}
EXPORT_SYMBOL(net_disable_timestamp);
-static inline void net_timestamp(struct sk_buff *skb)
+static inline void net_timestamp_set(struct sk_buff *skb)
{
if (atomic_read(&netstamp_needed))
__net_timestamp(skb);
skb->tstamp.tv64 = 0;
}
+static inline void net_timestamp_check(struct sk_buff *skb)
+{
+ if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed))
+ __net_timestamp(skb);
+}
+
/**
* dev_forward_skb - loopback an skb to another netif
*
*
* return values:
* NET_RX_SUCCESS (no congestion)
- * NET_RX_DROP (packet was dropped)
+ * NET_RX_DROP (packet was dropped, but freed)
*
* dev_forward_skb can be used for injecting an skb from the
* start_xmit function of one device into the receive queue
{
skb_orphan(skb);
- if (!(dev->flags & IFF_UP))
- return NET_RX_DROP;
-
- if (skb->len > (dev->mtu + dev->hard_header_len))
+ if (!(dev->flags & IFF_UP) ||
+ (skb->len > (dev->mtu + dev->hard_header_len))) {
+ kfree_skb(skb);
return NET_RX_DROP;
-
+ }
skb_set_dev(skb, dev);
skb->tstamp.tv64 = 0;
skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_CLS_ACT
if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS)))
- net_timestamp(skb);
+ net_timestamp_set(skb);
#else
- net_timestamp(skb);
+ net_timestamp_set(skb);
#endif
rcu_read_lock();
local_irq_save(flags);
sd = &__get_cpu_var(softnet_data);
- q->next_sched = sd->output_queue;
- sd->output_queue = q;
+ q->next_sched = NULL;
+ *sd->output_queue_tailp = q;
+ sd->output_queue_tailp = &q->next_sched;
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_restore(flags);
}
if (!list_empty(&ptype_all))
dev_queue_xmit_nit(skb, dev);
- if (netif_needs_gso(dev, skb)) {
- if (unlikely(dev_gso_segment(skb)))
- goto out_kfree_skb;
- if (skb->next)
- goto gso;
- }
-
/*
* If device doesnt need skb->dst, release it right now while
* its hot in this cpu cache
skb_dst_drop(skb);
skb_orphan_try(skb);
+
+ if (netif_needs_gso(dev, skb)) {
+ if (unlikely(dev_gso_segment(skb)))
+ goto out_kfree_skb;
+ if (skb->next)
+ goto gso;
+ }
+
rc = ops->ndo_start_xmit(skb, dev);
if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
* waiting to be sent out; and the qdisc is not running -
* xmit the skb directly.
*/
+ 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))
__qdisc_run(q);
rc = NET_XMIT_SUCCESS;
} else {
+ skb_dst_force(skb);
rc = qdisc_enqueue_root(skb, q);
qdisc_run(q);
}
=======================================================================*/
int netdev_max_backlog __read_mostly = 1000;
+int netdev_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
int weight_p __read_mostly = 64; /* old backlog weight */
-DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
+/* Called with irq disabled */
+static inline void ____napi_schedule(struct softnet_data *sd,
+ struct napi_struct *napi)
+{
+ list_add_tail(&napi->poll_list, &sd->poll_list);
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+}
#ifdef CONFIG_RPS
int cpu = -1;
u8 ip_proto;
u16 tcpu;
- u32 addr1, addr2, ports, ihl;
+ u32 addr1, addr2, ihl;
+ union {
+ u32 v32;
+ u16 v16[2];
+ } ports;
if (skb_rx_queue_recorded(skb)) {
u16 index = skb_get_rx_queue(skb);
default:
goto done;
}
- ports = 0;
switch (ip_proto) {
case IPPROTO_TCP:
case IPPROTO_UDP:
case IPPROTO_SCTP:
case IPPROTO_UDPLITE:
if (pskb_may_pull(skb, (ihl * 4) + 4)) {
- __be16 *hports = (__be16 *) (skb->data + (ihl * 4));
- u32 sport, dport;
-
- sport = (__force u16) hports[0];
- dport = (__force u16) hports[1];
- if (dport < sport)
- swap(sport, dport);
- ports = (sport << 16) + dport;
+ ports.v32 = * (__force u32 *) (skb->data + (ihl * 4));
+ if (ports.v16[1] < ports.v16[0])
+ swap(ports.v16[0], ports.v16[1]);
+ break;
}
- 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, hashrnd);
+ skb->rxhash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
if (!skb->rxhash)
skb->rxhash = 1;
{
struct softnet_data *sd = data;
- __napi_schedule(&sd->backlog);
- __get_cpu_var(netdev_rx_stat).received_rps++;
+ ____napi_schedule(sd, &sd->backlog);
+ sd->received_rps++;
}
#endif /* CONFIG_RPS */
sd = &per_cpu(softnet_data, cpu);
local_irq_save(flags);
- __get_cpu_var(netdev_rx_stat).total++;
rps_lock(sd);
- if (sd->input_pkt_queue.qlen <= netdev_max_backlog) {
- if (sd->input_pkt_queue.qlen) {
+ if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) {
+ if (skb_queue_len(&sd->input_pkt_queue)) {
enqueue:
__skb_queue_tail(&sd->input_pkt_queue, skb);
#ifdef CONFIG_RPS
- *qtail = sd->input_queue_head + sd->input_pkt_queue.qlen;
+ *qtail = sd->input_queue_head +
+ skb_queue_len(&sd->input_pkt_queue);
#endif
rps_unlock(sd);
local_irq_restore(flags);
return NET_RX_SUCCESS;
}
- /* Schedule NAPI for backlog device */
- if (napi_schedule_prep(&sd->backlog)) {
+ /* Schedule NAPI for backlog device
+ * We can use non atomic operation since we own the queue lock
+ */
+ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) {
if (!rps_ipi_queued(sd))
- __napi_schedule(&sd->backlog);
+ ____napi_schedule(sd, &sd->backlog);
}
goto enqueue;
}
+ sd->dropped++;
rps_unlock(sd);
- __get_cpu_var(netdev_rx_stat).dropped++;
local_irq_restore(flags);
kfree_skb(skb);
if (netpoll_rx(skb))
return NET_RX_DROP;
- if (!skb->tstamp.tv64)
- net_timestamp(skb);
+ if (netdev_tstamp_prequeue)
+ net_timestamp_check(skb);
#ifdef CONFIG_RPS
{
local_irq_disable();
head = sd->output_queue;
sd->output_queue = NULL;
+ sd->output_queue_tailp = &sd->output_queue;
local_irq_enable();
while (head) {
#endif
#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE)
-struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *skb) __read_mostly;
+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,
int *ret,
struct net_device *orig_dev)
{
- if (skb->dev->macvlan_port == NULL)
+ 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(skb);
+ return macvlan_handle_frame_hook(port, skb);
}
#else
#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb)
int ret = NET_RX_DROP;
__be16 type;
- if (!skb->tstamp.tv64)
- net_timestamp(skb);
+ if (!netdev_tstamp_prequeue)
+ net_timestamp_check(skb);
if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb))
return NET_RX_SUCCESS;
skb->dev = master;
}
- __get_cpu_var(netdev_rx_stat).total++;
+ __get_cpu_var(softnet_data).processed++;
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
*/
int netif_receive_skb(struct sk_buff *skb)
{
+ if (netdev_tstamp_prequeue)
+ net_timestamp_check(skb);
+
#ifdef CONFIG_RPS
- struct rps_dev_flow voidflow, *rflow = &voidflow;
- int cpu, ret;
+ {
+ struct rps_dev_flow voidflow, *rflow = &voidflow;
+ int cpu, ret;
- rcu_read_lock();
+ rcu_read_lock();
- cpu = get_rps_cpu(skb->dev, skb, &rflow);
+ cpu = get_rps_cpu(skb->dev, skb, &rflow);
- if (cpu >= 0) {
- ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
- rcu_read_unlock();
- } else {
- rcu_read_unlock();
- ret = __netif_receive_skb(skb);
- }
+ if (cpu >= 0) {
+ ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
+ rcu_read_unlock();
+ } else {
+ rcu_read_unlock();
+ ret = __netif_receive_skb(skb);
+ }
- return ret;
+ return ret;
+ }
#else
return __netif_receive_skb(skb);
#endif
struct sk_buff *skb, *tmp;
rps_lock(sd);
- skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp)
+ skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
if (skb->dev == dev) {
__skb_unlink(skb, &sd->input_pkt_queue);
kfree_skb(skb);
- input_queue_head_incr(sd);
+ input_queue_head_add(sd, 1);
}
+ }
rps_unlock(sd);
+
+ skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
+ if (skb->dev == dev) {
+ __skb_unlink(skb, &sd->process_queue);
+ kfree_skb(skb);
+ }
+ }
}
static int napi_gro_complete(struct sk_buff *skb)
}
EXPORT_SYMBOL(napi_gro_frags);
+/*
+ * net_rps_action 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)
+{
+#ifdef CONFIG_RPS
+ struct softnet_data *remsd = sd->rps_ipi_list;
+
+ if (remsd) {
+ sd->rps_ipi_list = NULL;
+
+ local_irq_enable();
+
+ /* Send pending IPI's to kick RPS processing on remote cpus. */
+ while (remsd) {
+ struct softnet_data *next = remsd->rps_ipi_next;
+
+ if (cpu_online(remsd->cpu))
+ __smp_call_function_single(remsd->cpu,
+ &remsd->csd, 0);
+ remsd = next;
+ }
+ } else
+#endif
+ local_irq_enable();
+}
+
static int process_backlog(struct napi_struct *napi, int quota)
{
int work = 0;
- struct softnet_data *sd = &__get_cpu_var(softnet_data);
+ struct softnet_data *sd = container_of(napi, struct softnet_data, backlog);
+#ifdef CONFIG_RPS
+ /* Check if we have pending ipi, its better to send them now,
+ * not waiting net_rx_action() end.
+ */
+ if (sd->rps_ipi_list) {
+ local_irq_disable();
+ net_rps_action_and_irq_enable(sd);
+ }
+#endif
napi->weight = weight_p;
- do {
+ local_irq_disable();
+ while (work < quota) {
struct sk_buff *skb;
+ unsigned int qlen;
- local_irq_disable();
- rps_lock(sd);
- skb = __skb_dequeue(&sd->input_pkt_queue);
- if (!skb) {
- __napi_complete(napi);
- rps_unlock(sd);
+ while ((skb = __skb_dequeue(&sd->process_queue))) {
local_irq_enable();
- break;
+ __netif_receive_skb(skb);
+ if (++work >= quota)
+ return work;
+ local_irq_disable();
}
- input_queue_head_incr(sd);
- rps_unlock(sd);
- local_irq_enable();
- __netif_receive_skb(skb);
- } while (++work < quota);
+ rps_lock(sd);
+ qlen = skb_queue_len(&sd->input_pkt_queue);
+ if (qlen) {
+ input_queue_head_add(sd, qlen);
+ skb_queue_splice_tail_init(&sd->input_pkt_queue,
+ &sd->process_queue);
+ }
+ if (qlen < quota - work) {
+ /*
+ * Inline a custom version of __napi_complete().
+ * only current cpu owns and manipulates this napi,
+ * and NAPI_STATE_SCHED is the only possible flag set on backlog.
+ * we can use a plain write instead of clear_bit(),
+ * and we dont need an smp_mb() memory barrier.
+ */
+ list_del(&napi->poll_list);
+ napi->state = 0;
+
+ quota = work + qlen;
+ }
+ rps_unlock(sd);
+ }
+ local_irq_enable();
return work;
}
unsigned long flags;
local_irq_save(flags);
- list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list);
- __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ ____napi_schedule(&__get_cpu_var(softnet_data), n);
local_irq_restore(flags);
}
EXPORT_SYMBOL(__napi_schedule);
}
EXPORT_SYMBOL(netif_napi_del);
-/*
- * net_rps_action 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_disable(void)
-{
-#ifdef CONFIG_RPS
- struct softnet_data *sd = &__get_cpu_var(softnet_data);
- struct softnet_data *remsd = sd->rps_ipi_list;
-
- if (remsd) {
- sd->rps_ipi_list = NULL;
-
- local_irq_enable();
-
- /* Send pending IPI's to kick RPS processing on remote cpus. */
- while (remsd) {
- struct softnet_data *next = remsd->rps_ipi_next;
-
- if (cpu_online(remsd->cpu))
- __smp_call_function_single(remsd->cpu,
- &remsd->csd, 0);
- remsd = next;
- }
- } else
-#endif
- local_irq_enable();
-}
-
static void net_rx_action(struct softirq_action *h)
{
- struct list_head *list = &__get_cpu_var(softnet_data).poll_list;
+ struct softnet_data *sd = &__get_cpu_var(softnet_data);
unsigned long time_limit = jiffies + 2;
int budget = netdev_budget;
void *have;
local_irq_disable();
- while (!list_empty(list)) {
+ while (!list_empty(&sd->poll_list)) {
struct napi_struct *n;
int work, weight;
* entries to the tail of this list, and only ->poll()
* calls can remove this head entry from the list.
*/
- n = list_first_entry(list, struct napi_struct, poll_list);
+ n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list);
have = netpoll_poll_lock(n);
napi_complete(n);
local_irq_disable();
} else
- list_move_tail(&n->poll_list, list);
+ list_move_tail(&n->poll_list, &sd->poll_list);
}
netpoll_poll_unlock(have);
}
out:
- net_rps_action_and_irq_disable();
+ net_rps_action_and_irq_enable(sd);
#ifdef CONFIG_NET_DMA
/*
return;
softnet_break:
- __get_cpu_var(netdev_rx_stat).time_squeeze++;
+ sd->time_squeeze++;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
return 0;
}
-static struct netif_rx_stats *softnet_get_online(loff_t *pos)
+static struct softnet_data *softnet_get_online(loff_t *pos)
{
- struct netif_rx_stats *rc = NULL;
+ struct softnet_data *sd = NULL;
while (*pos < nr_cpu_ids)
if (cpu_online(*pos)) {
- rc = &per_cpu(netdev_rx_stat, *pos);
+ sd = &per_cpu(softnet_data, *pos);
break;
} else
++*pos;
- return rc;
+ return sd;
}
static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
static int softnet_seq_show(struct seq_file *seq, void *v)
{
- struct netif_rx_stats *s = v;
+ struct softnet_data *sd = v;
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
- s->total, s->dropped, s->time_squeeze, 0,
+ sd->processed, sd->dropped, sd->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision, s->received_rps);
+ sd->cpu_collision, sd->received_rps);
return 0;
}
void *ocpu)
{
struct sk_buff **list_skb;
- struct Qdisc **list_net;
struct sk_buff *skb;
unsigned int cpu, oldcpu = (unsigned long)ocpu;
struct softnet_data *sd, *oldsd;
*list_skb = oldsd->completion_queue;
oldsd->completion_queue = NULL;
- /* Find end of our output_queue. */
- list_net = &sd->output_queue;
- while (*list_net)
- list_net = &(*list_net)->next_sched;
/* Append output queue from offline CPU. */
- *list_net = oldsd->output_queue;
- oldsd->output_queue = NULL;
+ if (oldsd->output_queue) {
+ *sd->output_queue_tailp = oldsd->output_queue;
+ sd->output_queue_tailp = oldsd->output_queue_tailp;
+ oldsd->output_queue = NULL;
+ oldsd->output_queue_tailp = &oldsd->output_queue;
+ }
raise_softirq_irqoff(NET_TX_SOFTIRQ);
local_irq_enable();
/* Process offline CPU's input_pkt_queue */
while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) {
netif_rx(skb);
- input_queue_head_incr(oldsd);
+ input_queue_head_add(oldsd, 1);
}
+ while ((skb = __skb_dequeue(&oldsd->process_queue)))
+ netif_rx(skb);
return NOTIFY_OK;
}
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;