* - Ingress support
*/
-#include <asm/uaccess.h>
-#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/socket.h>
-#include <linux/sockios.h>
-#include <linux/in.h>
#include <linux/errno.h>
-#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
-#include <net/sock.h>
#include <net/pkt_sched.h>
/* Main transmission queue. */
*/
void qdisc_lock_tree(struct net_device *dev)
+ __acquires(dev->queue_lock)
+ __acquires(dev->ingress_lock)
{
spin_lock_bh(&dev->queue_lock);
spin_lock(&dev->ingress_lock);
}
+EXPORT_SYMBOL(qdisc_lock_tree);
void qdisc_unlock_tree(struct net_device *dev)
+ __releases(dev->ingress_lock)
+ __releases(dev->queue_lock)
{
spin_unlock(&dev->ingress_lock);
spin_unlock_bh(&dev->queue_lock);
}
+EXPORT_SYMBOL(qdisc_unlock_tree);
-/*
- dev->queue_lock serializes queue accesses for this device
- AND dev->qdisc pointer itself.
+static inline int qdisc_qlen(struct Qdisc *q)
+{
+ return q->q.qlen;
+}
- netif_tx_lock serializes accesses to device driver.
+static inline int dev_requeue_skb(struct sk_buff *skb, struct net_device *dev,
+ struct Qdisc *q)
+{
+ if (unlikely(skb->next))
+ dev->gso_skb = skb;
+ else
+ q->ops->requeue(skb, q);
- dev->queue_lock and netif_tx_lock are mutually exclusive,
- if one is grabbed, another must be free.
- */
+ netif_schedule(dev);
+ return 0;
+}
+static inline struct sk_buff *dev_dequeue_skb(struct net_device *dev,
+ struct Qdisc *q)
+{
+ struct sk_buff *skb;
-/* Kick device.
+ if ((skb = dev->gso_skb))
+ dev->gso_skb = NULL;
+ else
+ skb = q->dequeue(q);
- Returns: 0 - queue is empty or throttled.
- >0 - queue is not empty.
+ return skb;
+}
+
+static inline int handle_dev_cpu_collision(struct sk_buff *skb,
+ struct net_device *dev,
+ struct Qdisc *q)
+{
+ int ret;
- NOTE: Called under dev->queue_lock with locally disabled BH.
-*/
+ if (unlikely(dev->xmit_lock_owner == smp_processor_id())) {
+ /*
+ * Same CPU holding the lock. It may be a transient
+ * configuration error, when hard_start_xmit() recurses. We
+ * detect it by checking xmit owner and drop the packet when
+ * deadloop is detected. Return OK to try the next skb.
+ */
+ kfree_skb(skb);
+ if (net_ratelimit())
+ printk(KERN_WARNING "Dead loop on netdevice %s, "
+ "fix it urgently!\n", dev->name);
+ ret = qdisc_qlen(q);
+ } else {
+ /*
+ * Another cpu is holding lock, requeue & delay xmits for
+ * some time.
+ */
+ __get_cpu_var(netdev_rx_stat).cpu_collision++;
+ ret = dev_requeue_skb(skb, dev, q);
+ }
+ return ret;
+}
+
+/*
+ * NOTE: Called under dev->queue_lock with locally disabled BH.
+ *
+ * __LINK_STATE_QDISC_RUNNING guarantees only one CPU can process this
+ * device at a time. dev->queue_lock serializes queue accesses for
+ * this device AND dev->qdisc pointer itself.
+ *
+ * netif_tx_lock serializes accesses to device driver.
+ *
+ * dev->queue_lock and netif_tx_lock are mutually exclusive,
+ * if one is grabbed, another must be free.
+ *
+ * Note, that this procedure can be called by a watchdog timer
+ *
+ * Returns to the caller:
+ * 0 - queue is empty or throttled.
+ * >0 - queue is not empty.
+ *
+ */
static inline int qdisc_restart(struct net_device *dev)
{
struct Qdisc *q = dev->qdisc;
struct sk_buff *skb;
+ int ret = NETDEV_TX_BUSY;
/* Dequeue packet */
- if (((skb = dev->gso_skb)) || ((skb = q->dequeue(q)))) {
- unsigned nolock = (dev->features & NETIF_F_LLTX);
+ if (unlikely((skb = dev_dequeue_skb(dev, q)) == NULL))
+ return 0;
- dev->gso_skb = NULL;
- /*
- * When the driver has LLTX set it does its own locking
- * in start_xmit. No need to add additional overhead by
- * locking again. These checks are worth it because
- * even uncongested locks can be quite expensive.
- * The driver can do trylock like here too, in case
- * of lock congestion it should return -1 and the packet
- * will be requeued.
- */
- if (!nolock) {
- if (!netif_tx_trylock(dev)) {
- collision:
- /* So, someone grabbed the driver. */
-
- /* It may be transient configuration error,
- when hard_start_xmit() recurses. We detect
- it by checking xmit owner and drop the
- packet when deadloop is detected.
- */
- if (dev->xmit_lock_owner == smp_processor_id()) {
- kfree_skb(skb);
- if (net_ratelimit())
- printk(KERN_DEBUG "Dead loop on netdevice %s, fix it urgently!\n", dev->name);
- goto out;
- }
- __get_cpu_var(netdev_rx_stat).cpu_collision++;
- goto requeue;
- }
- }
+ /* And release queue */
+ spin_unlock(&dev->queue_lock);
- {
- /* And release queue */
- spin_unlock(&dev->queue_lock);
-
- if (!netif_queue_stopped(dev)) {
- int ret;
-
- ret = dev_hard_start_xmit(skb, dev);
- if (ret == NETDEV_TX_OK) {
- if (!nolock) {
- netif_tx_unlock(dev);
- }
- spin_lock(&dev->queue_lock);
- q = dev->qdisc;
- goto out;
- }
- if (ret == NETDEV_TX_LOCKED && nolock) {
- spin_lock(&dev->queue_lock);
- q = dev->qdisc;
- goto collision;
- }
- }
+ HARD_TX_LOCK(dev, smp_processor_id());
+ if (!netif_subqueue_stopped(dev, skb))
+ ret = dev_hard_start_xmit(skb, dev);
+ HARD_TX_UNLOCK(dev);
- /* NETDEV_TX_BUSY - we need to requeue */
- /* Release the driver */
- if (!nolock) {
- netif_tx_unlock(dev);
- }
- spin_lock(&dev->queue_lock);
- q = dev->qdisc;
- }
+ spin_lock(&dev->queue_lock);
+ q = dev->qdisc;
- /* Device kicked us out :(
- This is possible in three cases:
+ switch (ret) {
+ case NETDEV_TX_OK:
+ /* Driver sent out skb successfully */
+ ret = qdisc_qlen(q);
+ break;
- 0. driver is locked
- 1. fastroute is enabled
- 2. device cannot determine busy state
- before start of transmission (f.e. dialout)
- 3. device is buggy (ppp)
- */
+ case NETDEV_TX_LOCKED:
+ /* Driver try lock failed */
+ ret = handle_dev_cpu_collision(skb, dev, q);
+ break;
+
+ default:
+ /* Driver returned NETDEV_TX_BUSY - requeue skb */
+ if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit()))
+ printk(KERN_WARNING "BUG %s code %d qlen %d\n",
+ dev->name, ret, q->q.qlen);
-requeue:
- if (unlikely(q == &noop_qdisc))
- kfree_skb(skb);
- else if (skb->next)
- dev->gso_skb = skb;
- else
- q->ops->requeue(skb, q);
- netif_schedule(dev);
+ ret = dev_requeue_skb(skb, dev, q);
+ break;
}
- return 0;
-out:
- BUG_ON((int) q->q.qlen < 0);
- return q->q.qlen;
+ return ret;
}
void __qdisc_run(struct net_device *dev)
{
- do {
- if (!qdisc_restart(dev))
+ unsigned long start_time = jiffies;
+
+ while (qdisc_restart(dev)) {
+ if (netif_queue_stopped(dev))
break;
- } while (!netif_queue_stopped(dev));
+
+ /*
+ * Postpone processing if
+ * 1. another process needs the CPU;
+ * 2. we've been doing it for too long.
+ */
+ if (need_resched() || jiffies != start_time) {
+ netif_schedule(dev);
+ break;
+ }
+ }
clear_bit(__LINK_STATE_QDISC_RUNNING, &dev->state);
}
printk(KERN_INFO "NETDEV WATCHDOG: %s: transmit timed out\n",
dev->name);
dev->tx_timeout(dev);
+ WARN_ON_ONCE(1);
}
if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo)))
dev_hold(dev);
dev_put(dev);
}
-static void dev_watchdog_init(struct net_device *dev)
-{
- init_timer(&dev->watchdog_timer);
- dev->watchdog_timer.data = (unsigned long)dev;
- dev->watchdog_timer.function = dev_watchdog;
-}
-
void __netdev_watchdog_up(struct net_device *dev)
{
if (dev->tx_timeout) {
netif_tx_unlock_bh(dev);
}
+/**
+ * netif_carrier_on - set carrier
+ * @dev: network device
+ *
+ * Device has detected that carrier.
+ */
void netif_carrier_on(struct net_device *dev)
{
- if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state))
+ if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
linkwatch_fire_event(dev);
- if (netif_running(dev))
- __netdev_watchdog_up(dev);
+ if (netif_running(dev))
+ __netdev_watchdog_up(dev);
+ }
}
+EXPORT_SYMBOL(netif_carrier_on);
+/**
+ * netif_carrier_off - clear carrier
+ * @dev: network device
+ *
+ * Device has detected loss of carrier.
+ */
void netif_carrier_off(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state))
linkwatch_fire_event(dev);
}
+EXPORT_SYMBOL(netif_carrier_off);
/* "NOOP" scheduler: the best scheduler, recommended for all interfaces
under all circumstances. It is difficult to invent anything faster or
return NET_XMIT_CN;
}
-struct Qdisc_ops noop_qdisc_ops = {
+struct Qdisc_ops noop_qdisc_ops __read_mostly = {
.id = "noop",
.priv_size = 0,
.enqueue = noop_enqueue,
.ops = &noop_qdisc_ops,
.list = LIST_HEAD_INIT(noop_qdisc.list),
};
+EXPORT_SYMBOL(noop_qdisc);
-static struct Qdisc_ops noqueue_qdisc_ops = {
+static struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
.id = "noqueue",
.priv_size = 0,
.enqueue = noop_enqueue,
struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1);
- RTA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
+ NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
return skb->len;
-rtattr_failure:
+nla_put_failure:
return -1;
}
-static int pfifo_fast_init(struct Qdisc *qdisc, struct rtattr *opt)
+static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt)
{
int prio;
struct sk_buff_head *list = qdisc_priv(qdisc);
return 0;
}
-static struct Qdisc_ops pfifo_fast_ops = {
+static struct Qdisc_ops pfifo_fast_ops __read_mostly = {
.id = "pfifo_fast",
.priv_size = PFIFO_FAST_BANDS * sizeof(struct sk_buff_head),
.enqueue = pfifo_fast_enqueue,
errout:
return NULL;
}
+EXPORT_SYMBOL(qdisc_create_dflt);
/* Under dev->queue_lock and BH! */
void qdisc_reset(struct Qdisc *qdisc)
{
- struct Qdisc_ops *ops = qdisc->ops;
+ const struct Qdisc_ops *ops = qdisc->ops;
if (ops->reset)
ops->reset(qdisc);
}
+EXPORT_SYMBOL(qdisc_reset);
/* this is the rcu callback function to clean up a qdisc when there
* are no further references to it */
void qdisc_destroy(struct Qdisc *qdisc)
{
- struct Qdisc_ops *ops = qdisc->ops;
+ const struct Qdisc_ops *ops = qdisc->ops;
if (qdisc->flags & TCQ_F_BUILTIN ||
!atomic_dec_and_test(&qdisc->refcnt))
return;
list_del(&qdisc->list);
-#ifdef CONFIG_NET_ESTIMATOR
gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
-#endif
if (ops->reset)
ops->reset(qdisc);
if (ops->destroy)
dev_put(qdisc->dev);
call_rcu(&qdisc->q_rcu, __qdisc_destroy);
}
+EXPORT_SYMBOL(qdisc_destroy);
void dev_activate(struct net_device *dev)
{
{
struct Qdisc *qdisc;
struct sk_buff *skb;
+ int running;
spin_lock_bh(&dev->queue_lock);
qdisc = dev->qdisc;
dev_watchdog_down(dev);
- /* Wait for outstanding dev_queue_xmit calls. */
+ /* Wait for outstanding qdisc-less dev_queue_xmit calls. */
synchronize_rcu();
/* Wait for outstanding qdisc_run calls. */
- while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
- yield();
+ do {
+ while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state))
+ yield();
+
+ /*
+ * Double-check inside queue lock to ensure that all effects
+ * of the queue run are visible when we return.
+ */
+ spin_lock_bh(&dev->queue_lock);
+ running = test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state);
+ spin_unlock_bh(&dev->queue_lock);
+
+ /*
+ * The running flag should never be set at this point because
+ * we've already set dev->qdisc to noop_qdisc *inside* the same
+ * pair of spin locks. That is, if any qdisc_run starts after
+ * our initial test it should see the noop_qdisc and then
+ * clear the RUNNING bit before dropping the queue lock. So
+ * if it is set here then we've found a bug.
+ */
+ } while (WARN_ON_ONCE(running));
}
void dev_init_scheduler(struct net_device *dev)
INIT_LIST_HEAD(&dev->qdisc_list);
qdisc_unlock_tree(dev);
- dev_watchdog_init(dev);
+ setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev);
}
void dev_shutdown(struct net_device *dev)
BUG_TRAP(!timer_pending(&dev->watchdog_timer));
qdisc_unlock_tree(dev);
}
-
-EXPORT_SYMBOL(netif_carrier_on);
-EXPORT_SYMBOL(netif_carrier_off);
-EXPORT_SYMBOL(noop_qdisc);
-EXPORT_SYMBOL(qdisc_create_dflt);
-EXPORT_SYMBOL(qdisc_destroy);
-EXPORT_SYMBOL(qdisc_reset);
-EXPORT_SYMBOL(qdisc_lock_tree);
-EXPORT_SYMBOL(qdisc_unlock_tree);
projects / linux-2.6-omap-h63xx.git / blobdiff