#include <linux/init.h>
#include <linux/rcupdate.h>
#include <linux/list.h>
+#include <linux/slab.h>
#include <net/pkt_sched.h>
+#include <net/dst.h>
/* Main transmission queue. */
* - updates to tree and tree walking are only done under the rtnl mutex.
*/
-static inline int qdisc_qlen(struct Qdisc *q)
-{
- return q->q.qlen;
-}
-
static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
{
- if (unlikely(skb->next))
- q->gso_skb = skb;
- else
- q->ops->requeue(skb, q);
-
+ skb_dst_force(skb);
+ q->gso_skb = skb;
+ q->qstats.requeues++;
+ q->q.qlen++; /* it's still part of the queue */
__netif_schedule(q);
+
return 0;
}
static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
{
- struct sk_buff *skb;
+ struct sk_buff *skb = q->gso_skb;
+
+ if (unlikely(skb)) {
+ struct net_device *dev = qdisc_dev(q);
+ struct netdev_queue *txq;
- if ((skb = q->gso_skb))
- q->gso_skb = NULL;
- else
+ /* check the reason of requeuing without tx lock first */
+ txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
+ if (!netif_tx_queue_frozen_or_stopped(txq)) {
+ q->gso_skb = NULL;
+ q->q.qlen--;
+ } else
+ skb = NULL;
+ } else {
skb = q->dequeue(q);
+ }
return skb;
}
*/
kfree_skb(skb);
if (net_ratelimit())
- printk(KERN_WARNING "Dead loop on netdevice %s, "
- "fix it urgently!\n", dev_queue->dev->name);
+ pr_warning("Dead loop on netdevice %s, fix it urgently!\n",
+ dev_queue->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++;
+ __this_cpu_inc(softnet_data.cpu_collision);
ret = dev_requeue_skb(skb, q);
}
return ret;
}
+/*
+ * Transmit one skb, and handle the return status as required. Holding the
+ * __QDISC_STATE_RUNNING bit guarantees that only one CPU can execute this
+ * function.
+ *
+ * Returns to the caller:
+ * 0 - queue is empty or throttled.
+ * >0 - queue is not empty.
+ */
+int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
+ struct net_device *dev, struct netdev_queue *txq,
+ spinlock_t *root_lock)
+{
+ int ret = NETDEV_TX_BUSY;
+
+ /* And release qdisc */
+ spin_unlock(root_lock);
+
+ HARD_TX_LOCK(dev, txq, smp_processor_id());
+ if (!netif_tx_queue_frozen_or_stopped(txq))
+ ret = dev_hard_start_xmit(skb, dev, txq);
+
+ HARD_TX_UNLOCK(dev, txq);
+
+ spin_lock(root_lock);
+
+ if (dev_xmit_complete(ret)) {
+ /* Driver sent out skb successfully or skb was consumed */
+ ret = qdisc_qlen(q);
+ } else if (ret == NETDEV_TX_LOCKED) {
+ /* Driver try lock failed */
+ ret = handle_dev_cpu_collision(skb, txq, q);
+ } else {
+ /* Driver returned NETDEV_TX_BUSY - requeue skb */
+ if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit()))
+ pr_warning("BUG %s code %d qlen %d\n",
+ dev->name, ret, q->q.qlen);
+
+ ret = dev_requeue_skb(skb, q);
+ }
+
+ if (ret && netif_tx_queue_frozen_or_stopped(txq))
+ ret = 0;
+
+ return ret;
+}
+
/*
* NOTE: Called under qdisc_lock(q) with locally disabled BH.
*
static inline int qdisc_restart(struct Qdisc *q)
{
struct netdev_queue *txq;
- int ret = NETDEV_TX_BUSY;
struct net_device *dev;
spinlock_t *root_lock;
struct sk_buff *skb;
/* Dequeue packet */
- if (unlikely((skb = dequeue_skb(q)) == NULL))
+ skb = dequeue_skb(q);
+ if (unlikely(!skb))
return 0;
-
+ WARN_ON_ONCE(skb_dst_is_noref(skb));
root_lock = qdisc_lock(q);
-
- /* And release qdisc */
- spin_unlock(root_lock);
-
dev = qdisc_dev(q);
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
- HARD_TX_LOCK(dev, txq, smp_processor_id());
- if (!netif_tx_queue_stopped(txq) &&
- !netif_tx_queue_frozen(txq))
- ret = dev_hard_start_xmit(skb, dev, txq);
- HARD_TX_UNLOCK(dev, txq);
-
- spin_lock(root_lock);
-
- switch (ret) {
- case NETDEV_TX_OK:
- /* Driver sent out skb successfully */
- ret = qdisc_qlen(q);
- break;
-
- case NETDEV_TX_LOCKED:
- /* Driver try lock failed */
- ret = handle_dev_cpu_collision(skb, txq, 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);
-
- ret = dev_requeue_skb(skb, q);
- break;
- }
-
- if (ret && (netif_tx_queue_stopped(txq) ||
- netif_tx_queue_frozen(txq)))
- ret = 0;
-
- return ret;
+ return sch_direct_xmit(skb, q, dev, txq, root_lock);
}
void __qdisc_run(struct Qdisc *q)
{
- unsigned long start_time = jiffies;
+ int quota = weight_p;
while (qdisc_restart(q)) {
/*
- * Postpone processing if
- * 1. another process needs the CPU;
- * 2. we've been doing it for too long.
+ * Ordered by possible occurrence: Postpone processing if
+ * 1. we've exceeded packet quota
+ * 2. another process needs the CPU;
*/
- if (need_resched() || jiffies != start_time) {
+ if (--quota <= 0 || need_resched()) {
__netif_schedule(q);
break;
}
}
- clear_bit(__QDISC_STATE_RUNNING, &q->state);
+ qdisc_run_end(q);
}
+unsigned long dev_trans_start(struct net_device *dev)
+{
+ unsigned long val, res = dev->trans_start;
+ unsigned int i;
+
+ for (i = 0; i < dev->num_tx_queues; i++) {
+ val = netdev_get_tx_queue(dev, i)->trans_start;
+ if (val && time_after(val, res))
+ res = val;
+ }
+ dev->trans_start = res;
+ return res;
+}
+EXPORT_SYMBOL(dev_trans_start);
+
static void dev_watchdog(unsigned long arg)
{
struct net_device *dev = (struct net_device *)arg;
if (netif_device_present(dev) &&
netif_running(dev) &&
netif_carrier_ok(dev)) {
- int some_queue_stopped = 0;
+ int some_queue_timedout = 0;
unsigned int i;
+ unsigned long trans_start;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq;
txq = netdev_get_tx_queue(dev, i);
- if (netif_tx_queue_stopped(txq)) {
- some_queue_stopped = 1;
+ /*
+ * old device drivers set dev->trans_start
+ */
+ trans_start = txq->trans_start ? : dev->trans_start;
+ if (netif_tx_queue_stopped(txq) &&
+ time_after(jiffies, (trans_start +
+ dev->watchdog_timeo))) {
+ some_queue_timedout = 1;
break;
}
}
- if (some_queue_stopped &&
- time_after(jiffies, (dev->trans_start +
- dev->watchdog_timeo))) {
- char drivername[64];
- WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit timed out\n",
- dev->name, netdev_drivername(dev, drivername, 64));
- dev->tx_timeout(dev);
+ if (some_queue_timedout) {
+ WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
+ dev->name, netdev_drivername(dev), i);
+ dev->netdev_ops->ndo_tx_timeout(dev);
}
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies +
void __netdev_watchdog_up(struct net_device *dev)
{
- if (dev->tx_timeout) {
+ if (dev->netdev_ops->ndo_tx_timeout) {
if (dev->watchdog_timeo <= 0)
dev->watchdog_timeo = 5*HZ;
if (!mod_timer(&dev->watchdog_timer,
void netif_carrier_on(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
+ if (dev->reg_state == NETREG_UNINITIALIZED)
+ return;
linkwatch_fire_event(dev);
if (netif_running(dev))
__netdev_watchdog_up(dev);
*/
void netif_carrier_off(struct net_device *dev)
{
- if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state))
+ if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
+ if (dev->reg_state == NETREG_UNINITIALIZED)
+ return;
linkwatch_fire_event(dev);
+ }
}
EXPORT_SYMBOL(netif_carrier_off);
+/**
+ * netif_notify_peers - notify network peers about existence of @dev
+ * @dev: network device
+ *
+ * Generate traffic such that interested network peers are aware of
+ * @dev, such as by generating a gratuitous ARP. This may be used when
+ * a device wants to inform the rest of the network about some sort of
+ * reconfiguration such as a failover event or virtual machine
+ * migration.
+ */
+void netif_notify_peers(struct net_device *dev)
+{
+ rtnl_lock();
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+ rtnl_unlock();
+}
+EXPORT_SYMBOL(netif_notify_peers);
+
/* "NOOP" scheduler: the best scheduler, recommended for all interfaces
under all circumstances. It is difficult to invent anything faster or
cheaper.
return NULL;
}
-static int noop_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
-{
- if (net_ratelimit())
- printk(KERN_DEBUG "%s deferred output. It is buggy.\n",
- skb->dev->name);
- kfree_skb(skb);
- return NET_XMIT_CN;
-}
-
struct Qdisc_ops noop_qdisc_ops __read_mostly = {
.id = "noop",
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
- .requeue = noop_requeue,
+ .peek = noop_dequeue,
.owner = THIS_MODULE,
};
static struct netdev_queue noop_netdev_queue = {
.qdisc = &noop_qdisc,
+ .qdisc_sleeping = &noop_qdisc,
};
struct Qdisc noop_qdisc = {
.list = LIST_HEAD_INIT(noop_qdisc.list),
.q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
.dev_queue = &noop_netdev_queue,
+ .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
};
EXPORT_SYMBOL(noop_qdisc);
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
- .requeue = noop_requeue,
+ .peek = noop_dequeue,
.owner = THIS_MODULE,
};
static struct Qdisc noqueue_qdisc;
static struct netdev_queue noqueue_netdev_queue = {
.qdisc = &noqueue_qdisc,
+ .qdisc_sleeping = &noqueue_qdisc,
};
static struct Qdisc noqueue_qdisc = {
.list = LIST_HEAD_INIT(noqueue_qdisc.list),
.q.lock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock),
.dev_queue = &noqueue_netdev_queue,
+ .busylock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.busylock),
};
-static const u8 prio2band[TC_PRIO_MAX+1] =
- { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 };
+static const u8 prio2band[TC_PRIO_MAX + 1] = {
+ 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
+};
/* 3-band FIFO queue: old style, but should be a bit faster than
generic prio+fifo combination.
#define PFIFO_FAST_BANDS 3
-static inline struct sk_buff_head *prio2list(struct sk_buff *skb,
- struct Qdisc *qdisc)
+/*
+ * Private data for a pfifo_fast scheduler containing:
+ * - queues for the three band
+ * - bitmap indicating which of the bands contain skbs
+ */
+struct pfifo_fast_priv {
+ u32 bitmap;
+ struct sk_buff_head q[PFIFO_FAST_BANDS];
+};
+
+/*
+ * Convert a bitmap to the first band number where an skb is queued, where:
+ * bitmap=0 means there are no skbs on any band.
+ * bitmap=1 means there is an skb on band 0.
+ * bitmap=7 means there are skbs on all 3 bands, etc.
+ */
+static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0};
+
+static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv,
+ int band)
{
- struct sk_buff_head *list = qdisc_priv(qdisc);
- return list + prio2band[skb->priority & TC_PRIO_MAX];
+ return priv->q + band;
}
-static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc)
+static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
{
- struct sk_buff_head *list = prio2list(skb, qdisc);
+ if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) {
+ int band = prio2band[skb->priority & TC_PRIO_MAX];
+ struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
+ struct sk_buff_head *list = band2list(priv, band);
- if (skb_queue_len(list) < qdisc_dev(qdisc)->tx_queue_len) {
+ priv->bitmap |= (1 << band);
qdisc->q.qlen++;
return __qdisc_enqueue_tail(skb, qdisc, list);
}
return qdisc_drop(skb, qdisc);
}
-static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc)
+static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
{
- int prio;
- struct sk_buff_head *list = qdisc_priv(qdisc);
+ struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
+ int band = bitmap2band[priv->bitmap];
- for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
- if (!skb_queue_empty(list + prio)) {
- qdisc->q.qlen--;
- return __qdisc_dequeue_head(qdisc, list + prio);
- }
+ if (likely(band >= 0)) {
+ struct sk_buff_head *list = band2list(priv, band);
+ struct sk_buff *skb = __qdisc_dequeue_head(qdisc, list);
+
+ qdisc->q.qlen--;
+ if (skb_queue_empty(list))
+ priv->bitmap &= ~(1 << band);
+
+ return skb;
}
return NULL;
}
-static int pfifo_fast_requeue(struct sk_buff *skb, struct Qdisc* qdisc)
+static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc)
{
- qdisc->q.qlen++;
- return __qdisc_requeue(skb, qdisc, prio2list(skb, qdisc));
+ struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
+ int band = bitmap2band[priv->bitmap];
+
+ if (band >= 0) {
+ struct sk_buff_head *list = band2list(priv, band);
+
+ return skb_peek(list);
+ }
+
+ return NULL;
}
-static void pfifo_fast_reset(struct Qdisc* qdisc)
+static void pfifo_fast_reset(struct Qdisc *qdisc)
{
int prio;
- struct sk_buff_head *list = qdisc_priv(qdisc);
+ struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
- __qdisc_reset_queue(qdisc, list + prio);
+ __qdisc_reset_queue(qdisc, band2list(priv, prio));
+ priv->bitmap = 0;
qdisc->qstats.backlog = 0;
qdisc->q.qlen = 0;
}
{
struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
- memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1);
+ memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt);
return skb->len;
static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt)
{
int prio;
- struct sk_buff_head *list = qdisc_priv(qdisc);
+ struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
- skb_queue_head_init(list + prio);
+ skb_queue_head_init(band2list(priv, prio));
+ /* Can by-pass the queue discipline */
+ qdisc->flags |= TCQ_F_CAN_BYPASS;
return 0;
}
-static struct Qdisc_ops pfifo_fast_ops __read_mostly = {
+struct Qdisc_ops pfifo_fast_ops __read_mostly = {
.id = "pfifo_fast",
- .priv_size = PFIFO_FAST_BANDS * sizeof(struct sk_buff_head),
+ .priv_size = sizeof(struct pfifo_fast_priv),
.enqueue = pfifo_fast_enqueue,
.dequeue = pfifo_fast_dequeue,
- .requeue = pfifo_fast_requeue,
+ .peek = pfifo_fast_peek,
.init = pfifo_fast_init,
.reset = pfifo_fast_reset,
.dump = pfifo_fast_dump,
.owner = THIS_MODULE,
};
+EXPORT_SYMBOL(pfifo_fast_ops);
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
struct Qdisc_ops *ops)
{
void *p;
struct Qdisc *sch;
- unsigned int size;
+ unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
int err = -ENOBUFS;
- /* ensure that the Qdisc and the private data are 32-byte aligned */
- size = QDISC_ALIGN(sizeof(*sch));
- size += ops->priv_size + (QDISC_ALIGNTO - 1);
+ p = kzalloc_node(size, GFP_KERNEL,
+ netdev_queue_numa_node_read(dev_queue));
- p = kzalloc(size, GFP_KERNEL);
if (!p)
goto errout;
sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
- sch->padded = (char *) sch - (char *) p;
-
+ /* if we got non aligned memory, ask more and do alignment ourself */
+ if (sch != p) {
+ kfree(p);
+ p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL,
+ netdev_queue_numa_node_read(dev_queue));
+ if (!p)
+ goto errout;
+ sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
+ sch->padded = (char *) sch - (char *) p;
+ }
INIT_LIST_HEAD(&sch->list);
skb_queue_head_init(&sch->q);
+ spin_lock_init(&sch->busylock);
sch->ops = ops;
sch->enqueue = ops->enqueue;
sch->dequeue = ops->dequeue;
return ERR_PTR(err);
}
-struct Qdisc * qdisc_create_dflt(struct net_device *dev,
- struct netdev_queue *dev_queue,
- struct Qdisc_ops *ops,
- unsigned int parentid)
+struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
+ struct Qdisc_ops *ops, unsigned int parentid)
{
struct Qdisc *sch;
if (ops->reset)
ops->reset(qdisc);
+
+ if (qdisc->gso_skb) {
+ kfree_skb(qdisc->gso_skb);
+ qdisc->gso_skb = NULL;
+ qdisc->q.qlen = 0;
+ }
}
EXPORT_SYMBOL(qdisc_reset);
+static void qdisc_rcu_free(struct rcu_head *head)
+{
+ struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
+
+ kfree((char *) qdisc - qdisc->padded);
+}
+
void qdisc_destroy(struct Qdisc *qdisc)
{
const struct Qdisc_ops *ops = qdisc->ops;
#ifdef CONFIG_NET_SCHED
qdisc_list_del(qdisc);
- qdisc_put_stab(qdisc->stab);
+ qdisc_put_stab(rtnl_dereference(qdisc->stab));
#endif
gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
if (ops->reset)
dev_put(qdisc_dev(qdisc));
kfree_skb(qdisc->gso_skb);
-
- kfree((char *) qdisc - qdisc->padded);
+ /*
+ * gen_estimator est_timer() might access qdisc->q.lock,
+ * wait a RCU grace period before freeing qdisc.
+ */
+ call_rcu(&qdisc->rcu_head, qdisc_rcu_free);
}
EXPORT_SYMBOL(qdisc_destroy);
-static bool dev_all_qdisc_sleeping_noop(struct net_device *dev)
+/* Attach toplevel qdisc to device queue. */
+struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
+ struct Qdisc *qdisc)
{
- unsigned int i;
+ struct Qdisc *oqdisc = dev_queue->qdisc_sleeping;
+ spinlock_t *root_lock;
- for (i = 0; i < dev->num_tx_queues; i++) {
- struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
+ root_lock = qdisc_lock(oqdisc);
+ spin_lock_bh(root_lock);
- if (txq->qdisc_sleeping != &noop_qdisc)
- return false;
- }
- return true;
+ /* Prune old scheduler */
+ if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1)
+ qdisc_reset(oqdisc);
+
+ /* ... and graft new one */
+ if (qdisc == NULL)
+ qdisc = &noop_qdisc;
+ dev_queue->qdisc_sleeping = qdisc;
+ rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc);
+
+ spin_unlock_bh(root_lock);
+
+ return oqdisc;
}
+EXPORT_SYMBOL(dev_graft_qdisc);
static void attach_one_default_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_unused)
{
- struct Qdisc *qdisc;
+ struct Qdisc *qdisc = &noqueue_qdisc;
if (dev->tx_queue_len) {
- qdisc = qdisc_create_dflt(dev, dev_queue,
+ qdisc = qdisc_create_dflt(dev_queue,
&pfifo_fast_ops, TC_H_ROOT);
if (!qdisc) {
- printk(KERN_INFO "%s: activation failed\n", dev->name);
+ netdev_info(dev, "activation failed\n");
return;
}
- } else {
- qdisc = &noqueue_qdisc;
}
dev_queue->qdisc_sleeping = qdisc;
}
+static void attach_default_qdiscs(struct net_device *dev)
+{
+ struct netdev_queue *txq;
+ struct Qdisc *qdisc;
+
+ txq = netdev_get_tx_queue(dev, 0);
+
+ if (!netif_is_multiqueue(dev) || dev->tx_queue_len == 0) {
+ netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
+ dev->qdisc = txq->qdisc_sleeping;
+ atomic_inc(&dev->qdisc->refcnt);
+ } else {
+ qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT);
+ if (qdisc) {
+ qdisc->ops->attach(qdisc);
+ dev->qdisc = qdisc;
+ }
+ }
+}
+
static void transition_one_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_need_watchdog)
clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state);
rcu_assign_pointer(dev_queue->qdisc, new_qdisc);
- if (need_watchdog_p && new_qdisc != &noqueue_qdisc)
+ if (need_watchdog_p && new_qdisc != &noqueue_qdisc) {
+ dev_queue->trans_start = 0;
*need_watchdog_p = 1;
+ }
}
void dev_activate(struct net_device *dev)
virtual interfaces
*/
- if (dev_all_qdisc_sleeping_noop(dev))
- netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
+ if (dev->qdisc == &noop_qdisc)
+ attach_default_qdiscs(dev);
if (!netif_carrier_ok(dev))
/* Delay activation until next carrier-on event */
need_watchdog = 0;
netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog);
- transition_one_qdisc(dev, &dev->rx_queue, NULL);
+ if (dev_ingress_queue(dev))
+ transition_one_qdisc(dev, dev_ingress_queue(dev), NULL);
if (need_watchdog) {
dev->trans_start = jiffies;
dev_watchdog_up(dev);
}
}
+EXPORT_SYMBOL(dev_activate);
static void dev_deactivate_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
spin_lock_bh(root_lock);
- val = (test_bit(__QDISC_STATE_RUNNING, &q->state) ||
+ val = (qdisc_is_running(q) ||
test_bit(__QDISC_STATE_SCHED, &q->state));
spin_unlock_bh(root_lock);
return false;
}
-void dev_deactivate(struct net_device *dev)
+/**
+ * dev_deactivate_many - deactivate transmissions on several devices
+ * @head: list of devices to deactivate
+ *
+ * This function returns only when all outstanding transmissions
+ * have completed, unless all devices are in dismantle phase.
+ */
+void dev_deactivate_many(struct list_head *head)
{
- netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc);
- dev_deactivate_queue(dev, &dev->rx_queue, &noop_qdisc);
+ struct net_device *dev;
+ bool sync_needed = false;
- dev_watchdog_down(dev);
+ list_for_each_entry(dev, head, unreg_list) {
+ netdev_for_each_tx_queue(dev, dev_deactivate_queue,
+ &noop_qdisc);
+ if (dev_ingress_queue(dev))
+ dev_deactivate_queue(dev, dev_ingress_queue(dev),
+ &noop_qdisc);
- /* Wait for outstanding qdisc-less dev_queue_xmit calls. */
- synchronize_rcu();
+ dev_watchdog_down(dev);
+ sync_needed |= !dev->dismantle;
+ }
+
+ /* Wait for outstanding qdisc-less dev_queue_xmit calls.
+ * This is avoided if all devices are in dismantle phase :
+ * Caller will call synchronize_net() for us
+ */
+ if (sync_needed)
+ synchronize_net();
/* Wait for outstanding qdisc_run calls. */
- while (some_qdisc_is_busy(dev))
- yield();
+ list_for_each_entry(dev, head, unreg_list)
+ while (some_qdisc_is_busy(dev))
+ yield();
}
+void dev_deactivate(struct net_device *dev)
+{
+ LIST_HEAD(single);
+
+ list_add(&dev->unreg_list, &single);
+ dev_deactivate_many(&single);
+ list_del(&single);
+}
+EXPORT_SYMBOL(dev_deactivate);
+
static void dev_init_scheduler_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc)
void dev_init_scheduler(struct net_device *dev)
{
+ dev->qdisc = &noop_qdisc;
netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
- dev_init_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc);
+ if (dev_ingress_queue(dev))
+ dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev);
}
void dev_shutdown(struct net_device *dev)
{
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
- shutdown_scheduler_queue(dev, &dev->rx_queue, &noop_qdisc);
+ if (dev_ingress_queue(dev))
+ shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
+ qdisc_destroy(dev->qdisc);
+ dev->qdisc = &noop_qdisc;
+
WARN_ON(timer_pending(&dev->watchdog_timer));
}
Code Review / linux-2.6.git / blobdiff