#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/module.h>
-#include <linux/kallsyms.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#include <linux/in.h>
#include <linux/jhash.h>
#include <linux/random.h>
+#include <trace/napi.h>
#include "net-sysfs.h"
+/* Instead of increasing this, you should create a hash table. */
+#define MAX_GRO_SKBS 8
+
+/* This should be increased if a protocol with a bigger head is added. */
+#define GRO_MAX_HEAD (MAX_HEADER + 128)
+
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
static struct list_head ptype_all __read_mostly; /* Taps */
-#ifdef CONFIG_NET_DMA
-struct net_dma {
- struct dma_client client;
- spinlock_t lock;
- cpumask_t channel_mask;
- struct dma_chan **channels;
-};
-
-static enum dma_state_client
-netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
- enum dma_state state);
-
-static struct net_dma net_dma = {
- .client = {
- .event_callback = netdev_dma_event,
- },
-};
-#endif
-
/*
* The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211,
- ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_VOID,
- ARPHRD_NONE};
+ ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET,
+ ARPHRD_PHONET_PIPE, ARPHRD_VOID, ARPHRD_NONE};
static const char *netdev_lock_name[] =
{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
"_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211",
- "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_VOID",
- "_xmit_NONE"};
+ "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET",
+ "_xmit_PHONET_PIPE", "_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
*/
int dev_open(struct net_device *dev)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int ret = 0;
ASSERT_RTNL();
*/
set_bit(__LINK_STATE_START, &dev->state);
- if (dev->validate_addr)
- ret = dev->validate_addr(dev);
+ if (ops->ndo_validate_addr)
+ ret = ops->ndo_validate_addr(dev);
- if (!ret && dev->open)
- ret = dev->open(dev);
+ if (!ret && ops->ndo_open)
+ ret = ops->ndo_open(dev);
/*
* If it went open OK then:
dev->flags |= IFF_UP;
/*
+ * Enable NET_DMA
+ */
+ net_dmaengine_get();
+
+ /*
* Initialize multicasting status
*/
dev_set_rx_mode(dev);
*/
int dev_close(struct net_device *dev)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
ASSERT_RTNL();
might_sleep();
* We allow it to be called even after a DETACH hot-plug
* event.
*/
- if (dev->stop)
- dev->stop(dev);
+ if (ops->ndo_stop)
+ ops->ndo_stop(dev);
/*
* Device is now down.
*/
call_netdevice_notifiers(NETDEV_DOWN, dev);
+ /*
+ * Shutdown NET_DMA
+ */
+ net_dmaengine_put();
+
return 0;
}
{
struct packet_type *ptype;
+#ifdef CONFIG_NET_CLS_ACT
+ if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS)))
+ net_timestamp(skb);
+#else
net_timestamp(skb);
+#endif
rcu_read_lock();
list_for_each_entry_rcu(ptype, &ptype_all, list) {
{
if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
- netif_stop_queue(dev);
+ netif_tx_stop_all_queues(dev);
}
}
EXPORT_SYMBOL(netif_device_detach);
{
if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
netif_running(dev)) {
- netif_wake_queue(dev);
+ netif_tx_wake_all_queues(dev);
__netdev_watchdog_up(dev);
}
}
((features & NETIF_F_IP_CSUM) &&
protocol == htons(ETH_P_IP)) ||
((features & NETIF_F_IPV6_CSUM) &&
- protocol == htons(ETH_P_IPV6)));
+ protocol == htons(ETH_P_IPV6)) ||
+ ((features & NETIF_F_FCOE_CRC) &&
+ protocol == htons(ETH_P_FCOE)));
}
static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb)
__be16 type = skb->protocol;
int err;
- BUG_ON(skb_shinfo(skb)->frag_list);
-
skb_reset_mac_header(skb);
skb->mac_len = skb->network_header - skb->mac_header;
__skb_pull(skb, skb->mac_len);
- if (WARN_ON(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
+ struct net_device *dev = skb->dev;
+ struct ethtool_drvinfo info = {};
+
+ if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo)
+ dev->ethtool_ops->get_drvinfo(dev, &info);
+
+ WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d "
+ "ip_summed=%d",
+ info.driver, dev ? dev->features : 0L,
+ skb->sk ? skb->sk->sk_route_caps : 0L,
+ skb->len, skb->data_len, skb->ip_summed);
+
if (skb_header_cloned(skb) &&
(err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
return ERR_PTR(err);
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ int rc;
+
if (likely(!skb->next)) {
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
goto gso;
}
- return dev->hard_start_xmit(skb, dev);
+ /*
+ * If device doesnt need skb->dst, release it right now while
+ * its hot in this cpu cache
+ */
+ if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
+ skb_dst_drop(skb);
+
+ rc = ops->ndo_start_xmit(skb, dev);
+ if (rc == 0)
+ txq_trans_update(txq);
+ /*
+ * TODO: if skb_orphan() was called by
+ * dev->hard_start_xmit() (for example, the unmodified
+ * igb driver does that; bnx2 doesn't), then
+ * skb_tx_software_timestamp() will be unable to send
+ * back the time stamp.
+ *
+ * How can this be prevented? Always create another
+ * reference to the socket before calling
+ * dev->hard_start_xmit()? Prevent that skb_orphan()
+ * does anything in dev->hard_start_xmit() by clearing
+ * the skb destructor before the call and restoring it
+ * afterwards, then doing the skb_orphan() ourselves?
+ */
+ return rc;
}
gso:
do {
struct sk_buff *nskb = skb->next;
- int rc;
skb->next = nskb->next;
nskb->next = NULL;
- rc = dev->hard_start_xmit(nskb, dev);
+ rc = ops->ndo_start_xmit(nskb, dev);
if (unlikely(rc)) {
nskb->next = skb->next;
skb->next = nskb;
return rc;
}
+ txq_trans_update(txq);
if (unlikely(netif_tx_queue_stopped(txq) && skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
return 0;
}
-static u32 simple_tx_hashrnd;
-static int simple_tx_hashrnd_initialized = 0;
+static u32 skb_tx_hashrnd;
-static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb)
+u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb)
{
- u32 addr1, addr2, ports;
- u32 hash, ihl;
- u8 ip_proto = 0;
-
- if (unlikely(!simple_tx_hashrnd_initialized)) {
- get_random_bytes(&simple_tx_hashrnd, 4);
- simple_tx_hashrnd_initialized = 1;
- }
+ u32 hash;
- switch (skb->protocol) {
- case htons(ETH_P_IP):
- if (!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)))
- ip_proto = ip_hdr(skb)->protocol;
- addr1 = ip_hdr(skb)->saddr;
- addr2 = ip_hdr(skb)->daddr;
- ihl = ip_hdr(skb)->ihl;
- break;
- case htons(ETH_P_IPV6):
- ip_proto = ipv6_hdr(skb)->nexthdr;
- addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3];
- addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3];
- ihl = (40 >> 2);
- break;
- default:
- return 0;
+ if (skb_rx_queue_recorded(skb)) {
+ hash = skb_get_rx_queue(skb);
+ while (unlikely (hash >= dev->real_num_tx_queues))
+ hash -= dev->real_num_tx_queues;
+ return hash;
}
+ if (skb->sk && skb->sk->sk_hash)
+ hash = skb->sk->sk_hash;
+ else
+ hash = skb->protocol;
- switch (ip_proto) {
- case IPPROTO_TCP:
- case IPPROTO_UDP:
- case IPPROTO_DCCP:
- case IPPROTO_ESP:
- case IPPROTO_AH:
- case IPPROTO_SCTP:
- case IPPROTO_UDPLITE:
- ports = *((u32 *) (skb_network_header(skb) + (ihl * 4)));
- break;
-
- default:
- ports = 0;
- break;
- }
-
- hash = jhash_3words(addr1, addr2, ports, simple_tx_hashrnd);
+ hash = jhash_1word(hash, skb_tx_hashrnd);
return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32);
}
+EXPORT_SYMBOL(skb_tx_hash);
static struct netdev_queue *dev_pick_tx(struct net_device *dev,
struct sk_buff *skb)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
u16 queue_index = 0;
- if (dev->select_queue)
- queue_index = dev->select_queue(dev, skb);
+ if (ops->ndo_select_queue)
+ queue_index = ops->ndo_select_queue(dev, skb);
else if (dev->real_num_tx_queues > 1)
- queue_index = simple_tx_hash(dev, skb);
+ queue_index = skb_tx_hash(dev, skb);
skb_set_queue_mapping(skb, queue_index);
return netdev_get_tx_queue(dev, queue_index);
rcu_read_lock();
- /* Don't receive packets in an exiting network namespace */
- if (!net_alive(dev_net(skb->dev))) {
- kfree_skb(skb);
- goto out;
- }
-
#ifdef CONFIG_NET_CLS_ACT
if (skb->tc_verd & TC_NCLS) {
skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
if (!skb)
goto out;
+ skb_orphan(skb);
+
type = skb->protocol;
list_for_each_entry_rcu(ptype,
&ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) {
}
}
+static int napi_gro_complete(struct sk_buff *skb)
+{
+ struct packet_type *ptype;
+ __be16 type = skb->protocol;
+ struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+ int err = -ENOENT;
+
+ if (NAPI_GRO_CB(skb)->count == 1) {
+ skb_shinfo(skb)->gso_size = 0;
+ goto out;
+ }
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, head, list) {
+ if (ptype->type != type || ptype->dev || !ptype->gro_complete)
+ continue;
+
+ err = ptype->gro_complete(skb);
+ break;
+ }
+ rcu_read_unlock();
+
+ if (err) {
+ WARN_ON(&ptype->list == head);
+ kfree_skb(skb);
+ return NET_RX_SUCCESS;
+ }
+
+out:
+ return netif_receive_skb(skb);
+}
+
+void napi_gro_flush(struct napi_struct *napi)
+{
+ struct sk_buff *skb, *next;
+
+ for (skb = napi->gro_list; skb; skb = next) {
+ next = skb->next;
+ skb->next = NULL;
+ napi_gro_complete(skb);
+ }
+
+ napi->gro_count = 0;
+ napi->gro_list = NULL;
+}
+EXPORT_SYMBOL(napi_gro_flush);
+
+int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+ struct sk_buff **pp = NULL;
+ struct packet_type *ptype;
+ __be16 type = skb->protocol;
+ struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
+ int same_flow;
+ int mac_len;
+ int ret;
+
+ if (!(skb->dev->features & NETIF_F_GRO))
+ goto normal;
+
+ if (skb_is_gso(skb) || skb_shinfo(skb)->frag_list)
+ goto normal;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(ptype, head, list) {
+ if (ptype->type != type || ptype->dev || !ptype->gro_receive)
+ continue;
+
+ skb_set_network_header(skb, skb_gro_offset(skb));
+ mac_len = skb->network_header - skb->mac_header;
+ skb->mac_len = mac_len;
+ NAPI_GRO_CB(skb)->same_flow = 0;
+ NAPI_GRO_CB(skb)->flush = 0;
+ NAPI_GRO_CB(skb)->free = 0;
+
+ pp = ptype->gro_receive(&napi->gro_list, skb);
+ break;
+ }
+ rcu_read_unlock();
+
+ if (&ptype->list == head)
+ goto normal;
+
+ same_flow = NAPI_GRO_CB(skb)->same_flow;
+ ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
+
+ if (pp) {
+ struct sk_buff *nskb = *pp;
+
+ *pp = nskb->next;
+ nskb->next = NULL;
+ napi_gro_complete(nskb);
+ napi->gro_count--;
+ }
+
+ if (same_flow)
+ goto ok;
+
+ if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
+ goto normal;
+
+ napi->gro_count++;
+ NAPI_GRO_CB(skb)->count = 1;
+ skb_shinfo(skb)->gso_size = skb_gro_len(skb);
+ skb->next = napi->gro_list;
+ napi->gro_list = skb;
+ ret = GRO_HELD;
+
+pull:
+ if (skb_headlen(skb) < skb_gro_offset(skb)) {
+ int grow = skb_gro_offset(skb) - skb_headlen(skb);
+
+ BUG_ON(skb->end - skb->tail < grow);
+
+ memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow);
+
+ skb->tail += grow;
+ skb->data_len -= grow;
+
+ skb_shinfo(skb)->frags[0].page_offset += grow;
+ skb_shinfo(skb)->frags[0].size -= grow;
+
+ if (unlikely(!skb_shinfo(skb)->frags[0].size)) {
+ put_page(skb_shinfo(skb)->frags[0].page);
+ memmove(skb_shinfo(skb)->frags,
+ skb_shinfo(skb)->frags + 1,
+ --skb_shinfo(skb)->nr_frags);
+ }
+ }
+
+ok:
+ return ret;
+
+normal:
+ ret = GRO_NORMAL;
+ goto pull;
+}
+EXPORT_SYMBOL(dev_gro_receive);
+
+static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+ struct sk_buff *p;
+
+ if (netpoll_rx_on(skb))
+ return GRO_NORMAL;
+
+ for (p = napi->gro_list; p; p = p->next) {
+ NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev)
+ && !compare_ether_header(skb_mac_header(p),
+ skb_gro_mac_header(skb));
+ NAPI_GRO_CB(p)->flush = 0;
+ }
+
+ return dev_gro_receive(napi, skb);
+}
+
+int napi_skb_finish(int ret, struct sk_buff *skb)
+{
+ int err = NET_RX_SUCCESS;
+
+ switch (ret) {
+ case GRO_NORMAL:
+ return netif_receive_skb(skb);
+
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
+
+ case GRO_MERGED_FREE:
+ kfree_skb(skb);
+ break;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(napi_skb_finish);
+
+void skb_gro_reset_offset(struct sk_buff *skb)
+{
+ 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->tail &&
+ !PageHighMem(skb_shinfo(skb)->frags[0].page)) {
+ 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;
+ }
+}
+EXPORT_SYMBOL(skb_gro_reset_offset);
+
+int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+{
+ skb_gro_reset_offset(skb);
+
+ return napi_skb_finish(__napi_gro_receive(napi, skb), skb);
+}
+EXPORT_SYMBOL(napi_gro_receive);
+
+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));
+
+ napi->skb = skb;
+}
+EXPORT_SYMBOL(napi_reuse_skb);
+
+struct sk_buff *napi_get_frags(struct napi_struct *napi)
+{
+ struct net_device *dev = napi->dev;
+ struct sk_buff *skb = napi->skb;
+
+ if (!skb) {
+ skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN);
+ if (!skb)
+ goto out;
+
+ skb_reserve(skb, NET_IP_ALIGN);
+
+ napi->skb = skb;
+ }
+
+out:
+ return skb;
+}
+EXPORT_SYMBOL(napi_get_frags);
+
+int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
+{
+ int err = NET_RX_SUCCESS;
+
+ switch (ret) {
+ case GRO_NORMAL:
+ case GRO_HELD:
+ skb->protocol = eth_type_trans(skb, napi->dev);
+
+ if (ret == GRO_NORMAL)
+ return netif_receive_skb(skb);
+
+ skb_gro_pull(skb, -ETH_HLEN);
+ break;
+
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
+
+ case GRO_MERGED_FREE:
+ napi_reuse_skb(napi, skb);
+ break;
+ }
+
+ return err;
+}
+EXPORT_SYMBOL(napi_frags_finish);
+
+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;
+ }
+ }
+
+ 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;
+}
+EXPORT_SYMBOL(napi_frags_skb);
+
+int napi_gro_frags(struct napi_struct *napi)
+{
+ struct sk_buff *skb = napi_frags_skb(napi);
+
+ if (!skb)
+ return NET_RX_DROP;
+
+ return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
+}
+EXPORT_SYMBOL(napi_gro_frags);
+
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
}
EXPORT_SYMBOL(__napi_schedule);
+void __napi_complete(struct napi_struct *n)
+{
+ BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
+ BUG_ON(n->gro_list);
+
+ list_del(&n->poll_list);
+ smp_mb__before_clear_bit();
+ clear_bit(NAPI_STATE_SCHED, &n->state);
+}
+EXPORT_SYMBOL(__napi_complete);
+
+void napi_complete(struct napi_struct *n)
+{
+ unsigned long flags;
+
+ /*
+ * don't let napi dequeue from the cpu poll list
+ * just in case its running on a different cpu
+ */
+ if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
+ return;
+
+ napi_gro_flush(n);
+ local_irq_save(flags);
+ __napi_complete(n);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(napi_complete);
+
+void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
+ int (*poll)(struct napi_struct *, int), int weight)
+{
+ INIT_LIST_HEAD(&napi->poll_list);
+ napi->gro_count = 0;
+ napi->gro_list = NULL;
+ napi->skb = NULL;
+ napi->poll = poll;
+ napi->weight = weight;
+ list_add(&napi->dev_list, &dev->napi_list);
+ napi->dev = dev;
+#ifdef CONFIG_NETPOLL
+ spin_lock_init(&napi->poll_lock);
+ napi->poll_owner = -1;
+#endif
+ set_bit(NAPI_STATE_SCHED, &napi->state);
+}
+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);
+ }
+
+ napi->gro_list = NULL;
+ napi->gro_count = 0;
+}
+EXPORT_SYMBOL(netif_napi_del);
+
static void net_rx_action(struct softirq_action *h)
{
* accidently calling ->poll() when NAPI is not scheduled.
*/
work = 0;
- if (test_bit(NAPI_STATE_SCHED, &n->state))
+ if (test_bit(NAPI_STATE_SCHED, &n->state)) {
work = n->poll(n, weight);
+ trace_napi_poll(n);
+ }
WARN_ON_ONCE(work > weight);
* There may not be any more sk_buffs coming right now, so push
* any pending DMA copies to hardware
*/
- if (!cpus_empty(net_dma.channel_mask)) {
- int chan_idx;
- for_each_cpu_mask_nr(chan_idx, net_dma.channel_mask) {
- struct dma_chan *chan = net_dma.channels[chan_idx];
- if (chan)
- dma_async_memcpy_issue_pending(chan);
- }
- }
+ dma_issue_pending_all();
#endif
return;
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
- struct net_device_stats *stats = dev->get_stats(dev);
+ const struct net_device_stats *stats = dev_get_stats(dev);
seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
rcu_read_unlock();
}
-static void ptype_seq_decode(struct seq_file *seq, void *sym)
-{
-#ifdef CONFIG_KALLSYMS
- unsigned long offset = 0, symsize;
- const char *symname;
- char *modname;
- char namebuf[128];
-
- symname = kallsyms_lookup((unsigned long)sym, &symsize, &offset,
- &modname, namebuf);
-
- if (symname) {
- char *delim = ":";
-
- if (!modname)
- modname = delim = "";
- seq_printf(seq, "%s%s%s%s+0x%lx", delim, modname, delim,
- symname, offset);
- return;
- }
-#endif
-
- seq_printf(seq, "[%p]", sym);
-}
-
static int ptype_seq_show(struct seq_file *seq, void *v)
{
struct packet_type *pt = v;
else
seq_printf(seq, "%04x", ntohs(pt->type));
- seq_printf(seq, " %-8s ",
- pt->dev ? pt->dev->name : "");
- ptype_seq_decode(seq, pt->func);
- seq_putc(seq, '\n');
+ seq_printf(seq, " %-8s %pF\n",
+ pt->dev ? pt->dev->name : "", pt->func);
}
return 0;
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
- if (dev->flags & IFF_UP && dev->change_rx_flags)
- dev->change_rx_flags(dev, flags);
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags)
+ ops->ndo_change_rx_flags(dev, flags);
}
static int __dev_set_promiscuity(struct net_device *dev, int inc)
{
unsigned short old_flags = dev->flags;
+ uid_t uid;
+ gid_t gid;
ASSERT_RTNL();
printk(KERN_INFO "device %s %s promiscuous mode\n",
dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
"left");
- if (audit_enabled)
+ if (audit_enabled) {
+ current_uid_gid(&uid, &gid);
audit_log(current->audit_context, GFP_ATOMIC,
AUDIT_ANOM_PROMISCUOUS,
"dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
dev->name, (dev->flags & IFF_PROMISC),
(old_flags & IFF_PROMISC),
audit_get_loginuid(current),
- current->uid, current->gid,
+ uid, gid,
audit_get_sessionid(current));
+ }
dev_change_rx_flags(dev, IFF_PROMISC);
}
*/
void __dev_set_rx_mode(struct net_device *dev)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
/* dev_open will call this function so the list will stay sane. */
if (!(dev->flags&IFF_UP))
return;
if (!netif_device_present(dev))
return;
- if (dev->set_rx_mode)
- dev->set_rx_mode(dev);
+ if (ops->ndo_set_rx_mode)
+ ops->ndo_set_rx_mode(dev);
else {
/* Unicast addresses changes may only happen under the rtnl,
* therefore calling __dev_set_promiscuity here is safe.
dev->uc_promisc = 0;
}
- if (dev->set_multicast_list)
- dev->set_multicast_list(dev);
+ if (ops->ndo_set_multicast_list)
+ ops->ndo_set_multicast_list(dev);
}
}
netif_addr_unlock_bh(dev);
}
-int __dev_addr_delete(struct dev_addr_list **list, int *count,
- void *addr, int alen, int glbl)
+/* hw addresses list handling functions */
+
+static int __hw_addr_add(struct list_head *list, int *delta,
+ unsigned char *addr, int addr_len,
+ unsigned char addr_type)
{
- struct dev_addr_list *da;
+ struct netdev_hw_addr *ha;
+ int alloc_size;
- for (; (da = *list) != NULL; list = &da->next) {
- if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
- alen == da->da_addrlen) {
- if (glbl) {
- int old_glbl = da->da_gusers;
- da->da_gusers = 0;
- if (old_glbl == 0)
- break;
- }
- if (--da->da_users)
- return 0;
+ if (addr_len > MAX_ADDR_LEN)
+ return -EINVAL;
- *list = da->next;
- kfree(da);
- (*count)--;
+ list_for_each_entry(ha, list, list) {
+ if (!memcmp(ha->addr, addr, addr_len) &&
+ ha->type == addr_type) {
+ ha->refcount++;
return 0;
}
}
- return -ENOENT;
+
+
+ alloc_size = sizeof(*ha);
+ if (alloc_size < L1_CACHE_BYTES)
+ alloc_size = L1_CACHE_BYTES;
+ ha = kmalloc(alloc_size, GFP_ATOMIC);
+ if (!ha)
+ return -ENOMEM;
+ memcpy(ha->addr, addr, addr_len);
+ ha->type = addr_type;
+ ha->refcount = 1;
+ ha->synced = false;
+ list_add_tail_rcu(&ha->list, list);
+ if (delta)
+ (*delta)++;
+ return 0;
}
-int __dev_addr_add(struct dev_addr_list **list, int *count,
- void *addr, int alen, int glbl)
+static void ha_rcu_free(struct rcu_head *head)
{
- struct dev_addr_list *da;
+ struct netdev_hw_addr *ha;
- for (da = *list; da != NULL; da = da->next) {
- if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
+ ha = container_of(head, struct netdev_hw_addr, rcu_head);
+ kfree(ha);
+}
+
+static int __hw_addr_del(struct list_head *list, int *delta,
+ unsigned char *addr, int addr_len,
+ unsigned char addr_type)
+{
+ struct netdev_hw_addr *ha;
+
+ list_for_each_entry(ha, list, list) {
+ if (!memcmp(ha->addr, addr, addr_len) &&
+ (ha->type == addr_type || !addr_type)) {
+ if (--ha->refcount)
+ return 0;
+ list_del_rcu(&ha->list);
+ call_rcu(&ha->rcu_head, ha_rcu_free);
+ if (delta)
+ (*delta)--;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+static int __hw_addr_add_multiple(struct list_head *to_list, int *to_delta,
+ struct list_head *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) {
+ type = addr_type ? addr_type : ha->type;
+ err = __hw_addr_add(to_list, to_delta, ha->addr,
+ addr_len, type);
+ if (err)
+ goto unroll;
+ }
+ return 0;
+
+unroll:
+ list_for_each_entry(ha2, from_list, list) {
+ if (ha2 == ha)
+ break;
+ type = addr_type ? addr_type : ha2->type;
+ __hw_addr_del(to_list, to_delta, ha2->addr,
+ addr_len, type);
+ }
+ return err;
+}
+
+static void __hw_addr_del_multiple(struct list_head *to_list, int *to_delta,
+ struct list_head *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) {
+ type = addr_type ? addr_type : ha->type;
+ __hw_addr_del(to_list, to_delta, ha->addr,
+ addr_len, addr_type);
+ }
+}
+
+static int __hw_addr_sync(struct list_head *to_list, int *to_delta,
+ struct list_head *from_list, int *from_delta,
+ int addr_len)
+{
+ int err = 0;
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, from_list, list) {
+ if (!ha->synced) {
+ err = __hw_addr_add(to_list, to_delta, ha->addr,
+ addr_len, ha->type);
+ if (err)
+ break;
+ ha->synced = true;
+ ha->refcount++;
+ } else if (ha->refcount == 1) {
+ __hw_addr_del(to_list, to_delta, ha->addr,
+ addr_len, ha->type);
+ __hw_addr_del(from_list, from_delta, ha->addr,
+ addr_len, ha->type);
+ }
+ }
+ return err;
+}
+
+static void __hw_addr_unsync(struct list_head *to_list, int *to_delta,
+ struct list_head *from_list, int *from_delta,
+ int addr_len)
+{
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, from_list, list) {
+ if (ha->synced) {
+ __hw_addr_del(to_list, to_delta, ha->addr,
+ addr_len, ha->type);
+ ha->synced = false;
+ __hw_addr_del(from_list, from_delta, ha->addr,
+ addr_len, ha->type);
+ }
+ }
+}
+
+
+static void __hw_addr_flush(struct list_head *list)
+{
+ struct netdev_hw_addr *ha, *tmp;
+
+ list_for_each_entry_safe(ha, tmp, list, list) {
+ list_del_rcu(&ha->list);
+ call_rcu(&ha->rcu_head, ha_rcu_free);
+ }
+}
+
+/* Device addresses handling functions */
+
+static void dev_addr_flush(struct net_device *dev)
+{
+ /* rtnl_mutex must be held here */
+
+ __hw_addr_flush(&dev->dev_addr_list);
+ dev->dev_addr = NULL;
+}
+
+static int dev_addr_init(struct net_device *dev)
+{
+ unsigned char addr[MAX_ADDR_LEN];
+ struct netdev_hw_addr *ha;
+ int err;
+
+ /* rtnl_mutex must be held here */
+
+ INIT_LIST_HEAD(&dev->dev_addr_list);
+ memset(addr, 0, sizeof(*addr));
+ err = __hw_addr_add(&dev->dev_addr_list, NULL, addr, sizeof(*addr),
+ NETDEV_HW_ADDR_T_LAN);
+ if (!err) {
+ /*
+ * Get the first (previously created) address from the list
+ * and set dev_addr pointer to this location.
+ */
+ ha = list_first_entry(&dev->dev_addr_list,
+ struct netdev_hw_addr, list);
+ dev->dev_addr = ha->addr;
+ }
+ return err;
+}
+
+/**
+ * dev_addr_add - Add a device address
+ * @dev: device
+ * @addr: address to add
+ * @addr_type: address type
+ *
+ * Add a device address to the device or increase the reference count if
+ * it already exists.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_addr_add(struct net_device *dev, unsigned char *addr,
+ unsigned char addr_type)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ err = __hw_addr_add(&dev->dev_addr_list, NULL, addr, dev->addr_len,
+ addr_type);
+ if (!err)
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_addr_add);
+
+/**
+ * dev_addr_del - Release a device address.
+ * @dev: device
+ * @addr: address to delete
+ * @addr_type: address type
+ *
+ * Release reference to a device address and remove it from the device
+ * if the reference count drops to zero.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_addr_del(struct net_device *dev, unsigned char *addr,
+ unsigned char addr_type)
+{
+ int err;
+ struct netdev_hw_addr *ha;
+
+ ASSERT_RTNL();
+
+ /*
+ * We can not remove the first address from the list because
+ * dev->dev_addr points to that.
+ */
+ ha = list_first_entry(&dev->dev_addr_list, struct netdev_hw_addr, list);
+ if (ha->addr == dev->dev_addr && ha->refcount == 1)
+ return -ENOENT;
+
+ err = __hw_addr_del(&dev->dev_addr_list, NULL, addr, dev->addr_len,
+ addr_type);
+ if (!err)
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return err;
+}
+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_addr_list, NULL,
+ &from_dev->dev_addr_list,
+ 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 by which addresses the addresses will be deleted
+ * @addr_type: address type - 0 means type will 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_addr_list, NULL,
+ &from_dev->dev_addr_list,
+ to_dev->addr_len, addr_type);
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev);
+ return 0;
+}
+EXPORT_SYMBOL(dev_addr_del_multiple);
+
+/* unicast and multicast addresses handling functions */
+
+int __dev_addr_delete(struct dev_addr_list **list, int *count,
+ void *addr, int alen, int glbl)
+{
+ struct dev_addr_list *da;
+
+ for (; (da = *list) != NULL; list = &da->next) {
+ if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
+ alen == da->da_addrlen) {
+ if (glbl) {
+ int old_glbl = da->da_gusers;
+ da->da_gusers = 0;
+ if (old_glbl == 0)
+ break;
+ }
+ if (--da->da_users)
+ return 0;
+
+ *list = da->next;
+ kfree(da);
+ (*count)--;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+int __dev_addr_add(struct dev_addr_list **list, int *count,
+ void *addr, int alen, int glbl)
+{
+ struct dev_addr_list *da;
+
+ for (da = *list; da != NULL; da = da->next) {
+ if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
da->da_addrlen == alen) {
if (glbl) {
int old_glbl = da->da_gusers;
* dev_unicast_delete - Release secondary unicast address.
* @dev: device
* @addr: address to delete
- * @alen: length of @addr
*
* Release reference to a secondary unicast address and remove it
* from the device if the reference count drops to zero.
*
* The caller must hold the rtnl_mutex.
*/
-int dev_unicast_delete(struct net_device *dev, void *addr, int alen)
+int dev_unicast_delete(struct net_device *dev, void *addr)
{
int err;
ASSERT_RTNL();
- netif_addr_lock_bh(dev);
- err = __dev_addr_delete(&dev->uc_list, &dev->uc_count, addr, alen, 0);
+ err = __hw_addr_del(&dev->uc_list, &dev->uc_count, addr,
+ dev->addr_len, NETDEV_HW_ADDR_T_UNICAST);
if (!err)
__dev_set_rx_mode(dev);
- netif_addr_unlock_bh(dev);
return err;
}
EXPORT_SYMBOL(dev_unicast_delete);
* dev_unicast_add - add a secondary unicast address
* @dev: device
* @addr: address to add
- * @alen: length of @addr
*
* Add a secondary unicast address to the device or increase
* the reference count if it already exists.
*
* The caller must hold the rtnl_mutex.
*/
-int dev_unicast_add(struct net_device *dev, void *addr, int alen)
+int dev_unicast_add(struct net_device *dev, void *addr)
{
int err;
ASSERT_RTNL();
- netif_addr_lock_bh(dev);
- err = __dev_addr_add(&dev->uc_list, &dev->uc_count, addr, alen, 0);
+ err = __hw_addr_add(&dev->uc_list, &dev->uc_count, addr,
+ dev->addr_len, NETDEV_HW_ADDR_T_UNICAST);
if (!err)
__dev_set_rx_mode(dev);
- netif_addr_unlock_bh(dev);
return err;
}
EXPORT_SYMBOL(dev_unicast_add);
* @from: source device
*
* Add newly added addresses to the destination device and release
- * addresses that have no users left. The source device must be
- * locked by netif_tx_lock_bh.
+ * addresses that have no users left.
*
* This function is intended to be called from the dev->set_rx_mode
* function of layered software devices.
{
int err = 0;
- netif_addr_lock_bh(to);
- err = __dev_addr_sync(&to->uc_list, &to->uc_count,
- &from->uc_list, &from->uc_count);
+ ASSERT_RTNL();
+
+ if (to->addr_len != from->addr_len)
+ return -EINVAL;
+
+ err = __hw_addr_sync(&to->uc_list, &to->uc_count,
+ &from->uc_list, &from->uc_count, to->addr_len);
if (!err)
__dev_set_rx_mode(to);
- netif_addr_unlock_bh(to);
return err;
}
EXPORT_SYMBOL(dev_unicast_sync);
*/
void dev_unicast_unsync(struct net_device *to, struct net_device *from)
{
- netif_addr_lock_bh(from);
- netif_addr_lock(to);
+ ASSERT_RTNL();
- __dev_addr_unsync(&to->uc_list, &to->uc_count,
- &from->uc_list, &from->uc_count);
- __dev_set_rx_mode(to);
+ if (to->addr_len != from->addr_len)
+ return;
- netif_addr_unlock(to);
- netif_addr_unlock_bh(from);
+ __hw_addr_unsync(&to->uc_list, &to->uc_count,
+ &from->uc_list, &from->uc_count, to->addr_len);
+ __dev_set_rx_mode(to);
}
EXPORT_SYMBOL(dev_unicast_unsync);
+static void dev_unicast_flush(struct net_device *dev)
+{
+ /* rtnl_mutex must be held here */
+
+ __hw_addr_flush(&dev->uc_list);
+ dev->uc_count = 0;
+}
+
+static void dev_unicast_init(struct net_device *dev)
+{
+ /* rtnl_mutex must be held here */
+
+ INIT_LIST_HEAD(&dev->uc_list);
+}
+
+
static void __dev_addr_discard(struct dev_addr_list **list)
{
struct dev_addr_list *tmp;
{
netif_addr_lock_bh(dev);
- __dev_addr_discard(&dev->uc_list);
- dev->uc_count = 0;
-
__dev_addr_discard(&dev->mc_list);
dev->mc_count = 0;
*/
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int err;
if (new_mtu == dev->mtu)
return -ENODEV;
err = 0;
- if (dev->change_mtu)
- err = dev->change_mtu(dev, new_mtu);
+ if (ops->ndo_change_mtu)
+ err = ops->ndo_change_mtu(dev, new_mtu);
else
dev->mtu = new_mtu;
+
if (!err && dev->flags & IFF_UP)
call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
return err;
*/
int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
{
+ const struct net_device_ops *ops = dev->netdev_ops;
int err;
- if (!dev->set_mac_address)
+ if (!ops->ndo_set_mac_address)
return -EOPNOTSUPP;
if (sa->sa_family != dev->type)
return -EINVAL;
if (!netif_device_present(dev))
return -ENODEV;
- err = dev->set_mac_address(dev, sa);
+ err = ops->ndo_set_mac_address(dev, sa);
if (!err)
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return err;
{
int err;
struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+ const struct net_device_ops *ops;
if (!dev)
return -ENODEV;
+ ops = dev->netdev_ops;
+
switch (cmd) {
case SIOCSIFFLAGS: /* Set interface flags */
return dev_change_flags(dev, ifr->ifr_flags);
return 0;
case SIOCSIFMAP:
- if (dev->set_config) {
+ if (ops->ndo_set_config) {
if (!netif_device_present(dev))
return -ENODEV;
- return dev->set_config(dev, &ifr->ifr_map);
+ return ops->ndo_set_config(dev, &ifr->ifr_map);
}
return -EOPNOTSUPP;
case SIOCADDMULTI:
- if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
dev->addr_len, 1);
case SIOCDELMULTI:
- if ((!dev->set_multicast_list && !dev->set_rx_mode) ||
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
return -EINVAL;
if (!netif_device_present(dev))
cmd == SIOCSMIIREG ||
cmd == SIOCBRADDIF ||
cmd == SIOCBRDELIF ||
+ cmd == SIOCSHWTSTAMP ||
cmd == SIOCWANDEV) {
err = -EOPNOTSUPP;
- if (dev->do_ioctl) {
+ if (ops->ndo_do_ioctl) {
if (netif_device_present(dev))
- err = dev->do_ioctl(dev, ifr,
- cmd);
+ err = ops->ndo_do_ioctl(dev, ifr, cmd);
else
err = -ENODEV;
}
case SIOCBONDCHANGEACTIVE:
case SIOCBRADDIF:
case SIOCBRDELIF:
+ case SIOCSHWTSTAMP:
if (!capable(CAP_NET_ADMIN))
return -EPERM;
/* fall through */
/*
* Flush the unicast and multicast chains
*/
+ dev_unicast_flush(dev);
dev_addr_discard(dev);
- if (dev->uninit)
- dev->uninit(dev);
+ if (dev->netdev_ops->ndo_uninit)
+ dev->netdev_ops->ndo_uninit(dev);
/* Notifier chain MUST detach us from master device. */
WARN_ON(dev->master);
struct hlist_head *head;
struct hlist_node *p;
int ret;
- struct net *net;
+ struct net *net = dev_net(dev);
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
/* When net_device's are persistent, this will be fatal. */
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
- BUG_ON(!dev_net(dev));
- net = dev_net(dev);
+ BUG_ON(!net);
spin_lock_init(&dev->addr_list_lock);
netdev_set_addr_lockdep_class(dev);
dev->iflink = -1;
/* Init, if this function is available */
- if (dev->init) {
- ret = dev->init(dev);
+ if (dev->netdev_ops->ndo_init) {
+ ret = dev->netdev_ops->ndo_init(dev);
if (ret) {
if (ret > 0)
ret = -EIO;
return ret;
err_uninit:
- if (dev->uninit)
- dev->uninit(dev);
+ if (dev->netdev_ops->ndo_uninit)
+ dev->netdev_ops->ndo_uninit(dev);
goto out;
}
/**
+ * init_dummy_netdev - init a dummy network device for NAPI
+ * @dev: device to init
+ *
+ * This takes a network device structure and initialize the minimum
+ * amount of fields so it can be used to schedule NAPI polls without
+ * registering a full blown interface. This is to be used by drivers
+ * that need to tie several hardware interfaces to a single NAPI
+ * poll scheduler due to HW limitations.
+ */
+int init_dummy_netdev(struct net_device *dev)
+{
+ /* Clear everything. Note we don't initialize spinlocks
+ * are they aren't supposed to be taken by any of the
+ * NAPI code and this dummy netdev is supposed to be
+ * only ever used for NAPI polls
+ */
+ memset(dev, 0, sizeof(struct net_device));
+
+ /* make sure we BUG if trying to hit standard
+ * register/unregister code path
+ */
+ dev->reg_state = NETREG_DUMMY;
+
+ /* initialize the ref count */
+ atomic_set(&dev->refcnt, 1);
+
+ /* NAPI wants this */
+ INIT_LIST_HEAD(&dev->napi_list);
+
+ /* a dummy interface is started by default */
+ set_bit(__LINK_STATE_PRESENT, &dev->state);
+ set_bit(__LINK_STATE_START, &dev->state);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(init_dummy_netdev);
+
+
+/**
* register_netdev - register a network device
* @dev: device to register
*
}
}
-static struct net_device_stats *internal_stats(struct net_device *dev)
+/**
+ * dev_get_stats - get network device statistics
+ * @dev: device to get statistics from
+ *
+ * Get network statistics from device. The device driver may provide
+ * its own method by setting dev->netdev_ops->get_stats; otherwise
+ * the internal statistics structure is used.
+ */
+const struct net_device_stats *dev_get_stats(struct net_device *dev)
{
- return &dev->stats;
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_get_stats)
+ return ops->ndo_get_stats(dev);
+ else {
+ unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
+ struct net_device_stats *stats = &dev->stats;
+ unsigned int i;
+ struct netdev_queue *txq;
+
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ txq = netdev_get_tx_queue(dev, i);
+ tx_bytes += txq->tx_bytes;
+ tx_packets += txq->tx_packets;
+ tx_dropped += txq->tx_dropped;
+ }
+ if (tx_bytes || tx_packets || tx_dropped) {
+ stats->tx_bytes = tx_bytes;
+ stats->tx_packets = tx_packets;
+ stats->tx_dropped = tx_dropped;
+ }
+ return stats;
+ }
}
+EXPORT_SYMBOL(dev_get_stats);
static void netdev_init_one_queue(struct net_device *dev,
struct netdev_queue *queue,
struct netdev_queue *tx;
struct net_device *dev;
size_t alloc_size;
- void *p;
+ struct net_device *p;
BUG_ON(strlen(name) >= sizeof(dev->name));
alloc_size = sizeof(struct net_device);
if (sizeof_priv) {
/* ensure 32-byte alignment of private area */
- alloc_size = (alloc_size + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
+ alloc_size = ALIGN(alloc_size, NETDEV_ALIGN);
alloc_size += sizeof_priv;
}
/* ensure 32-byte alignment of whole construct */
- alloc_size += NETDEV_ALIGN_CONST;
+ alloc_size += NETDEV_ALIGN - 1;
p = kzalloc(alloc_size, GFP_KERNEL);
if (!p) {
if (!tx) {
printk(KERN_ERR "alloc_netdev: Unable to allocate "
"tx qdiscs.\n");
- kfree(p);
- return NULL;
+ goto free_p;
}
- dev = (struct net_device *)
- (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
+ dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
+
+ if (dev_addr_init(dev))
+ goto free_tx;
+
+ dev_unicast_init(dev);
+
dev_net_set(dev, &init_net);
dev->_tx = tx;
dev->num_tx_queues = queue_count;
dev->real_num_tx_queues = queue_count;
- if (sizeof_priv) {
- dev->priv = ((char *)dev +
- ((sizeof(struct net_device) + NETDEV_ALIGN_CONST)
- & ~NETDEV_ALIGN_CONST));
- }
-
dev->gso_max_size = GSO_MAX_SIZE;
netdev_init_queues(dev);
- dev->get_stats = internal_stats;
- netpoll_netdev_init(dev);
+ INIT_LIST_HEAD(&dev->napi_list);
+ dev->priv_flags = IFF_XMIT_DST_RELEASE;
setup(dev);
strcpy(dev->name, name);
return dev;
+
+free_tx:
+ kfree(tx);
+
+free_p:
+ kfree(p);
+ return NULL;
}
EXPORT_SYMBOL(alloc_netdev_mq);
*/
void free_netdev(struct net_device *dev)
{
+ struct napi_struct *p, *n;
+
release_net(dev_net(dev));
kfree(dev->_tx);
+ /* Flush device addresses */
+ dev_addr_flush(dev);
+
+ list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
+ netif_napi_del(p);
+
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
kfree((char *)dev - dev->padded);
/*
* Flush the unicast and multicast chains
*/
+ dev_unicast_flush(dev);
dev_addr_discard(dev);
netdev_unregister_kobject(dev);
return NOTIFY_OK;
}
-#ifdef CONFIG_NET_DMA
-/**
- * net_dma_rebalance - try to maintain one DMA channel per CPU
- * @net_dma: DMA client and associated data (lock, channels, channel_mask)
- *
- * This is called when the number of channels allocated to the net_dma client
- * changes. The net_dma client tries to have one DMA channel per CPU.
- */
-
-static void net_dma_rebalance(struct net_dma *net_dma)
-{
- unsigned int cpu, i, n, chan_idx;
- struct dma_chan *chan;
-
- if (cpus_empty(net_dma->channel_mask)) {
- for_each_online_cpu(cpu)
- rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL);
- return;
- }
-
- i = 0;
- cpu = first_cpu(cpu_online_map);
-
- for_each_cpu_mask_nr(chan_idx, net_dma->channel_mask) {
- chan = net_dma->channels[chan_idx];
-
- n = ((num_online_cpus() / cpus_weight(net_dma->channel_mask))
- + (i < (num_online_cpus() %
- cpus_weight(net_dma->channel_mask)) ? 1 : 0));
-
- while(n) {
- per_cpu(softnet_data, cpu).net_dma = chan;
- cpu = next_cpu(cpu, cpu_online_map);
- n--;
- }
- i++;
- }
-}
-
-/**
- * netdev_dma_event - event callback for the net_dma_client
- * @client: should always be net_dma_client
- * @chan: DMA channel for the event
- * @state: DMA state to be handled
- */
-static enum dma_state_client
-netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
- enum dma_state state)
-{
- int i, found = 0, pos = -1;
- struct net_dma *net_dma =
- container_of(client, struct net_dma, client);
- enum dma_state_client ack = DMA_DUP; /* default: take no action */
-
- spin_lock(&net_dma->lock);
- switch (state) {
- case DMA_RESOURCE_AVAILABLE:
- for (i = 0; i < nr_cpu_ids; i++)
- if (net_dma->channels[i] == chan) {
- found = 1;
- break;
- } else if (net_dma->channels[i] == NULL && pos < 0)
- pos = i;
-
- if (!found && pos >= 0) {
- ack = DMA_ACK;
- net_dma->channels[pos] = chan;
- cpu_set(pos, net_dma->channel_mask);
- net_dma_rebalance(net_dma);
- }
- break;
- case DMA_RESOURCE_REMOVED:
- for (i = 0; i < nr_cpu_ids; i++)
- if (net_dma->channels[i] == chan) {
- found = 1;
- pos = i;
- break;
- }
-
- if (found) {
- ack = DMA_ACK;
- cpu_clear(pos, net_dma->channel_mask);
- net_dma->channels[i] = NULL;
- net_dma_rebalance(net_dma);
- }
- break;
- default:
- break;
- }
- spin_unlock(&net_dma->lock);
-
- return ack;
-}
-
-/**
- * netdev_dma_register - register the networking subsystem as a DMA client
- */
-static int __init netdev_dma_register(void)
-{
- net_dma.channels = kzalloc(nr_cpu_ids * sizeof(struct net_dma),
- GFP_KERNEL);
- if (unlikely(!net_dma.channels)) {
- printk(KERN_NOTICE
- "netdev_dma: no memory for net_dma.channels\n");
- return -ENOMEM;
- }
- spin_lock_init(&net_dma.lock);
- dma_cap_set(DMA_MEMCPY, net_dma.client.cap_mask);
- dma_async_client_register(&net_dma.client);
- dma_async_client_chan_request(&net_dma.client);
- return 0;
-}
-
-#else
-static int __init netdev_dma_register(void) { return -ENODEV; }
-#endif /* CONFIG_NET_DMA */
/**
* netdev_increment_features - increment feature set by one
static void __net_exit default_device_exit(struct net *net)
{
- struct net_device *dev, *next;
+ struct net_device *dev;
/*
* Push all migratable of the network devices back to the
* initial network namespace
*/
rtnl_lock();
- for_each_netdev_safe(net, dev, next) {
+restart:
+ for_each_netdev(net, dev) {
int err;
char fb_name[IFNAMSIZ];
/* Delete virtual devices */
if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) {
dev->rtnl_link_ops->dellink(dev);
- continue;
+ goto restart;
}
/* Push remaing network devices to init_net */
__func__, dev->name, err);
BUG();
}
+ goto restart;
}
rtnl_unlock();
}
if (register_pernet_subsys(&netdev_net_ops))
goto out;
- /* The loopback device is special if any other network devices
- * is present in a network namespace the loopback device must
- * be present. Since we now dynamically allocate and free the
- * loopback device ensure this invariant is maintained by
- * keeping the loopback device as the first device on the
- * list of network devices. Ensuring the loopback devices
- * is the first device that appears and the last network device
- * that disappears.
- */
- if (register_pernet_device(&loopback_net_ops))
- goto out;
-
- if (register_pernet_device(&default_device_ops))
- goto out;
-
/*
* Initialise the packet receive queues.
*/
queue->backlog.poll = process_backlog;
queue->backlog.weight = weight_p;
+ queue->backlog.gro_list = NULL;
+ queue->backlog.gro_count = 0;
}
- netdev_dma_register();
-
dev_boot_phase = 0;
+ /* The loopback device is special if any other network devices
+ * is present in a network namespace the loopback device must
+ * be present. Since we now dynamically allocate and free the
+ * loopback device ensure this invariant is maintained by
+ * keeping the loopback device as the first device on the
+ * list of network devices. Ensuring the loopback devices
+ * is the first device that appears and the last network device
+ * that disappears.
+ */
+ if (register_pernet_device(&loopback_net_ops))
+ goto out;
+
+ if (register_pernet_device(&default_device_ops))
+ goto out;
+
open_softirq(NET_TX_SOFTIRQ, net_tx_action);
open_softirq(NET_RX_SOFTIRQ, net_rx_action);
subsys_initcall(net_dev_init);
+static int __init initialize_hashrnd(void)
+{
+ get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd));
+ return 0;
+}
+
+late_initcall_sync(initialize_hashrnd);
+
EXPORT_SYMBOL(__dev_get_by_index);
EXPORT_SYMBOL(__dev_get_by_name);
EXPORT_SYMBOL(__dev_remove_pack);