_hwtstamp_validate(struct ifreq *ifr)
+{
+ struct hwtstamp_config cfg;
+ enum hwtstamp_tx_types tx_type;
+ enum hwtstamp_rx_filters rx_filter;
+ int tx_type_valid = 0;
+ int rx_filter_valid = 0;
+
+ if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+ return -EFAULT;
+
+ if (cfg.flags) /* reserved for future extensions */
+ return -EINVAL;
+
+ tx_type = cfg.tx_type;
+ rx_filter = cfg.rx_filter;
+
+ switch (tx_type) {
+ case HWTSTAMP_TX_OFF:
+ case HWTSTAMP_TX_ON:
+ case HWTSTAMP_TX_ONESTEP_SYNC:
+ tx_type_valid = 1;
+ break;
+ }
+
+ switch (rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ case HWTSTAMP_FILTER_ALL:
+ case HWTSTAMP_FILTER_SOME:
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ rx_filter_valid = 1;
+ break;
+ }
+
+ if (!tx_type_valid || !rx_filter_valid)
+ return -ERANGE;
+
+ return 0;
+}
+
static inline bool is_skb_forwardable(struct net_device *dev,
struct sk_buff *skb)
{
kfree_skb(skb);
return NET_RX_DROP;
}
- skb_set_dev(skb, dev);
+ skb->dev = dev;
+ skb_dst_drop(skb);
skb->tstamp.tv64 = 0;
skb->pkt_type = PACKET_HOST;
skb->protocol = eth_type_trans(skb, dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+ skb->mark = 0;
+ secpath_reset(skb);
+ nf_reset(skb);
+ nf_reset_trace(skb);
return netif_rx(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
+static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
+{
+ if (!ptype->af_packet_priv || !skb->sk)
+ return false;
+
+ if (ptype->id_match)
+ return ptype->id_match(ptype, skb->sk);
+ else if ((struct sock *)ptype->af_packet_priv == skb->sk)
+ return true;
+
+ return false;
+}
+
/*
* Support routine. Sends outgoing frames to any network
* taps currently in use.
* they originated from - MvS (miquels@drinkel.ow.org)
*/
if ((ptype->dev == dev || !ptype->dev) &&
- (ptype->af_packet_priv == NULL ||
- (struct sock *)ptype->af_packet_priv != skb->sk)) {
+ (!skb_loop_sk(ptype, skb))) {
if (pt_prev) {
deliver_skb(skb2, pt_prev, skb->dev);
pt_prev = ptype;
}
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 */
-
/*
* Invalidate hardware checksum when packet is to be mangled, and
* complete checksum manually on outgoing path.
#ifdef CONFIG_HIGHMEM
int i;
if (!(dev->features & NETIF_F_HIGHDMA)) {
- for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
- if (PageHighMem(skb_shinfo(skb)->frags[i].page))
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ if (PageHighMem(skb_frag_page(frag)))
return 1;
+ }
}
if (PCI_DMA_BUS_IS_PHYS) {
if (!pdev)
return 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
- dma_addr_t addr = page_to_phys(skb_shinfo(skb)->frags[i].page);
+ skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+ dma_addr_t addr = page_to_phys(skb_frag_page(frag));
if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
return 1;
}
return 0;
}
-/*
- * Try to orphan skb early, right before transmission by the device.
- * We cannot orphan skb if tx timestamp is requested or the sk-reference
- * is needed on driver level for other reasons, e.g. see net/can/raw.c
- */
-static inline void skb_orphan_try(struct sk_buff *skb)
-{
- struct sock *sk = skb->sk;
-
- if (sk && !skb_shinfo(skb)->tx_flags) {
- /* skb_tx_hash() wont be able to get sk.
- * We copy sk_hash into skb->rxhash
- */
- if (!skb->rxhash)
- skb->rxhash = sk->sk_hash;
- skb_orphan(skb);
- }
-}
-
static bool can_checksum_protocol(unsigned long features, __be16 protocol)
{
return ((features & NETIF_F_GEN_CSUM) ||
static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features)
{
- if (!can_checksum_protocol(features, protocol)) {
+ 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)) {
__be16 protocol = skb->protocol;
u32 features = skb->dev->features;
- if (protocol == htons(ETH_P_8021Q)) {
- 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);
+ if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
+ features &= ~NETIF_F_GSO_MASK;
+
+ if (!vlan_tx_tag_present(skb)) {
+ if (unlikely(protocol == htons(ETH_P_8021Q))) {
+ struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
+ protocol = veh->h_vlan_encapsulated_proto;
+ } else {
+ return harmonize_features(skb, protocol, features);
+ }
}
features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX);
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
- skb_orphan_try(skb);
-
features = netif_skb_features(skb);
if (vlan_tx_tag_present(skb) &&
if (skb->sk && skb->sk->sk_hash)
hash = skb->sk->sk_hash;
else
- hash = (__force u16) skb->protocol ^ skb->rxhash;
+ hash = (__force u16) skb->protocol;
hash = jhash_1word(hash, hashrnd);
return (u16) (((u64) hash * qcount) >> 32) + qoffset;
/*
* __skb_get_rxhash: calculate a flow hash based on src/dst addresses
- * and src/dst port numbers. Returns a non-zero hash number on success
- * and 0 on failure.
+ * 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.
*/
-__u32 __skb_get_rxhash(struct sk_buff *skb)
+void __skb_get_rxhash(struct sk_buff *skb)
{
int nhoff, hash = 0, poff;
const struct ipv6hdr *ip6;
const struct iphdr *ip;
+ const struct vlan_hdr *vlan;
u8 ip_proto;
- u32 addr1, addr2, ihl;
+ u32 addr1, addr2;
+ u16 proto;
union {
u32 v32;
u16 v16[2];
} ports;
nhoff = skb_network_offset(skb);
+ proto = skb->protocol;
- switch (skb->protocol) {
+again:
+ switch (proto) {
case __constant_htons(ETH_P_IP):
+ip:
if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
goto done;
ip = (const struct iphdr *) (skb->data + nhoff);
+ if (ip->ihl < 5)
+ goto done;
if (ip_is_fragment(ip))
ip_proto = 0;
else
ip_proto = ip->protocol;
addr1 = (__force u32) ip->saddr;
addr2 = (__force u32) ip->daddr;
- ihl = ip->ihl;
+ nhoff += ip->ihl * 4;
break;
case __constant_htons(ETH_P_IPV6):
+ipv6:
if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
goto done;
ip_proto = ip6->nexthdr;
addr1 = (__force u32) ip6->saddr.s6_addr32[3];
addr2 = (__force u32) ip6->daddr.s6_addr32[3];
- ihl = (40 >> 2);
+ nhoff += 40;
break;
+ case __constant_htons(ETH_P_8021Q):
+ if (!pskb_may_pull(skb, sizeof(*vlan) + nhoff))
+ goto done;
+ vlan = (const struct vlan_hdr *) (skb->data + nhoff);
+ proto = vlan->h_vlan_encapsulated_proto;
+ nhoff += sizeof(*vlan);
+ goto again;
+ case __constant_htons(ETH_P_PPP_SES):
+ if (!pskb_may_pull(skb, PPPOE_SES_HLEN + nhoff))
+ goto done;
+ proto = *((__be16 *) (skb->data + nhoff +
+ sizeof(struct pppoe_hdr)));
+ nhoff += PPPOE_SES_HLEN;
+ switch (proto) {
+ case __constant_htons(PPP_IP):
+ goto ip;
+ case __constant_htons(PPP_IPV6):
+ goto ipv6;
+ default:
+ goto done;
+ }
default:
goto done;
}
+ switch (ip_proto) {
+ case IPPROTO_GRE:
+ if (pskb_may_pull(skb, nhoff + 16)) {
+ u8 *h = skb->data + nhoff;
+ __be16 flags = *(__be16 *)h;
+
+ /*
+ * Only look inside GRE if version zero and no
+ * routing
+ */
+ if (!(flags & (GRE_VERSION|GRE_ROUTING))) {
+ proto = *(__be16 *)(h + 2);
+ nhoff += 4;
+ if (flags & GRE_CSUM)
+ nhoff += 4;
+ if (flags & GRE_KEY)
+ nhoff += 4;
+ if (flags & GRE_SEQ)
+ nhoff += 4;
+ goto again;
+ }
+ }
+ break;
+ case IPPROTO_IPIP:
+ goto again;
+ default:
+ break;
+ }
+
ports.v32 = 0;
poff = proto_ports_offset(ip_proto);
if (poff >= 0) {
- nhoff += ihl * 4 + poff;
+ nhoff += poff;
if (pskb_may_pull(skb, nhoff + 4)) {
ports.v32 = * (__force u32 *) (skb->data + nhoff);
- if (ports.v16[1] < ports.v16[0])
- swap(ports.v16[0], ports.v16[1]);
+ skb->l4_rxhash = 1;
}
}
/* get a consistent hash (same value on both flow directions) */
- if (addr2 < addr1)
+ if (addr2 < addr1 ||
+ (addr2 == addr1 &&
+ ports.v16[1] < ports.v16[0])) {
swap(addr1, addr2);
-
+ swap(ports.v16[0], ports.v16[1]);
+ }
hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
if (!hash)
hash = 1;
done:
- return hash;
+ skb->rxhash = hash;
}
EXPORT_SYMBOL(__skb_get_rxhash);
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow *rflow, u16 next_cpu)
{
- u16 tcpu;
-
- tcpu = rflow->cpu = next_cpu;
- if (tcpu != RPS_NO_CPU) {
+ if (next_cpu != RPS_NO_CPU) {
#ifdef CONFIG_RFS_ACCEL
struct netdev_rx_queue *rxqueue;
struct rps_dev_flow_table *flow_table;
goto out;
old_rflow = rflow;
rflow = &flow_table->flows[flow_id];
- rflow->cpu = next_cpu;
rflow->filter = rc;
if (old_rflow->filter == rflow->filter)
old_rflow->filter = RPS_NO_FILTER;
out:
#endif
rflow->last_qtail =
- per_cpu(softnet_data, tcpu).input_queue_head;
+ per_cpu(softnet_data, next_cpu).input_queue_head;
}
+ rflow->cpu = next_cpu;
return rflow;
}
map = rcu_dereference(rxqueue->rps_map);
if (map) {
if (map->len == 1 &&
- !rcu_dereference_raw(rxqueue->rps_flow_table)) {
+ !rcu_access_pointer(rxqueue->rps_flow_table)) {
tcpu = map->cpus[0];
if (cpu_online(tcpu))
cpu = tcpu;
goto done;
}
- } else if (!rcu_dereference_raw(rxqueue->rps_flow_table)) {
+ } else if (!rcu_access_pointer(rxqueue->rps_flow_table)) {
goto done;
}
if (unlikely(tcpu != next_cpu) &&
(tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
((int)(per_cpu(softnet_data, tcpu).input_queue_head -
- rflow->last_qtail)) >= 0))
+ rflow->last_qtail)) >= 0)) {
+ tcpu = next_cpu;
rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
+ }
if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
*rflowp = rflow;
local_irq_save(flags);
rps_lock(sd);
+ if (!netif_running(skb->dev))
+ goto drop;
if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
goto enqueue;
}
+drop:
sd->dropped++;
rps_unlock(sd);
if (dev->rx_handler)
return -EBUSY;
+ /* Note: rx_handler_data must be set before rx_handler */
rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
rcu_assign_pointer(dev->rx_handler, rx_handler);
{
ASSERT_RTNL();
- rcu_assign_pointer(dev->rx_handler, NULL);
- rcu_assign_pointer(dev->rx_handler_data, NULL);
+ RCU_INIT_POINTER(dev->rx_handler, NULL);
+ /* a reader seeing a non NULL rx_handler in a rcu_read_lock()
+ * section has a guarantee to see a non NULL rx_handler_data
+ * as well.
+ */
+ synchronize_net();
+ RCU_INIT_POINTER(dev->rx_handler_data, NULL);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
pt_prev = NULL;
- rcu_read_lock();
-
another_round:
__this_cpu_inc(softnet_data.processed);
ncls:
#endif
+ if (vlan_tx_tag_present(skb)) {
+ if (pt_prev) {
+ ret = deliver_skb(skb, pt_prev, orig_dev);
+ pt_prev = NULL;
+ }
+ if (vlan_do_receive(&skb))
+ goto another_round;
+ else if (unlikely(!skb))
+ goto out;
+ }
+
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (rx_handler) {
if (pt_prev) {
}
switch (rx_handler(&skb)) {
case RX_HANDLER_CONSUMED:
+ ret = NET_RX_SUCCESS;
goto out;
case RX_HANDLER_ANOTHER:
goto another_round;
}
}
- if (vlan_tx_tag_present(skb)) {
- if (pt_prev) {
- ret = deliver_skb(skb, pt_prev, orig_dev);
- pt_prev = NULL;
- }
- if (vlan_do_receive(&skb)) {
- ret = __netif_receive_skb(skb);
- goto out;
- } else if (unlikely(!skb))
- goto out;
- }
+ if (vlan_tx_nonzero_tag_present(skb))
+ skb->pkt_type = PACKET_OTHERHOST;
/* deliver only exact match when indicated */
null_or_dev = deliver_exact ? skb->dev : NULL;
}
out:
- rcu_read_unlock();
return ret;
}
*/
int netif_receive_skb(struct sk_buff *skb)
{
+ int ret;
+
if (netdev_tstamp_prequeue)
net_timestamp_check(skb);
if (skb_defer_rx_timestamp(skb))
return NET_RX_SUCCESS;
+ rcu_read_lock();
+
#ifdef CONFIG_RPS
{
struct rps_dev_flow voidflow, *rflow = &voidflow;
- int cpu, ret;
-
- rcu_read_lock();
-
- cpu = get_rps_cpu(skb->dev, skb, &rflow);
+ int cpu = get_rps_cpu(skb->dev, skb, &rflow);
if (cpu >= 0) {
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
- } else {
- rcu_read_unlock();
- ret = __netif_receive_skb(skb);
+ return ret;
}
-
- return ret;
}
-#else
- return __netif_receive_skb(skb);
#endif
+ ret = __netif_receive_skb(skb);
+ rcu_read_unlock();
+ return ret;
}
EXPORT_SYMBOL(netif_receive_skb);
skb->data_len -= grow;
skb_shinfo(skb)->frags[0].page_offset += grow;
- skb_shinfo(skb)->frags[0].size -= grow;
+ skb_frag_size_sub(&skb_shinfo(skb)->frags[0], grow);
- if (unlikely(!skb_shinfo(skb)->frags[0].size)) {
- put_page(skb_shinfo(skb)->frags[0].page);
+ if (unlikely(!skb_frag_size(&skb_shinfo(skb)->frags[0]))) {
+ skb_frag_unref(skb, 0);
memmove(skb_shinfo(skb)->frags,
skb_shinfo(skb)->frags + 1,
--skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff *p;
+ unsigned int maclen = skb->dev->hard_header_len;
for (p = napi->gro_list; p; p = p->next) {
unsigned long diffs;
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= p->vlan_tci ^ skb->vlan_tci;
- diffs |= compare_ether_header(skb_mac_header(p),
- skb_gro_mac_header(skb));
+ if (maclen == ETH_HLEN)
+ diffs |= compare_ether_header(skb_mac_header(p),
+ skb_gro_mac_header(skb));
+ else if (!diffs)
+ diffs = memcmp(skb_mac_header(p),
+ skb_gro_mac_header(skb),
+ maclen);
NAPI_GRO_CB(p)->same_flow = !diffs;
NAPI_GRO_CB(p)->flush = 0;
}
NAPI_GRO_CB(skb)->frag0_len = 0;
if (skb->mac_header == skb->tail &&
- !PageHighMem(skb_shinfo(skb)->frags[0].page)) {
+ !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
NAPI_GRO_CB(skb)->frag0 =
- page_address(skb_shinfo(skb)->frags[0].page) +
- skb_shinfo(skb)->frags[0].page_offset;
- NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size;
+ skb_frag_address(&skb_shinfo(skb)->frags[0]);
+ NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]);
}
}
EXPORT_SYMBOL(skb_gro_reset_offset);
static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
{
__skb_pull(skb, skb_headlen(skb));
- skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb));
+ /* restore the reserve we had after netdev_alloc_skb_ip_align() */
+ skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb));
skb->vlan_tci = 0;
skb->dev = napi->dev;
skb->skb_iif = 0;
+ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
napi->skb = skb;
}
unsigned int qlen;
while ((skb = __skb_dequeue(&sd->process_queue))) {
+ rcu_read_lock();
local_irq_enable();
__netif_receive_skb(skb);
+ rcu_read_unlock();
local_irq_disable();
input_queue_head_incr(sd);
if (++work >= quota) {
}
#ifdef CONFIG_PROC_FS
+
+#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, loff_t *pos)
+{
+ struct net *net = seq_file_net(seq);
+ struct net_device *dev;
+ struct hlist_node *p;
+ struct hlist_head *h;
+ unsigned int count = 0, offset = get_offset(*pos);
+
+ h = &net->dev_name_head[get_bucket(*pos)];
+ hlist_for_each_entry_rcu(dev, p, h, name_hlist) {
+ if (++count == offset)
+ return dev;
+ }
+
+ return NULL;
+}
+
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
+{
+ struct net_device *dev;
+ unsigned int bucket;
+
+ do {
+ dev = dev_from_same_bucket(seq, pos);
+ if (dev)
+ return dev;
+
+ bucket = get_bucket(*pos) + 1;
+ *pos = set_bucket_offset(bucket, 1);
+ } while (bucket < NETDEV_HASHENTRIES);
+
+ return NULL;
+}
+
/*
* This is invoked by the /proc filesystem handler to display a device
* in detail.
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(RCU)
{
- struct net *net = seq_file_net(seq);
- loff_t off;
- struct net_device *dev;
-
rcu_read_lock();
if (!*pos)
return SEQ_START_TOKEN;
- off = 1;
- for_each_netdev_rcu(net, dev)
- if (off++ == *pos)
- return dev;
+ if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
+ return NULL;
- return NULL;
+ return dev_from_bucket(seq, pos);
}
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct net_device *dev = v;
-
- if (v == SEQ_START_TOKEN)
- dev = first_net_device_rcu(seq_file_net(seq));
- else
- dev = next_net_device_rcu(dev);
-
++*pos;
- return dev;
+ return dev_from_bucket(seq, pos);
}
void dev_seq_stop(struct seq_file *seq, void *v)
{
const struct net_device_ops *ops = dev->netdev_ops;
- if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ if (ops->ndo_change_rx_flags)
ops->ndo_change_rx_flags(dev, flags);
}
if (!netif_device_present(dev))
return;
- if (ops->ndo_set_rx_mode)
- ops->ndo_set_rx_mode(dev);
- else {
+ if (!(dev->priv_flags & IFF_UNICAST_FLT)) {
/* Unicast addresses changes may only happen under the rtnl,
* therefore calling __dev_set_promiscuity here is safe.
*/
__dev_set_promiscuity(dev, -1);
dev->uc_promisc = false;
}
-
- if (ops->ndo_set_multicast_list)
- ops->ndo_set_multicast_list(dev);
}
+
+ if (ops->ndo_set_rx_mode)
+ ops->ndo_set_rx_mode(dev);
}
void dev_set_rx_mode(struct net_device *dev)
netif_addr_unlock_bh(dev);
}
-/**
- * dev_ethtool_get_settings - call device's ethtool_ops::get_settings()
- * @dev: device
- * @cmd: memory area for ethtool_ops::get_settings() result
- *
- * The cmd arg is initialized properly (cleared and
- * ethtool_cmd::cmd field set to ETHTOOL_GSET).
- *
- * Return device's ethtool_ops::get_settings() result value or
- * -EOPNOTSUPP when device doesn't expose
- * ethtool_ops::get_settings() operation.
- */
-int dev_ethtool_get_settings(struct net_device *dev,
- struct ethtool_cmd *cmd)
-{
- if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings)
- return -EOPNOTSUPP;
-
- memset(cmd, 0, sizeof(struct ethtool_cmd));
- cmd->cmd = ETHTOOL_GSET;
- return dev->ethtool_ops->get_settings(dev, cmd);
-}
-EXPORT_SYMBOL(dev_ethtool_get_settings);
-
/**
* dev_get_flags - get flags reported to userspace
* @dev: device
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);
return -EOPNOTSUPP;
case SIOCADDMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ if (!ops->ndo_set_rx_mode ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
case SIOCDELMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ if (!ops->ndo_set_rx_mode ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
ifr->ifr_newname[IFNAMSIZ-1] = '\0';
return dev_change_name(dev, ifr->ifr_newname);
+ case SIOCSHWTSTAMP:
+ err = net_hwtstamp_validate(ifr);
+ if (err)
+ return err;
+ /* fall through */
+
/*
* Unknown or private ioctl
*/
unlist_netdevice(dev);
dev->reg_state = NETREG_UNREGISTERING;
+ on_each_cpu(flush_backlog, dev, 1);
}
synchronize_net();
dev = list_first_entry(head, struct net_device, unreg_list);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
- rcu_barrier();
+ synchronize_net();
list_for_each_entry(dev, head, unreg_list)
dev_put(dev);
netdev_err(dev,
"set_features() failed (%d); wanted 0x%08x, left 0x%08x\n",
err, features, dev->features);
- return -1;
+ return 0;
}
if (!err)
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);
__rtnl_unlock();
+ /* Wait for rcu callbacks to finish before attempting to drain
+ * the device list. This usually avoids a 250ms wait.
+ */
+ if (!list_empty(&list))
+ rcu_barrier();
+
while (!list_empty(&list)) {
struct net_device *dev
= list_first_entry(&list, struct net_device, todo_list);
dev->reg_state = NETREG_UNREGISTERED;
- on_each_cpu(flush_backlog, dev, 1);
-
netdev_wait_allrefs(dev);
/* paranoia */
BUG_ON(netdev_refcnt_read(dev));
- WARN_ON(rcu_dereference_raw(dev->ip_ptr));
- WARN_ON(rcu_dereference_raw(dev->ip6_ptr));
+ WARN_ON(rcu_access_pointer(dev->ip_ptr));
+ WARN_ON(rcu_access_pointer(dev->ip6_ptr));
WARN_ON(dev->dn_ptr);
if (dev->destructor)
dev_net_set(dev, &init_net);
dev->gso_max_size = GSO_MAX_SIZE;
+ dev->gso_max_segs = GSO_MAX_SEGS;
INIT_LIST_HEAD(&dev->napi_list);
INIT_LIST_HEAD(&dev->unreg_list);
kfree(dev->_rx);
#endif
- kfree(rcu_dereference_raw(dev->ingress_queue));
+ kfree(rcu_dereference_protected(dev->ingress_queue, 1));
/* Flush device addresses */
dev_addr_flush(dev);
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
+ rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
/*
* Flush the unicast and multicast chains
oldsd->output_queue = NULL;
oldsd->output_queue_tailp = &oldsd->output_queue;
}
- /* Append NAPI poll list from offline CPU. */
- if (!list_empty(&oldsd->poll_list)) {
- list_splice_init(&oldsd->poll_list, &sd->poll_list);
- raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ /* Append NAPI poll list from offline CPU, with one exception :
+ * process_backlog() must be called by cpu owning percpu backlog.
+ * We properly handle process_queue & input_pkt_queue later.
+ */
+ while (!list_empty(&oldsd->poll_list)) {
+ struct napi_struct *napi = list_first_entry(&oldsd->poll_list,
+ struct napi_struct,
+ poll_list);
+
+ list_del_init(&napi->poll_list);
+ if (napi->poll == process_backlog)
+ napi->state = 0;
+ else
+ ____napi_schedule(sd, napi);
}
raise_softirq_irqoff(NET_TX_SOFTIRQ);
netif_rx(skb);
input_queue_head_incr(oldsd);
}
- while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
+ while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
input_queue_head_incr(oldsd);
}
/* 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)
return empty;
}
-static int __netdev_printk(const char *level, const struct net_device *dev,
+int __netdev_printk(const char *level, const struct net_device *dev,
struct va_format *vaf)
{
int r;
return r;
}
+EXPORT_SYMBOL(__netdev_printk);
int netdev_printk(const char *level, const struct net_device *dev,
const char *format, ...)