* 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, <bir7@leland.Stanford.Edu>
+ * Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
*
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
+#include <linux/capability.h>
#include <linux/config.h>
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
+#include <linux/mutex.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
-#ifdef CONFIG_NET_RADIO
-#include <linux/wireless.h> /* Note : will define WIRELESS_EXT */
+#include <linux/wireless.h>
#include <net/iw_handler.h>
-#endif /* CONFIG_NET_RADIO */
#include <asm/current.h>
-
-/* This define, if set, will randomly drop a packet when congestion
- * is more than moderate. It helps fairness in the multi-interface
- * case when one of them is a hog, but it kills performance for the
- * single interface case so it is off now by default.
- */
-#undef RAND_LIE
-
-/* Setting this will sample the queue lengths and thus congestion
- * via a timer instead of as each packet is received.
- */
-#undef OFFLINE_SAMPLE
+#include <linux/audit.h>
+#include <linux/dmaengine.h>
/*
* The list of packet types we will receive (as opposed to discard)
* sure which should go first, but I bet it won't make much
* difference if we are running VLANs. The good news is that
* this protocol won't be in the list unless compiled in, so
- * the average user (w/out VLANs) will not be adversly affected.
+ * the average user (w/out VLANs) will not be adversely affected.
* --BLG
*
* 0800 IP
static struct list_head ptype_base[16]; /* 16 way hashed list */
static struct list_head ptype_all; /* Taps */
-#ifdef OFFLINE_SAMPLE
-static void sample_queue(unsigned long dummy);
-static struct timer_list samp_timer = TIMER_INITIALIZER(sample_queue, 0, 0);
+#ifdef CONFIG_NET_DMA
+static struct dma_client *net_dma_client;
+static unsigned int net_dma_count;
+static spinlock_t net_dma_event_lock;
#endif
/*
- * The @dev_base list is protected by @dev_base_lock and the rtln
+ * The @dev_base list is protected by @dev_base_lock and the rtnl
* semaphore.
*
* Pure readers hold dev_base_lock for reading.
* Our notifier list
*/
-static struct notifier_block *netdev_chain;
+static RAW_NOTIFIER_HEAD(netdev_chain);
/*
* Device drivers call our routines to queue packets here. We empty the
* queue in the local softnet handler.
*/
-DEFINE_PER_CPU(struct softnet_data, softnet_data) = { 0, };
+DEFINE_PER_CPU(struct softnet_data, softnet_data) = { NULL };
#ifdef CONFIG_SYSFS
extern int netdev_sysfs_init(void);
spin_unlock_bh(&ptype_lock);
}
-extern void linkwatch_run_queue(void);
-
-
-
/**
* __dev_remove_pack - remove packet handler
* @pt: packet type declaration
return dev;
}
+EXPORT_SYMBOL(dev_getbyhwaddr);
+
struct net_device *dev_getfirstbyhwtype(unsigned short type)
{
struct net_device *dev;
* Network device names need to be valid file names to
* to allow sysfs to work
*/
-static int dev_valid_name(const char *name)
+int dev_valid_name(const char *name)
{
return !(*name == '\0'
|| !strcmp(name, ".")
* @name: name format string
*
* Passed a format string - eg "lt%d" it will try and find a suitable
- * id. Not efficient for many devices, not called a lot. The caller
- * must hold the dev_base or rtnl lock while allocating the name and
- * adding the device in order to avoid duplicates. Returns the number
- * of the unit assigned or a negative errno code.
+ * id. It scans list of devices to build up a free map, then chooses
+ * the first empty slot. The caller must hold the dev_base or rtnl lock
+ * while allocating the name and adding the device in order to avoid
+ * duplicates.
+ * Limited to bits_per_byte * page size devices (ie 32K on most platforms).
+ * Returns the number of the unit assigned or a negative errno code.
*/
int dev_alloc_name(struct net_device *dev, const char *name)
if (!err) {
hlist_del(&dev->name_hlist);
hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
- notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
+ raw_notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGENAME, dev);
}
return err;
}
/**
+ * netdev_features_change - device changes features
+ * @dev: device to cause notification
+ *
+ * Called to indicate a device has changed features.
+ */
+void netdev_features_change(struct net_device *dev)
+{
+ raw_notifier_call_chain(&netdev_chain, NETDEV_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL(netdev_features_change);
+
+/**
* netdev_state_change - device changes state
* @dev: device to cause notification
*
void netdev_state_change(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
- notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
+ raw_notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGE, dev);
rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
}
}
/*
* ... and announce new interface.
*/
- notifier_call_chain(&netdev_chain, NETDEV_UP, dev);
+ raw_notifier_call_chain(&netdev_chain, NETDEV_UP, dev);
}
return ret;
}
* Tell people we are going down, so that they can
* prepare to death, when device is still operating.
*/
- notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev);
+ raw_notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev);
dev_deactivate(dev);
smp_mb__after_clear_bit(); /* Commit netif_running(). */
while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) {
/* No hurry. */
- current->state = TASK_INTERRUPTIBLE;
- schedule_timeout(1);
+ msleep(1);
}
/*
/*
* Tell people we are down
*/
- notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);
+ raw_notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);
return 0;
}
int err;
rtnl_lock();
- err = notifier_chain_register(&netdev_chain, nb);
+ err = raw_notifier_chain_register(&netdev_chain, nb);
if (!err) {
for (dev = dev_base; dev; dev = dev->next) {
nb->notifier_call(nb, NETDEV_REGISTER, dev);
int unregister_netdevice_notifier(struct notifier_block *nb)
{
- return notifier_chain_unregister(&netdev_chain, nb);
+ int err;
+
+ rtnl_lock();
+ err = raw_notifier_chain_unregister(&netdev_chain, nb);
+ rtnl_unlock();
+ return err;
}
/**
* @v: pointer passed unmodified to notifier function
*
* Call all network notifier blocks. Parameters and return value
- * are as for notifier_call_chain().
+ * are as for raw_notifier_call_chain().
*/
int call_netdevice_notifiers(unsigned long val, void *v)
{
- return notifier_call_chain(&netdev_chain, val, v);
+ return raw_notifier_call_chain(&netdev_chain, val, v);
}
/* When > 0 there are consumers of rx skb time stamps */
atomic_dec(&netstamp_needed);
}
-static inline void net_timestamp(struct timeval *stamp)
+void __net_timestamp(struct sk_buff *skb)
+{
+ struct timeval tv;
+
+ do_gettimeofday(&tv);
+ skb_set_timestamp(skb, &tv);
+}
+EXPORT_SYMBOL(__net_timestamp);
+
+static inline void net_timestamp(struct sk_buff *skb)
{
if (atomic_read(&netstamp_needed))
- do_gettimeofday(stamp);
+ __net_timestamp(skb);
else {
- stamp->tv_sec = 0;
- stamp->tv_usec = 0;
+ skb->tstamp.off_sec = 0;
+ skb->tstamp.off_usec = 0;
}
}
void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
{
struct packet_type *ptype;
- net_timestamp(&skb->stamp);
+
+ net_timestamp(skb);
rcu_read_lock();
list_for_each_entry_rcu(ptype, &ptype_all, list) {
skb2->h.raw = skb2->nh.raw;
skb2->pkt_type = PACKET_OUTGOING;
- ptype->func(skb2, skb->dev, ptype);
+ ptype->func(skb2, skb->dev, ptype, skb->dev);
}
}
rcu_read_unlock();
}
+
+void __netif_schedule(struct net_device *dev)
+{
+ if (!test_and_set_bit(__LINK_STATE_SCHED, &dev->state)) {
+ unsigned long flags;
+ struct softnet_data *sd;
+
+ local_irq_save(flags);
+ sd = &__get_cpu_var(softnet_data);
+ dev->next_sched = sd->output_queue;
+ sd->output_queue = dev;
+ raise_softirq_irqoff(NET_TX_SOFTIRQ);
+ local_irq_restore(flags);
+ }
+}
+EXPORT_SYMBOL(__netif_schedule);
+
+void __netif_rx_schedule(struct net_device *dev)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ dev_hold(dev);
+ list_add_tail(&dev->poll_list, &__get_cpu_var(softnet_data).poll_list);
+ if (dev->quota < 0)
+ dev->quota += dev->weight;
+ else
+ dev->quota = dev->weight;
+ __raise_softirq_irqoff(NET_RX_SOFTIRQ);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__netif_rx_schedule);
+
+void dev_kfree_skb_any(struct sk_buff *skb)
+{
+ if (in_irq() || irqs_disabled())
+ dev_kfree_skb_irq(skb);
+ else
+ dev_kfree_skb(skb);
+}
+EXPORT_SYMBOL(dev_kfree_skb_any);
+
+
+/* Hot-plugging. */
+void netif_device_detach(struct net_device *dev)
+{
+ if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) &&
+ netif_running(dev)) {
+ netif_stop_queue(dev);
+ }
+}
+EXPORT_SYMBOL(netif_device_detach);
+
+void netif_device_attach(struct net_device *dev)
+{
+ if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) &&
+ netif_running(dev)) {
+ netif_wake_queue(dev);
+ __netdev_watchdog_up(dev);
+ }
+}
+EXPORT_SYMBOL(netif_device_attach);
+
+
/*
* Invalidate hardware checksum when packet is to be mangled, and
* complete checksum manually on outgoing path.
goto out;
}
- if (offset > (int)skb->len)
- BUG();
+ BUG_ON(offset > (int)skb->len);
csum = skb_checksum(skb, offset, skb->len-offset, 0);
offset = skb->tail - skb->h.raw;
- if (offset <= 0)
- BUG();
- if (skb->csum + 2 > offset)
- BUG();
+ BUG_ON(offset <= 0);
+ BUG_ON(skb->csum + 2 > offset);
*(u16*)(skb->h.raw + skb->csum) = csum_fold(csum);
skb->ip_summed = CHECKSUM_NONE;
return ret;
}
+/* Take action when hardware reception checksum errors are detected. */
+#ifdef CONFIG_BUG
+void netdev_rx_csum_fault(struct net_device *dev)
+{
+ if (net_ratelimit()) {
+ printk(KERN_ERR "%s: hw csum failure.\n",
+ dev ? dev->name : "<unknown>");
+ dump_stack();
+ }
+}
+EXPORT_SYMBOL(netdev_rx_csum_fault);
+#endif
+
#ifdef CONFIG_HIGHMEM
/* Actually, we should eliminate this check as soon as we know, that:
* 1. IOMMU is present and allows to map all the memory.
#define illegal_highdma(dev, skb) (0)
#endif
-extern void skb_release_data(struct sk_buff *);
-
-/* Keep head the same: replace data */
-int __skb_linearize(struct sk_buff *skb, int gfp_mask)
-{
- unsigned int size;
- u8 *data;
- long offset;
- struct skb_shared_info *ninfo;
- int headerlen = skb->data - skb->head;
- int expand = (skb->tail + skb->data_len) - skb->end;
-
- if (skb_shared(skb))
- BUG();
-
- if (expand <= 0)
- expand = 0;
-
- size = skb->end - skb->head + expand;
- size = SKB_DATA_ALIGN(size);
- data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
- if (!data)
- return -ENOMEM;
-
- /* Copy entire thing */
- if (skb_copy_bits(skb, -headerlen, data, headerlen + skb->len))
- BUG();
-
- /* Set up shinfo */
- ninfo = (struct skb_shared_info*)(data + size);
- atomic_set(&ninfo->dataref, 1);
- ninfo->tso_size = skb_shinfo(skb)->tso_size;
- ninfo->tso_segs = skb_shinfo(skb)->tso_segs;
- ninfo->nr_frags = 0;
- ninfo->frag_list = NULL;
-
- /* Offset between the two in bytes */
- offset = data - skb->head;
-
- /* Free old data. */
- skb_release_data(skb);
-
- skb->head = data;
- skb->end = data + size;
-
- /* Set up new pointers */
- skb->h.raw += offset;
- skb->nh.raw += offset;
- skb->mac.raw += offset;
- skb->tail += offset;
- skb->data += offset;
-
- /* We are no longer a clone, even if we were. */
- skb->cloned = 0;
-
- skb->tail += skb->data_len;
- skb->data_len = 0;
- return 0;
-}
-
#define HARD_TX_LOCK(dev, cpu) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
- spin_lock(&dev->xmit_lock); \
- dev->xmit_lock_owner = cpu; \
+ netif_tx_lock(dev); \
} \
}
#define HARD_TX_UNLOCK(dev) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
- dev->xmit_lock_owner = -1; \
- spin_unlock(&dev->xmit_lock); \
+ netif_tx_unlock(dev); \
} \
}
if (skb_shinfo(skb)->frag_list &&
!(dev->features & NETIF_F_FRAGLIST) &&
- __skb_linearize(skb, GFP_ATOMIC))
+ __skb_linearize(skb))
goto out_kfree_skb;
/* Fragmented skb is linearized if device does not support SG,
*/
if (skb_shinfo(skb)->nr_frags &&
(!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
- __skb_linearize(skb, GFP_ATOMIC))
+ __skb_linearize(skb))
goto out_kfree_skb;
/* If packet is not checksummed and device does not support
if (skb_checksum_help(skb, 0))
goto out_kfree_skb;
+ spin_lock_prefetch(&dev->queue_lock);
+
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
/* The device has no queue. Common case for software devices:
loopback, all the sorts of tunnels...
- Really, it is unlikely that xmit_lock protection is necessary here.
- (f.e. loopback and IP tunnels are clean ignoring statistics
+ 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.
Receiver routines
=======================================================================*/
-int netdev_max_backlog = 300;
+int netdev_max_backlog = 1000;
+int netdev_budget = 300;
int weight_p = 64; /* old backlog weight */
-/* These numbers are selected based on intuition and some
- * experimentatiom, if you have more scientific way of doing this
- * please go ahead and fix things.
- */
-int no_cong_thresh = 10;
-int no_cong = 20;
-int lo_cong = 100;
-int mod_cong = 290;
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
-static void get_sample_stats(int cpu)
-{
-#ifdef RAND_LIE
- unsigned long rd;
- int rq;
-#endif
- struct softnet_data *sd = &per_cpu(softnet_data, cpu);
- int blog = sd->input_pkt_queue.qlen;
- int avg_blog = sd->avg_blog;
-
- avg_blog = (avg_blog >> 1) + (blog >> 1);
-
- if (avg_blog > mod_cong) {
- /* Above moderate congestion levels. */
- sd->cng_level = NET_RX_CN_HIGH;
-#ifdef RAND_LIE
- rd = net_random();
- rq = rd % netdev_max_backlog;
- if (rq < avg_blog) /* unlucky bastard */
- sd->cng_level = NET_RX_DROP;
-#endif
- } else if (avg_blog > lo_cong) {
- sd->cng_level = NET_RX_CN_MOD;
-#ifdef RAND_LIE
- rd = net_random();
- rq = rd % netdev_max_backlog;
- if (rq < avg_blog) /* unlucky bastard */
- sd->cng_level = NET_RX_CN_HIGH;
-#endif
- } else if (avg_blog > no_cong)
- sd->cng_level = NET_RX_CN_LOW;
- else /* no congestion */
- sd->cng_level = NET_RX_SUCCESS;
-
- sd->avg_blog = avg_blog;
-}
-
-#ifdef OFFLINE_SAMPLE
-static void sample_queue(unsigned long dummy)
-{
-/* 10 ms 0r 1ms -- i don't care -- JHS */
- int next_tick = 1;
- int cpu = smp_processor_id();
-
- get_sample_stats(cpu);
- next_tick += jiffies;
- mod_timer(&samp_timer, next_tick);
-}
-#endif
-
-
/**
* netif_rx - post buffer to the network code
* @skb: buffer to post
int netif_rx(struct sk_buff *skb)
{
- int this_cpu;
struct softnet_data *queue;
unsigned long flags;
if (netpoll_rx(skb))
return NET_RX_DROP;
- if (!skb->stamp.tv_sec)
- net_timestamp(&skb->stamp);
+ if (!skb->tstamp.off_sec)
+ net_timestamp(skb);
/*
* The code is rearranged so that the path is the most
* short when CPU is congested, but is still operating.
*/
local_irq_save(flags);
- this_cpu = smp_processor_id();
queue = &__get_cpu_var(softnet_data);
__get_cpu_var(netdev_rx_stat).total++;
if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
if (queue->input_pkt_queue.qlen) {
- if (queue->throttle)
- goto drop;
-
enqueue:
dev_hold(skb->dev);
__skb_queue_tail(&queue->input_pkt_queue, skb);
-#ifndef OFFLINE_SAMPLE
- get_sample_stats(this_cpu);
-#endif
local_irq_restore(flags);
- return queue->cng_level;
+ return NET_RX_SUCCESS;
}
- if (queue->throttle)
- queue->throttle = 0;
-
netif_rx_schedule(&queue->backlog_dev);
goto enqueue;
}
- if (!queue->throttle) {
- queue->throttle = 1;
- __get_cpu_var(netdev_rx_stat).throttled++;
- }
-
-drop:
__get_cpu_var(netdev_rx_stat).dropped++;
local_irq_restore(flags);
EXPORT_SYMBOL(netif_rx_ni);
-static __inline__ void skb_bond(struct sk_buff *skb)
+static inline struct net_device *skb_bond(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
if (dev->master) {
- skb->real_dev = skb->dev;
+ /*
+ * On bonding slaves other than the currently active
+ * slave, suppress duplicates except for 802.3ad
+ * ETH_P_SLOW and alb non-mcast/bcast.
+ */
+ if (dev->priv_flags & IFF_SLAVE_INACTIVE) {
+ if (dev->master->priv_flags & IFF_MASTER_ALB) {
+ if (skb->pkt_type != PACKET_BROADCAST &&
+ skb->pkt_type != PACKET_MULTICAST)
+ goto keep;
+ }
+
+ if (dev->master->priv_flags & IFF_MASTER_8023AD &&
+ skb->protocol == __constant_htons(ETH_P_SLOW))
+ goto keep;
+
+ kfree_skb(skb);
+ return NULL;
+ }
+keep:
skb->dev = dev->master;
}
+
+ return dev;
}
static void net_tx_action(struct softirq_action *h)
}
static __inline__ int deliver_skb(struct sk_buff *skb,
- struct packet_type *pt_prev)
+ struct packet_type *pt_prev,
+ struct net_device *orig_dev)
{
atomic_inc(&skb->users);
- return pt_prev->func(skb, skb->dev, pt_prev);
+ return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent);
static __inline__ int handle_bridge(struct sk_buff **pskb,
- struct packet_type **pt_prev, int *ret)
+ struct packet_type **pt_prev, int *ret,
+ struct net_device *orig_dev)
{
struct net_bridge_port *port;
return 0;
if (*pt_prev) {
- *ret = deliver_skb(*pskb, *pt_prev);
+ *ret = deliver_skb(*pskb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
return br_handle_frame_hook(port, pskb);
}
#else
-#define handle_bridge(skb, pt_prev, ret) (0)
+#define handle_bridge(skb, pt_prev, ret, orig_dev) (0)
#endif
#ifdef CONFIG_NET_CLS_ACT
__u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd);
if (MAX_RED_LOOP < ttl++) {
printk("Redir loop detected Dropping packet (%s->%s)\n",
- skb->input_dev?skb->input_dev->name:"??",skb->dev->name);
+ skb->input_dev->name, skb->dev->name);
return TC_ACT_SHOT;
}
skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl);
skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS);
- if (NULL == skb->input_dev) {
- skb->input_dev = skb->dev;
- printk("ing_filter: fixed %s out %s\n",skb->input_dev->name,skb->dev->name);
- }
+
spin_lock(&dev->ingress_lock);
if ((q = dev->qdisc_ingress) != NULL)
result = q->enqueue(skb, q);
int netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
+ struct net_device *orig_dev;
int ret = NET_RX_DROP;
unsigned short type;
if (skb->dev->poll && netpoll_rx(skb))
return NET_RX_DROP;
- if (!skb->stamp.tv_sec)
- net_timestamp(&skb->stamp);
+ if (!skb->tstamp.off_sec)
+ net_timestamp(skb);
+
+ if (!skb->input_dev)
+ skb->input_dev = skb->dev;
- skb_bond(skb);
+ orig_dev = skb_bond(skb);
+
+ if (!orig_dev)
+ return NET_RX_DROP;
__get_cpu_var(netdev_rx_stat).total++;
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
- ret = deliver_skb(skb, pt_prev);
+ ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
}
#ifdef CONFIG_NET_CLS_ACT
if (pt_prev) {
- ret = deliver_skb(skb, pt_prev);
+ ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = NULL; /* noone else should process this after*/
} else {
skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
handle_diverter(skb);
- if (handle_bridge(&skb, &pt_prev, &ret))
+ if (handle_bridge(&skb, &pt_prev, &ret, orig_dev))
goto out;
type = skb->protocol;
if (ptype->type == type &&
(!ptype->dev || ptype->dev == skb->dev)) {
if (pt_prev)
- ret = deliver_skb(skb, pt_prev);
+ ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = ptype;
}
}
if (pt_prev) {
- ret = pt_prev->func(skb, skb->dev, pt_prev);
+ ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
+ backlog_dev->weight = weight_p;
for (;;) {
struct sk_buff *skb;
struct net_device *dev;
smp_mb__before_clear_bit();
netif_poll_enable(backlog_dev);
- if (queue->throttle)
- queue->throttle = 0;
local_irq_enable();
return 0;
}
{
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
- int budget = netdev_max_backlog;
+ int budget = netdev_budget;
+ void *have;
-
local_irq_disable();
while (!list_empty(&queue->poll_list)) {
dev = list_entry(queue->poll_list.next,
struct net_device, poll_list);
- netpoll_poll_lock(dev);
+ have = netpoll_poll_lock(dev);
if (dev->quota <= 0 || dev->poll(dev, &budget)) {
- netpoll_poll_unlock(dev);
+ netpoll_poll_unlock(have);
local_irq_disable();
- list_del(&dev->poll_list);
- list_add_tail(&dev->poll_list, &queue->poll_list);
+ list_move_tail(&dev->poll_list, &queue->poll_list);
if (dev->quota < 0)
dev->quota += dev->weight;
else
dev->quota = dev->weight;
} else {
- netpoll_poll_unlock(dev);
+ netpoll_poll_unlock(have);
dev_put(dev);
local_irq_disable();
}
}
out:
+#ifdef CONFIG_NET_DMA
+ /*
+ * There may not be any more sk_buffs coming right now, so push
+ * any pending DMA copies to hardware
+ */
+ if (net_dma_client) {
+ struct dma_chan *chan;
+ rcu_read_lock();
+ list_for_each_entry_rcu(chan, &net_dma_client->channels, client_node)
+ dma_async_memcpy_issue_pending(chan);
+ rcu_read_unlock();
+ }
+#endif
local_irq_enable();
return;
struct netif_rx_stats *s = v;
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
- s->total, s->dropped, s->time_squeeze, s->throttled,
- s->fastroute_hit, s->fastroute_success, s->fastroute_defer,
- s->fastroute_deferred_out,
-#if 0
- s->fastroute_latency_reduction
-#else
- s->cpu_collision
-#endif
- );
+ s->total, s->dropped, s->time_squeeze, 0,
+ 0, 0, 0, 0, /* was fastroute */
+ s->cpu_collision );
return 0;
}
.release = seq_release,
};
-#ifdef WIRELESS_EXT
+#ifdef CONFIG_WIRELESS_EXT
extern int wireless_proc_init(void);
#else
#define wireless_proc_init() 0
* @dev: device
* @inc: modifier
*
- * Add or remove promsicuity from a device. While the count in the device
+ * Add or remove promiscuity from a device. While the count in the device
* remains above zero the interface remains promiscuous. Once it hits zero
* the device reverts back to normal filtering operation. A negative inc
* value is used to drop promiscuity on the device.
{
unsigned short old_flags = dev->flags;
- dev->flags |= IFF_PROMISC;
if ((dev->promiscuity += inc) == 0)
dev->flags &= ~IFF_PROMISC;
- if (dev->flags ^ old_flags) {
+ else
+ dev->flags |= IFF_PROMISC;
+ if (dev->flags != old_flags) {
dev_mc_upload(dev);
printk(KERN_INFO "device %s %s promiscuous mode\n",
dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
"left");
+ audit_log(current->audit_context, GFP_ATOMIC,
+ AUDIT_ANOM_PROMISCUOUS,
+ "dev=%s prom=%d old_prom=%d auid=%u",
+ dev->name, (dev->flags & IFF_PROMISC),
+ (old_flags & IFF_PROMISC),
+ audit_get_loginuid(current->audit_context));
}
}
flags = (dev->flags & ~(IFF_PROMISC |
IFF_ALLMULTI |
- IFF_RUNNING)) |
+ IFF_RUNNING |
+ IFF_LOWER_UP |
+ IFF_DORMANT)) |
(dev->gflags & (IFF_PROMISC |
IFF_ALLMULTI));
- if (netif_running(dev) && netif_carrier_ok(dev))
- flags |= IFF_RUNNING;
+ if (netif_running(dev)) {
+ if (netif_oper_up(dev))
+ flags |= IFF_RUNNING;
+ if (netif_carrier_ok(dev))
+ flags |= IFF_LOWER_UP;
+ if (netif_dormant(dev))
+ flags |= IFF_DORMANT;
+ }
return flags;
}
if (dev->flags & IFF_UP &&
((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
IFF_VOLATILE)))
- notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
+ raw_notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGE, dev);
if ((flags ^ dev->gflags) & IFF_PROMISC) {
int inc = (flags & IFF_PROMISC) ? +1 : -1;
else
dev->mtu = new_mtu;
if (!err && dev->flags & IFF_UP)
- notifier_call_chain(&netdev_chain,
- NETDEV_CHANGEMTU, dev);
+ raw_notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGEMTU, dev);
return err;
}
return -ENODEV;
err = dev->set_mac_address(dev, sa);
if (!err)
- notifier_call_chain(&netdev_chain, NETDEV_CHANGEADDR, dev);
+ raw_notifier_call_chain(&netdev_chain,
+ NETDEV_CHANGEADDR, dev);
return err;
}
return -EINVAL;
memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- notifier_call_chain(&netdev_chain,
+ raw_notifier_call_chain(&netdev_chain,
NETDEV_CHANGEADDR, dev);
return 0;
*/
if (cmd == SIOCGIFCONF) {
- rtnl_shlock();
+ rtnl_lock();
ret = dev_ifconf((char __user *) arg);
- rtnl_shunlock();
+ rtnl_unlock();
return ret;
}
if (cmd == SIOCGIFNAME)
case SIOCBONDENSLAVE:
case SIOCBONDRELEASE:
case SIOCBONDSETHWADDR:
- case SIOCBONDSLAVEINFOQUERY:
- case SIOCBONDINFOQUERY:
case SIOCBONDCHANGEACTIVE:
case SIOCBRADDIF:
case SIOCBRDELIF:
if (!capable(CAP_NET_ADMIN))
return -EPERM;
+ /* fall through */
+ case SIOCBONDSLAVEINFOQUERY:
+ case SIOCBONDINFOQUERY:
dev_load(ifr.ifr_name);
rtnl_lock();
ret = dev_ifsioc(&ifr, cmd);
ret = -EFAULT;
return ret;
}
-#ifdef WIRELESS_EXT
+#ifdef CONFIG_WIRELESS_EXT
/* Take care of Wireless Extensions */
if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) {
/* If command is `set a parameter', or
* `get the encoding parameters', check if
* the user has the right to do it */
- if (IW_IS_SET(cmd) || cmd == SIOCGIWENCODE) {
+ if (IW_IS_SET(cmd) || cmd == SIOCGIWENCODE
+ || cmd == SIOCGIWENCODEEXT) {
if (!capable(CAP_NET_ADMIN))
return -EPERM;
}
ret = -EFAULT;
return ret;
}
-#endif /* WIRELESS_EXT */
+#endif /* CONFIG_WIRELESS_EXT */
return -EINVAL;
}
}
BUG_ON(dev_boot_phase);
ASSERT_RTNL();
+ might_sleep();
+
/* When net_device's are persistent, this will be fatal. */
BUG_ON(dev->reg_state != NETREG_UNINITIALIZED);
spin_lock_init(&dev->queue_lock);
- spin_lock_init(&dev->xmit_lock);
+ spin_lock_init(&dev->_xmit_lock);
dev->xmit_lock_owner = -1;
#ifdef CONFIG_NET_CLS_ACT
spin_lock_init(&dev->ingress_lock);
dev->name);
dev->features &= ~NETIF_F_TSO;
}
+ if (dev->features & NETIF_F_UFO) {
+ if (!(dev->features & NETIF_F_HW_CSUM)) {
+ printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
+ "NETIF_F_HW_CSUM feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_UFO;
+ }
+ if (!(dev->features & NETIF_F_SG)) {
+ printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
+ "NETIF_F_SG feature.\n",
+ dev->name);
+ dev->features &= ~NETIF_F_UFO;
+ }
+ }
/*
* nil rebuild_header routine,
if (!dev->rebuild_header)
dev->rebuild_header = default_rebuild_header;
+ ret = netdev_register_sysfs(dev);
+ if (ret)
+ goto out_err;
+ dev->reg_state = NETREG_REGISTERED;
+
/*
* Default initial state at registry is that the
* device is present.
hlist_add_head(&dev->name_hlist, head);
hlist_add_head(&dev->index_hlist, dev_index_hash(dev->ifindex));
dev_hold(dev);
- dev->reg_state = NETREG_REGISTERING;
write_unlock_bh(&dev_base_lock);
/* Notify protocols, that a new device appeared. */
- notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
+ raw_notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
- /* Finish registration after unlock */
- net_set_todo(dev);
ret = 0;
out:
rebroadcast_time = warning_time = jiffies;
while (atomic_read(&dev->refcnt) != 0) {
if (time_after(jiffies, rebroadcast_time + 1 * HZ)) {
- rtnl_shlock();
+ rtnl_lock();
/* Rebroadcast unregister notification */
- notifier_call_chain(&netdev_chain,
+ raw_notifier_call_chain(&netdev_chain,
NETDEV_UNREGISTER, dev);
if (test_bit(__LINK_STATE_LINKWATCH_PENDING,
linkwatch_run_queue();
}
- rtnl_shunlock();
+ __rtnl_unlock();
rebroadcast_time = jiffies;
}
*
* We are invoked by rtnl_unlock() after it drops the semaphore.
* This allows us to deal with problems:
- * 1) We can create/delete sysfs objects which invoke hotplug
+ * 1) We can delete sysfs objects which invoke hotplug
* without deadlocking with linkwatch via keventd.
* 2) Since we run with the RTNL semaphore not held, we can sleep
* safely in order to wait for the netdev refcnt to drop to zero.
*/
-static DECLARE_MUTEX(net_todo_run_mutex);
+static DEFINE_MUTEX(net_todo_run_mutex);
void netdev_run_todo(void)
{
struct list_head list = LIST_HEAD_INIT(list);
- int err;
-
/* Need to guard against multiple cpu's getting out of order. */
- down(&net_todo_run_mutex);
+ mutex_lock(&net_todo_run_mutex);
/* Not safe to do outside the semaphore. We must not return
* until all unregister events invoked by the local processor
= list_entry(list.next, struct net_device, todo_list);
list_del(&dev->todo_list);
- switch(dev->reg_state) {
- case NETREG_REGISTERING:
- err = netdev_register_sysfs(dev);
- if (err)
- printk(KERN_ERR "%s: failed sysfs registration (%d)\n",
- dev->name, err);
- dev->reg_state = NETREG_REGISTERED;
- break;
-
- case NETREG_UNREGISTERING:
- netdev_unregister_sysfs(dev);
- dev->reg_state = NETREG_UNREGISTERED;
-
- netdev_wait_allrefs(dev);
+ if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) {
+ printk(KERN_ERR "network todo '%s' but state %d\n",
+ dev->name, dev->reg_state);
+ dump_stack();
+ continue;
+ }
- /* paranoia */
- BUG_ON(atomic_read(&dev->refcnt));
- BUG_TRAP(!dev->ip_ptr);
- BUG_TRAP(!dev->ip6_ptr);
- BUG_TRAP(!dev->dn_ptr);
+ netdev_unregister_sysfs(dev);
+ dev->reg_state = NETREG_UNREGISTERED;
+ netdev_wait_allrefs(dev);
- /* It must be the very last action,
- * after this 'dev' may point to freed up memory.
- */
- if (dev->destructor)
- dev->destructor(dev);
- break;
+ /* paranoia */
+ BUG_ON(atomic_read(&dev->refcnt));
+ BUG_TRAP(!dev->ip_ptr);
+ BUG_TRAP(!dev->ip6_ptr);
+ BUG_TRAP(!dev->dn_ptr);
- default:
- printk(KERN_ERR "network todo '%s' but state %d\n",
- dev->name, dev->reg_state);
- break;
- }
+ /* It must be the very last action,
+ * after this 'dev' may point to freed up memory.
+ */
+ if (dev->destructor)
+ dev->destructor(dev);
}
out:
- up(&net_todo_run_mutex);
+ mutex_unlock(&net_todo_run_mutex);
}
/**
alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
alloc_size += sizeof_priv + NETDEV_ALIGN_CONST;
- p = kmalloc(alloc_size, GFP_KERNEL);
+ p = kzalloc(alloc_size, GFP_KERNEL);
if (!p) {
printk(KERN_ERR "alloc_dev: Unable to allocate device.\n");
return NULL;
}
- memset(p, 0, alloc_size);
dev = (struct net_device *)
(((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
void free_netdev(struct net_device *dev)
{
#ifdef CONFIG_SYSFS
- /* Compatiablity with error handling in drivers */
+ /* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
kfree((char *)dev - dev->padded);
return;
void synchronize_net(void)
{
might_sleep();
- synchronize_kernel();
+ synchronize_rcu();
}
/**
/* Notify protocols, that we are about to destroy
this device. They should clean all the things.
*/
- notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev);
+ raw_notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev);
/*
* Flush the multicast chain
}
#endif /* CONFIG_HOTPLUG_CPU */
+#ifdef CONFIG_NET_DMA
+/**
+ * net_dma_rebalance -
+ * This is called when the number of channels allocated to the net_dma_client
+ * changes. The net_dma_client tries to have one DMA channel per CPU.
+ */
+static void net_dma_rebalance(void)
+{
+ unsigned int cpu, i, n;
+ struct dma_chan *chan;
+
+ lock_cpu_hotplug();
+
+ if (net_dma_count == 0) {
+ for_each_online_cpu(cpu)
+ rcu_assign_pointer(per_cpu(softnet_data.net_dma, cpu), NULL);
+ unlock_cpu_hotplug();
+ return;
+ }
+
+ i = 0;
+ cpu = first_cpu(cpu_online_map);
+
+ rcu_read_lock();
+ list_for_each_entry(chan, &net_dma_client->channels, client_node) {
+ n = ((num_online_cpus() / net_dma_count)
+ + (i < (num_online_cpus() % net_dma_count) ? 1 : 0));
+
+ while(n) {
+ per_cpu(softnet_data.net_dma, cpu) = chan;
+ cpu = next_cpu(cpu, cpu_online_map);
+ n--;
+ }
+ i++;
+ }
+ rcu_read_unlock();
+
+ unlock_cpu_hotplug();
+}
+
+/**
+ * netdev_dma_event - event callback for the net_dma_client
+ * @client: should always be net_dma_client
+ * @chan:
+ * @event:
+ */
+static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
+ enum dma_event event)
+{
+ spin_lock(&net_dma_event_lock);
+ switch (event) {
+ case DMA_RESOURCE_ADDED:
+ net_dma_count++;
+ net_dma_rebalance();
+ break;
+ case DMA_RESOURCE_REMOVED:
+ net_dma_count--;
+ net_dma_rebalance();
+ break;
+ default:
+ break;
+ }
+ spin_unlock(&net_dma_event_lock);
+}
+
+/**
+ * netdev_dma_regiser - register the networking subsystem as a DMA client
+ */
+static int __init netdev_dma_register(void)
+{
+ spin_lock_init(&net_dma_event_lock);
+ net_dma_client = dma_async_client_register(netdev_dma_event);
+ if (net_dma_client == NULL)
+ return -ENOMEM;
+
+ dma_async_client_chan_request(net_dma_client, num_online_cpus());
+ return 0;
+}
+
+#else
+static int __init netdev_dma_register(void) { return -ENODEV; }
+#endif /* CONFIG_NET_DMA */
/*
* Initialize the DEV module. At boot time this walks the device list and
* Initialise the packet receive queues.
*/
- for (i = 0; i < NR_CPUS; i++) {
+ for_each_possible_cpu(i) {
struct softnet_data *queue;
queue = &per_cpu(softnet_data, i);
skb_queue_head_init(&queue->input_pkt_queue);
- queue->throttle = 0;
- queue->cng_level = 0;
- queue->avg_blog = 10; /* arbitrary non-zero */
queue->completion_queue = NULL;
INIT_LIST_HEAD(&queue->poll_list);
set_bit(__LINK_STATE_START, &queue->backlog_dev.state);
atomic_set(&queue->backlog_dev.refcnt, 1);
}
-#ifdef OFFLINE_SAMPLE
- samp_timer.expires = jiffies + (10 * HZ);
- add_timer(&samp_timer);
-#endif
+ netdev_dma_register();
dev_boot_phase = 0;
EXPORT_SYMBOL(__dev_get_by_index);
EXPORT_SYMBOL(__dev_get_by_name);
EXPORT_SYMBOL(__dev_remove_pack);
-EXPORT_SYMBOL(__skb_linearize);
+EXPORT_SYMBOL(dev_valid_name);
EXPORT_SYMBOL(dev_add_pack);
EXPORT_SYMBOL(dev_alloc_name);
EXPORT_SYMBOL(dev_close);
EXPORT_SYMBOL(dev_get_by_flags);
EXPORT_SYMBOL(dev_get_by_index);
EXPORT_SYMBOL(dev_get_by_name);
-EXPORT_SYMBOL(dev_ioctl);
EXPORT_SYMBOL(dev_open);
EXPORT_SYMBOL(dev_queue_xmit);
EXPORT_SYMBOL(dev_remove_pack);