/* This should be increased if a protocol with a bigger head is added. */
#define GRO_MAX_HEAD (MAX_HEADER + 128)
+enum {
+ GRO_MERGED,
+ GRO_MERGED_FREE,
+ GRO_HELD,
+ GRO_NORMAL,
+ GRO_DROP,
+};
+
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)];
}
+static inline void *skb_gro_mac_header(struct sk_buff *skb)
+{
+ return skb_headlen(skb) ? skb_mac_header(skb) :
+ page_address(skb_shinfo(skb)->frags[0].page) +
+ skb_shinfo(skb)->frags[0].page_offset;
+}
+
/* Device list insertion */
static int list_netdevice(struct net_device *dev)
{
*/
dev->flags |= IFF_UP;
+ /*
+ * Enable NET_DMA
+ */
+ dmaengine_get();
+
/*
* Initialize multicasting status
*/
*/
call_netdevice_notifiers(NETDEV_DOWN, dev);
+ /*
+ * Shutdown NET_DMA
+ */
+ dmaengine_put();
+
return 0;
}
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);
return 0;
}
-static u32 simple_tx_hashrnd;
-static int simple_tx_hashrnd_initialized = 0;
+static u32 skb_tx_hashrnd;
+static int skb_tx_hashrnd_initialized = 0;
-static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb)
+static u16 skb_tx_hash(struct net_device *dev, struct sk_buff *skb)
{
- u32 addr1, addr2, ports;
- u32 hash, ihl;
- u8 ip_proto = 0;
+ u32 hash;
- if (unlikely(!simple_tx_hashrnd_initialized)) {
- get_random_bytes(&simple_tx_hashrnd, 4);
- simple_tx_hashrnd_initialized = 1;
+ if (unlikely(!skb_tx_hashrnd_initialized)) {
+ get_random_bytes(&skb_tx_hashrnd, 4);
+ skb_tx_hashrnd_initialized = 1;
}
- 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;
- }
-
-
- 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;
- }
+ if (skb_rx_queue_recorded(skb)) {
+ hash = skb_get_rx_queue(skb);
+ } else if (skb->sk && skb->sk->sk_hash) {
+ hash = skb->sk->sk_hash;
+ } else
+ hash = skb->protocol;
- 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);
}
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);
out:
skb_shinfo(skb)->gso_size = 0;
- __skb_push(skb, -skb_network_offset(skb));
return netif_receive_skb(skb);
}
}
EXPORT_SYMBOL(napi_gro_flush);
+void *skb_gro_header(struct sk_buff *skb, unsigned int hlen)
+{
+ unsigned int offset = skb_gro_offset(skb);
+
+ hlen += offset;
+ if (hlen <= skb_headlen(skb))
+ return skb->data + offset;
+
+ if (unlikely(!skb_shinfo(skb)->nr_frags ||
+ skb_shinfo(skb)->frags[0].size <=
+ hlen - skb_headlen(skb) ||
+ PageHighMem(skb_shinfo(skb)->frags[0].page)))
+ return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL;
+
+ return page_address(skb_shinfo(skb)->frags[0].page) +
+ skb_shinfo(skb)->frags[0].page_offset + offset;
+}
+EXPORT_SYMBOL(skb_gro_header);
+
int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
int count = 0;
int same_flow;
int mac_len;
- int free;
+ 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) {
struct sk_buff *p;
+ void *mac;
if (ptype->type != type || ptype->dev || !ptype->gro_receive)
continue;
- skb_reset_network_header(skb);
+ skb_set_network_header(skb, skb_gro_offset(skb));
+ mac = skb_gro_mac_header(skb);
mac_len = skb->network_header - skb->mac_header;
skb->mac_len = mac_len;
NAPI_GRO_CB(skb)->same_flow = 0;
continue;
if (p->mac_len != mac_len ||
- memcmp(skb_mac_header(p), skb_mac_header(skb),
- mac_len))
+ memcmp(skb_mac_header(p), mac, mac_len))
NAPI_GRO_CB(p)->same_flow = 0;
}
goto normal;
same_flow = NAPI_GRO_CB(skb)->same_flow;
- free = NAPI_GRO_CB(skb)->free;
+ ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
if (pp) {
struct sk_buff *nskb = *pp;
if (same_flow)
goto ok;
- if (NAPI_GRO_CB(skb)->flush || count >= MAX_GRO_SKBS) {
- __skb_push(skb, -skb_network_offset(skb));
+ if (NAPI_GRO_CB(skb)->flush || count >= MAX_GRO_SKBS)
goto normal;
- }
NAPI_GRO_CB(skb)->count = 1;
- skb_shinfo(skb)->gso_size = skb->len;
+ skb_shinfo(skb)->gso_size = skb_gro_len(skb);
skb->next = napi->gro_list;
napi->gro_list = skb;
+ ret = GRO_HELD;
ok:
- return free;
+ return ret;
normal:
- return -1;
+ return GRO_NORMAL;
}
EXPORT_SYMBOL(dev_gro_receive);
return dev_gro_receive(napi, skb);
}
-int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+int napi_skb_finish(int ret, struct sk_buff *skb)
{
- switch (__napi_gro_receive(napi, skb)) {
- case -1:
+ int err = NET_RX_SUCCESS;
+
+ switch (ret) {
+ case GRO_NORMAL:
return netif_receive_skb(skb);
- case 1:
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
+
+ case GRO_MERGED_FREE:
kfree_skb(skb);
break;
}
- return NET_RX_SUCCESS;
+ return err;
}
-EXPORT_SYMBOL(napi_gro_receive);
+EXPORT_SYMBOL(napi_skb_finish);
-void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
+int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
- skb_shinfo(skb)->nr_frags = 0;
+ skb_gro_reset_offset(skb);
- skb->len -= skb->data_len;
- skb->truesize -= skb->data_len;
- skb->data_len = 0;
+ 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));
{
struct net_device *dev = napi->dev;
struct sk_buff *skb = napi->skb;
+ struct ethhdr *eth;
napi->skb = NULL;
skb->len += info->len;
skb->truesize += info->len;
- if (!pskb_may_pull(skb, ETH_HLEN)) {
+ skb_reset_mac_header(skb);
+ skb_gro_reset_offset(skb);
+
+ eth = skb_gro_header(skb, sizeof(*eth));
+ if (!eth) {
napi_reuse_skb(napi, skb);
+ skb = NULL;
goto out;
}
- skb->protocol = eth_type_trans(skb, dev);
+ skb_gro_pull(skb, sizeof(*eth));
+
+ /*
+ * This works because the only protocols we care about don't require
+ * special handling. We'll fix it up properly at the end.
+ */
+ skb->protocol = eth->h_proto;
skb->ip_summed = info->ip_summed;
skb->csum = info->csum;
}
EXPORT_SYMBOL(napi_fraginfo_skb);
-int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
+int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
{
- struct sk_buff *skb = napi_fraginfo_skb(napi, info);
- int err = NET_RX_DROP;
+ int err = NET_RX_SUCCESS;
+ int may;
- if (!skb)
- goto out;
+ switch (ret) {
+ case GRO_NORMAL:
+ case GRO_HELD:
+ may = pskb_may_pull(skb, skb_gro_offset(skb));
+ BUG_ON(!may);
- err = NET_RX_SUCCESS;
+ skb->protocol = eth_type_trans(skb, napi->dev);
- switch (__napi_gro_receive(napi, skb)) {
- case -1:
- return netif_receive_skb(skb);
+ if (ret == GRO_NORMAL)
+ return netif_receive_skb(skb);
- case 0:
- goto out;
- }
+ skb_gro_pull(skb, -ETH_HLEN);
+ break;
- napi_reuse_skb(napi, skb);
+ case GRO_DROP:
+ err = NET_RX_DROP;
+ /* fall through */
+
+ case GRO_MERGED_FREE:
+ napi_reuse_skb(napi, skb);
+ break;
+ }
-out:
return err;
}
+EXPORT_SYMBOL(napi_frags_finish);
+
+int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info)
+{
+ struct sk_buff *skb = napi_fraginfo_skb(napi, info);
+
+ 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)
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
hotcpu_notifier(dev_cpu_callback, 0);
dst_init();
dev_mcast_init();
- #ifdef CONFIG_NET_DMA
- dmaengine_get();
- #endif
rc = 0;
out:
return rc;