#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>
#endif /* CONFIG_NET_RADIO */
#include <linux/vs_network.h>
#include <asm/current.h>
-#include <linux/vs_network.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
/*
* The list of packet types we will receive (as opposed to discard)
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);
-#endif
-
/*
* The @dev_base list is protected by @dev_base_lock and the rtln
* semaphore.
* 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, ".")
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);
}
/*
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;
}
}
* taps currently in use.
*/
+#if !((defined(CONFIG_VNET) || defined(CONFIG_VNET_MODULE)))
+#if LINUX_VERSION_CODE > KERNEL_VERSION(2,6,12)
+static
+#endif
+#endif
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();
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)
+int __skb_linearize(struct sk_buff *skb, gfp_t gfp_mask)
{
unsigned int size;
u8 *data;
atomic_set(&ninfo->dataref, 1);
ninfo->tso_size = skb_shinfo(skb)->tso_size;
ninfo->tso_segs = skb_shinfo(skb)->tso_segs;
+ ninfo->ufo_size = skb_shinfo(skb)->ufo_size;
ninfo->nr_frags = 0;
ninfo->frag_list = NULL;
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.
*/
if (q->enqueue) {
/* Grab device queue */
spin_lock(&dev->queue_lock);
+ q = dev->qdisc;
+ if (q->enqueue) {
+ rc = q->enqueue(skb, q);
+ qdisc_run(dev);
+ spin_unlock(&dev->queue_lock);
- rc = q->enqueue(skb, q);
-
- qdisc_run(dev);
-
+ rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
+ goto out;
+ }
spin_unlock(&dev->queue_lock);
- rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
- goto out;
}
/* The device has no queue. Common case for software devices:
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;
+ if (dev->master)
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);
__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
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);
else
dev->quota = dev->weight;
} else {
- netpoll_poll_unlock(dev);
+ netpoll_poll_unlock(have);
dev_put(dev);
local_irq_disable();
}
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;
}
{
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" :
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);
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,
switch(dev->reg_state) {
case NETREG_REGISTERING:
+ dev->reg_state = NETREG_REGISTERED;
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:
* Initialise the packet receive queues.
*/
- for (i = 0; i < NR_CPUS; i++) {
+ for_each_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
-
dev_boot_phase = 0;
open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL);
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);
#if defined(CONFIG_VNET) || defined(CONFIG_VNET_MODULE)
EXPORT_SYMBOL(dev_set_allmulti);
EXPORT_SYMBOL(dev_set_promiscuity);
EXPORT_SYMBOL(dev_change_flags);
-EXPORT_SYMBOL(dev_change_name);
EXPORT_SYMBOL(dev_set_mtu);
EXPORT_SYMBOL(dev_set_mac_address);
EXPORT_SYMBOL(free_netdev);