aboutsummaryrefslogtreecommitdiff
path: root/net/core/dev.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2014-01-25 11:17:34 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2014-01-25 11:17:34 -0800
commit4ba9920e5e9c0e16b5ed24292d45322907bb9035 (patch)
tree7d023baea59ed0886ded1f0b6d1c6385690b88f7 /net/core/dev.c
parent82c477669a4665eb4e52030792051e0559ee2a36 (diff)
parent8b662fe70c68282f78482dc272df0c4f355e49f5 (diff)
downloadlinux-linaro-stable-4ba9920e5e9c0e16b5ed24292d45322907bb9035.tar.gz
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller: 1) BPF debugger and asm tool by Daniel Borkmann. 2) Speed up create/bind in AF_PACKET, also from Daniel Borkmann. 3) Correct reciprocal_divide and update users, from Hannes Frederic Sowa and Daniel Borkmann. 4) Currently we only have a "set" operation for the hw timestamp socket ioctl, add a "get" operation to match. From Ben Hutchings. 5) Add better trace events for debugging driver datapath problems, also from Ben Hutchings. 6) Implement auto corking in TCP, from Eric Dumazet. Basically, if we have a small send and a previous packet is already in the qdisc or device queue, defer until TX completion or we get more data. 7) Allow userspace to manage ipv6 temporary addresses, from Jiri Pirko. 8) Add a qdisc bypass option for AF_PACKET sockets, from Daniel Borkmann. 9) Share IP header compression code between Bluetooth and IEEE802154 layers, from Jukka Rissanen. 10) Fix ipv6 router reachability probing, from Jiri Benc. 11) Allow packets to be captured on macvtap devices, from Vlad Yasevich. 12) Support tunneling in GRO layer, from Jerry Chu. 13) Allow bonding to be configured fully using netlink, from Scott Feldman. 14) Allow AF_PACKET users to obtain the VLAN TPID, just like they can already get the TCI. From Atzm Watanabe. 15) New "Heavy Hitter" qdisc, from Terry Lam. 16) Significantly improve the IPSEC support in pktgen, from Fan Du. 17) Allow ipv4 tunnels to cache routes, just like sockets. From Tom Herbert. 18) Add Proportional Integral Enhanced packet scheduler, from Vijay Subramanian. 19) Allow openvswitch to mmap'd netlink, from Thomas Graf. 20) Key TCP metrics blobs also by source address, not just destination address. From Christoph Paasch. 21) Support 10G in generic phylib. From Andy Fleming. 22) Try to short-circuit GRO flow compares using device provided RX hash, if provided. From Tom Herbert. The wireless and netfilter folks have been busy little bees too. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2064 commits) net/cxgb4: Fix referencing freed adapter ipv6: reallocate addrconf router for ipv6 address when lo device up fib_frontend: fix possible NULL pointer dereference rtnetlink: remove IFLA_BOND_SLAVE definition rtnetlink: remove check for fill_slave_info in rtnl_have_link_slave_info qlcnic: update version to 5.3.55 qlcnic: Enhance logic to calculate msix vectors. qlcnic: Refactor interrupt coalescing code for all adapters. qlcnic: Update poll controller code path qlcnic: Interrupt code cleanup qlcnic: Enhance Tx timeout debugging. qlcnic: Use bool for rx_mac_learn. bonding: fix u64 division rtnetlink: add missing IFLA_BOND_AD_INFO_UNSPEC sfc: Use the correct maximum TX DMA ring size for SFC9100 Add Shradha Shah as the sfc driver maintainer. net/vxlan: Share RX skb de-marking and checksum checks with ovs tulip: cleanup by using ARRAY_SIZE() ip_tunnel: clear IPCB in ip_tunnel_xmit() in case dst_link_failure() is called net/cxgb4: Don't retrieve stats during recovery ...
Diffstat (limited to 'net/core/dev.c')
-rw-r--r--net/core/dev.c562
1 files changed, 309 insertions, 253 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 2e0c6a90f6f2..3721db716350 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -147,6 +147,8 @@ struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
struct list_head ptype_all __read_mostly; /* Taps */
static struct list_head offload_base __read_mostly;
+static int netif_rx_internal(struct sk_buff *skb);
+
/*
* The @dev_base_head list is protected by @dev_base_lock and the rtnl
* semaphore.
@@ -480,7 +482,7 @@ EXPORT_SYMBOL(dev_add_offload);
* and must not be freed until after all the CPU's have gone
* through a quiescent state.
*/
-void __dev_remove_offload(struct packet_offload *po)
+static void __dev_remove_offload(struct packet_offload *po)
{
struct list_head *head = &offload_base;
struct packet_offload *po1;
@@ -498,7 +500,6 @@ void __dev_remove_offload(struct packet_offload *po)
out:
spin_unlock(&offload_lock);
}
-EXPORT_SYMBOL(__dev_remove_offload);
/**
* dev_remove_offload - remove packet offload handler
@@ -1118,6 +1119,8 @@ rollback:
write_seqcount_end(&devnet_rename_seq);
+ netdev_adjacent_rename_links(dev, oldname);
+
write_lock_bh(&dev_base_lock);
hlist_del_rcu(&dev->name_hlist);
write_unlock_bh(&dev_base_lock);
@@ -1137,6 +1140,7 @@ rollback:
err = ret;
write_seqcount_begin(&devnet_rename_seq);
memcpy(dev->name, oldname, IFNAMSIZ);
+ memcpy(oldname, newname, IFNAMSIZ);
goto rollback;
} else {
pr_err("%s: name change rollback failed: %d\n",
@@ -1566,14 +1570,14 @@ EXPORT_SYMBOL(unregister_netdevice_notifier);
* are as for raw_notifier_call_chain().
*/
-int call_netdevice_notifiers_info(unsigned long val, struct net_device *dev,
- struct netdev_notifier_info *info)
+static 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
@@ -1699,7 +1703,7 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
skb_scrub_packet(skb, true);
skb->protocol = eth_type_trans(skb, dev);
- return netif_rx(skb);
+ return netif_rx_internal(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
@@ -2079,7 +2083,7 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq)
}
EXPORT_SYMBOL(netif_set_real_num_tx_queues);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
/**
* netif_set_real_num_rx_queues - set actual number of RX queues used
* @dev: Network device
@@ -2145,30 +2149,42 @@ void __netif_schedule(struct Qdisc *q)
}
EXPORT_SYMBOL(__netif_schedule);
-void dev_kfree_skb_irq(struct sk_buff *skb)
+struct dev_kfree_skb_cb {
+ enum skb_free_reason reason;
+};
+
+static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb)
{
- if (atomic_dec_and_test(&skb->users)) {
- struct softnet_data *sd;
- unsigned long flags;
+ return (struct dev_kfree_skb_cb *)skb->cb;
+}
+
+void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason)
+{
+ unsigned long flags;
- local_irq_save(flags);
- sd = &__get_cpu_var(softnet_data);
- skb->next = sd->completion_queue;
- sd->completion_queue = skb;
- raise_softirq_irqoff(NET_TX_SOFTIRQ);
- local_irq_restore(flags);
+ if (likely(atomic_read(&skb->users) == 1)) {
+ smp_rmb();
+ atomic_set(&skb->users, 0);
+ } else if (likely(!atomic_dec_and_test(&skb->users))) {
+ return;
}
+ get_kfree_skb_cb(skb)->reason = reason;
+ local_irq_save(flags);
+ skb->next = __this_cpu_read(softnet_data.completion_queue);
+ __this_cpu_write(softnet_data.completion_queue, skb);
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_restore(flags);
}
-EXPORT_SYMBOL(dev_kfree_skb_irq);
+EXPORT_SYMBOL(__dev_kfree_skb_irq);
-void dev_kfree_skb_any(struct sk_buff *skb)
+void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason)
{
if (in_irq() || irqs_disabled())
- dev_kfree_skb_irq(skb);
+ __dev_kfree_skb_irq(skb, reason);
else
dev_kfree_skb(skb);
}
-EXPORT_SYMBOL(dev_kfree_skb_any);
+EXPORT_SYMBOL(__dev_kfree_skb_any);
/**
@@ -2442,13 +2458,8 @@ static void dev_gso_skb_destructor(struct sk_buff *skb)
{
struct dev_gso_cb *cb;
- do {
- struct sk_buff *nskb = skb->next;
-
- skb->next = nskb->next;
- nskb->next = NULL;
- kfree_skb(nskb);
- } while (skb->next);
+ kfree_skb_list(skb->next);
+ skb->next = NULL;
cb = DEV_GSO_CB(skb);
if (cb->destructor)
@@ -2523,21 +2534,6 @@ netdev_features_t netif_skb_features(struct sk_buff *skb)
}
EXPORT_SYMBOL(netif_skb_features);
-/*
- * Returns true if either:
- * 1. skb has frag_list and the device doesn't support FRAGLIST, or
- * 2. skb is fragmented and the device does not support SG.
- */
-static inline int skb_needs_linearize(struct sk_buff *skb,
- netdev_features_t features)
-{
- return skb_is_nonlinear(skb) &&
- ((skb_has_frag_list(skb) &&
- !(features & NETIF_F_FRAGLIST)) ||
- (skb_shinfo(skb)->nr_frags &&
- !(features & NETIF_F_SG)));
-}
-
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
@@ -2605,8 +2601,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
dev_queue_xmit_nit(skb, dev);
skb_len = skb->len;
- rc = ops->ndo_start_xmit(skb, dev);
-
+ trace_net_dev_start_xmit(skb, dev);
+ rc = ops->ndo_start_xmit(skb, dev);
trace_net_dev_xmit(skb, rc, dev, skb_len);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
@@ -2624,6 +2620,7 @@ gso:
dev_queue_xmit_nit(nskb, dev);
skb_len = nskb->len;
+ trace_net_dev_start_xmit(nskb, dev);
rc = ops->ndo_start_xmit(nskb, dev);
trace_net_dev_xmit(nskb, rc, dev, skb_len);
if (unlikely(rc != NETDEV_TX_OK)) {
@@ -2744,7 +2741,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
return rc;
}
-#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
static void skb_update_prio(struct sk_buff *skb)
{
struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
@@ -2781,8 +2778,9 @@ int dev_loopback_xmit(struct sk_buff *skb)
EXPORT_SYMBOL(dev_loopback_xmit);
/**
- * dev_queue_xmit - transmit a buffer
+ * __dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
+ * @accel_priv: private data used for L2 forwarding offload
*
* Queue a buffer for transmission to a network device. The caller must
* have set the device and priority and built the buffer before calling
@@ -3014,7 +3012,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
}
skb_reset_network_header(skb);
- if (!skb_get_rxhash(skb))
+ if (!skb_get_hash(skb))
goto done;
flow_table = rcu_dereference(rxqueue->rps_flow_table);
@@ -3159,7 +3157,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen)
rcu_read_lock();
fl = rcu_dereference(sd->flow_limit);
if (fl) {
- new_flow = skb_get_rxhash(skb) & (fl->num_buckets - 1);
+ new_flow = skb_get_hash(skb) & (fl->num_buckets - 1);
old_flow = fl->history[fl->history_head];
fl->history[fl->history_head] = new_flow;
@@ -3227,22 +3225,7 @@ enqueue:
return NET_RX_DROP;
}
-/**
- * netif_rx - post buffer to the network code
- * @skb: buffer to post
- *
- * This function receives a packet from a device driver and queues it for
- * the upper (protocol) levels to process. It always succeeds. The buffer
- * may be dropped during processing for congestion control or by the
- * protocol layers.
- *
- * return values:
- * NET_RX_SUCCESS (no congestion)
- * NET_RX_DROP (packet was dropped)
- *
- */
-
-int netif_rx(struct sk_buff *skb)
+static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
@@ -3278,14 +3261,38 @@ int netif_rx(struct sk_buff *skb)
}
return ret;
}
+
+/**
+ * netif_rx - post buffer to the network code
+ * @skb: buffer to post
+ *
+ * This function receives a packet from a device driver and queues it for
+ * the upper (protocol) levels to process. It always succeeds. The buffer
+ * may be dropped during processing for congestion control or by the
+ * protocol layers.
+ *
+ * return values:
+ * NET_RX_SUCCESS (no congestion)
+ * NET_RX_DROP (packet was dropped)
+ *
+ */
+
+int netif_rx(struct sk_buff *skb)
+{
+ trace_netif_rx_entry(skb);
+
+ return netif_rx_internal(skb);
+}
EXPORT_SYMBOL(netif_rx);
int netif_rx_ni(struct sk_buff *skb)
{
int err;
+ trace_netif_rx_ni_entry(skb);
+
preempt_disable();
- err = netif_rx(skb);
+ err = netif_rx_internal(skb);
if (local_softirq_pending())
do_softirq();
preempt_enable();
@@ -3311,7 +3318,10 @@ static void net_tx_action(struct softirq_action *h)
clist = clist->next;
WARN_ON(atomic_read(&skb->users));
- trace_kfree_skb(skb, net_tx_action);
+ if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED))
+ trace_consume_skb(skb);
+ else
+ trace_kfree_skb(skb, net_tx_action);
__kfree_skb(skb);
}
}
@@ -3667,22 +3677,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
return ret;
}
-/**
- * netif_receive_skb - process receive buffer from network
- * @skb: buffer to process
- *
- * netif_receive_skb() is the main receive data processing function.
- * It always succeeds. The buffer may be dropped during processing
- * for congestion control or by the protocol layers.
- *
- * This function may only be called from softirq context and interrupts
- * should be enabled.
- *
- * Return values (usually ignored):
- * NET_RX_SUCCESS: no congestion
- * NET_RX_DROP: packet was dropped
- */
-int netif_receive_skb(struct sk_buff *skb)
+static int netif_receive_skb_internal(struct sk_buff *skb)
{
net_timestamp_check(netdev_tstamp_prequeue, skb);
@@ -3708,6 +3703,28 @@ int netif_receive_skb(struct sk_buff *skb)
#endif
return __netif_receive_skb(skb);
}
+
+/**
+ * netif_receive_skb - process receive buffer from network
+ * @skb: buffer to process
+ *
+ * netif_receive_skb() is the main receive data processing function.
+ * It always succeeds. The buffer may be dropped during processing
+ * for congestion control or by the protocol layers.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb(struct sk_buff *skb)
+{
+ trace_netif_receive_skb_entry(skb);
+
+ return netif_receive_skb_internal(skb);
+}
EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending
@@ -3757,7 +3774,7 @@ static int napi_gro_complete(struct sk_buff *skb)
if (ptype->type != type || !ptype->callbacks.gro_complete)
continue;
- err = ptype->callbacks.gro_complete(skb);
+ err = ptype->callbacks.gro_complete(skb, 0);
break;
}
rcu_read_unlock();
@@ -3769,7 +3786,7 @@ static int napi_gro_complete(struct sk_buff *skb)
}
out:
- return netif_receive_skb(skb);
+ return netif_receive_skb_internal(skb);
}
/* napi->gro_list contains packets ordered by age.
@@ -3805,10 +3822,18 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff *p;
unsigned int maclen = skb->dev->hard_header_len;
+ u32 hash = skb_get_hash_raw(skb);
for (p = napi->gro_list; p; p = p->next) {
unsigned long diffs;
+ NAPI_GRO_CB(p)->flush = 0;
+
+ if (hash != skb_get_hash_raw(p)) {
+ NAPI_GRO_CB(p)->same_flow = 0;
+ continue;
+ }
+
diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
diffs |= p->vlan_tci ^ skb->vlan_tci;
if (maclen == ETH_HLEN)
@@ -3819,7 +3844,23 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
skb_gro_mac_header(skb),
maclen);
NAPI_GRO_CB(p)->same_flow = !diffs;
- NAPI_GRO_CB(p)->flush = 0;
+ }
+}
+
+static void skb_gro_reset_offset(struct sk_buff *skb)
+{
+ const struct skb_shared_info *pinfo = skb_shinfo(skb);
+ const skb_frag_t *frag0 = &pinfo->frags[0];
+
+ 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) == skb_tail_pointer(skb) &&
+ pinfo->nr_frags &&
+ !PageHighMem(skb_frag_page(frag0))) {
+ NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+ NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
}
}
@@ -3838,7 +3879,9 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
if (skb_is_gso(skb) || skb_has_frag_list(skb))
goto normal;
+ skb_gro_reset_offset(skb);
gro_list_prepare(napi, skb);
+ NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */
rcu_read_lock();
list_for_each_entry_rcu(ptype, head, list) {
@@ -3850,6 +3893,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
NAPI_GRO_CB(skb)->same_flow = 0;
NAPI_GRO_CB(skb)->flush = 0;
NAPI_GRO_CB(skb)->free = 0;
+ NAPI_GRO_CB(skb)->udp_mark = 0;
pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
break;
@@ -3874,10 +3918,23 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
if (same_flow)
goto ok;
- if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS)
+ if (NAPI_GRO_CB(skb)->flush)
goto normal;
- napi->gro_count++;
+ if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
+ struct sk_buff *nskb = napi->gro_list;
+
+ /* locate the end of the list to select the 'oldest' flow */
+ while (nskb->next) {
+ pp = &nskb->next;
+ nskb = *pp;
+ }
+ *pp = NULL;
+ nskb->next = NULL;
+ napi_gro_complete(nskb);
+ } else {
+ napi->gro_count++;
+ }
NAPI_GRO_CB(skb)->count = 1;
NAPI_GRO_CB(skb)->age = jiffies;
skb_shinfo(skb)->gso_size = skb_gro_len(skb);
@@ -3915,12 +3972,39 @@ normal:
goto pull;
}
+struct packet_offload *gro_find_receive_by_type(__be16 type)
+{
+ struct list_head *offload_head = &offload_base;
+ struct packet_offload *ptype;
+
+ list_for_each_entry_rcu(ptype, offload_head, list) {
+ if (ptype->type != type || !ptype->callbacks.gro_receive)
+ continue;
+ return ptype;
+ }
+ return NULL;
+}
+EXPORT_SYMBOL(gro_find_receive_by_type);
+
+struct packet_offload *gro_find_complete_by_type(__be16 type)
+{
+ struct list_head *offload_head = &offload_base;
+ struct packet_offload *ptype;
+
+ list_for_each_entry_rcu(ptype, offload_head, list) {
+ if (ptype->type != type || !ptype->callbacks.gro_complete)
+ continue;
+ return ptype;
+ }
+ return NULL;
+}
+EXPORT_SYMBOL(gro_find_complete_by_type);
static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
{
switch (ret) {
case GRO_NORMAL:
- if (netif_receive_skb(skb))
+ if (netif_receive_skb_internal(skb))
ret = GRO_DROP;
break;
@@ -3943,26 +4027,9 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
return ret;
}
-static void skb_gro_reset_offset(struct sk_buff *skb)
-{
- const struct skb_shared_info *pinfo = skb_shinfo(skb);
- const skb_frag_t *frag0 = &pinfo->frags[0];
-
- 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) == skb_tail_pointer(skb) &&
- pinfo->nr_frags &&
- !PageHighMem(skb_frag_page(frag0))) {
- NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
- NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
- }
-}
-
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
- skb_gro_reset_offset(skb);
+ trace_napi_gro_receive_entry(skb);
return napi_skb_finish(dev_gro_receive(napi, skb), skb);
}
@@ -3986,8 +4053,7 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
if (!skb) {
skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD);
- if (skb)
- napi->skb = skb;
+ napi->skb = skb;
}
return skb;
}
@@ -3998,12 +4064,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
{
switch (ret) {
case GRO_NORMAL:
- case GRO_HELD:
- skb->protocol = eth_type_trans(skb, skb->dev);
-
- if (ret == GRO_HELD)
- skb_gro_pull(skb, -ETH_HLEN);
- else if (netif_receive_skb(skb))
+ if (netif_receive_skb_internal(skb))
ret = GRO_DROP;
break;
@@ -4012,6 +4073,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
napi_reuse_skb(napi, skb);
break;
+ case GRO_HELD:
case GRO_MERGED:
break;
}
@@ -4022,36 +4084,15 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *
static 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;
- }
+ if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) {
+ napi_reuse_skb(napi, skb);
+ return NULL;
}
+ skb->protocol = eth_type_trans(skb, 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;
-
-out:
return skb;
}
@@ -4062,12 +4103,14 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
if (!skb)
return GRO_DROP;
+ trace_napi_gro_frags_entry(skb);
+
return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
}
EXPORT_SYMBOL(napi_gro_frags);
/*
- * net_rps_action sends any pending IPI's for rps.
+ * net_rps_action_and_irq_enable sends any pending IPI's for rps.
* Note: called with local irq disabled, but exits with local irq enabled.
*/
static void net_rps_action_and_irq_enable(struct softnet_data *sd)
@@ -4272,17 +4315,10 @@ 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);
- }
-
+ kfree_skb_list(napi->gro_list);
napi->gro_list = NULL;
napi->gro_count = 0;
}
@@ -4399,19 +4435,6 @@ struct netdev_adjacent {
struct rcu_head rcu;
};
-static struct netdev_adjacent *__netdev_find_adj_rcu(struct net_device *dev,
- struct net_device *adj_dev,
- struct list_head *adj_list)
-{
- struct netdev_adjacent *adj;
-
- list_for_each_entry_rcu(adj, adj_list, list) {
- if (adj->dev == adj_dev)
- return adj;
- }
- return NULL;
-}
-
static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *adj_list)
@@ -4450,13 +4473,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
* Find out if a device is linked to an upper device and return true in case
* it is. The caller must hold the RTNL lock.
*/
-bool netdev_has_any_upper_dev(struct net_device *dev)
+static bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
return !list_empty(&dev->all_adj_list.upper);
}
-EXPORT_SYMBOL(netdev_has_any_upper_dev);
/**
* netdev_master_upper_dev_get - Get master upper device
@@ -4576,6 +4598,27 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
/**
+ * netdev_lower_get_first_private_rcu - Get the first ->private from the
+ * lower neighbour list, RCU
+ * variant
+ * @dev: device
+ *
+ * Gets the first netdev_adjacent->private from the dev's lower neighbour
+ * list. The caller must hold RCU read lock.
+ */
+void *netdev_lower_get_first_private_rcu(struct net_device *dev)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_first_or_null_rcu(&dev->adj_list.lower,
+ struct netdev_adjacent, list);
+ if (lower)
+ return lower->private;
+ return NULL;
+}
+EXPORT_SYMBOL(netdev_lower_get_first_private_rcu);
+
+/**
* netdev_master_upper_dev_get_rcu - Get master upper device
* @dev: device
*
@@ -4594,13 +4637,36 @@ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu);
+int netdev_adjacent_sysfs_add(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *dev_list)
+{
+ char linkname[IFNAMSIZ+7];
+ sprintf(linkname, dev_list == &dev->adj_list.upper ?
+ "upper_%s" : "lower_%s", adj_dev->name);
+ return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj),
+ linkname);
+}
+void netdev_adjacent_sysfs_del(struct net_device *dev,
+ char *name,
+ struct list_head *dev_list)
+{
+ char linkname[IFNAMSIZ+7];
+ sprintf(linkname, dev_list == &dev->adj_list.upper ?
+ "upper_%s" : "lower_%s", name);
+ sysfs_remove_link(&(dev->dev.kobj), linkname);
+}
+
+#define netdev_adjacent_is_neigh_list(dev, dev_list) \
+ (dev_list == &dev->adj_list.upper || \
+ dev_list == &dev->adj_list.lower)
+
static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct net_device *adj_dev,
struct list_head *dev_list,
void *private, bool master)
{
struct netdev_adjacent *adj;
- char linkname[IFNAMSIZ+7];
int ret;
adj = __netdev_find_adj(dev, adj_dev, dev_list);
@@ -4623,16 +4689,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
pr_debug("dev_hold for %s, because of link added from %s to %s\n",
adj_dev->name, dev->name, adj_dev->name);
- if (dev_list == &dev->adj_list.lower) {
- sprintf(linkname, "lower_%s", adj_dev->name);
- ret = sysfs_create_link(&(dev->dev.kobj),
- &(adj_dev->dev.kobj), linkname);
- if (ret)
- goto free_adj;
- } else if (dev_list == &dev->adj_list.upper) {
- sprintf(linkname, "upper_%s", adj_dev->name);
- ret = sysfs_create_link(&(dev->dev.kobj),
- &(adj_dev->dev.kobj), linkname);
+ if (netdev_adjacent_is_neigh_list(dev, dev_list)) {
+ ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list);
if (ret)
goto free_adj;
}
@@ -4652,14 +4710,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
return 0;
remove_symlinks:
- if (dev_list == &dev->adj_list.lower) {
- sprintf(linkname, "lower_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- } else if (dev_list == &dev->adj_list.upper) {
- sprintf(linkname, "upper_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- }
-
+ if (netdev_adjacent_is_neigh_list(dev, dev_list))
+ netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
free_adj:
kfree(adj);
dev_put(adj_dev);
@@ -4667,12 +4719,11 @@ free_adj:
return ret;
}
-void __netdev_adjacent_dev_remove(struct net_device *dev,
- struct net_device *adj_dev,
- struct list_head *dev_list)
+static void __netdev_adjacent_dev_remove(struct net_device *dev,
+ struct net_device *adj_dev,
+ struct list_head *dev_list)
{
struct netdev_adjacent *adj;
- char linkname[IFNAMSIZ+7];
adj = __netdev_find_adj(dev, adj_dev, dev_list);
@@ -4692,13 +4743,8 @@ void __netdev_adjacent_dev_remove(struct net_device *dev,
if (adj->master)
sysfs_remove_link(&(dev->dev.kobj), "master");
- if (dev_list == &dev->adj_list.lower) {
- sprintf(linkname, "lower_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- } else if (dev_list == &dev->adj_list.upper) {
- sprintf(linkname, "upper_%s", adj_dev->name);
- sysfs_remove_link(&(dev->dev.kobj), linkname);
- }
+ if (netdev_adjacent_is_neigh_list(dev, dev_list))
+ netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
list_del_rcu(&adj->list);
pr_debug("dev_put for %s, because link removed from %s to %s\n",
@@ -4707,11 +4753,11 @@ void __netdev_adjacent_dev_remove(struct net_device *dev,
kfree_rcu(adj, rcu);
}
-int __netdev_adjacent_dev_link_lists(struct net_device *dev,
- struct net_device *upper_dev,
- struct list_head *up_list,
- struct list_head *down_list,
- void *private, bool master)
+static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list,
+ void *private, bool master)
{
int ret;
@@ -4730,8 +4776,8 @@ int __netdev_adjacent_dev_link_lists(struct net_device *dev,
return 0;
}
-int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
+static int __netdev_adjacent_dev_link(struct net_device *dev,
+ struct net_device *upper_dev)
{
return __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->all_adj_list.upper,
@@ -4739,26 +4785,26 @@ int __netdev_adjacent_dev_link(struct net_device *dev,
NULL, false);
}
-void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
- struct net_device *upper_dev,
- struct list_head *up_list,
- struct list_head *down_list)
+static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
+ struct net_device *upper_dev,
+ struct list_head *up_list,
+ struct list_head *down_list)
{
__netdev_adjacent_dev_remove(dev, upper_dev, up_list);
__netdev_adjacent_dev_remove(upper_dev, dev, down_list);
}
-void __netdev_adjacent_dev_unlink(struct net_device *dev,
- struct net_device *upper_dev)
+static void __netdev_adjacent_dev_unlink(struct net_device *dev,
+ struct net_device *upper_dev)
{
__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
&dev->all_adj_list.upper,
&upper_dev->all_adj_list.lower);
}
-int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
- struct net_device *upper_dev,
- void *private, bool master)
+static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
+ struct net_device *upper_dev,
+ void *private, bool master)
{
int ret = __netdev_adjacent_dev_link(dev, upper_dev);
@@ -4777,8 +4823,8 @@ int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
return 0;
}
-void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
- struct net_device *upper_dev)
+static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
+ struct net_device *upper_dev)
{
__netdev_adjacent_dev_unlink(dev, upper_dev);
__netdev_adjacent_dev_unlink_lists(dev, upper_dev,
@@ -4967,20 +5013,24 @@ void netdev_upper_dev_unlink(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_dev_unlink);
-void *netdev_lower_dev_get_private_rcu(struct net_device *dev,
- struct net_device *lower_dev)
+void netdev_adjacent_rename_links(struct net_device *dev, char *oldname)
{
- struct netdev_adjacent *lower;
+ struct netdev_adjacent *iter;
- if (!lower_dev)
- return NULL;
- lower = __netdev_find_adj_rcu(dev, lower_dev, &dev->adj_list.lower);
- if (!lower)
- return NULL;
+ list_for_each_entry(iter, &dev->adj_list.upper, list) {
+ netdev_adjacent_sysfs_del(iter->dev, oldname,
+ &iter->dev->adj_list.lower);
+ netdev_adjacent_sysfs_add(iter->dev, dev,
+ &iter->dev->adj_list.lower);
+ }
- return lower->private;
+ list_for_each_entry(iter, &dev->adj_list.lower, list) {
+ netdev_adjacent_sysfs_del(iter->dev, oldname,
+ &iter->dev->adj_list.upper);
+ netdev_adjacent_sysfs_add(iter->dev, dev,
+ &iter->dev->adj_list.upper);
+ }
}
-EXPORT_SYMBOL(netdev_lower_dev_get_private_rcu);
void *netdev_lower_dev_get_private(struct net_device *dev,
struct net_device *lower_dev)
@@ -5314,6 +5364,17 @@ int dev_change_flags(struct net_device *dev, unsigned int flags)
}
EXPORT_SYMBOL(dev_change_flags);
+static int __dev_set_mtu(struct net_device *dev, int new_mtu)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_change_mtu)
+ return ops->ndo_change_mtu(dev, new_mtu);
+
+ dev->mtu = new_mtu;
+ return 0;
+}
+
/**
* dev_set_mtu - Change maximum transfer unit
* @dev: device
@@ -5323,8 +5384,7 @@ EXPORT_SYMBOL(dev_change_flags);
*/
int dev_set_mtu(struct net_device *dev, int new_mtu)
{
- const struct net_device_ops *ops = dev->netdev_ops;
- int err;
+ int err, orig_mtu;
if (new_mtu == dev->mtu)
return 0;
@@ -5336,14 +5396,25 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
if (!netif_device_present(dev))
return -ENODEV;
- err = 0;
- if (ops->ndo_change_mtu)
- err = ops->ndo_change_mtu(dev, new_mtu);
- else
- dev->mtu = new_mtu;
+ err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev);
+ err = notifier_to_errno(err);
+ if (err)
+ return err;
- if (!err)
- call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ orig_mtu = dev->mtu;
+ err = __dev_set_mtu(dev, new_mtu);
+
+ if (!err) {
+ err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ err = notifier_to_errno(err);
+ if (err) {
+ /* setting mtu back and notifying everyone again,
+ * so that they have a chance to revert changes.
+ */
+ __dev_set_mtu(dev, orig_mtu);
+ call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
+ }
+ }
return err;
}
EXPORT_SYMBOL(dev_set_mtu);
@@ -5697,7 +5768,7 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev,
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
static int netif_alloc_rx_queues(struct net_device *dev)
{
unsigned int i, count = dev->num_rx_queues;
@@ -5836,13 +5907,8 @@ int register_netdevice(struct net_device *dev)
dev->features |= NETIF_F_SOFT_FEATURES;
dev->wanted_features = dev->features & dev->hw_features;
- /* Turn on no cache copy if HW is doing checksum */
if (!(dev->flags & IFF_LOOPBACK)) {
dev->hw_features |= NETIF_F_NOCACHE_COPY;
- if (dev->features & NETIF_F_ALL_CSUM) {
- dev->wanted_features |= NETIF_F_NOCACHE_COPY;
- dev->features |= NETIF_F_NOCACHE_COPY;
- }
}
/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
@@ -6247,7 +6313,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
return NULL;
}
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
if (rxqs < 1) {
pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n");
return NULL;
@@ -6303,7 +6369,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
if (netif_alloc_netdev_queues(dev))
goto free_all;
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
dev->num_rx_queues = rxqs;
dev->real_num_rx_queues = rxqs;
if (netif_alloc_rx_queues(dev))
@@ -6323,7 +6389,7 @@ free_all:
free_pcpu:
free_percpu(dev->pcpu_refcnt);
netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
kfree(dev->_rx);
#endif
@@ -6348,7 +6414,7 @@ void free_netdev(struct net_device *dev)
release_net(dev_net(dev));
netif_free_tx_queues(dev);
-#ifdef CONFIG_RPS
+#ifdef CONFIG_SYSFS
kfree(dev->_rx);
#endif
@@ -6618,11 +6684,11 @@ static int dev_cpu_callback(struct notifier_block *nfb,
/* Process offline CPU's input_pkt_queue */
while ((skb = __skb_dequeue(&oldsd->process_queue))) {
- netif_rx(skb);
+ netif_rx_internal(skb);
input_queue_head_incr(oldsd);
}
while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
- netif_rx(skb);
+ netif_rx_internal(skb);
input_queue_head_incr(oldsd);
}
@@ -6935,28 +7001,18 @@ static int __init net_dev_init(void)
for_each_possible_cpu(i) {
struct softnet_data *sd = &per_cpu(softnet_data, i);
- memset(sd, 0, sizeof(*sd));
skb_queue_head_init(&sd->input_pkt_queue);
skb_queue_head_init(&sd->process_queue);
- sd->completion_queue = NULL;
INIT_LIST_HEAD(&sd->poll_list);
- sd->output_queue = NULL;
sd->output_queue_tailp = &sd->output_queue;
#ifdef CONFIG_RPS
sd->csd.func = rps_trigger_softirq;
sd->csd.info = sd;
- sd->csd.flags = 0;
sd->cpu = i;
#endif
sd->backlog.poll = process_backlog;
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;