/*
- * NET3 Protocol independent device support routines.
+ * NET3 Protocol independent device support routines.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* 2 of the License, or (at your option) any later version.
*
* Derived from the non IP parts of dev.c 1.0.19
- * Authors: Ross Biro
+ * Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
*
*
* Changes:
* D.J. Barrow : Fixed bug where dev->refcnt gets set
- * to 2 if register_netdev gets called
- * before net_dev_init & also removed a
- * few lines of code in the process.
+ * to 2 if register_netdev gets called
+ * before net_dev_init & also removed a
+ * few lines of code in the process.
* Alan Cox : device private ioctl copies fields back.
* Alan Cox : Transmit queue code does relevant
* stunts to keep the queue safe.
* Alan Cox : 100 backlog just doesn't cut it when
* you start doing multicast video 8)
* Alan Cox : Rewrote net_bh and list manager.
- * Alan Cox : Fix ETH_P_ALL echoback lengths.
+ * Alan Cox : Fix ETH_P_ALL echoback lengths.
* Alan Cox : Took out transmit every packet pass
* Saved a few bytes in the ioctl handler
* Alan Cox : Network driver sets packet type before
* Richard Kooijman: Timestamp fixes.
* Alan Cox : Wrong field in SIOCGIFDSTADDR
* Alan Cox : Device lock protection.
- * Alan Cox : Fixed nasty side effect of device close
+ * Alan Cox : Fixed nasty side effect of device close
* changes.
* Rudi Cilibrasi : Pass the right thing to
* set_mac_address()
* Paul Rusty Russell : SIOCSIFNAME
* Pekka Riikonen : Netdev boot-time settings code
* Andrew Morton : Make unregister_netdevice wait
- * indefinitely on dev->refcnt
- * J Hadi Salim : - Backlog queue sampling
+ * indefinitely on dev->refcnt
+ * J Hadi Salim : - Backlog queue sampling
* - netif_rx() feedback
*/
static inline void dev_base_seq_inc(struct net *net)
{
- while (++net->dev_base_seq == 0);
+ while (++net->dev_base_seq == 0)
+ ;
}
static inline struct hlist_head *dev_name_hash(struct net *net, const char *name)
* register_netdevice() inits txq->_xmit_lock and sets lockdep class
* according to dev->type
*/
-static const unsigned short netdev_lock_type[] =
- {ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
+static const unsigned short netdev_lock_type[] = {
+ ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
-static const char *const netdev_lock_name[] =
- {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
- "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
- "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
- "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
- "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
- "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
- "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
- "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
- "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
- "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
- "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
- "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
- "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
- "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
- "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
+static const char *const netdev_lock_name[] = {
+ "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
+ "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
+ "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
+ "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
+ "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
+ "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
+ "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
+ "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
+ "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
+ "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
+ "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
+ "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
+ "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
+ "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
+ "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
#endif
/*******************************************************************************
+ *
+ * Protocol management and registration routines
+ *
+ *******************************************************************************/
- Protocol management and registration routines
-
-*******************************************************************************/
/*
* Add a protocol ID to the list. Now that the input handler is
EXPORT_SYMBOL(dev_remove_offload);
/******************************************************************************
-
- Device Boot-time Settings Routines
-
-*******************************************************************************/
+ *
+ * Device Boot-time Settings Routines
+ *
+ ******************************************************************************/
/* Boot time configuration table */
static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];
}
/**
- * netdev_boot_setup_check - check boot time settings
- * @dev: the netdevice
+ * netdev_boot_setup_check - check boot time settings
+ * @dev: the netdevice
*
- * Check boot time settings for the device.
- * The found settings are set for the device to be used
- * later in the device probing.
- * Returns 0 if no settings found, 1 if they are.
+ * Check boot time settings for the device.
+ * The found settings are set for the device to be used
+ * later in the device probing.
+ * Returns 0 if no settings found, 1 if they are.
*/
int netdev_boot_setup_check(struct net_device *dev)
{
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
!strcmp(dev->name, s[i].name)) {
- dev->irq = s[i].map.irq;
- dev->base_addr = s[i].map.base_addr;
- dev->mem_start = s[i].map.mem_start;
- dev->mem_end = s[i].map.mem_end;
+ dev->irq = s[i].map.irq;
+ dev->base_addr = s[i].map.base_addr;
+ dev->mem_start = s[i].map.mem_start;
+ dev->mem_end = s[i].map.mem_end;
return 1;
}
}
/**
- * netdev_boot_base - get address from boot time settings
- * @prefix: prefix for network device
- * @unit: id for network device
+ * netdev_boot_base - get address from boot time settings
+ * @prefix: prefix for network device
+ * @unit: id for network device
*
- * Check boot time settings for the base address of device.
- * The found settings are set for the device to be used
- * later in the device probing.
- * Returns 0 if no settings found.
+ * Check boot time settings for the base address of device.
+ * The found settings are set for the device to be used
+ * later in the device probing.
+ * Returns 0 if no settings found.
*/
unsigned long netdev_boot_base(const char *prefix, int unit)
{
__setup("netdev=", netdev_boot_setup);
/*******************************************************************************
-
- Device Interface Subroutines
-
-*******************************************************************************/
+ *
+ * Device Interface Subroutines
+ *
+ *******************************************************************************/
/**
* dev_get_iflink - get 'iflink' value of a interface
EXPORT_SYMBOL(__dev_get_by_name);
/**
- * dev_get_by_name_rcu - find a device by its name
- * @net: the applicable net namespace
- * @name: name to find
+ * dev_get_by_name_rcu - find a device by its name
+ * @net: the applicable net namespace
+ * @name: name to find
*
- * Find an interface by name.
- * If the name is found a pointer to the device is returned.
- * If the name is not found then %NULL is returned.
- * The reference counters are not incremented so the caller must be
- * careful with locks. The caller must hold RCU lock.
+ * Find an interface by name.
+ * If the name is found a pointer to the device is returned.
+ * If the name is not found then %NULL is returned.
+ * The reference counters are not incremented so the caller must be
+ * careful with locks. The caller must hold RCU lock.
*/
struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
EXPORT_SYMBOL(netdev_state_change);
/**
- * netdev_notify_peers - notify network peers about existence of @dev
- * @dev: network device
+ * netdev_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
{
rtnl_lock();
call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+ call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
rtnl_unlock();
}
EXPORT_SYMBOL(netdev_notify_peers);
static int dev_boot_phase = 1;
/**
- * register_netdevice_notifier - register a network notifier block
- * @nb: notifier
+ * register_netdevice_notifier - register a network notifier block
+ * @nb: notifier
*
- * Register a notifier to be called when network device events occur.
- * The notifier passed is linked into the kernel structures and must
- * not be reused until it has been unregistered. A negative errno code
- * is returned on a failure.
+ * Register a notifier to be called when network device events occur.
+ * The notifier passed is linked into the kernel structures and must
+ * not be reused until it has been unregistered. A negative errno code
+ * is returned on a failure.
*
- * When registered all registration and up events are replayed
- * to the new notifier to allow device to have a race free
- * view of the network device list.
+ * When registered all registration and up events are replayed
+ * to the new notifier to allow device to have a race free
+ * view of the network device list.
*/
int register_netdevice_notifier(struct notifier_block *nb)
EXPORT_SYMBOL(register_netdevice_notifier);
/**
- * unregister_netdevice_notifier - unregister a network notifier block
- * @nb: notifier
+ * unregister_netdevice_notifier - unregister a network notifier block
+ * @nb: notifier
*
- * Unregister a notifier previously registered by
- * register_netdevice_notifier(). The notifier is unlinked into the
- * kernel structures and may then be reused. A negative errno code
- * is returned on a failure.
+ * Unregister a notifier previously registered by
+ * register_netdevice_notifier(). The notifier is unlinked into the
+ * kernel structures and may then be reused. A negative errno code
+ * is returned on a failure.
*
- * After unregistering unregister and down device events are synthesized
- * for all devices on the device list to the removed notifier to remove
- * the need for special case cleanup code.
+ * After unregistering unregister and down device events are synthesized
+ * for all devices on the device list to the removed notifier to remove
+ * the need for special case cleanup code.
*/
int unregister_netdevice_notifier(struct notifier_block *nb)
static struct static_key netstamp_needed __read_mostly;
#ifdef HAVE_JUMP_LABEL
static atomic_t netstamp_needed_deferred;
+static atomic_t netstamp_wanted;
static void netstamp_clear(struct work_struct *work)
{
int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+ int wanted;
- while (deferred--)
- static_key_slow_dec(&netstamp_needed);
+ wanted = atomic_add_return(deferred, &netstamp_wanted);
+ if (wanted > 0)
+ static_key_enable(&netstamp_needed);
+ else
+ static_key_disable(&netstamp_needed);
}
static DECLARE_WORK(netstamp_work, netstamp_clear);
#endif
void net_enable_timestamp(void)
{
+#ifdef HAVE_JUMP_LABEL
+ int wanted;
+
+ while (1) {
+ wanted = atomic_read(&netstamp_wanted);
+ if (wanted <= 0)
+ break;
+ if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted)
+ return;
+ }
+ atomic_inc(&netstamp_needed_deferred);
+ schedule_work(&netstamp_work);
+#else
static_key_slow_inc(&netstamp_needed);
+#endif
}
EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
#ifdef HAVE_JUMP_LABEL
- /* net_disable_timestamp() can be called from non process context */
- atomic_inc(&netstamp_needed_deferred);
+ int wanted;
+
+ while (1) {
+ wanted = atomic_read(&netstamp_wanted);
+ if (wanted <= 1)
+ break;
+ if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted)
+ return;
+ }
+ atomic_dec(&netstamp_needed_deferred);
schedule_work(&netstamp_work);
#else
static_key_slow_dec(&netstamp_needed);
}
EXPORT_SYMBOL(netif_schedule_queue);
-/**
- * netif_wake_subqueue - allow sending packets on subqueue
- * @dev: network device
- * @queue_index: sub queue index
- *
- * Resume individual transmit queue of a device with multiple transmit queues.
- */
-void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
-{
- struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index);
-
- if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state)) {
- struct Qdisc *q;
-
- rcu_read_lock();
- q = rcu_dereference(txq->qdisc);
- __netif_schedule(q);
- rcu_read_unlock();
- }
-}
-EXPORT_SYMBOL(netif_wake_subqueue);
-
void netif_tx_wake_queue(struct netdev_queue *dev_queue)
{
if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) {
if (dev->num_tc) {
u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+
qoffset = dev->tc_to_txq[tc].offset;
qcount = dev->tc_to_txq[tc].count;
}
static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path)
{
if (tx_path)
- return skb->ip_summed != CHECKSUM_PARTIAL;
- else
- return skb->ip_summed == CHECKSUM_NONE;
+ return skb->ip_summed != CHECKSUM_PARTIAL &&
+ skb->ip_summed != CHECKSUM_NONE;
+
+ return skb->ip_summed == CHECKSUM_NONE;
}
/**
struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
netdev_features_t features, bool tx_path)
{
+ struct sk_buff *segs;
+
if (unlikely(skb_needs_check(skb, tx_path))) {
int err;
- skb_warn_bad_offload(skb);
-
+ /* We're going to init ->check field in TCP or UDP header */
err = skb_cow_head(skb, 0);
if (err < 0)
return ERR_PTR(err);
skb_reset_mac_header(skb);
skb_reset_mac_len(skb);
- return skb_mac_gso_segment(skb, features);
+ segs = skb_mac_gso_segment(skb, features);
+
+ if (unlikely(skb_needs_check(skb, tx_path)))
+ skb_warn_bad_offload(skb);
+
+ return segs;
}
EXPORT_SYMBOL(__skb_gso_segment);
{
#ifdef CONFIG_HIGHMEM
int i;
+
if (!(dev->features & NETIF_F_HIGHDMA)) {
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
if (PageHighMem(skb_frag_page(frag)))
return 1;
}
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
dma_addr_t addr = page_to_phys(skb_frag_page(frag));
+
if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask)
return 1;
}
if (!cl)
return skb;
- /* skb->tc_verd and qdisc_skb_cb(skb)->pkt_len were already set
- * earlier by the caller.
- */
+ /* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
qdisc_bstats_cpu_update(cl->q, skb);
switch (tc_classify(skb, cl, &cl_res, false)) {
if (queue_index < 0 || skb->ooo_okay ||
queue_index >= dev->real_num_tx_queues) {
int new_index = get_xps_queue(dev, skb);
+
if (new_index < 0)
new_index = skb_tx_hash(dev, skb);
if (dev->real_num_tx_queues != 1) {
const struct net_device_ops *ops = dev->netdev_ops;
+
if (ops->ndo_select_queue)
queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
__netdev_pick_tx);
qdisc_pkt_len_init(skb);
#ifdef CONFIG_NET_CLS_ACT
- skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
+ skb->tc_at_ingress = 0;
# ifdef CONFIG_NET_EGRESS
if (static_key_false(&egress_needed)) {
skb = sch_handle_egress(skb, &rc, dev);
}
/* The device has no queue. Common case for software devices:
- loopback, all the sorts of tunnels...
+ * loopback, all the sorts of tunnels...
- Really, it is unlikely that netif_tx_lock protection is necessary
- here. (f.e. loopback and IP tunnels are clean ignoring statistics
- counters.)
- However, it is possible, that they rely on protection
- made by us here.
+ * Really, it is unlikely that netif_tx_lock protection is necessary
+ * here. (f.e. loopback and IP tunnels are clean ignoring statistics
+ * counters.)
+ * However, it is possible, that they rely on protection
+ * made by us here.
- Check this and shot the lock. It is not prone from deadlocks.
- Either shot noqueue qdisc, it is even simpler 8)
+ * Check this and shot the lock. It is not prone from deadlocks.
+ *Either shot noqueue qdisc, it is even simpler 8)
*/
if (dev->flags & IFF_UP) {
int cpu = smp_processor_id(); /* ok because BHs are off */
EXPORT_SYMBOL(dev_queue_xmit_accel);
-/*=======================================================================
- Receiver routines
- =======================================================================*/
+/*************************************************************************
+ * Receiver routines
+ *************************************************************************/
int netdev_max_backlog __read_mostly = 1000;
EXPORT_SYMBOL(netdev_max_backlog);
int netdev_tstamp_prequeue __read_mostly = 1;
int netdev_budget __read_mostly = 300;
-int weight_p __read_mostly = 64; /* old backlog weight */
+int weight_p __read_mostly = 64; /* old backlog weight */
+int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */
+int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */
+int dev_rx_weight __read_mostly = 64;
+int dev_tx_weight __read_mostly = 64;
/* Called with irq disabled */
static inline void ____napi_schedule(struct softnet_data *sd,
#endif
{
unsigned int qtail;
+
ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
put_cpu();
}
while (clist) {
struct sk_buff *skb = clist;
+
clist = clist->next;
WARN_ON(atomic_read(&skb->users));
}
qdisc_skb_cb(skb)->pkt_len = skb->len;
- skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS);
+ skb->tc_at_ingress = 1;
qdisc_bstats_cpu_update(cl->q, skb);
switch (tc_classify(skb, cl, &cl_res, false)) {
rx_handler_func_t *rx_handler,
void *rx_handler_data)
{
- ASSERT_RTNL();
-
- if (dev->rx_handler)
+ if (netdev_is_rx_handler_busy(dev))
return -EBUSY;
/* Note: rx_handler_data must be set before rx_handler */
goto out;
}
-#ifdef CONFIG_NET_CLS_ACT
- if (skb->tc_verd & TC_NCLS) {
- skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
- goto ncls;
- }
-#endif
+ if (skb_skip_tc_classify(skb))
+ goto skip_classify;
if (pfmemalloc)
goto skip_taps;
goto out;
}
#endif
-#ifdef CONFIG_NET_CLS_ACT
- skb->tc_verd = 0;
-ncls:
-#endif
+ skb_reset_tc(skb);
+skip_classify:
if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
goto drop;
if (&ptype->list == head)
goto normal;
+ if (IS_ERR(pp) && PTR_ERR(pp) == -EINPROGRESS) {
+ ret = GRO_CONSUMED;
+ goto ok;
+ }
+
same_flow = NAPI_GRO_CB(skb)->same_flow;
ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
case GRO_MERGED_FREE:
if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) {
skb_dst_drop(skb);
+ secpath_reset(skb);
kmem_cache_free(skbuff_head_cache, skb);
} else {
__kfree_skb(skb);
case GRO_HELD:
case GRO_MERGED:
+ case GRO_CONSUMED:
break;
}
skb->encapsulation = 0;
skb_shinfo(skb)->gso_type = 0;
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
+ secpath_reset(skb);
napi->skb = skb;
}
break;
case GRO_MERGED:
+ case GRO_CONSUMED:
break;
}
net_rps_action_and_irq_enable(sd);
}
- napi->weight = weight_p;
+ napi->weight = dev_rx_weight;
while (again) {
struct sk_buff *skb;
}
EXPORT_SYMBOL(__napi_schedule);
+/**
+ * napi_schedule_prep - check if napi can be scheduled
+ * @n: napi context
+ *
+ * Test if NAPI routine is already running, and if not mark
+ * it as running. This is used as a condition variable
+ * insure only one NAPI poll instance runs. We also make
+ * sure there is no pending NAPI disable.
+ */
+bool napi_schedule_prep(struct napi_struct *n)
+{
+ unsigned long val, new;
+
+ do {
+ val = READ_ONCE(n->state);
+ if (unlikely(val & NAPIF_STATE_DISABLE))
+ return false;
+ new = val | NAPIF_STATE_SCHED;
+
+ /* Sets STATE_MISSED bit if STATE_SCHED was already set
+ * This was suggested by Alexander Duyck, as compiler
+ * emits better code than :
+ * if (val & NAPIF_STATE_SCHED)
+ * new |= NAPIF_STATE_MISSED;
+ */
+ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED *
+ NAPIF_STATE_MISSED;
+ } while (cmpxchg(&n->state, val, new) != val);
+
+ return !(val & NAPIF_STATE_SCHED);
+}
+EXPORT_SYMBOL(napi_schedule_prep);
+
/**
* __napi_schedule_irqoff - schedule for receive
* @n: entry to schedule
}
EXPORT_SYMBOL(__napi_schedule_irqoff);
-bool __napi_complete(struct napi_struct *n)
-{
- BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
-
- /* Some drivers call us directly, instead of calling
- * napi_complete_done().
- */
- if (unlikely(test_bit(NAPI_STATE_IN_BUSY_POLL, &n->state)))
- return false;
-
- list_del_init(&n->poll_list);
- smp_mb__before_atomic();
- clear_bit(NAPI_STATE_SCHED, &n->state);
- return true;
-}
-EXPORT_SYMBOL(__napi_complete);
-
bool napi_complete_done(struct napi_struct *n, int work_done)
{
- unsigned long flags;
+ unsigned long flags, val, new;
/*
* 1) Don't let napi dequeue from the cpu poll list
else
napi_gro_flush(n, false);
}
- if (likely(list_empty(&n->poll_list))) {
- WARN_ON_ONCE(!test_and_clear_bit(NAPI_STATE_SCHED, &n->state));
- } else {
+ if (unlikely(!list_empty(&n->poll_list))) {
/* If n->poll_list is not empty, we need to mask irqs */
local_irq_save(flags);
- __napi_complete(n);
+ list_del_init(&n->poll_list);
local_irq_restore(flags);
}
+
+ do {
+ val = READ_ONCE(n->state);
+
+ WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
+
+ new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+
+ /* If STATE_MISSED was set, leave STATE_SCHED set,
+ * because we will call napi->poll() one more time.
+ * This C code was suggested by Alexander Duyck to help gcc.
+ */
+ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED *
+ NAPIF_STATE_SCHED;
+ } while (cmpxchg(&n->state, val, new) != val);
+
+ if (unlikely(val & NAPIF_STATE_MISSED)) {
+ __napi_schedule(n);
+ return false;
+ }
+
return true;
}
EXPORT_SYMBOL(napi_complete_done);
{
int rc;
+ /* Busy polling means there is a high chance device driver hard irq
+ * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was
+ * set in napi_schedule_prep().
+ * Since we are about to call napi->poll() once more, we can safely
+ * clear NAPI_STATE_MISSED.
+ *
+ * Note: x86 could use a single "lock and ..." instruction
+ * to perform these two clear_bit()
+ */
+ clear_bit(NAPI_STATE_MISSED, &napi->state);
clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
local_bh_disable();
{
unsigned long end_time = !nonblock ? sk_busy_loop_end_time(sk) : 0;
int (*napi_poll)(struct napi_struct *napi, int budget);
- int (*busy_poll)(struct napi_struct *dev);
void *have_poll_lock = NULL;
struct napi_struct *napi;
int rc;
if (!napi)
goto out;
- /* Note: ndo_busy_poll method is optional in linux-4.5 */
- busy_poll = napi->dev->netdev_ops->ndo_busy_poll;
-
preempt_disable();
for (;;) {
rc = 0;
local_bh_disable();
- if (busy_poll) {
- rc = busy_poll(napi);
- goto count;
- }
if (!napi_poll) {
unsigned long val = READ_ONCE(napi->state);
LINUX_MIB_BUSYPOLLRXPACKETS, rc);
local_bh_enable();
- if (rc == LL_FLUSH_FAILED)
- break; /* permanent failure */
-
if (nonblock || !skb_queue_empty(&sk->sk_receive_queue) ||
busy_loop_timeout(end_time))
break;
struct napi_struct *napi;
napi = container_of(timer, struct napi_struct, timer);
- if (napi->gro_list)
- napi_schedule(napi);
+
+ /* Note : we use a relaxed variant of napi_schedule_prep() not setting
+ * NAPI_STATE_MISSED, since we do not react to a device IRQ.
+ */
+ if (napi->gro_list && !napi_disable_pending(napi) &&
+ !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+ __napi_schedule_irqoff(napi);
return HRTIMER_NORESTART;
}
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),
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);
struct net_device *upper_dev)
{
struct netdev_notifier_changeupper_info changeupper_info;
+
ASSERT_RTNL();
changeupper_info.upper_dev = upper_dev;
}
EXPORT_SYMBOL(netdev_lower_state_changed);
-int netdev_default_l2upper_neigh_construct(struct net_device *dev,
- struct neighbour *n)
-{
- struct net_device *lower_dev, *stop_dev;
- struct list_head *iter;
- int err;
-
- netdev_for_each_lower_dev(dev, lower_dev, iter) {
- if (!lower_dev->netdev_ops->ndo_neigh_construct)
- continue;
- err = lower_dev->netdev_ops->ndo_neigh_construct(lower_dev, n);
- if (err) {
- stop_dev = lower_dev;
- goto rollback;
- }
- }
- return 0;
-
-rollback:
- netdev_for_each_lower_dev(dev, lower_dev, iter) {
- if (lower_dev == stop_dev)
- break;
- if (!lower_dev->netdev_ops->ndo_neigh_destroy)
- continue;
- lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
- }
- return err;
-}
-EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_construct);
-
-void netdev_default_l2upper_neigh_destroy(struct net_device *dev,
- struct neighbour *n)
-{
- struct net_device *lower_dev;
- struct list_head *iter;
-
- netdev_for_each_lower_dev(dev, lower_dev, iter) {
- if (!lower_dev->netdev_ops->ndo_neigh_destroy)
- continue;
- lower_dev->netdev_ops->ndo_neigh_destroy(lower_dev, n);
- }
-}
-EXPORT_SYMBOL_GPL(netdev_default_l2upper_neigh_destroy);
-
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
const struct net_device_ops *ops = dev->netdev_ops;
}
/* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI
- is important. Some (broken) drivers set IFF_PROMISC, when
- IFF_ALLMULTI is requested not asking us and not reporting.
+ * is important. Some (broken) drivers set IFF_PROMISC, when
+ * IFF_ALLMULTI is requested not asking us and not reporting.
*/
if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
static int dev_new_index(struct net *net)
{
int ifindex = net->ifindex;
+
for (;;) {
if (++ifindex <= 0)
ifindex = 1;
/* Notify protocols, that we are about to destroy
- this device. They should clean all the things.
- */
+ * this device. They should clean all the things.
+ */
call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
if (!dev->rtnl_link_ops ||
features &= ~dev->gso_partial_features;
}
-#ifdef CONFIG_NET_RX_BUSY_POLL
- if (dev->netdev_ops->ndo_busy_poll)
- features |= NETIF_F_BUSY_POLL;
- else
-#endif
- features &= ~NETIF_F_BUSY_POLL;
-
return features;
}
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
+
netif_tx_stop_queue(txq);
}
}
}
/**
- * alloc_netdev_mqs - allocate network device
- * @sizeof_priv: size of private data to allocate space for
- * @name: device name format string
- * @name_assign_type: origin of device name
- * @setup: callback to initialize device
- * @txqs: the number of TX subqueues to allocate
- * @rxqs: the number of RX subqueues to allocate
- *
- * Allocates a struct net_device with private data area for driver use
- * and performs basic initialization. Also allocates subqueue structs
- * for each queue on the device.
+ * alloc_netdev_mqs - allocate network device
+ * @sizeof_priv: size of private data to allocate space for
+ * @name: device name format string
+ * @name_assign_type: origin of device name
+ * @setup: callback to initialize device
+ * @txqs: the number of TX subqueues to allocate
+ * @rxqs: the number of RX subqueues to allocate
+ *
+ * Allocates a struct net_device with private data area for driver use
+ * and performs basic initialization. Also allocates subqueue structs
+ * for each queue on the device.
*/
struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
unsigned char name_assign_type,
EXPORT_SYMBOL(alloc_netdev_mqs);
/**
- * free_netdev - free network device
- * @dev: device
+ * free_netdev - free network device
+ * @dev: device
*
- * This function does the last stage of destroying an allocated device
- * interface. The reference to the device object is released.
- * If this is the last reference then it will be freed.
- * Must be called in process context.
+ * This function does the last stage of destroying an allocated device
+ * interface. The reference to the device object is released. If this
+ * is the last reference then it will be freed.Must be called in process
+ * context.
*/
void free_netdev(struct net_device *dev)
{
dev_shutdown(dev);
/* 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.
- */
+ * 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);
rcu_barrier();
call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev);
projects / karo-tx-linux.git / blobdiff