#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
-#include <linux/if_bridge.h>
-#include <linux/if_macvlan.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <linux/random.h>
#include <trace/events/napi.h>
#include <linux/pci.h>
+#include <linux/inetdevice.h>
#include "net-sysfs.h"
* --ANK (980803)
*/
+static inline struct list_head *ptype_head(const struct packet_type *pt)
+{
+ if (pt->type == htons(ETH_P_ALL))
+ return &ptype_all;
+ else
+ return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
+}
+
/**
* dev_add_pack - add packet handler
* @pt: packet type declaration
void dev_add_pack(struct packet_type *pt)
{
- int hash;
+ struct list_head *head = ptype_head(pt);
- spin_lock_bh(&ptype_lock);
- if (pt->type == htons(ETH_P_ALL))
- list_add_rcu(&pt->list, &ptype_all);
- else {
- hash = ntohs(pt->type) & PTYPE_HASH_MASK;
- list_add_rcu(&pt->list, &ptype_base[hash]);
- }
- spin_unlock_bh(&ptype_lock);
+ spin_lock(&ptype_lock);
+ list_add_rcu(&pt->list, head);
+ spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(dev_add_pack);
*/
void __dev_remove_pack(struct packet_type *pt)
{
- struct list_head *head;
+ struct list_head *head = ptype_head(pt);
struct packet_type *pt1;
- spin_lock_bh(&ptype_lock);
-
- if (pt->type == htons(ETH_P_ALL))
- head = &ptype_all;
- else
- head = &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
+ spin_lock(&ptype_lock);
list_for_each_entry(pt1, head, list) {
if (pt == pt1) {
printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt);
out:
- spin_unlock_bh(&ptype_lock);
+ spin_unlock(&ptype_lock);
}
EXPORT_SYMBOL(__dev_remove_pack);
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
- * dev_get_by_flags - find any device with given flags
+ * dev_get_by_flags_rcu - find any device with given flags
* @net: the applicable net namespace
* @if_flags: IFF_* values
* @mask: bitmask of bits in if_flags to check
*
* Search for any interface with the given flags. Returns NULL if a device
- * is not found or a pointer to the device. The device returned has
- * had a reference added and the pointer is safe until the user calls
- * dev_put to indicate they have finished with it.
+ * is not found or a pointer to the device. Must be called inside
+ * rcu_read_lock(), and result refcount is unchanged.
*/
-struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags,
+struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
unsigned short mask)
{
struct net_device *dev, *ret;
ret = NULL;
- rcu_read_lock();
for_each_netdev_rcu(net, dev) {
if (((dev->flags ^ if_flags) & mask) == 0) {
- dev_hold(dev);
ret = dev;
break;
}
}
- rcu_read_unlock();
return ret;
}
-EXPORT_SYMBOL(dev_get_by_flags);
+EXPORT_SYMBOL(dev_get_by_flags_rcu);
/**
* dev_valid_name - check if name is okay for network device
if (net_ratelimit())
printk(KERN_CRIT "protocol %04x is "
"buggy, dev %s\n",
- skb2->protocol, dev->name);
+ ntohs(skb2->protocol),
+ dev->name);
skb_reset_network_header(skb2);
}
/*
* Try to orphan skb early, right before transmission by the device.
- * We cannot orphan skb if tx timestamp is requested, since
- * drivers need to call skb_tstamp_tx() to send the timestamp.
+ * 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_tx(skb)->flags) {
+ if (sk && !skb_shinfo(skb)->tx_flags) {
/* skb_tx_hash() wont be able to get sk.
* We copy sk_hash into skb->rxhash
*/
}
}
+/*
+ * 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, or if
+ * at least one of fragments is in highmem and device does not
+ * support DMA from it.
+ */
+static inline int skb_needs_linearize(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ return skb_is_nonlinear(skb) &&
+ ((skb_has_frag_list(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
+ (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
+ illegal_highdma(dev, skb))));
+}
+
int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq)
{
goto out_kfree_skb;
if (skb->next)
goto gso;
+ } else {
+ if (skb_needs_linearize(skb, dev) &&
+ __skb_linearize(skb))
+ goto out_kfree_skb;
+
+ /* If packet is not checksummed and device does not
+ * support checksumming for this protocol, complete
+ * checksumming here.
+ */
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ skb_set_transport_header(skb, skb->csum_start -
+ skb_headroom(skb));
+ if (!dev_can_checksum(dev, skb) &&
+ skb_checksum_help(skb))
+ goto out_kfree_skb;
+ }
}
rc = ops->ndo_start_xmit(skb, dev);
struct sk_buff *skb)
{
int queue_index;
- struct sock *sk = skb->sk;
+ const struct net_device_ops *ops = dev->netdev_ops;
- queue_index = sk_tx_queue_get(sk);
- if (queue_index < 0) {
- const struct net_device_ops *ops = dev->netdev_ops;
+ if (ops->ndo_select_queue) {
+ queue_index = ops->ndo_select_queue(dev, skb);
+ queue_index = dev_cap_txqueue(dev, queue_index);
+ } else {
+ struct sock *sk = skb->sk;
+ queue_index = sk_tx_queue_get(sk);
+ if (queue_index < 0) {
- if (ops->ndo_select_queue) {
- queue_index = ops->ndo_select_queue(dev, skb);
- queue_index = dev_cap_txqueue(dev, queue_index);
- } else {
queue_index = 0;
if (dev->real_num_tx_queues > 1)
queue_index = skb_tx_hash(dev, skb);
struct netdev_queue *txq)
{
spinlock_t *root_lock = qdisc_lock(q);
+ bool contended = qdisc_is_running(q);
int rc;
+ /*
+ * Heuristic to force contended enqueues to serialize on a
+ * separate lock before trying to get qdisc main lock.
+ * This permits __QDISC_STATE_RUNNING owner to get the lock more often
+ * and dequeue packets faster.
+ */
+ if (unlikely(contended))
+ spin_lock(&q->busylock);
+
spin_lock(root_lock);
if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
kfree_skb(skb);
rc = NET_XMIT_DROP;
} else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
- !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {
+ qdisc_run_begin(q)) {
/*
* This is a work-conserving queue; there are no old skbs
* waiting to be sent out; and the qdisc is not running -
if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE))
skb_dst_force(skb);
__qdisc_update_bstats(q, skb->len);
- if (sch_direct_xmit(skb, q, dev, txq, root_lock))
+ if (sch_direct_xmit(skb, q, dev, txq, root_lock)) {
+ if (unlikely(contended)) {
+ spin_unlock(&q->busylock);
+ contended = false;
+ }
__qdisc_run(q);
- else
- clear_bit(__QDISC_STATE_RUNNING, &q->state);
+ } else
+ qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
skb_dst_force(skb);
rc = qdisc_enqueue_root(skb, q);
- qdisc_run(q);
+ if (qdisc_run_begin(q)) {
+ if (unlikely(contended)) {
+ spin_unlock(&q->busylock);
+ contended = false;
+ }
+ __qdisc_run(q);
+ }
}
spin_unlock(root_lock);
-
+ if (unlikely(contended))
+ spin_unlock(&q->busylock);
return rc;
}
-/*
- * 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, or if
- * at least one of fragments is in highmem and device does not
- * support DMA from it.
- */
-static inline int skb_needs_linearize(struct sk_buff *skb,
- struct net_device *dev)
-{
- return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) ||
- (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) ||
- illegal_highdma(dev, skb)));
-}
-
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
struct Qdisc *q;
int rc = -ENOMEM;
- /* GSO will handle the following emulations directly. */
- if (netif_needs_gso(dev, skb))
- goto gso;
-
- /* Convert a paged skb to linear, if required */
- if (skb_needs_linearize(skb, dev) && __skb_linearize(skb))
- goto out_kfree_skb;
-
- /* If packet is not checksummed and device does not support
- * checksumming for this protocol, complete checksumming here.
- */
- if (skb->ip_summed == CHECKSUM_PARTIAL) {
- skb_set_transport_header(skb, skb->csum_start -
- skb_headroom(skb));
- if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb))
- goto out_kfree_skb;
- }
-
-gso:
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
rc = -ENETDOWN;
rcu_read_unlock_bh();
-out_kfree_skb:
kfree_skb(skb);
return rc;
out:
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
}
-#ifdef CONFIG_RPS
-
-/* One global table that all flow-based protocols share. */
-struct rps_sock_flow_table *rps_sock_flow_table __read_mostly;
-EXPORT_SYMBOL(rps_sock_flow_table);
-
/*
- * get_rps_cpu is called from netif_receive_skb and returns the target
- * CPU from the RPS map of the receiving queue for a given skb.
- * rcu_read_lock must be held on entry.
+ * __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.
*/
-static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
- struct rps_dev_flow **rflowp)
+__u32 __skb_get_rxhash(struct sk_buff *skb)
{
+ int nhoff, hash = 0, poff;
struct ipv6hdr *ip6;
struct iphdr *ip;
- struct netdev_rx_queue *rxqueue;
- struct rps_map *map;
- struct rps_dev_flow_table *flow_table;
- struct rps_sock_flow_table *sock_flow_table;
- int cpu = -1;
u8 ip_proto;
- u16 tcpu;
u32 addr1, addr2, ihl;
union {
u32 v32;
u16 v16[2];
} ports;
- if (skb_rx_queue_recorded(skb)) {
- u16 index = skb_get_rx_queue(skb);
- if (unlikely(index >= dev->num_rx_queues)) {
- WARN_ONCE(dev->num_rx_queues > 1, "%s received packet "
- "on queue %u, but number of RX queues is %u\n",
- dev->name, index, dev->num_rx_queues);
- goto done;
- }
- rxqueue = dev->_rx + index;
- } else
- rxqueue = dev->_rx;
-
- if (!rxqueue->rps_map && !rxqueue->rps_flow_table)
- goto done;
-
- if (skb->rxhash)
- goto got_hash; /* Skip hash computation on packet header */
+ nhoff = skb_network_offset(skb);
switch (skb->protocol) {
case __constant_htons(ETH_P_IP):
- if (!pskb_may_pull(skb, sizeof(*ip)))
+ if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
goto done;
- ip = (struct iphdr *) skb->data;
- ip_proto = ip->protocol;
+ ip = (struct iphdr *) (skb->data + nhoff);
+ if (ip->frag_off & htons(IP_MF | IP_OFFSET))
+ ip_proto = 0;
+ else
+ ip_proto = ip->protocol;
addr1 = (__force u32) ip->saddr;
addr2 = (__force u32) ip->daddr;
ihl = ip->ihl;
break;
case __constant_htons(ETH_P_IPV6):
- if (!pskb_may_pull(skb, sizeof(*ip6)))
+ if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
goto done;
- ip6 = (struct ipv6hdr *) skb->data;
+ ip6 = (struct ipv6hdr *) (skb->data + nhoff);
ip_proto = ip6->nexthdr;
addr1 = (__force u32) ip6->saddr.s6_addr32[3];
addr2 = (__force u32) ip6->daddr.s6_addr32[3];
default:
goto done;
}
- switch (ip_proto) {
- case IPPROTO_TCP:
- case IPPROTO_UDP:
- case IPPROTO_DCCP:
- case IPPROTO_ESP:
- case IPPROTO_AH:
- case IPPROTO_SCTP:
- case IPPROTO_UDPLITE:
- if (pskb_may_pull(skb, (ihl * 4) + 4)) {
- ports.v32 = * (__force u32 *) (skb->data + (ihl * 4));
+
+ ports.v32 = 0;
+ poff = proto_ports_offset(ip_proto);
+ if (poff >= 0) {
+ nhoff += ihl * 4 + 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]);
- break;
}
- default:
- ports.v32 = 0;
- break;
}
/* get a consistent hash (same value on both flow directions) */
if (addr2 < addr1)
swap(addr1, addr2);
- skb->rxhash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
- if (!skb->rxhash)
- skb->rxhash = 1;
-got_hash:
+ hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
+ if (!hash)
+ hash = 1;
+
+done:
+ return hash;
+}
+EXPORT_SYMBOL(__skb_get_rxhash);
+
+#ifdef CONFIG_RPS
+
+/* One global table that all flow-based protocols share. */
+struct rps_sock_flow_table *rps_sock_flow_table __read_mostly;
+EXPORT_SYMBOL(rps_sock_flow_table);
+
+/*
+ * get_rps_cpu is called from netif_receive_skb and returns the target
+ * CPU from the RPS map of the receiving queue for a given skb.
+ * rcu_read_lock must be held on entry.
+ */
+static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
+ struct rps_dev_flow **rflowp)
+{
+ struct netdev_rx_queue *rxqueue;
+ struct rps_map *map = NULL;
+ struct rps_dev_flow_table *flow_table;
+ struct rps_sock_flow_table *sock_flow_table;
+ int cpu = -1;
+ u16 tcpu;
+
+ if (skb_rx_queue_recorded(skb)) {
+ u16 index = skb_get_rx_queue(skb);
+ if (unlikely(index >= dev->num_rx_queues)) {
+ WARN_ONCE(dev->num_rx_queues > 1, "%s received packet "
+ "on queue %u, but number of RX queues is %u\n",
+ dev->name, index, dev->num_rx_queues);
+ goto done;
+ }
+ rxqueue = dev->_rx + index;
+ } else
+ rxqueue = dev->_rx;
+
+ if (rxqueue->rps_map) {
+ map = rcu_dereference(rxqueue->rps_map);
+ if (map && map->len == 1) {
+ tcpu = map->cpus[0];
+ if (cpu_online(tcpu))
+ cpu = tcpu;
+ goto done;
+ }
+ } else if (!rxqueue->rps_flow_table) {
+ goto done;
+ }
+
+ skb_reset_network_header(skb);
+ if (!skb_get_rxhash(skb))
+ goto done;
+
flow_table = rcu_dereference(rxqueue->rps_flow_table);
sock_flow_table = rcu_dereference(rps_sock_flow_table);
if (flow_table && sock_flow_table) {
}
}
- map = rcu_dereference(rxqueue->rps_map);
if (map) {
tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32];
struct rps_dev_flow voidflow, *rflow = &voidflow;
int cpu;
+ preempt_disable();
rcu_read_lock();
cpu = get_rps_cpu(skb->dev, skb, &rflow);
ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
rcu_read_unlock();
+ preempt_enable();
}
#else
{
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
-#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
-
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \
+ (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE))
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
unsigned char *addr) __read_mostly;
EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
#endif
-/*
- * If bridge module is loaded call bridging hook.
- * returns NULL if packet was consumed.
- */
-struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
- struct sk_buff *skb) __read_mostly;
-EXPORT_SYMBOL_GPL(br_handle_frame_hook);
-
-static inline struct sk_buff *handle_bridge(struct sk_buff *skb,
- struct packet_type **pt_prev, int *ret,
- struct net_device *orig_dev)
-{
- struct net_bridge_port *port;
-
- if (skb->pkt_type == PACKET_LOOPBACK ||
- (port = rcu_dereference(skb->dev->br_port)) == NULL)
- return skb;
-
- if (*pt_prev) {
- *ret = deliver_skb(skb, *pt_prev, orig_dev);
- *pt_prev = NULL;
- }
-
- return br_handle_frame_hook(port, skb);
-}
-#else
-#define handle_bridge(skb, pt_prev, ret, orig_dev) (skb)
-#endif
-
-#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE)
-struct sk_buff *(*macvlan_handle_frame_hook)(struct macvlan_port *p,
- struct sk_buff *skb) __read_mostly;
-EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook);
-
-static inline struct sk_buff *handle_macvlan(struct sk_buff *skb,
- struct packet_type **pt_prev,
- int *ret,
- struct net_device *orig_dev)
-{
- struct macvlan_port *port;
-
- port = rcu_dereference(skb->dev->macvlan_port);
- if (!port)
- return skb;
-
- if (*pt_prev) {
- *ret = deliver_skb(skb, *pt_prev, orig_dev);
- *pt_prev = NULL;
- }
- return macvlan_handle_frame_hook(port, skb);
-}
-#else
-#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb)
-#endif
-
#ifdef CONFIG_NET_CLS_ACT
/* TODO: Maybe we should just force sch_ingress to be compiled in
* when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
int result = TC_ACT_OK;
struct Qdisc *q;
- if (MAX_RED_LOOP < ttl++) {
- printk(KERN_WARNING
- "Redir loop detected Dropping packet (%d->%d)\n",
- skb->skb_iif, dev->ifindex);
+ if (unlikely(MAX_RED_LOOP < ttl++)) {
+ if (net_ratelimit())
+ pr_warning( "Redir loop detected Dropping packet (%d->%d)\n",
+ skb->skb_iif, dev->ifindex);
return TC_ACT_SHOT;
}
if (*pt_prev) {
*ret = deliver_skb(skb, *pt_prev, orig_dev);
*pt_prev = NULL;
- } else {
- /* Huh? Why does turning on AF_PACKET affect this? */
- skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
}
switch (ing_filter(skb)) {
rcu_read_unlock();
}
+/**
+ * netdev_rx_handler_register - register receive handler
+ * @dev: device to register a handler for
+ * @rx_handler: receive handler to register
+ * @rx_handler_data: data pointer that is used by rx handler
+ *
+ * Register a receive hander for a device. This handler will then be
+ * called from __netif_receive_skb. A negative errno code is returned
+ * on a failure.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int netdev_rx_handler_register(struct net_device *dev,
+ rx_handler_func_t *rx_handler,
+ void *rx_handler_data)
+{
+ ASSERT_RTNL();
+
+ if (dev->rx_handler)
+ return -EBUSY;
+
+ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
+ rcu_assign_pointer(dev->rx_handler, rx_handler);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_rx_handler_register);
+
+/**
+ * netdev_rx_handler_unregister - unregister receive handler
+ * @dev: device to unregister a handler from
+ *
+ * Unregister a receive hander from a device.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+void netdev_rx_handler_unregister(struct net_device *dev)
+{
+
+ ASSERT_RTNL();
+ rcu_assign_pointer(dev->rx_handler, NULL);
+ rcu_assign_pointer(dev->rx_handler_data, NULL);
+}
+EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
+
static inline void skb_bond_set_mac_by_master(struct sk_buff *skb,
struct net_device *master)
{
if (master->priv_flags & IFF_MASTER_ARPMON)
dev->last_rx = jiffies;
- if ((master->priv_flags & IFF_MASTER_ALB) && master->br_port) {
+ if ((master->priv_flags & IFF_MASTER_ALB) &&
+ (master->priv_flags & IFF_BRIDGE_PORT)) {
/* Do address unmangle. The local destination address
* will be always the one master has. Provides the right
* functionality in a bridge.
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
+ rx_handler_func_t *rx_handler;
struct net_device *orig_dev;
struct net_device *master;
struct net_device *null_or_orig;
if (!netdev_tstamp_prequeue)
net_timestamp_check(skb);
- if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
- return NET_RX_SUCCESS;
+ if (vlan_tx_tag_present(skb))
+ vlan_hwaccel_do_receive(skb);
/* if we've gotten here through NAPI, check netpoll */
if (netpoll_receive_skb(skb))
skb->dev = master;
}
- __get_cpu_var(softnet_data).processed++;
-
+ __this_cpu_inc(softnet_data.processed);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
skb->mac_len = skb->network_header - skb->mac_header;
ncls:
#endif
- skb = handle_bridge(skb, &pt_prev, &ret, orig_dev);
- if (!skb)
- goto out;
- skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev);
- if (!skb)
- goto out;
+ /* Handle special case of bridge or macvlan */
+ rx_handler = rcu_dereference(skb->dev->rx_handler);
+ if (rx_handler) {
+ if (pt_prev) {
+ ret = deliver_skb(skb, pt_prev, orig_dev);
+ pt_prev = NULL;
+ }
+ skb = rx_handler(skb);
+ if (!skb)
+ goto out;
+ }
/*
* Make sure frames received on VLAN interfaces stacked on
if (netdev_tstamp_prequeue)
net_timestamp_check(skb);
+ if (skb_defer_rx_timestamp(skb))
+ return NET_RX_SUCCESS;
+
#ifdef CONFIG_RPS
{
struct rps_dev_flow voidflow, *rflow = &voidflow;
return netif_receive_skb(skb);
}
-static void napi_gro_flush(struct napi_struct *napi)
+inline void napi_gro_flush(struct napi_struct *napi)
{
struct sk_buff *skb, *next;
napi->gro_count = 0;
napi->gro_list = NULL;
}
+EXPORT_SYMBOL(napi_gro_flush);
enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
int mac_len;
enum gro_result ret;
- if (!(skb->dev->features & NETIF_F_GRO))
+ if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb))
goto normal;
- if (skb_is_gso(skb) || skb_has_frags(skb))
+ if (skb_is_gso(skb) || skb_has_frag_list(skb))
goto normal;
rcu_read_lock();
put_page(skb_shinfo(skb)->frags[0].page);
memmove(skb_shinfo(skb)->frags,
skb_shinfo(skb)->frags + 1,
- --skb_shinfo(skb)->nr_frags);
+ --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t));
}
}
}
EXPORT_SYMBOL(dev_gro_receive);
-static gro_result_t
+static inline gro_result_t
__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),
+ unsigned long diffs;
+
+ diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
+ diffs |= compare_ether_header(skb_mac_header(p),
skb_gro_mac_header(skb));
+ NAPI_GRO_CB(p)->same_flow = !diffs;
NAPI_GRO_CB(p)->flush = 0;
}
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
- const struct net_device_stats *stats = dev_get_stats(dev);
+ struct rtnl_link_stats64 temp;
+ const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
- seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
- "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
+ seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
+ "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",
dev->name, stats->rx_bytes, stats->rx_packets,
stats->rx_errors,
stats->rx_dropped + stats->rx_missed_errors,
dev = list_first_entry(head, struct net_device, unreg_list);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
- synchronize_net();
+ rcu_barrier();
list_for_each_entry(dev, head, unreg_list)
dev_put(dev);
}
EXPORT_SYMBOL(netif_stacked_transfer_operstate);
+static int netif_alloc_rx_queues(struct net_device *dev)
+{
+#ifdef CONFIG_RPS
+ unsigned int i, count = dev->num_rx_queues;
+
+ if (count) {
+ struct netdev_rx_queue *rx;
+
+ rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
+ if (!rx) {
+ pr_err("netdev: Unable to allocate %u rx queues.\n",
+ count);
+ return -ENOMEM;
+ }
+ dev->_rx = rx;
+ atomic_set(&rx->count, count);
+
+ /*
+ * Set a pointer to first element in the array which holds the
+ * reference count.
+ */
+ for (i = 0; i < count; i++)
+ rx[i].first = rx;
+ }
+#endif
+ return 0;
+}
+
/**
* register_netdevice - register a network device
* @dev: device to register
dev->iflink = -1;
-#ifdef CONFIG_RPS
- if (!dev->num_rx_queues) {
- /*
- * Allocate a single RX queue if driver never called
- * alloc_netdev_mq
- */
-
- dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL);
- if (!dev->_rx) {
- ret = -ENOMEM;
- goto out;
- }
+ ret = netif_alloc_rx_queues(dev);
+ if (ret)
+ goto out;
- dev->_rx->first = dev->_rx;
- atomic_set(&dev->_rx->count, 1);
- dev->num_rx_queues = 1;
- }
-#endif
/* Init, if this function is available */
if (dev->netdev_ops->ndo_init) {
ret = dev->netdev_ops->ndo_init(dev);
if (dev->features & NETIF_F_SG)
dev->features |= NETIF_F_GSO;
+ /* Enable GRO and NETIF_F_HIGHDMA for vlans by default,
+ * vlan_dev_init() will do the dev->features check, so these features
+ * are enabled only if supported by underlying device.
+ */
+ dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA);
+
ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev);
ret = notifier_to_errno(ret);
if (ret)
/* paranoia */
BUG_ON(atomic_read(&dev->refcnt));
- WARN_ON(dev->ip_ptr);
+ WARN_ON(rcu_dereference_raw(dev->ip_ptr));
WARN_ON(dev->ip6_ptr);
WARN_ON(dev->dn_ptr);
/**
* dev_txq_stats_fold - fold tx_queues stats
* @dev: device to get statistics from
- * @stats: struct net_device_stats to hold results
+ * @stats: struct rtnl_link_stats64 to hold results
*/
void dev_txq_stats_fold(const struct net_device *dev,
- struct net_device_stats *stats)
+ struct rtnl_link_stats64 *stats)
{
- unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
+ u64 tx_bytes = 0, tx_packets = 0, tx_dropped = 0;
unsigned int i;
struct netdev_queue *txq;
for (i = 0; i < dev->num_tx_queues; i++) {
txq = netdev_get_tx_queue(dev, i);
+ spin_lock_bh(&txq->_xmit_lock);
tx_bytes += txq->tx_bytes;
tx_packets += txq->tx_packets;
tx_dropped += txq->tx_dropped;
+ spin_unlock_bh(&txq->_xmit_lock);
}
if (tx_bytes || tx_packets || tx_dropped) {
stats->tx_bytes = tx_bytes;
}
EXPORT_SYMBOL(dev_txq_stats_fold);
+/* Convert net_device_stats to rtnl_link_stats64. They have the same
+ * fields in the same order, with only the type differing.
+ */
+static void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
+ const struct net_device_stats *netdev_stats)
+{
+#if BITS_PER_LONG == 64
+ BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats));
+ memcpy(stats64, netdev_stats, sizeof(*stats64));
+#else
+ size_t i, n = sizeof(*stats64) / sizeof(u64);
+ const unsigned long *src = (const unsigned long *)netdev_stats;
+ u64 *dst = (u64 *)stats64;
+
+ BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) !=
+ sizeof(*stats64) / sizeof(u64));
+ for (i = 0; i < n; i++)
+ dst[i] = src[i];
+#endif
+}
+
/**
* dev_get_stats - get network device statistics
* @dev: device to get statistics from
+ * @storage: place to store stats
*
- * 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.
+ * Get network statistics from device. Return @storage.
+ * The device driver may provide its own method by setting
+ * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats;
+ * otherwise the internal statistics structure is used.
*/
-const struct net_device_stats *dev_get_stats(struct net_device *dev)
+struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
+ struct rtnl_link_stats64 *storage)
{
const struct net_device_ops *ops = dev->netdev_ops;
- if (ops->ndo_get_stats)
- return ops->ndo_get_stats(dev);
-
- dev_txq_stats_fold(dev, &dev->stats);
- return &dev->stats;
+ if (ops->ndo_get_stats64) {
+ memset(storage, 0, sizeof(*storage));
+ return ops->ndo_get_stats64(dev, storage);
+ }
+ if (ops->ndo_get_stats) {
+ netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev));
+ return storage;
+ }
+ netdev_stats_to_stats64(storage, &dev->stats);
+ dev_txq_stats_fold(dev, storage);
+ return storage;
}
EXPORT_SYMBOL(dev_get_stats);
struct net_device *dev;
size_t alloc_size;
struct net_device *p;
-#ifdef CONFIG_RPS
- struct netdev_rx_queue *rx;
- int i;
-#endif
BUG_ON(strlen(name) >= sizeof(dev->name));
goto free_p;
}
-#ifdef CONFIG_RPS
- rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
- if (!rx) {
- printk(KERN_ERR "alloc_netdev: Unable to allocate "
- "rx queues.\n");
- goto free_tx;
- }
-
- atomic_set(&rx->count, queue_count);
-
- /*
- * Set a pointer to first element in the array which holds the
- * reference count.
- */
- for (i = 0; i < queue_count; i++)
- rx[i].first = rx;
-#endif
dev = PTR_ALIGN(p, NETDEV_ALIGN);
dev->padded = (char *)dev - (char *)p;
if (dev_addr_init(dev))
- goto free_rx;
+ goto free_tx;
dev_mc_init(dev);
dev_uc_init(dev);
dev->real_num_tx_queues = queue_count;
#ifdef CONFIG_RPS
- dev->_rx = rx;
dev->num_rx_queues = queue_count;
#endif
strcpy(dev->name, name);
return dev;
-free_rx:
-#ifdef CONFIG_RPS
- kfree(rx);
free_tx:
-#endif
kfree(tx);
free_p:
kfree(p);
/* Notify protocols, that we are about to destroy
this device. They should clean all the things.
+
+ Note that dev->reg_state stays at NETREG_REGISTERED.
+ This is wanted because this way 8021q and macvlan know
+ the device is just moving and can keep their slaves up.
*/
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev);
return buffer;
}
+static int __netdev_printk(const char *level, const struct net_device *dev,
+ struct va_format *vaf)
+{
+ int r;
+
+ if (dev && dev->dev.parent)
+ r = dev_printk(level, dev->dev.parent, "%s: %pV",
+ netdev_name(dev), vaf);
+ else if (dev)
+ r = printk("%s%s: %pV", level, netdev_name(dev), vaf);
+ else
+ r = printk("%s(NULL net_device): %pV", level, vaf);
+
+ return r;
+}
+
+int netdev_printk(const char *level, const struct net_device *dev,
+ const char *format, ...)
+{
+ struct va_format vaf;
+ va_list args;
+ int r;
+
+ va_start(args, format);
+
+ vaf.fmt = format;
+ vaf.va = &args;
+
+ r = __netdev_printk(level, dev, &vaf);
+ va_end(args);
+
+ return r;
+}
+EXPORT_SYMBOL(netdev_printk);
+
+#define define_netdev_printk_level(func, level) \
+int func(const struct net_device *dev, const char *fmt, ...) \
+{ \
+ int r; \
+ struct va_format vaf; \
+ va_list args; \
+ \
+ va_start(args, fmt); \
+ \
+ vaf.fmt = fmt; \
+ vaf.va = &args; \
+ \
+ r = __netdev_printk(level, dev, &vaf); \
+ va_end(args); \
+ \
+ return r; \
+} \
+EXPORT_SYMBOL(func);
+
+define_netdev_printk_level(netdev_emerg, KERN_EMERG);
+define_netdev_printk_level(netdev_alert, KERN_ALERT);
+define_netdev_printk_level(netdev_crit, KERN_CRIT);
+define_netdev_printk_level(netdev_err, KERN_ERR);
+define_netdev_printk_level(netdev_warn, KERN_WARNING);
+define_netdev_printk_level(netdev_notice, KERN_NOTICE);
+define_netdev_printk_level(netdev_info, KERN_INFO);
+
static void __net_exit netdev_exit(struct net *net)
{
kfree(net->dev_name_head);