#include <linux/seq_file.h>
#include <linux/stat.h>
#include <linux/if_bridge.h>
+#include <linux/if_macvlan.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
*/
int dev_change_name(struct net_device *dev, char *newname)
{
+ char oldname[IFNAMSIZ];
int err = 0;
+ int ret;
ASSERT_RTNL();
if (!dev_valid_name(newname))
return -EINVAL;
+ memcpy(oldname, dev->name, IFNAMSIZ);
+
if (strchr(newname, '%')) {
err = dev_alloc_name(dev, newname);
if (err < 0)
else
strlcpy(dev->name, newname, IFNAMSIZ);
+rollback:
device_rename(&dev->dev, dev->name);
+
+ write_lock_bh(&dev_base_lock);
hlist_del(&dev->name_hlist);
hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
- raw_notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
+ write_unlock_bh(&dev_base_lock);
+
+ ret = raw_notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
+ ret = notifier_to_errno(ret);
+
+ if (ret) {
+ if (err) {
+ printk(KERN_ERR
+ "%s: name change rollback failed: %d.\n",
+ dev->name, ret);
+ } else {
+ err = ret;
+ memcpy(dev->name, oldname, IFNAMSIZ);
+ goto rollback;
+ }
+ }
return err;
}
/*
* Initialize multicasting status
*/
- dev_mc_upload(dev);
+ dev_set_rx_mode(dev);
/*
* Wakeup transmit queue engine
int register_netdevice_notifier(struct notifier_block *nb)
{
struct net_device *dev;
+ struct net_device *last;
int err;
rtnl_lock();
err = raw_notifier_chain_register(&netdev_chain, nb);
- if (!err) {
- for_each_netdev(dev) {
- nb->notifier_call(nb, NETDEV_REGISTER, dev);
+ if (err)
+ goto unlock;
- if (dev->flags & IFF_UP)
- nb->notifier_call(nb, NETDEV_UP, dev);
- }
+ for_each_netdev(dev) {
+ err = nb->notifier_call(nb, NETDEV_REGISTER, dev);
+ err = notifier_to_errno(err);
+ if (err)
+ goto rollback;
+
+ if (!(dev->flags & IFF_UP))
+ continue;
+
+ nb->notifier_call(nb, NETDEV_UP, dev);
}
+
+unlock:
rtnl_unlock();
return err;
+
+rollback:
+ last = dev;
+ for_each_netdev(dev) {
+ if (dev == last)
+ break;
+
+ if (dev->flags & IFF_UP) {
+ nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
+ nb->notifier_call(nb, NETDEV_DOWN, dev);
+ }
+ nb->notifier_call(nb, NETDEV_UNREGISTER, dev);
+ }
+ goto unlock;
}
/**
skb->next = nskb;
return rc;
}
- if (unlikely(netif_queue_stopped(dev) && skb->next))
+ if (unlikely((netif_queue_stopped(dev) ||
+ netif_subqueue_stopped(dev, skb->queue_mapping)) &&
+ skb->next))
return NETDEV_TX_BUSY;
} while (skb->next);
skb_headroom(skb));
if (!(dev->features & NETIF_F_GEN_CSUM) &&
- (!(dev->features & NETIF_F_IP_CSUM) ||
- skb->protocol != htons(ETH_P_IP)))
+ !((dev->features & NETIF_F_IP_CSUM) &&
+ skb->protocol == htons(ETH_P_IP)) &&
+ !((dev->features & NETIF_F_IPV6_CSUM) &&
+ skb->protocol == htons(ETH_P_IPV6)))
if (skb_checksum_help(skb))
goto out_kfree_skb;
}
spin_lock(&dev->queue_lock);
q = dev->qdisc;
if (q->enqueue) {
+ /* reset queue_mapping to zero */
+ skb->queue_mapping = 0;
rc = q->enqueue(skb, q);
qdisc_run(dev);
spin_unlock(&dev->queue_lock);
HARD_TX_LOCK(dev, cpu);
- if (!netif_queue_stopped(dev)) {
+ if (!netif_queue_stopped(dev) &&
+ !netif_subqueue_stopped(dev, skb->queue_mapping)) {
rc = 0;
if (!dev_hard_start_xmit(skb, dev)) {
HARD_TX_UNLOCK(dev);
#define handle_bridge(skb, pt_prev, ret, orig_dev) (skb)
#endif
+#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE)
+struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *skb) __read_mostly;
+EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook);
+
+static inline struct sk_buff *handle_macvlan(struct sk_buff *skb,
+ struct packet_type **pt_prev,
+ int *ret,
+ struct net_device *orig_dev)
+{
+ if (skb->dev->macvlan_port == NULL)
+ return skb;
+
+ if (*pt_prev) {
+ *ret = deliver_skb(skb, *pt_prev, orig_dev);
+ *pt_prev = NULL;
+ }
+ return macvlan_handle_frame_hook(skb);
+}
+#else
+#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb)
+#endif
+
#ifdef CONFIG_NET_CLS_ACT
/* TODO: Maybe we should just force sch_ingress to be compiled in
* when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
#endif
skb = handle_bridge(skb, &pt_prev, &ret, orig_dev);
+ if (!skb)
+ goto out;
+ skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev);
if (!skb)
goto out;
return 0;
}
-/**
- * dev_set_promiscuity - update promiscuity count on a device
- * @dev: device
- * @inc: modifier
- *
- * 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.
- */
-void dev_set_promiscuity(struct net_device *dev, int inc)
+static void __dev_set_promiscuity(struct net_device *dev, int inc)
{
unsigned short old_flags = dev->flags;
+ ASSERT_RTNL();
+
if ((dev->promiscuity += inc) == 0)
dev->flags &= ~IFF_PROMISC;
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");
dev->name, (dev->flags & IFF_PROMISC),
(old_flags & IFF_PROMISC),
audit_get_loginuid(current->audit_context));
+
+ if (dev->change_rx_flags)
+ dev->change_rx_flags(dev, IFF_PROMISC);
}
}
+/**
+ * dev_set_promiscuity - update promiscuity count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * 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.
+ */
+void dev_set_promiscuity(struct net_device *dev, int inc)
+{
+ unsigned short old_flags = dev->flags;
+
+ __dev_set_promiscuity(dev, inc);
+ if (dev->flags != old_flags)
+ dev_set_rx_mode(dev);
+}
+
/**
* dev_set_allmulti - update allmulti count on a device
* @dev: device
{
unsigned short old_flags = dev->flags;
+ ASSERT_RTNL();
+
dev->flags |= IFF_ALLMULTI;
if ((dev->allmulti += inc) == 0)
dev->flags &= ~IFF_ALLMULTI;
- if (dev->flags ^ old_flags)
- dev_mc_upload(dev);
+ if (dev->flags ^ old_flags) {
+ if (dev->change_rx_flags)
+ dev->change_rx_flags(dev, IFF_ALLMULTI);
+ dev_set_rx_mode(dev);
+ }
+}
+
+/*
+ * Upload unicast and multicast address lists to device and
+ * configure RX filtering. When the device doesn't support unicast
+ * filtering it is put in promiscous mode while unicast addresses
+ * are present.
+ */
+void __dev_set_rx_mode(struct net_device *dev)
+{
+ /* dev_open will call this function so the list will stay sane. */
+ if (!(dev->flags&IFF_UP))
+ return;
+
+ if (!netif_device_present(dev))
+ return;
+
+ if (dev->set_rx_mode)
+ dev->set_rx_mode(dev);
+ else {
+ /* Unicast addresses changes may only happen under the rtnl,
+ * therefore calling __dev_set_promiscuity here is safe.
+ */
+ if (dev->uc_count > 0 && !dev->uc_promisc) {
+ __dev_set_promiscuity(dev, 1);
+ dev->uc_promisc = 1;
+ } else if (dev->uc_count == 0 && dev->uc_promisc) {
+ __dev_set_promiscuity(dev, -1);
+ dev->uc_promisc = 0;
+ }
+
+ if (dev->set_multicast_list)
+ dev->set_multicast_list(dev);
+ }
+}
+
+void dev_set_rx_mode(struct net_device *dev)
+{
+ netif_tx_lock_bh(dev);
+ __dev_set_rx_mode(dev);
+ netif_tx_unlock_bh(dev);
+}
+
+int __dev_addr_delete(struct dev_addr_list **list, int *count,
+ void *addr, int alen, int glbl)
+{
+ struct dev_addr_list *da;
+
+ for (; (da = *list) != NULL; list = &da->next) {
+ if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
+ alen == da->da_addrlen) {
+ if (glbl) {
+ int old_glbl = da->da_gusers;
+ da->da_gusers = 0;
+ if (old_glbl == 0)
+ break;
+ }
+ if (--da->da_users)
+ return 0;
+
+ *list = da->next;
+ kfree(da);
+ (*count)--;
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+int __dev_addr_add(struct dev_addr_list **list, int *count,
+ void *addr, int alen, int glbl)
+{
+ struct dev_addr_list *da;
+
+ for (da = *list; da != NULL; da = da->next) {
+ if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 &&
+ da->da_addrlen == alen) {
+ if (glbl) {
+ int old_glbl = da->da_gusers;
+ da->da_gusers = 1;
+ if (old_glbl)
+ return 0;
+ }
+ da->da_users++;
+ return 0;
+ }
+ }
+
+ da = kmalloc(sizeof(*da), GFP_ATOMIC);
+ if (da == NULL)
+ return -ENOMEM;
+ memcpy(da->da_addr, addr, alen);
+ da->da_addrlen = alen;
+ da->da_users = 1;
+ da->da_gusers = glbl ? 1 : 0;
+ da->next = *list;
+ *list = da;
+ (*count)++;
+ return 0;
+}
+
+/**
+ * dev_unicast_delete - Release secondary unicast address.
+ * @dev: device
+ * @addr: address to delete
+ * @alen: length of @addr
+ *
+ * Release reference to a secondary unicast address and remove it
+ * from the device if the reference count drops to zero.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_unicast_delete(struct net_device *dev, void *addr, int alen)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ netif_tx_lock_bh(dev);
+ err = __dev_addr_delete(&dev->uc_list, &dev->uc_count, addr, alen, 0);
+ if (!err)
+ __dev_set_rx_mode(dev);
+ netif_tx_unlock_bh(dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_unicast_delete);
+
+/**
+ * dev_unicast_add - add a secondary unicast address
+ * @dev: device
+ * @addr: address to delete
+ * @alen: length of @addr
+ *
+ * Add a secondary unicast address to the device or increase
+ * the reference count if it already exists.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+int dev_unicast_add(struct net_device *dev, void *addr, int alen)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ netif_tx_lock_bh(dev);
+ err = __dev_addr_add(&dev->uc_list, &dev->uc_count, addr, alen, 0);
+ if (!err)
+ __dev_set_rx_mode(dev);
+ netif_tx_unlock_bh(dev);
+ return err;
+}
+EXPORT_SYMBOL(dev_unicast_add);
+
+static void __dev_addr_discard(struct dev_addr_list **list)
+{
+ struct dev_addr_list *tmp;
+
+ while (*list != NULL) {
+ tmp = *list;
+ *list = tmp->next;
+ if (tmp->da_users > tmp->da_gusers)
+ printk("__dev_addr_discard: address leakage! "
+ "da_users=%d\n", tmp->da_users);
+ kfree(tmp);
+ }
+}
+
+static void dev_addr_discard(struct net_device *dev)
+{
+ netif_tx_lock_bh(dev);
+
+ __dev_addr_discard(&dev->uc_list);
+ dev->uc_count = 0;
+
+ __dev_addr_discard(&dev->mc_list);
+ dev->mc_count = 0;
+
+ netif_tx_unlock_bh(dev);
}
unsigned dev_get_flags(const struct net_device *dev)
int ret, changes;
int old_flags = dev->flags;
+ ASSERT_RTNL();
+
/*
* Set the flags on our device.
*/
* Load in the correct multicast list now the flags have changed.
*/
- dev_mc_upload(dev);
+ if (dev->change_rx_flags && (dev->flags ^ flags) & IFF_MULTICAST)
+ dev->change_rx_flags(dev, IFF_MULTICAST);
+
+ dev_set_rx_mode(dev);
/*
* Have we downed the interface. We handle IFF_UP ourselves
ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev);
if (!ret)
- dev_mc_upload(dev);
+ dev_set_rx_mode(dev);
}
if (dev->flags & IFF_UP &&
if (!dev_valid_name(dev->name)) {
ret = -EINVAL;
- goto out;
+ goto err_uninit;
}
dev->ifindex = dev_new_index();
= hlist_entry(p, struct net_device, name_hlist);
if (!strncmp(d->name, dev->name, IFNAMSIZ)) {
ret = -EEXIST;
- goto out;
+ goto err_uninit;
}
}
+ /* Fix illegal checksum combinations */
+ if ((dev->features & NETIF_F_HW_CSUM) &&
+ (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
+ printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n",
+ dev->name);
+ dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
+ }
+
+ if ((dev->features & NETIF_F_NO_CSUM) &&
+ (dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
+ printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n",
+ dev->name);
+ dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
+ }
+
+
/* Fix illegal SG+CSUM combinations. */
if ((dev->features & NETIF_F_SG) &&
!(dev->features & NETIF_F_ALL_CSUM)) {
ret = netdev_register_sysfs(dev);
if (ret)
- goto out;
+ goto err_uninit;
dev->reg_state = NETREG_REGISTERED;
/*
write_unlock_bh(&dev_base_lock);
/* Notify protocols, that a new device appeared. */
- raw_notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
-
- ret = 0;
+ ret = raw_notifier_call_chain(&netdev_chain, NETDEV_REGISTER, dev);
+ ret = notifier_to_errno(ret);
+ if (ret)
+ unregister_netdevice(dev);
out:
return ret;
+
+err_uninit:
+ if (dev->uninit)
+ dev->uninit(dev);
+ goto out;
}
/**
}
/**
- * alloc_netdev - allocate network device
+ * alloc_netdev_mq - allocate network device
* @sizeof_priv: size of private data to allocate space for
* @name: device name format string
* @setup: callback to initialize device
+ * @queue_count: the number of subqueues to allocate
*
* Allocates a struct net_device with private data area for driver use
- * and performs basic initialization.
+ * and performs basic initialization. Also allocates subquue structs
+ * for each queue on the device at the end of the netdevice.
*/
-struct net_device *alloc_netdev(int sizeof_priv, const char *name,
- void (*setup)(struct net_device *))
+struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
+ void (*setup)(struct net_device *), unsigned int queue_count)
{
void *p;
struct net_device *dev;
BUG_ON(strlen(name) >= sizeof(dev->name));
/* ensure 32-byte alignment of both the device and private area */
- alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
+ alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST +
+ (sizeof(struct net_device_subqueue) * (queue_count - 1))) &
+ ~NETDEV_ALIGN_CONST;
alloc_size += sizeof_priv + NETDEV_ALIGN_CONST;
p = kzalloc(alloc_size, GFP_KERNEL);
(((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
dev->padded = (char *)dev - (char *)p;
- if (sizeof_priv)
- dev->priv = netdev_priv(dev);
+ if (sizeof_priv) {
+ dev->priv = ((char *)dev +
+ ((sizeof(struct net_device) +
+ (sizeof(struct net_device_subqueue) *
+ (queue_count - 1)) + NETDEV_ALIGN_CONST)
+ & ~NETDEV_ALIGN_CONST));
+ }
+
+ dev->egress_subqueue_count = queue_count;
dev->get_stats = internal_stats;
setup(dev);
strcpy(dev->name, name);
return dev;
}
-EXPORT_SYMBOL(alloc_netdev);
+EXPORT_SYMBOL(alloc_netdev_mq);
/**
* free_netdev - free network device
raw_notifier_call_chain(&netdev_chain, NETDEV_UNREGISTER, dev);
/*
- * Flush the multicast chain
+ * Flush the unicast and multicast chains
*/
- dev_mc_discard(dev);
+ dev_addr_discard(dev);
if (dev->uninit)
dev->uninit(dev);
#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.
+ * net_dma_rebalance - try to maintain one DMA channel per CPU
+ * @net_dma: DMA client and associated data (lock, channels, channel_mask)
+ *
+ * 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(struct net_dma *net_dma)
* netdev_dma_event - event callback for the net_dma_client
* @client: should always be net_dma_client
* @chan: DMA channel for the event
- * @event: event type
+ * @state: DMA state to be handled
*/
static enum dma_state_client
netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
static int __init netdev_dma_register(void) { return -ENODEV; }
#endif /* CONFIG_NET_DMA */
+/**
+ * netdev_compute_feature - compute conjunction of two feature sets
+ * @all: first feature set
+ * @one: second feature set
+ *
+ * Computes a new feature set after adding a device with feature set
+ * @one to the master device with current feature set @all. Returns
+ * the new feature set.
+ */
+int netdev_compute_features(unsigned long all, unsigned long one)
+{
+ /* if device needs checksumming, downgrade to hw checksumming */
+ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
+ all ^= NETIF_F_NO_CSUM | NETIF_F_HW_CSUM;
+
+ /* if device can't do all checksum, downgrade to ipv4/ipv6 */
+ if (all & NETIF_F_HW_CSUM && !(one & NETIF_F_HW_CSUM))
+ all ^= NETIF_F_HW_CSUM
+ | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+
+ if (one & NETIF_F_GSO)
+ one |= NETIF_F_GSO_SOFTWARE;
+ one |= NETIF_F_GSO;
+
+ /* If even one device supports robust GSO, enable it for all. */
+ if (one & NETIF_F_GSO_ROBUST)
+ all |= NETIF_F_GSO_ROBUST;
+
+ all &= one | NETIF_F_LLTX;
+
+ if (!(all & NETIF_F_ALL_CSUM))
+ all &= ~NETIF_F_SG;
+ if (!(all & NETIF_F_SG))
+ all &= ~NETIF_F_GSO_MASK;
+
+ return all;
+}
+EXPORT_SYMBOL(netdev_compute_features);
+
/*
* Initialize the DEV module. At boot time this walks the device list and
* unhooks any devices that fail to initialise (normally hardware not
projects / linux.git / blobdiff