diff options
| author | Paul Mundt <lethal@linux-sh.org> | 2011-01-13 15:06:28 +0900 |
|---|---|---|
| committer | Paul Mundt <lethal@linux-sh.org> | 2011-01-13 15:06:28 +0900 |
| commit | f43dc23d5ea91fca257be02138a255f02d98e806 (patch) | |
| tree | b29722f6e965316e90ac97abf79923ced250dc21 /net/core/dev.c | |
| parent | f8e53553f452dcbf67cb89c8cba63a1cd6eb4cc0 (diff) | |
| parent | 4162cf64973df51fc885825bc9ca4d055891c49f (diff) | |
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework
Conflicts:
arch/sh/kernel/cpu/sh2/setup-sh7619.c
arch/sh/kernel/cpu/sh2a/setup-mxg.c
arch/sh/kernel/cpu/sh2a/setup-sh7201.c
arch/sh/kernel/cpu/sh2a/setup-sh7203.c
arch/sh/kernel/cpu/sh2a/setup-sh7206.c
arch/sh/kernel/cpu/sh3/setup-sh7705.c
arch/sh/kernel/cpu/sh3/setup-sh770x.c
arch/sh/kernel/cpu/sh3/setup-sh7710.c
arch/sh/kernel/cpu/sh3/setup-sh7720.c
arch/sh/kernel/cpu/sh4/setup-sh4-202.c
arch/sh/kernel/cpu/sh4/setup-sh7750.c
arch/sh/kernel/cpu/sh4/setup-sh7760.c
arch/sh/kernel/cpu/sh4a/setup-sh7343.c
arch/sh/kernel/cpu/sh4a/setup-sh7366.c
arch/sh/kernel/cpu/sh4a/setup-sh7722.c
arch/sh/kernel/cpu/sh4a/setup-sh7723.c
arch/sh/kernel/cpu/sh4a/setup-sh7724.c
arch/sh/kernel/cpu/sh4a/setup-sh7763.c
arch/sh/kernel/cpu/sh4a/setup-sh7770.c
arch/sh/kernel/cpu/sh4a/setup-sh7780.c
arch/sh/kernel/cpu/sh4a/setup-sh7785.c
arch/sh/kernel/cpu/sh4a/setup-sh7786.c
arch/sh/kernel/cpu/sh4a/setup-shx3.c
arch/sh/kernel/cpu/sh5/setup-sh5.c
drivers/serial/sh-sci.c
drivers/serial/sh-sci.h
include/linux/serial_sci.h
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 3927 |
1 files changed, 2300 insertions, 1627 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index baf2dc13a34..a3ef808b5e3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -79,6 +79,8 @@ #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/hash.h> +#include <linux/slab.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/string.h> @@ -99,11 +101,10 @@ #include <linux/proc_fs.h> #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> +#include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/kmod.h> @@ -127,6 +128,10 @@ #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> +#include <trace/events/net.h> +#include <trace/events/skb.h> +#include <linux/pci.h> +#include <linux/inetdevice.h> #include "net-sysfs.h" @@ -175,7 +180,7 @@ static struct list_head ptype_all __read_mostly; /* Taps */ * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. * - * Pure readers hold dev_base_lock for reading. + * Pure readers hold dev_base_lock for reading, or rcu_read_lock() * * Writers must hold the rtnl semaphore while they loop through the * dev_base_head list, and hold dev_base_lock for writing when they do the @@ -191,21 +196,31 @@ static struct list_head ptype_all __read_mostly; /* Taps */ * semaphore held. */ DEFINE_RWLOCK(dev_base_lock); - EXPORT_SYMBOL(dev_base_lock); -#define NETDEV_HASHBITS 8 -#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) - static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); - return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)]; + return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { - return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)]; + return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; +} + +static inline void rps_lock(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + spin_lock(&sd->input_pkt_queue.lock); +#endif +} + +static inline void rps_unlock(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + spin_unlock(&sd->input_pkt_queue.lock); +#endif } /* Device list insertion */ @@ -216,23 +231,26 @@ static int list_netdevice(struct net_device *dev) ASSERT_RTNL(); write_lock_bh(&dev_base_lock); - list_add_tail(&dev->dev_list, &net->dev_base_head); - hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name)); - hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); + list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + hlist_add_head_rcu(&dev->index_hlist, + dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); return 0; } -/* Device list removal */ +/* Device list removal + * caller must respect a RCU grace period before freeing/reusing dev + */ static void unlist_netdevice(struct net_device *dev) { ASSERT_RTNL(); /* Unlink dev from the device chain */ write_lock_bh(&dev_base_lock); - list_del(&dev->dev_list); - hlist_del(&dev->name_hlist); - hlist_del(&dev->index_hlist); + list_del_rcu(&dev->dev_list); + hlist_del_rcu(&dev->name_hlist); + hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); } @@ -247,7 +265,8 @@ static RAW_NOTIFIER_HEAD(netdev_chain); * queue in the local softnet handler. */ -DEFINE_PER_CPU(struct softnet_data, softnet_data); +DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +EXPORT_PER_CPU_SYMBOL(softnet_data); #ifdef CONFIG_LOCKDEP /* @@ -269,10 +288,10 @@ static const unsigned short netdev_lock_type[] = ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, - ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_IEEE802154_PHY, + ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; -static const char *netdev_lock_name[] = +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", @@ -287,7 +306,7 @@ static const char *netdev_lock_name[] = "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", - "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_IEEE802154_PHY", + "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -355,6 +374,14 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) * --ANK (980803) */ +static inline struct list_head *ptype_head(const struct packet_type *pt) +{ + if (pt->type == htons(ETH_P_ALL)) + return &ptype_all; + else + return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; +} + /** * dev_add_pack - add packet handler * @pt: packet type declaration @@ -370,17 +397,13 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) void dev_add_pack(struct packet_type *pt) { - int hash; + struct list_head *head = ptype_head(pt); - spin_lock_bh(&ptype_lock); - if (pt->type == htons(ETH_P_ALL)) - list_add_rcu(&pt->list, &ptype_all); - else { - hash = ntohs(pt->type) & PTYPE_HASH_MASK; - list_add_rcu(&pt->list, &ptype_base[hash]); - } - spin_unlock_bh(&ptype_lock); + spin_lock(&ptype_lock); + list_add_rcu(&pt->list, head); + spin_unlock(&ptype_lock); } +EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler @@ -397,15 +420,10 @@ void dev_add_pack(struct packet_type *pt) */ void __dev_remove_pack(struct packet_type *pt) { - struct list_head *head; + struct list_head *head = ptype_head(pt); struct packet_type *pt1; - spin_lock_bh(&ptype_lock); - - if (pt->type == htons(ETH_P_ALL)) - head = &ptype_all; - else - head = &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; + spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { @@ -416,8 +434,10 @@ void __dev_remove_pack(struct packet_type *pt) printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); out: - spin_unlock_bh(&ptype_lock); + spin_unlock(&ptype_lock); } +EXPORT_SYMBOL(__dev_remove_pack); + /** * dev_remove_pack - remove packet handler * @pt: packet type declaration @@ -436,6 +456,7 @@ void dev_remove_pack(struct packet_type *pt) synchronize_net(); } +EXPORT_SYMBOL(dev_remove_pack); /****************************************************************************** @@ -499,6 +520,7 @@ int netdev_boot_setup_check(struct net_device *dev) } return 0; } +EXPORT_SYMBOL(netdev_boot_setup_check); /** @@ -582,15 +604,42 @@ __setup("netdev=", netdev_boot_setup); struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each(p, dev_name_hash(net, name)) { - struct net_device *dev - = hlist_entry(p, struct net_device, name_hlist); + hlist_for_each_entry(dev, p, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; - } + return NULL; } +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 + * + * 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) +{ + struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); + + hlist_for_each_entry_rcu(dev, p, head, name_hlist) + if (!strncmp(dev->name, name, IFNAMSIZ)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_get_by_name_rcu); /** * dev_get_by_name - find a device by its name @@ -608,13 +657,14 @@ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(net, name); + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } +EXPORT_SYMBOL(dev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex @@ -631,15 +681,41 @@ struct net_device *dev_get_by_name(struct net *net, const char *name) struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each(p, dev_index_hash(net, ifindex)) { - struct net_device *dev - = hlist_entry(p, struct net_device, index_hlist); + hlist_for_each_entry(dev, p, head, index_hlist) if (dev->ifindex == ifindex) return dev; - } + + return NULL; +} +EXPORT_SYMBOL(__dev_get_by_index); + +/** + * dev_get_by_index_rcu - find a device by its ifindex + * @net: the applicable net namespace + * @ifindex: index of device + * + * Search for an interface by index. Returns %NULL if the device + * is not found or a pointer to the device. The device has not + * had its reference counter increased so the caller must be careful + * about locking. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) +{ + struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); + + hlist_for_each_entry_rcu(dev, p, head, index_hlist) + if (dev->ifindex == ifindex) + return dev; + return NULL; } +EXPORT_SYMBOL(dev_get_by_index_rcu); /** @@ -657,44 +733,41 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } +EXPORT_SYMBOL(dev_get_by_index); /** - * dev_getbyhwaddr - find a device by its hardware address + * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device - * is not found or a pointer to the device. The caller must hold the - * rtnl semaphore. The returned device has not had its ref count increased + * is not found or a pointer to the device. The caller must hold RCU + * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * - * BUGS: - * If the API was consistent this would be __dev_get_by_hwaddr */ -struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha) +struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *ha) { struct net_device *dev; - ASSERT_RTNL(); - - for_each_netdev(net, dev) + for_each_netdev_rcu(net, dev) if (dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) return dev; return NULL; } - -EXPORT_SYMBOL(dev_getbyhwaddr); +EXPORT_SYMBOL(dev_getbyhwaddr_rcu); struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) { @@ -707,51 +780,50 @@ struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) return NULL; } - EXPORT_SYMBOL(__dev_getfirstbyhwtype); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { - struct net_device *dev; + struct net_device *dev, *ret = NULL; - rtnl_lock(); - dev = __dev_getfirstbyhwtype(net, type); - if (dev) - dev_hold(dev); - rtnl_unlock(); - return dev; + rcu_read_lock(); + for_each_netdev_rcu(net, dev) + if (dev->type == type) { + dev_hold(dev); + ret = dev; + break; + } + rcu_read_unlock(); + return ret; } - EXPORT_SYMBOL(dev_getfirstbyhwtype); /** - * dev_get_by_flags - find any device with given flags + * dev_get_by_flags_rcu - find any device with given flags * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device - * is not found or a pointer to the device. The device returned has - * had a reference added and the pointer is safe until the user calls - * dev_put to indicate they have finished with it. + * is not found or a pointer to the device. Must be called inside + * rcu_read_lock(), and result refcount is unchanged. */ -struct net_device * dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask) +struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags, + unsigned short mask) { struct net_device *dev, *ret; ret = NULL; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { + for_each_netdev_rcu(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { - dev_hold(dev); ret = dev; break; } } - read_unlock(&dev_base_lock); return ret; } +EXPORT_SYMBOL(dev_get_by_flags_rcu); /** * dev_valid_name - check if name is okay for network device @@ -777,6 +849,7 @@ int dev_valid_name(const char *name) } return 1; } +EXPORT_SYMBOL(dev_valid_name); /** * __dev_alloc_name - allocate a name for a device @@ -832,7 +905,8 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) free_page((unsigned long) inuse); } - snprintf(buf, IFNAMSIZ, name, i); + if (buf != name) + snprintf(buf, IFNAMSIZ, name, i); if (!__dev_get_by_name(net, buf)) return i; @@ -870,7 +944,27 @@ int dev_alloc_name(struct net_device *dev, const char *name) strlcpy(dev->name, buf, IFNAMSIZ); return ret; } +EXPORT_SYMBOL(dev_alloc_name); +static int dev_get_valid_name(struct net_device *dev, const char *name, bool fmt) +{ + struct net *net; + + BUG_ON(!dev_net(dev)); + net = dev_net(dev); + + if (!dev_valid_name(name)) + return -EINVAL; + + if (fmt && strchr(name, '%')) + return dev_alloc_name(dev, name); + else if (__dev_get_by_name(net, name)) + return -EEXIST; + else if (dev->name != name) + strlcpy(dev->name, name, IFNAMSIZ); + + return 0; +} /** * dev_change_name - change name of a device @@ -894,53 +988,45 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - if (!dev_valid_name(newname)) - return -EINVAL; - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) return 0; memcpy(oldname, dev->name, IFNAMSIZ); - if (strchr(newname, '%')) { - err = dev_alloc_name(dev, newname); - if (err < 0) - return err; - } - else if (__dev_get_by_name(net, newname)) - return -EEXIST; - else - strlcpy(dev->name, newname, IFNAMSIZ); + err = dev_get_valid_name(dev, newname, 1); + if (err < 0) + return err; rollback: - /* For now only devices in the initial network namespace - * are in sysfs. - */ - if (net == &init_net) { - ret = device_rename(&dev->dev, dev->name); - if (ret) { - memcpy(dev->name, oldname, IFNAMSIZ); - return ret; - } + ret = device_rename(&dev->dev, dev->name); + if (ret) { + memcpy(dev->name, oldname, IFNAMSIZ); + return ret; } write_lock_bh(&dev_base_lock); hlist_del(&dev->name_hlist); - hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name)); + write_unlock_bh(&dev_base_lock); + + synchronize_rcu(); + + write_lock_bh(&dev_base_lock); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); write_unlock_bh(&dev_base_lock); ret = call_netdevice_notifiers(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 >= 0 after dev_alloc_name() or stores the first errno */ + if (err >= 0) { err = ret; memcpy(dev->name, oldname, IFNAMSIZ); goto rollback; + } else { + printk(KERN_ERR + "%s: name change rollback failed: %d.\n", + dev->name, ret); } } @@ -970,7 +1056,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return 0; } - dev->ifalias = krealloc(dev->ifalias, len+1, GFP_KERNEL); + dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); if (!dev->ifalias) return -ENOMEM; @@ -1006,10 +1092,11 @@ void netdev_state_change(struct net_device *dev) rtmsg_ifinfo(RTM_NEWLINK, dev, 0); } } +EXPORT_SYMBOL(netdev_state_change); -void netdev_bonding_change(struct net_device *dev) +int netdev_bonding_change(struct net_device *dev, unsigned long event) { - call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, dev); + return call_netdevice_notifiers(event, dev); } EXPORT_SYMBOL(netdev_bonding_change); @@ -1027,27 +1114,16 @@ void dev_load(struct net *net, const char *name) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(net, name); - read_unlock(&dev_base_lock); + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); + rcu_read_unlock(); - if (!dev && capable(CAP_SYS_MODULE)) + if (!dev && capable(CAP_NET_ADMIN)) request_module("%s", name); } +EXPORT_SYMBOL(dev_load); -/** - * dev_open - prepare an interface for use. - * @dev: device to open - * - * Takes a device from down to up state. The device's private open - * function is invoked and then the multicast lists are loaded. Finally - * the device is moved into the up state and a %NETDEV_UP message is - * sent to the netdev notifier chain. - * - * Calling this function on an active interface is a nop. On a failure - * a negative errno code is returned. - */ -int dev_open(struct net_device *dev) +static int __dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; int ret; @@ -1055,13 +1131,6 @@ int dev_open(struct net_device *dev) ASSERT_RTNL(); /* - * Is it already up? - */ - - if (dev->flags & IFF_UP) - return 0; - - /* * Is it even present? */ if (!netif_device_present(dev)) @@ -1109,81 +1178,156 @@ int dev_open(struct net_device *dev) * Wakeup transmit queue engine */ dev_activate(dev); - - /* - * ... and announce new interface. - */ - call_netdevice_notifiers(NETDEV_UP, dev); } return ret; } /** - * dev_close - shutdown an interface. - * @dev: device to shutdown + * dev_open - prepare an interface for use. + * @dev: device to open * - * This function moves an active device into down state. A - * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device - * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier - * chain. + * Takes a device from down to up state. The device's private open + * function is invoked and then the multicast lists are loaded. Finally + * the device is moved into the up state and a %NETDEV_UP message is + * sent to the netdev notifier chain. + * + * Calling this function on an active interface is a nop. On a failure + * a negative errno code is returned. */ -int dev_close(struct net_device *dev) +int dev_open(struct net_device *dev) { - const struct net_device_ops *ops = dev->netdev_ops; - ASSERT_RTNL(); - - might_sleep(); + int ret; - if (!(dev->flags & IFF_UP)) + /* + * Is it already up? + */ + if (dev->flags & IFF_UP) return 0; /* - * Tell people we are going down, so that they can - * prepare to death, when device is still operating. + * Open device */ - call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); - - clear_bit(__LINK_STATE_START, &dev->state); + ret = __dev_open(dev); + if (ret < 0) + return ret; - /* Synchronize to scheduled poll. We cannot touch poll list, - * it can be even on different cpu. So just clear netif_running(). - * - * dev->stop() will invoke napi_disable() on all of it's - * napi_struct instances on this device. + /* + * ... and announce new interface. */ - smp_mb__after_clear_bit(); /* Commit netif_running(). */ + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_UP, dev); - dev_deactivate(dev); + return ret; +} +EXPORT_SYMBOL(dev_open); - /* - * Call the device specific close. This cannot fail. - * Only if device is UP - * - * We allow it to be called even after a DETACH hot-plug - * event. - */ - if (ops->ndo_stop) - ops->ndo_stop(dev); +static int __dev_close_many(struct list_head *head) +{ + struct net_device *dev; - /* - * Device is now down. - */ + ASSERT_RTNL(); + might_sleep(); - dev->flags &= ~IFF_UP; + list_for_each_entry(dev, head, unreg_list) { + /* + * Tell people we are going down, so that they can + * prepare to death, when device is still operating. + */ + call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); + + clear_bit(__LINK_STATE_START, &dev->state); + + /* Synchronize to scheduled poll. We cannot touch poll list, it + * can be even on different cpu. So just clear netif_running(). + * + * dev->stop() will invoke napi_disable() on all of it's + * napi_struct instances on this device. + */ + smp_mb__after_clear_bit(); /* Commit netif_running(). */ + } + + dev_deactivate_many(head); + + list_for_each_entry(dev, head, unreg_list) { + const struct net_device_ops *ops = dev->netdev_ops; + + /* + * Call the device specific close. This cannot fail. + * Only if device is UP + * + * We allow it to be called even after a DETACH hot-plug + * event. + */ + if (ops->ndo_stop) + ops->ndo_stop(dev); + + /* + * Device is now down. + */ + + dev->flags &= ~IFF_UP; + + /* + * Shutdown NET_DMA + */ + net_dmaengine_put(); + } + + return 0; +} + +static int __dev_close(struct net_device *dev) +{ + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + return __dev_close_many(&single); +} + +int dev_close_many(struct list_head *head) +{ + struct net_device *dev, *tmp; + LIST_HEAD(tmp_list); + + list_for_each_entry_safe(dev, tmp, head, unreg_list) + if (!(dev->flags & IFF_UP)) + list_move(&dev->unreg_list, &tmp_list); + + __dev_close_many(head); /* * Tell people we are down */ - call_netdevice_notifiers(NETDEV_DOWN, dev); + list_for_each_entry(dev, head, unreg_list) { + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_DOWN, dev); + } - /* - * Shutdown NET_DMA - */ - net_dmaengine_put(); + /* rollback_registered_many needs the complete original list */ + list_splice(&tmp_list, head); + return 0; +} + +/** + * dev_close - shutdown an interface. + * @dev: device to shutdown + * + * This function moves an active device into down state. A + * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device + * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier + * chain. + */ +int dev_close(struct net_device *dev) +{ + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + dev_close_many(&single); return 0; } +EXPORT_SYMBOL(dev_close); /** @@ -1273,12 +1417,14 @@ rollback: nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } +EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block @@ -1299,6 +1445,7 @@ int unregister_netdevice_notifier(struct notifier_block *nb) rtnl_unlock(); return err; } +EXPORT_SYMBOL(unregister_netdevice_notifier); /** * call_netdevice_notifiers - call all network notifier blocks @@ -1311,6 +1458,7 @@ int unregister_netdevice_notifier(struct notifier_block *nb) int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { + ASSERT_RTNL(); return raw_notifier_call_chain(&netdev_chain, val, dev); } @@ -1321,13 +1469,15 @@ void net_enable_timestamp(void) { atomic_inc(&netstamp_needed); } +EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { atomic_dec(&netstamp_needed); } +EXPORT_SYMBOL(net_disable_timestamp); -static inline void net_timestamp(struct sk_buff *skb) +static inline void net_timestamp_set(struct sk_buff *skb) { if (atomic_read(&netstamp_needed)) __net_timestamp(skb); @@ -1335,6 +1485,57 @@ static inline void net_timestamp(struct sk_buff *skb) skb->tstamp.tv64 = 0; } +static inline void net_timestamp_check(struct sk_buff *skb) +{ + if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed)) + __net_timestamp(skb); +} + +/** + * dev_forward_skb - loopback an skb to another netif + * + * @dev: destination network device + * @skb: buffer to forward + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped, but freed) + * + * dev_forward_skb can be used for injecting an skb from the + * start_xmit function of one device into the receive queue + * of another device. + * + * The receiving device may be in another namespace, so + * we have to clear all information in the skb that could + * impact namespace isolation. + */ +int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + skb_orphan(skb); + nf_reset(skb); + + if (unlikely(!(dev->flags & IFF_UP) || + (skb->len > (dev->mtu + dev->hard_header_len + VLAN_HLEN)))) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + skb_set_dev(skb, dev); + skb->tstamp.tv64 = 0; + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, dev); + return netif_rx(skb); +} +EXPORT_SYMBOL_GPL(dev_forward_skb); + +static inline int deliver_skb(struct sk_buff *skb, + struct packet_type *pt_prev, + struct net_device *orig_dev) +{ + atomic_inc(&skb->users); + return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); +} + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1343,13 +1544,8 @@ static inline void net_timestamp(struct sk_buff *skb) static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; - -#ifdef CONFIG_NET_CLS_ACT - if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS))) - net_timestamp(skb); -#else - net_timestamp(skb); -#endif + struct sk_buff *skb2 = NULL; + struct packet_type *pt_prev = NULL; rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_all, list) { @@ -1359,10 +1555,18 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if ((ptype->dev == dev || !ptype->dev) && (ptype->af_packet_priv == NULL || (struct sock *)ptype->af_packet_priv != skb->sk)) { - struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC); + if (pt_prev) { + deliver_skb(skb2, pt_prev, skb->dev); + pt_prev = ptype; + continue; + } + + skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) break; + net_timestamp_set(skb2); + /* skb->nh should be correctly set by sender, so that the second statement is just protection against buggy protocols. @@ -1374,18 +1578,81 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if (net_ratelimit()) printk(KERN_CRIT "protocol %04x is " "buggy, dev %s\n", - skb2->protocol, dev->name); + ntohs(skb2->protocol), + dev->name); skb_reset_network_header(skb2); } skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; - ptype->func(skb2, skb->dev, ptype, skb->dev); + pt_prev = ptype; } } + if (pt_prev) + pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); rcu_read_unlock(); } +/* + * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues + * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. + */ +int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) +{ + int rc; + + if (txq < 1 || txq > dev->num_tx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED) { + ASSERT_RTNL(); + + rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, + txq); + if (rc) + return rc; + + if (txq < dev->real_num_tx_queues) + qdisc_reset_all_tx_gt(dev, txq); + } + + dev->real_num_tx_queues = txq; + return 0; +} +EXPORT_SYMBOL(netif_set_real_num_tx_queues); + +#ifdef CONFIG_RPS +/** + * netif_set_real_num_rx_queues - set actual number of RX queues used + * @dev: Network device + * @rxq: Actual number of RX queues + * + * This must be called either with the rtnl_lock held or before + * registration of the net device. Returns 0 on success, or a + * negative error code. If called before registration, it always + * succeeds. + */ +int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) +{ + int rc; + + if (rxq < 1 || rxq > dev->num_rx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED) { + ASSERT_RTNL(); + + rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, + rxq); + if (rc) + return rc; + } + + dev->real_num_rx_queues = rxq; + return 0; +} +EXPORT_SYMBOL(netif_set_real_num_rx_queues); +#endif static inline void __netif_reschedule(struct Qdisc *q) { @@ -1394,8 +1661,9 @@ static inline void __netif_reschedule(struct Qdisc *q) local_irq_save(flags); sd = &__get_cpu_var(softnet_data); - q->next_sched = sd->output_queue; - sd->output_queue = q; + q->next_sched = NULL; + *sd->output_queue_tailp = q; + sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } @@ -1464,31 +1732,35 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -static bool can_checksum_protocol(unsigned long features, __be16 protocol) -{ - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_IP_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_IPV6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); -} - -static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) -{ - if (can_checksum_protocol(dev->features, skb->protocol)) - return true; - - if (skb->protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - if (can_checksum_protocol(dev->features & dev->vlan_features, - veh->h_vlan_encapsulated_proto)) - return true; +/** + * skb_dev_set -- assign a new device to a buffer + * @skb: buffer for the new device + * @dev: network device + * + * If an skb is owned by a device already, we have to reset + * all data private to the namespace a device belongs to + * before assigning it a new device. + */ +#ifdef CONFIG_NET_NS +void skb_set_dev(struct sk_buff *skb, struct net_device *dev) +{ + skb_dst_drop(skb); + if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) { + secpath_reset(skb); + nf_reset(skb); + skb_init_secmark(skb); + skb->mark = 0; + skb->priority = 0; + skb->nf_trace = 0; + skb->ipvs_property = 0; +#ifdef CONFIG_NET_SCHED + skb->tc_index = 0; +#endif } - - return false; + skb->dev = dev; } +EXPORT_SYMBOL(skb_set_dev); +#endif /* CONFIG_NET_NS */ /* * Invalidate hardware checksum when packet is to be mangled, and @@ -1507,7 +1779,7 @@ int skb_checksum_help(struct sk_buff *skb) goto out_set_summed; } - offset = skb->csum_start - skb_headroom(skb); + offset = skb_checksum_start_offset(skb); BUG_ON(offset >= skb_headlen(skb)); csum = skb_checksum(skb, offset, skb->len - offset, 0); @@ -1527,6 +1799,7 @@ out_set_summed: out: return ret; } +EXPORT_SYMBOL(skb_checksum_help); /** * skb_gso_segment - Perform segmentation on skb. @@ -1543,8 +1816,20 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_type *ptype; __be16 type = skb->protocol; + int vlan_depth = ETH_HLEN; int err; + while (type == htons(ETH_P_8021Q)) { + struct vlan_hdr *vh; + + if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) + return ERR_PTR(-EINVAL); + + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; + } + skb_reset_mac_header(skb); skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); @@ -1556,8 +1841,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) dev->ethtool_ops->get_drvinfo(dev, &info); - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d " - "ip_summed=%d", + WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n", info.driver, dev ? dev->features : 0L, skb->sk ? skb->sk->sk_route_caps : 0L, skb->len, skb->data_len, skb->ip_summed); @@ -1589,7 +1873,6 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) return segs; } - EXPORT_SYMBOL(skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ @@ -1610,18 +1893,27 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; + if (!(dev->features & NETIF_F_HIGHDMA)) { + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + if (PageHighMem(skb_shinfo(skb)->frags[i].page)) + return 1; + } - if (dev->features & NETIF_F_HIGHDMA) - return 0; - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - if (PageHighMem(skb_shinfo(skb)->frags[i].page)) - return 1; + if (PCI_DMA_BUS_IS_PHYS) { + struct device *pdev = dev->dev.parent; + if (!pdev) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + dma_addr_t addr = page_to_phys(skb_shinfo(skb)->frags[i].page); + if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) + return 1; + } + } #endif return 0; } @@ -1652,16 +1944,14 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) /** * dev_gso_segment - Perform emulated hardware segmentation on skb. * @skb: buffer to segment + * @features: device features as applicable to this skb * * This function segments the given skb and stores the list of segments * in skb->next. */ -static int dev_gso_segment(struct sk_buff *skb) +static int dev_gso_segment(struct sk_buff *skb, int features) { - struct net_device *dev = skb->dev; struct sk_buff *segs; - int features = dev->features & ~(illegal_highdma(dev, skb) ? - NETIF_F_SG : 0); segs = skb_gso_segment(skb, features); @@ -1679,22 +1969,97 @@ static int dev_gso_segment(struct sk_buff *skb) return 0; } +/* + * Try to orphan skb early, right before transmission by the device. + * We cannot orphan skb if tx timestamp is requested or the sk-reference + * is needed on driver level for other reasons, e.g. see net/can/raw.c + */ +static inline void skb_orphan_try(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + + if (sk && !skb_shinfo(skb)->tx_flags) { + /* skb_tx_hash() wont be able to get sk. + * We copy sk_hash into skb->rxhash + */ + if (!skb->rxhash) + skb->rxhash = sk->sk_hash; + skb_orphan(skb); + } +} + +static bool can_checksum_protocol(unsigned long features, __be16 protocol) +{ + return ((features & NETIF_F_GEN_CSUM) || + ((features & NETIF_F_V4_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_V6_CSUM) && + protocol == htons(ETH_P_IPV6)) || + ((features & NETIF_F_FCOE_CRC) && + protocol == htons(ETH_P_FCOE))); +} + +static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features) +{ + if (!can_checksum_protocol(protocol, features)) { + features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_SG; + } else if (illegal_highdma(skb->dev, skb)) { + features &= ~NETIF_F_SG; + } + + return features; +} + +int netif_skb_features(struct sk_buff *skb) +{ + __be16 protocol = skb->protocol; + int features = skb->dev->features; + + if (protocol == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else if (!vlan_tx_tag_present(skb)) { + return harmonize_features(skb, protocol, features); + } + + features &= skb->dev->vlan_features; + + if (protocol != htons(ETH_P_8021Q)) { + return harmonize_features(skb, protocol, features); + } else { + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM; + return harmonize_features(skb, protocol, features); + } +} +EXPORT_SYMBOL(netif_skb_features); + +/* + * Returns true if either: + * 1. skb has frag_list and the device doesn't support FRAGLIST, or + * 2. skb is fragmented and the device does not support SG, or if + * at least one of fragments is in highmem and device does not + * support DMA from it. + */ +static inline int skb_needs_linearize(struct sk_buff *skb, + int features) +{ + return skb_is_nonlinear(skb) && + ((skb_has_frag_list(skb) && + !(features & NETIF_F_FRAGLIST)) || + (skb_shinfo(skb)->nr_frags && + !(features & NETIF_F_SG))); +} + int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { const struct net_device_ops *ops = dev->netdev_ops; - int rc; + int rc = NETDEV_TX_OK; if (likely(!skb->next)) { - if (!list_empty(&ptype_all)) - dev_queue_xmit_nit(skb, dev); - - if (netif_needs_gso(dev, skb)) { - if (unlikely(dev_gso_segment(skb))) - goto out_kfree_skb; - if (skb->next) - goto gso; - } + int features; /* * If device doesnt need skb->dst, release it right now while @@ -1703,23 +2068,49 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + + skb_orphan_try(skb); + + features = netif_skb_features(skb); + + if (vlan_tx_tag_present(skb) && + !(features & NETIF_F_HW_VLAN_TX)) { + skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + if (unlikely(!skb)) + goto out; + + skb->vlan_tci = 0; + } + + if (netif_needs_gso(skb, features)) { + if (unlikely(dev_gso_segment(skb, features))) + goto out_kfree_skb; + if (skb->next) + goto gso; + } else { + if (skb_needs_linearize(skb, features) && + __skb_linearize(skb)) + goto out_kfree_skb; + + /* If packet is not checksummed and device does not + * support checksumming for this protocol, complete + * checksumming here. + */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); + if (!(features & NETIF_F_ALL_CSUM) && + skb_checksum_help(skb)) + goto out_kfree_skb; + } + } + rc = ops->ndo_start_xmit(skb, dev); - if (rc == 0) + trace_net_dev_xmit(skb, rc); + if (rc == NETDEV_TX_OK) txq_trans_update(txq); - /* - * TODO: if skb_orphan() was called by - * dev->hard_start_xmit() (for example, the unmodified - * igb driver does that; bnx2 doesn't), then - * skb_tx_software_timestamp() will be unable to send - * back the time stamp. - * - * How can this be prevented? Always create another - * reference to the socket before calling - * dev->hard_start_xmit()? Prevent that skb_orphan() - * does anything in dev->hard_start_xmit() by clearing - * the skb destructor before the call and restoring it - * afterwards, then doing the skb_orphan() ourselves? - */ return rc; } @@ -1729,8 +2120,19 @@ gso: skb->next = nskb->next; nskb->next = NULL; + + /* + * If device doesnt need nskb->dst, release it right now while + * its hot in this cpu cache + */ + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(nskb); + rc = ops->ndo_start_xmit(nskb, dev); - if (unlikely(rc)) { + trace_net_dev_xmit(nskb, rc); + if (unlikely(rc != NETDEV_TX_OK)) { + if (rc & ~NETDEV_TX_MASK) + goto out_kfree_gso_skb; nskb->next = skb->next; skb->next = nskb; return rc; @@ -1740,52 +2142,195 @@ gso: return NETDEV_TX_BUSY; } while (skb->next); - skb->destructor = DEV_GSO_CB(skb)->destructor; - +out_kfree_gso_skb: + if (likely(skb->next == NULL)) + skb->destructor = DEV_GSO_CB(skb)->destructor; out_kfree_skb: kfree_skb(skb); - return 0; +out: + return rc; } -static u32 skb_tx_hashrnd; +static u32 hashrnd __read_mostly; -u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) { u32 hash; if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); - while (unlikely (hash >= dev->real_num_tx_queues)) - hash -= dev->real_num_tx_queues; + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; return hash; } if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else - hash = skb->protocol; + hash = (__force u16) skb->protocol ^ skb->rxhash; + hash = jhash_1word(hash, hashrnd); + + return (u16) (((u64) hash * num_tx_queues) >> 32); +} +EXPORT_SYMBOL(__skb_tx_hash); + +static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + if (net_ratelimit()) { + pr_warning("%s selects TX queue %d, but " + "real number of TX queues is %d\n", + dev->name, queue_index, dev->real_num_tx_queues); + } + return 0; + } + return queue_index; +} - hash = jhash_1word(hash, skb_tx_hashrnd); +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->rxhash; + hash = jhash_1word(hash, hashrnd); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); - return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); + return queue_index; +#else + return -1; +#endif } -EXPORT_SYMBOL(skb_tx_hash); static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { + int queue_index; const struct net_device_ops *ops = dev->netdev_ops; - u16 queue_index = 0; - if (ops->ndo_select_queue) + if (dev->real_num_tx_queues == 1) + queue_index = 0; + else if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb); - else if (dev->real_num_tx_queues > 1) - queue_index = skb_tx_hash(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } else { + struct sock *sk = skb->sk; + queue_index = sk_tx_queue_get(sk); + + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int old_index = queue_index; + + queue_index = get_xps_queue(dev, skb); + if (queue_index < 0) + queue_index = skb_tx_hash(dev, skb); + + if (queue_index != old_index && sk) { + struct dst_entry *dst = + rcu_dereference_check(sk->sk_dst_cache, 1); + + if (dst && skb_dst(skb) == dst) + sk_tx_queue_set(sk, queue_index); + } + } + } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); } +static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, + struct netdev_queue *txq) +{ + spinlock_t *root_lock = qdisc_lock(q); + bool contended = qdisc_is_running(q); + int rc; + + /* + * Heuristic to force contended enqueues to serialize on a + * separate lock before trying to get qdisc main lock. + * This permits __QDISC_STATE_RUNNING owner to get the lock more often + * and dequeue packets faster. + */ + if (unlikely(contended)) + spin_lock(&q->busylock); + + spin_lock(root_lock); + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { + kfree_skb(skb); + rc = NET_XMIT_DROP; + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && + qdisc_run_begin(q)) { + /* + * This is a work-conserving queue; there are no old skbs + * waiting to be sent out; and the qdisc is not running - + * xmit the skb directly. + */ + if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) + skb_dst_force(skb); + + qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_bstats_update(q, skb); + + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } + __qdisc_run(q); + } else + qdisc_run_end(q); + + rc = NET_XMIT_SUCCESS; + } else { + skb_dst_force(skb); + rc = qdisc_enqueue_root(skb, q); + if (qdisc_run_begin(q)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } + __qdisc_run(q); + } + } + spin_unlock(root_lock); + if (unlikely(contended)) + spin_unlock(&q->busylock); + return rc; +} + +static DEFINE_PER_CPU(int, xmit_recursion); +#define RECURSION_LIMIT 10 + /** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -1818,60 +2363,20 @@ int dev_queue_xmit(struct sk_buff *skb) struct Qdisc *q; int rc = -ENOMEM; - /* GSO will handle the following emulations directly. */ - if (netif_needs_gso(dev, skb)) - goto gso; - - if (skb_has_frags(skb) && - !(dev->features & NETIF_F_FRAGLIST) && - __skb_linearize(skb)) - goto out_kfree_skb; - - /* Fragmented skb is linearized if device does not support SG, - * or if at least one of fragments is in highmem and device - * does not support DMA from it. - */ - if (skb_shinfo(skb)->nr_frags && - (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) && - __skb_linearize(skb)) - goto out_kfree_skb; - - /* If packet is not checksummed and device does not support - * checksumming for this protocol, complete checksumming here. - */ - if (skb->ip_summed == CHECKSUM_PARTIAL) { - skb_set_transport_header(skb, skb->csum_start - - skb_headroom(skb)); - if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb)) - goto out_kfree_skb; - } - -gso: /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ rcu_read_lock_bh(); txq = dev_pick_tx(dev, skb); - q = rcu_dereference(txq->qdisc); + q = rcu_dereference_bh(txq->qdisc); #ifdef CONFIG_NET_CLS_ACT - skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS); + skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); #endif + trace_net_dev_queue(skb); if (q->enqueue) { - spinlock_t *root_lock = qdisc_lock(q); - - spin_lock(root_lock); - - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { - kfree_skb(skb); - rc = NET_XMIT_DROP; - } else { - rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); - } - spin_unlock(root_lock); - + rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } @@ -1892,11 +2397,16 @@ gso: if (txq->xmit_lock_owner != cpu) { + if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT) + goto recursion_alert; + HARD_TX_LOCK(dev, txq, cpu); if (!netif_tx_queue_stopped(txq)) { - rc = 0; - if (!dev_hard_start_xmit(skb, dev, txq)) { + __this_cpu_inc(xmit_recursion); + rc = dev_hard_start_xmit(skb, dev, txq); + __this_cpu_dec(xmit_recursion); + if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; } @@ -1907,7 +2417,9 @@ gso: "queue packet!\n", dev->name); } else { /* Recursion is detected! It is possible, - * unfortunately */ + * unfortunately + */ +recursion_alert: if (net_ratelimit()) printk(KERN_CRIT "Dead loop on virtual device " "%s, fix it urgently!\n", dev->name); @@ -1917,13 +2429,13 @@ gso: rc = -ENETDOWN; rcu_read_unlock_bh(); -out_kfree_skb: kfree_skb(skb); return rc; out: rcu_read_unlock_bh(); return rc; } +EXPORT_SYMBOL(dev_queue_xmit); /*======================================================================= @@ -1931,11 +2443,267 @@ out: =======================================================================*/ int netdev_max_backlog __read_mostly = 1000; +int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; int weight_p __read_mostly = 64; /* old backlog weight */ -DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; +/* Called with irq disabled */ +static inline void ____napi_schedule(struct softnet_data *sd, + struct napi_struct *napi) +{ + list_add_tail(&napi->poll_list, &sd->poll_list); + __raise_softirq_irqoff(NET_RX_SOFTIRQ); +} + +/* + * __skb_get_rxhash: calculate a flow hash based on src/dst addresses + * and src/dst port numbers. Returns a non-zero hash number on success + * and 0 on failure. + */ +__u32 __skb_get_rxhash(struct sk_buff *skb) +{ + int nhoff, hash = 0, poff; + struct ipv6hdr *ip6; + struct iphdr *ip; + u8 ip_proto; + u32 addr1, addr2, ihl; + union { + u32 v32; + u16 v16[2]; + } ports; + + nhoff = skb_network_offset(skb); + + switch (skb->protocol) { + case __constant_htons(ETH_P_IP): + if (!pskb_may_pull(skb, sizeof(*ip) + nhoff)) + goto done; + + ip = (struct iphdr *) (skb->data + nhoff); + if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + ip_proto = 0; + else + ip_proto = ip->protocol; + addr1 = (__force u32) ip->saddr; + addr2 = (__force u32) ip->daddr; + ihl = ip->ihl; + break; + case __constant_htons(ETH_P_IPV6): + if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff)) + goto done; + + ip6 = (struct ipv6hdr *) (skb->data + nhoff); + ip_proto = ip6->nexthdr; + addr1 = (__force u32) ip6->saddr.s6_addr32[3]; + addr2 = (__force u32) ip6->daddr.s6_addr32[3]; + ihl = (40 >> 2); + break; + default: + goto done; + } + + ports.v32 = 0; + poff = proto_ports_offset(ip_proto); + if (poff >= 0) { + nhoff += ihl * 4 + poff; + if (pskb_may_pull(skb, nhoff + 4)) { + ports.v32 = * (__force u32 *) (skb->data + nhoff); + if (ports.v16[1] < ports.v16[0]) + swap(ports.v16[0], ports.v16[1]); + } + } + + /* get a consistent hash (same value on both flow directions) */ + if (addr2 < addr1) + swap(addr1, addr2); + + hash = jhash_3words(addr1, addr2, ports.v32, hashrnd); + if (!hash) + hash = 1; + +done: + return hash; +} +EXPORT_SYMBOL(__skb_get_rxhash); + +#ifdef CONFIG_RPS + +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; +EXPORT_SYMBOL(rps_sock_flow_table); + +/* + * get_rps_cpu is called from netif_receive_skb and returns the target + * CPU from the RPS map of the receiving queue for a given skb. + * rcu_read_lock must be held on entry. + */ +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow **rflowp) +{ + struct netdev_rx_queue *rxqueue; + struct rps_map *map; + struct rps_dev_flow_table *flow_table; + struct rps_sock_flow_table *sock_flow_table; + int cpu = -1; + u16 tcpu; + + if (skb_rx_queue_recorded(skb)) { + u16 index = skb_get_rx_queue(skb); + if (unlikely(index >= dev->real_num_rx_queues)) { + WARN_ONCE(dev->real_num_rx_queues > 1, + "%s received packet on queue %u, but number " + "of RX queues is %u\n", + dev->name, index, dev->real_num_rx_queues); + goto done; + } + rxqueue = dev->_rx + index; + } else + rxqueue = dev->_rx; + + map = rcu_dereference(rxqueue->rps_map); + if (map) { + if (map->len == 1) { + tcpu = map->cpus[0]; + if (cpu_online(tcpu)) + cpu = tcpu; + goto done; + } + } else if (!rcu_dereference_raw(rxqueue->rps_flow_table)) { + goto done; + } + + skb_reset_network_header(skb); + if (!skb_get_rxhash(skb)) + goto done; + + flow_table = rcu_dereference(rxqueue->rps_flow_table); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + if (flow_table && sock_flow_table) { + u16 next_cpu; + struct rps_dev_flow *rflow; + + rflow = &flow_table->flows[skb->rxhash & flow_table->mask]; + tcpu = rflow->cpu; + + next_cpu = sock_flow_table->ents[skb->rxhash & + sock_flow_table->mask]; + /* + * If the desired CPU (where last recvmsg was done) is + * different from current CPU (one in the rx-queue flow + * table entry), switch if one of the following holds: + * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is offline. + * - The current CPU's queue tail has advanced beyond the + * last packet that was enqueued using this table entry. + * This guarantees that all previous packets for the flow + * have been dequeued, thus preserving in order delivery. + */ + if (unlikely(tcpu != next_cpu) && + (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + ((int)(per_cpu(softnet_data, tcpu).input_queue_head - + rflow->last_qtail)) >= 0)) { + tcpu = rflow->cpu = next_cpu; + if (tcpu != RPS_NO_CPU) + rflow->last_qtail = per_cpu(softnet_data, + tcpu).input_queue_head; + } + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + *rflowp = rflow; + cpu = tcpu; + goto done; + } + } + + if (map) { + tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + + if (cpu_online(tcpu)) { + cpu = tcpu; + goto done; + } + } + +done: + return cpu; +} + +/* Called from hardirq (IPI) context */ +static void rps_trigger_softirq(void *data) +{ + struct softnet_data *sd = data; + + ____napi_schedule(sd, &sd->backlog); + sd->received_rps++; +} + +#endif /* CONFIG_RPS */ + +/* + * Check if this softnet_data structure is another cpu one + * If yes, queue it to our IPI list and return 1 + * If no, return 0 + */ +static int rps_ipi_queued(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + struct softnet_data *mysd = &__get_cpu_var(softnet_data); + + if (sd != mysd) { + sd->rps_ipi_next = mysd->rps_ipi_list; + mysd->rps_ipi_list = sd; + + __raise_softirq_irqoff(NET_RX_SOFTIRQ); + return 1; + } +#endif /* CONFIG_RPS */ + return 0; +} + +/* + * enqueue_to_backlog is called to queue an skb to a per CPU backlog + * queue (may be a remote CPU queue). + */ +static int enqueue_to_backlog(struct sk_buff *skb, int cpu, + unsigned int *qtail) +{ + struct softnet_data *sd; + unsigned long flags; + + sd = &per_cpu(softnet_data, cpu); + + local_irq_save(flags); + + rps_lock(sd); + if (skb_queue_len(&sd->input_pkt_queue) <= netdev_max_backlog) { + if (skb_queue_len(&sd->input_pkt_queue)) { +enqueue: + __skb_queue_tail(&sd->input_pkt_queue, skb); + input_queue_tail_incr_save(sd, qtail); + rps_unlock(sd); + local_irq_restore(flags); + return NET_RX_SUCCESS; + } + + /* Schedule NAPI for backlog device + * We can use non atomic operation since we own the queue lock + */ + if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) { + if (!rps_ipi_queued(sd)) + ____napi_schedule(sd, &sd->backlog); + } + goto enqueue; + } + + sd->dropped++; + rps_unlock(sd); + + local_irq_restore(flags); + + atomic_long_inc(&skb->dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; +} /** * netif_rx - post buffer to the network code @@ -1954,42 +2722,43 @@ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; int netif_rx(struct sk_buff *skb) { - struct softnet_data *queue; - unsigned long flags; + int ret; /* if netpoll wants it, pretend we never saw it */ if (netpoll_rx(skb)) return NET_RX_DROP; - if (!skb->tstamp.tv64) - net_timestamp(skb); + if (netdev_tstamp_prequeue) + net_timestamp_check(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); - queue = &__get_cpu_var(softnet_data); + trace_netif_rx(skb); +#ifdef CONFIG_RPS + { + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; - __get_cpu_var(netdev_rx_stat).total++; - if (queue->input_pkt_queue.qlen <= netdev_max_backlog) { - if (queue->input_pkt_queue.qlen) { -enqueue: - __skb_queue_tail(&queue->input_pkt_queue, skb); - local_irq_restore(flags); - return NET_RX_SUCCESS; - } + preempt_disable(); + rcu_read_lock(); - napi_schedule(&queue->backlog); - goto enqueue; - } + cpu = get_rps_cpu(skb->dev, skb, &rflow); + if (cpu < 0) + cpu = smp_processor_id(); - __get_cpu_var(netdev_rx_stat).dropped++; - local_irq_restore(flags); + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); - kfree_skb(skb); - return NET_RX_DROP; + rcu_read_unlock(); + preempt_enable(); + } +#else + { + unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); + } +#endif + return ret; } +EXPORT_SYMBOL(netif_rx); int netif_rx_ni(struct sk_buff *skb) { @@ -2003,7 +2772,6 @@ int netif_rx_ni(struct sk_buff *skb) return err; } - EXPORT_SYMBOL(netif_rx_ni); static void net_tx_action(struct softirq_action *h) @@ -2023,6 +2791,7 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } @@ -2033,6 +2802,7 @@ static void net_tx_action(struct softirq_action *h) local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; + sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); while (head) { @@ -2062,72 +2832,12 @@ static void net_tx_action(struct softirq_action *h) } } -static inline int deliver_skb(struct sk_buff *skb, - struct packet_type *pt_prev, - struct net_device *orig_dev) -{ - atomic_inc(&skb->users); - return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); -} - -#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE) - -#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \ + (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)) /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; -EXPORT_SYMBOL(br_fdb_test_addr_hook); -#endif - -/* - * If bridge module is loaded call bridging hook. - * returns NULL if packet was consumed. - */ -struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, - struct sk_buff *skb) __read_mostly; -EXPORT_SYMBOL(br_handle_frame_hook); - -static inline struct sk_buff *handle_bridge(struct sk_buff *skb, - struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) -{ - struct net_bridge_port *port; - - if (skb->pkt_type == PACKET_LOOPBACK || - (port = rcu_dereference(skb->dev->br_port)) == NULL) - return skb; - - if (*pt_prev) { - *ret = deliver_skb(skb, *pt_prev, orig_dev); - *pt_prev = NULL; - } - - return br_handle_frame_hook(port, skb); -} -#else -#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) +EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif #ifdef CONFIG_NET_CLS_ACT @@ -2139,26 +2849,23 @@ static inline struct sk_buff *handle_macvlan(struct sk_buff *skb, * the ingress scheduler, you just cant add policies on ingress. * */ -static int ing_filter(struct sk_buff *skb) +static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) { struct net_device *dev = skb->dev; u32 ttl = G_TC_RTTL(skb->tc_verd); - struct netdev_queue *rxq; int result = TC_ACT_OK; struct Qdisc *q; - if (MAX_RED_LOOP < ttl++) { - printk(KERN_WARNING - "Redir loop detected Dropping packet (%d->%d)\n", - skb->iif, dev->ifindex); + if (unlikely(MAX_RED_LOOP < ttl++)) { + if (net_ratelimit()) + pr_warning( "Redir loop detected Dropping packet (%d->%d)\n", + skb->skb_iif, dev->ifindex); 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); - rxq = &dev->rx_queue; - q = rxq->qdisc; if (q != &noop_qdisc) { spin_lock(qdisc_lock(q)); @@ -2174,18 +2881,17 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { - if (skb->dev->rx_queue.qdisc == &noop_qdisc) + struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); + + if (!rxq || rxq->qdisc == &noop_qdisc) goto out; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; - } else { - /* Huh? Why does turning on AF_PACKET affect this? */ - skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); } - switch (ing_filter(skb)) { + switch (ing_filter(skb, rxq)) { case TC_ACT_SHOT: case TC_ACT_STOLEN: kfree_skb(skb); @@ -2198,80 +2904,145 @@ out: } #endif -/* - * netif_nit_deliver - deliver received packets to network taps - * @skb: buffer +/** + * netdev_rx_handler_register - register receive handler + * @dev: device to register a handler for + * @rx_handler: receive handler to register + * @rx_handler_data: data pointer that is used by rx handler * - * This function is used to deliver incoming packets to network - * taps. It should be used when the normal netif_receive_skb path - * is bypassed, for example because of VLAN acceleration. + * Register a receive hander for a device. This handler will then be + * called from __netif_receive_skb. A negative errno code is returned + * on a failure. + * + * The caller must hold the rtnl_mutex. */ -void netif_nit_deliver(struct sk_buff *skb) +int netdev_rx_handler_register(struct net_device *dev, + rx_handler_func_t *rx_handler, + void *rx_handler_data) { - struct packet_type *ptype; + ASSERT_RTNL(); - if (list_empty(&ptype_all)) - return; + if (dev->rx_handler) + return -EBUSY; - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; + rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); + rcu_assign_pointer(dev->rx_handler, rx_handler); - rcu_read_lock(); - list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == skb->dev) - deliver_skb(skb, ptype, skb->dev); - } - rcu_read_unlock(); + return 0; } +EXPORT_SYMBOL_GPL(netdev_rx_handler_register); /** - * netif_receive_skb - process receive buffer from network - * @skb: buffer to process - * - * netif_receive_skb() is the main receive data processing function. - * It always succeeds. The buffer may be dropped during processing - * for congestion control or by the protocol layers. + * netdev_rx_handler_unregister - unregister receive handler + * @dev: device to unregister a handler from * - * This function may only be called from softirq context and interrupts - * should be enabled. + * Unregister a receive hander from a device. * - * Return values (usually ignored): - * NET_RX_SUCCESS: no congestion - * NET_RX_DROP: packet was dropped + * The caller must hold the rtnl_mutex. */ -int netif_receive_skb(struct sk_buff *skb) +void netdev_rx_handler_unregister(struct net_device *dev) +{ + + ASSERT_RTNL(); + rcu_assign_pointer(dev->rx_handler, NULL); + rcu_assign_pointer(dev->rx_handler_data, NULL); +} +EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); + +static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, + struct net_device *master) +{ + if (skb->pkt_type == PACKET_HOST) { + u16 *dest = (u16 *) eth_hdr(skb)->h_dest; + + memcpy(dest, master->dev_addr, ETH_ALEN); + } +} + +/* On bonding slaves other than the currently active slave, suppress + * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and + * ARP on active-backup slaves with arp_validate enabled. + */ +int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) +{ + struct net_device *dev = skb->dev; + + if (master->priv_flags & IFF_MASTER_ARPMON) + dev->last_rx = jiffies; + + if ((master->priv_flags & IFF_MASTER_ALB) && + (master->priv_flags & IFF_BRIDGE_PORT)) { + /* Do address unmangle. The local destination address + * will be always the one master has. Provides the right + * functionality in a bridge. + */ + skb_bond_set_mac_by_master(skb, master); + } + + if (dev->priv_flags & IFF_SLAVE_INACTIVE) { + if ((dev->priv_flags & IFF_SLAVE_NEEDARP) && + skb->protocol == __cpu_to_be16(ETH_P_ARP)) + return 0; + + if (master->priv_flags & IFF_MASTER_ALB) { + if (skb->pkt_type != PACKET_BROADCAST && + skb->pkt_type != PACKET_MULTICAST) + return 0; + } + if (master->priv_flags & IFF_MASTER_8023AD && + skb->protocol == __cpu_to_be16(ETH_P_SLOW)) + return 0; + + return 1; + } + return 0; +} +EXPORT_SYMBOL(__skb_bond_should_drop); + +static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; + rx_handler_func_t *rx_handler; struct net_device *orig_dev; + struct net_device *master; struct net_device *null_or_orig; + struct net_device *orig_or_bond; int ret = NET_RX_DROP; __be16 type; - if (skb->vlan_tci && vlan_hwaccel_do_receive(skb)) - return NET_RX_SUCCESS; + if (!netdev_tstamp_prequeue) + net_timestamp_check(skb); + + trace_netif_receive_skb(skb); /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) return NET_RX_DROP; - if (!skb->tstamp.tv64) - net_timestamp(skb); - - if (!skb->iif) - skb->iif = skb->dev->ifindex; + if (!skb->skb_iif) + skb->skb_iif = skb->dev->ifindex; + /* + * bonding note: skbs received on inactive slaves should only + * be delivered to pkt handlers that are exact matches. Also + * the deliver_no_wcard flag will be set. If packet handlers + * are sensitive to duplicate packets these skbs will need to + * be dropped at the handler. + */ null_or_orig = NULL; orig_dev = skb->dev; - if (orig_dev->master) { - if (skb_bond_should_drop(skb)) + master = ACCESS_ONCE(orig_dev->master); + if (skb->deliver_no_wcard) + null_or_orig = orig_dev; + else if (master) { + if (skb_bond_should_drop(skb, master)) { + skb->deliver_no_wcard = 1; null_or_orig = orig_dev; /* deliver only exact match */ - else - skb->dev = orig_dev->master; + } else + skb->dev = master; } - __get_cpu_var(netdev_rx_stat).total++; - + __this_cpu_inc(softnet_data.processed); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->mac_len = skb->network_header - skb->mac_header; @@ -2303,21 +3074,48 @@ int netif_receive_skb(struct sk_buff *skb) ncls: #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; + /* Handle special case of bridge or macvlan */ + rx_handler = rcu_dereference(skb->dev->rx_handler); + if (rx_handler) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + skb = rx_handler(skb); + if (!skb) + goto out; + } - skb_orphan(skb); + if (vlan_tx_tag_present(skb)) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + if (vlan_hwaccel_do_receive(&skb)) { + ret = __netif_receive_skb(skb); + goto out; + } else if (unlikely(!skb)) + goto out; + } + + /* + * Make sure frames received on VLAN interfaces stacked on + * bonding interfaces still make their way to any base bonding + * device that may have registered for a specific ptype. The + * handler may have to adjust skb->dev and orig_dev. + */ + orig_or_bond = orig_dev; + if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) && + (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) { + orig_or_bond = vlan_dev_real_dev(skb->dev); + } type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && - (ptype->dev == null_or_orig || ptype->dev == skb->dev || - ptype->dev == orig_dev)) { + if (ptype->type == type && (ptype->dev == null_or_orig || + ptype->dev == skb->dev || ptype->dev == orig_dev || + ptype->dev == orig_or_bond)) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -2327,6 +3125,7 @@ ncls: if (pt_prev) { ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) @@ -2339,18 +3138,80 @@ out: return ret; } -/* Network device is going away, flush any packets still pending */ +/** + * netif_receive_skb - process receive buffer from network + * @skb: buffer to process + * + * netif_receive_skb() is the main receive data processing function. + * It always succeeds. The buffer may be dropped during processing + * for congestion control or by the protocol layers. + * + * This function may only be called from softirq context and interrupts + * should be enabled. + * + * Return values (usually ignored): + * NET_RX_SUCCESS: no congestion + * NET_RX_DROP: packet was dropped + */ +int netif_receive_skb(struct sk_buff *skb) +{ + if (netdev_tstamp_prequeue) + net_timestamp_check(skb); + + if (skb_defer_rx_timestamp(skb)) + return NET_RX_SUCCESS; + +#ifdef CONFIG_RPS + { + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu, ret; + + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); + + if (cpu >= 0) { + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + rcu_read_unlock(); + } else { + rcu_read_unlock(); + ret = __netif_receive_skb(skb); + } + + return ret; + } +#else + return __netif_receive_skb(skb); +#endif +} +EXPORT_SYMBOL(netif_receive_skb); + +/* Network device is going away, flush any packets still pending + * Called with irqs disabled. + */ static void flush_backlog(void *arg) { struct net_device *dev = arg; - struct softnet_data *queue = &__get_cpu_var(softnet_data); + struct softnet_data *sd = &__get_cpu_var(softnet_data); struct sk_buff *skb, *tmp; - skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp) + rps_lock(sd); + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { + if (skb->dev == dev) { + __skb_unlink(skb, &sd->input_pkt_queue); + kfree_skb(skb); + input_queue_head_incr(sd); + } + } + rps_unlock(sd); + + skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (skb->dev == dev) { - __skb_unlink(skb, &queue->input_pkt_queue); + __skb_unlink(skb, &sd->process_queue); kfree_skb(skb); + input_queue_head_incr(sd); } + } } static int napi_gro_complete(struct sk_buff *skb) @@ -2385,7 +3246,7 @@ out: return netif_receive_skb(skb); } -void napi_gro_flush(struct napi_struct *napi) +inline void napi_gro_flush(struct napi_struct *napi) { struct sk_buff *skb, *next; @@ -2400,7 +3261,7 @@ void napi_gro_flush(struct napi_struct *napi) } EXPORT_SYMBOL(napi_gro_flush); -int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; struct packet_type *ptype; @@ -2408,12 +3269,12 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; int same_flow; int mac_len; - int ret; + enum gro_result ret; - if (!(skb->dev->features & NETIF_F_GRO)) + if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb)) goto normal; - if (skb_is_gso(skb) || skb_has_frags(skb)) + if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; rcu_read_lock(); @@ -2479,7 +3340,7 @@ pull: put_page(skb_shinfo(skb)->frags[0].page); memmove(skb_shinfo(skb)->frags, skb_shinfo(skb)->frags + 1, - --skb_shinfo(skb)->nr_frags); + --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t)); } } @@ -2492,41 +3353,44 @@ normal: } EXPORT_SYMBOL(dev_gro_receive); -static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static inline gro_result_t +__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; - if (netpoll_rx_on(skb)) - return GRO_NORMAL; - for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev) - && !compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + unsigned long diffs; + + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); + NAPI_GRO_CB(p)->same_flow = !diffs; NAPI_GRO_CB(p)->flush = 0; } return dev_gro_receive(napi, skb); } -int napi_skb_finish(int ret, struct sk_buff *skb) +gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { - int err = NET_RX_SUCCESS; - switch (ret) { case GRO_NORMAL: - return netif_receive_skb(skb); + if (netif_receive_skb(skb)) + ret = GRO_DROP; + break; case GRO_DROP: - err = NET_RX_DROP; - /* fall through */ - case GRO_MERGED_FREE: kfree_skb(skb); break; + + case GRO_HELD: + case GRO_MERGED: + break; } - return err; + return ret; } EXPORT_SYMBOL(napi_skb_finish); @@ -2546,7 +3410,7 @@ void skb_gro_reset_offset(struct sk_buff *skb) } EXPORT_SYMBOL(skb_gro_reset_offset); -int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { skb_gro_reset_offset(skb); @@ -2554,60 +3418,52 @@ int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) } EXPORT_SYMBOL(napi_gro_receive); -void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) +static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { __skb_pull(skb, skb_headlen(skb)); skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb)); + skb->vlan_tci = 0; napi->skb = skb; } -EXPORT_SYMBOL(napi_reuse_skb); struct sk_buff *napi_get_frags(struct napi_struct *napi) { - struct net_device *dev = napi->dev; struct sk_buff *skb = napi->skb; if (!skb) { - skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN); - if (!skb) - goto out; - - skb_reserve(skb, NET_IP_ALIGN); - - napi->skb = skb; + skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); + if (skb) + napi->skb = skb; } - -out: return skb; } EXPORT_SYMBOL(napi_get_frags); -int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret) +gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, + gro_result_t ret) { - int err = NET_RX_SUCCESS; - switch (ret) { case GRO_NORMAL: case GRO_HELD: - skb->protocol = eth_type_trans(skb, napi->dev); - - if (ret == GRO_NORMAL) - return netif_receive_skb(skb); + skb->protocol = eth_type_trans(skb, skb->dev); - skb_gro_pull(skb, -ETH_HLEN); + if (ret == GRO_HELD) + skb_gro_pull(skb, -ETH_HLEN); + else if (netif_receive_skb(skb)) + ret = GRO_DROP; break; case GRO_DROP: - err = NET_RX_DROP; - /* fall through */ - case GRO_MERGED_FREE: napi_reuse_skb(napi, skb); break; + + case GRO_MERGED: + break; } - return err; + return ret; } EXPORT_SYMBOL(napi_frags_finish); @@ -2648,38 +3504,98 @@ out: } EXPORT_SYMBOL(napi_frags_skb); -int napi_gro_frags(struct napi_struct *napi) +gro_result_t napi_gro_frags(struct napi_struct *napi) { struct sk_buff *skb = napi_frags_skb(napi); if (!skb) - return NET_RX_DROP; + return GRO_DROP; return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb)); } EXPORT_SYMBOL(napi_gro_frags); +/* + * net_rps_action sends any pending IPI's for rps. + * Note: called with local irq disabled, but exits with local irq enabled. + */ +static void net_rps_action_and_irq_enable(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + struct softnet_data *remsd = sd->rps_ipi_list; + + if (remsd) { + sd->rps_ipi_list = NULL; + + local_irq_enable(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + while (remsd) { + struct softnet_data *next = remsd->rps_ipi_next; + + if (cpu_online(remsd->cpu)) + __smp_call_function_single(remsd->cpu, + &remsd->csd, 0); + remsd = next; + } + } else +#endif + local_irq_enable(); +} + static int process_backlog(struct napi_struct *napi, int quota) { int work = 0; - struct softnet_data *queue = &__get_cpu_var(softnet_data); - unsigned long start_time = jiffies; + struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); +#ifdef CONFIG_RPS + /* Check if we have pending ipi, its better to send them now, + * not waiting net_rx_action() end. + */ + if (sd->rps_ipi_list) { + local_irq_disable(); + net_rps_action_and_irq_enable(sd); + } +#endif napi->weight = weight_p; - do { + local_irq_disable(); + while (work < quota) { struct sk_buff *skb; + unsigned int qlen; - local_irq_disable(); - skb = __skb_dequeue(&queue->input_pkt_queue); - if (!skb) { - __napi_complete(napi); + while ((skb = __skb_dequeue(&sd->process_queue))) { local_irq_enable(); - break; + __netif_receive_skb(skb); + local_irq_disable(); + input_queue_head_incr(sd); + if (++work >= quota) { + local_irq_enable(); + return work; + } } - local_irq_enable(); - netif_receive_skb(skb); - } while (++work < quota && jiffies == start_time); + rps_lock(sd); + qlen = skb_queue_len(&sd->input_pkt_queue); + if (qlen) + skb_queue_splice_tail_init(&sd->input_pkt_queue, + &sd->process_queue); + + if (qlen < quota - work) { + /* + * Inline a custom version of __napi_complete(). + * only current cpu owns and manipulates this napi, + * and NAPI_STATE_SCHED is the only possible flag set on backlog. + * we can use a plain write instead of clear_bit(), + * and we dont need an smp_mb() memory barrier. + */ + list_del(&napi->poll_list); + napi->state = 0; + + quota = work + qlen; + } + rps_unlock(sd); + } + local_irq_enable(); return work; } @@ -2695,8 +3611,7 @@ void __napi_schedule(struct napi_struct *n) unsigned long flags; local_irq_save(flags); - list_add_tail(&n->poll_list, &__get_cpu_var(softnet_data).poll_list); - __raise_softirq_irqoff(NET_RX_SOFTIRQ); + ____napi_schedule(&__get_cpu_var(softnet_data), n); local_irq_restore(flags); } EXPORT_SYMBOL(__napi_schedule); @@ -2767,17 +3682,16 @@ void netif_napi_del(struct napi_struct *napi) } EXPORT_SYMBOL(netif_napi_del); - static void net_rx_action(struct softirq_action *h) { - struct list_head *list = &__get_cpu_var(softnet_data).poll_list; + struct softnet_data *sd = &__get_cpu_var(softnet_data); unsigned long time_limit = jiffies + 2; int budget = netdev_budget; void *have; local_irq_disable(); - while (!list_empty(list)) { + while (!list_empty(&sd->poll_list)) { struct napi_struct *n; int work, weight; @@ -2795,7 +3709,7 @@ static void net_rx_action(struct softirq_action *h) * entries to the tail of this list, and only ->poll() * calls can remove this head entry from the list. */ - n = list_entry(list->next, struct napi_struct, poll_list); + n = list_first_entry(&sd->poll_list, struct napi_struct, poll_list); have = netpoll_poll_lock(n); @@ -2825,16 +3739,18 @@ static void net_rx_action(struct softirq_action *h) * move the instance around on the list at-will. */ if (unlikely(work == weight)) { - if (unlikely(napi_disable_pending(n))) - __napi_complete(n); - else - list_move_tail(&n->poll_list, list); + if (unlikely(napi_disable_pending(n))) { + local_irq_enable(); + napi_complete(n); + local_irq_disable(); + } else + list_move_tail(&n->poll_list, &sd->poll_list); } netpoll_poll_unlock(have); } out: - local_irq_enable(); + net_rps_action_and_irq_enable(sd); #ifdef CONFIG_NET_DMA /* @@ -2847,12 +3763,12 @@ out: return; softnet_break: - __get_cpu_var(netdev_rx_stat).time_squeeze++; + sd->time_squeeze++; __raise_softirq_irqoff(NET_RX_SOFTIRQ); goto out; } -static gifconf_func_t * gifconf_list [NPROTO]; +static gifconf_func_t *gifconf_list[NPROTO]; /** * register_gifconf - register a SIOCGIF handler @@ -2863,13 +3779,14 @@ static gifconf_func_t * gifconf_list [NPROTO]; * that is passed must not be freed or reused until it has been replaced * by another handler. */ -int register_gifconf(unsigned int family, gifconf_func_t * gifconf) +int register_gifconf(unsigned int family, gifconf_func_t *gifconf) { if (family >= NPROTO) return -EINVAL; gifconf_list[family] = gifconf; return 0; } +EXPORT_SYMBOL(register_gifconf); /* @@ -2895,15 +3812,15 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifr.ifr_ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); if (!dev) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); return -ENODEV; } strcpy(ifr.ifr_name, dev->name); - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; @@ -2973,18 +3890,18 @@ static int dev_ifconf(struct net *net, char __user *arg) * in detail. */ void *dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; - read_lock(&dev_base_lock); + rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; - for_each_netdev(net, dev) + for_each_netdev_rcu(net, dev) if (off++ == *pos) return dev; @@ -2993,24 +3910,27 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos) void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net *net = seq_file_net(seq); + struct net_device *dev = (v == SEQ_START_TOKEN) ? + first_net_device(seq_file_net(seq)) : + next_net_device((struct net_device *)v); + ++*pos; - return v == SEQ_START_TOKEN ? - first_net_device(net) : next_net_device((struct net_device *)v); + return rcu_dereference(dev); } void dev_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { - const struct net_device_stats *stats = dev_get_stats(dev); + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); - seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " - "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", + seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " + "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, @@ -3045,17 +3965,17 @@ static int dev_seq_show(struct seq_file *seq, void *v) return 0; } -static struct netif_rx_stats *softnet_get_online(loff_t *pos) +static struct softnet_data *softnet_get_online(loff_t *pos) { - struct netif_rx_stats *rc = NULL; + struct softnet_data *sd = NULL; while (*pos < nr_cpu_ids) if (cpu_online(*pos)) { - rc = &per_cpu(netdev_rx_stat, *pos); + sd = &per_cpu(softnet_data, *pos); break; } else ++*pos; - return rc; + return sd; } static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) @@ -3075,12 +3995,12 @@ static void softnet_seq_stop(struct seq_file *seq, void *v) static int softnet_seq_show(struct seq_file *seq, void *v) { - struct netif_rx_stats *s = v; + struct softnet_data *sd = v; - seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", - s->total, s->dropped, s->time_squeeze, 0, + seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", + sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ - s->cpu_collision ); + sd->cpu_collision, sd->received_rps); return 0; } @@ -3303,11 +4223,10 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) slave->master = master; - synchronize_net(); - - if (old) + if (old) { + synchronize_net(); dev_put(old); - + } if (master) slave->flags |= IFF_SLAVE; else @@ -3316,6 +4235,7 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); return 0; } +EXPORT_SYMBOL(netdev_set_master); static void dev_change_rx_flags(struct net_device *dev, int flags) { @@ -3394,6 +4314,7 @@ int dev_set_promiscuity(struct net_device *dev, int inc) dev_set_rx_mode(dev); return err; } +EXPORT_SYMBOL(dev_set_promiscuity); /** * dev_set_allmulti - update allmulti count on a device @@ -3437,6 +4358,7 @@ int dev_set_allmulti(struct net_device *dev, int inc) } return 0; } +EXPORT_SYMBOL(dev_set_allmulti); /* * Upload unicast and multicast address lists to device and @@ -3461,10 +4383,10 @@ void __dev_set_rx_mode(struct net_device *dev) /* 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) { + if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1); dev->uc_promisc = 1; - } else if (dev->uc.count == 0 && dev->uc_promisc) { + } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1); dev->uc_promisc = 0; } @@ -3481,555 +4403,6 @@ void dev_set_rx_mode(struct net_device *dev) netif_addr_unlock_bh(dev); } -/* hw addresses list handling functions */ - -static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - int alloc_size; - - if (addr_len > MAX_ADDR_LEN) - return -EINVAL; - - list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - ha->type == addr_type) { - ha->refcount++; - return 0; - } - } - - - alloc_size = sizeof(*ha); - if (alloc_size < L1_CACHE_BYTES) - alloc_size = L1_CACHE_BYTES; - ha = kmalloc(alloc_size, GFP_ATOMIC); - if (!ha) - return -ENOMEM; - memcpy(ha->addr, addr, addr_len); - ha->type = addr_type; - ha->refcount = 1; - ha->synced = false; - list_add_tail_rcu(&ha->list, &list->list); - list->count++; - return 0; -} - -static void ha_rcu_free(struct rcu_head *head) -{ - struct netdev_hw_addr *ha; - - ha = container_of(head, struct netdev_hw_addr, rcu_head); - kfree(ha); -} - -static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - - list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - (ha->type == addr_type || !addr_type)) { - if (--ha->refcount) - return 0; - list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); - list->count--; - return 0; - } - } - return -ENOENT; -} - -static int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, - unsigned char addr_type) -{ - int err; - struct netdev_hw_addr *ha, *ha2; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - err = __hw_addr_add(to_list, ha->addr, addr_len, type); - if (err) - goto unroll; - } - return 0; - -unroll: - list_for_each_entry(ha2, &from_list->list, list) { - if (ha2 == ha) - break; - type = addr_type ? addr_type : ha2->type; - __hw_addr_del(to_list, ha2->addr, addr_len, type); - } - return err; -} - -static void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, - unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - __hw_addr_del(to_list, ha->addr, addr_len, addr_type); - } -} - -static int __hw_addr_sync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) -{ - int err = 0; - struct netdev_hw_addr *ha, *tmp; - - list_for_each_entry_safe(ha, tmp, &from_list->list, list) { - if (!ha->synced) { - err = __hw_addr_add(to_list, ha->addr, - addr_len, ha->type); - if (err) - break; - ha->synced = true; - ha->refcount++; - } else if (ha->refcount == 1) { - __hw_addr_del(to_list, ha->addr, addr_len, ha->type); - __hw_addr_del(from_list, ha->addr, addr_len, ha->type); - } - } - return err; -} - -static void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) -{ - struct netdev_hw_addr *ha, *tmp; - - list_for_each_entry_safe(ha, tmp, &from_list->list, list) { - if (ha->synced) { - __hw_addr_del(to_list, ha->addr, - addr_len, ha->type); - ha->synced = false; - __hw_addr_del(from_list, ha->addr, - addr_len, ha->type); - } - } -} - -static void __hw_addr_flush(struct netdev_hw_addr_list *list) -{ - struct netdev_hw_addr *ha, *tmp; - - list_for_each_entry_safe(ha, tmp, &list->list, list) { - list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); - } - list->count = 0; -} - -static void __hw_addr_init(struct netdev_hw_addr_list *list) -{ - INIT_LIST_HEAD(&list->list); - list->count = 0; -} - -/* Device addresses handling functions */ - -static void dev_addr_flush(struct net_device *dev) -{ - /* rtnl_mutex must be held here */ - - __hw_addr_flush(&dev->dev_addrs); - dev->dev_addr = NULL; -} - -static int dev_addr_init(struct net_device *dev) -{ - unsigned char addr[MAX_ADDR_LEN]; - struct netdev_hw_addr *ha; - int err; - - /* rtnl_mutex must be held here */ - - __hw_addr_init(&dev->dev_addrs); - memset(addr, 0, sizeof(addr)); - err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), - NETDEV_HW_ADDR_T_LAN); - if (!err) { - /* - * Get the first (previously created) address from the list - * and set dev_addr pointer to this location. - */ - ha = list_first_entry(&dev->dev_addrs.list, - struct netdev_hw_addr, list); - dev->dev_addr = ha->addr; - } - return err; -} - -/** - * dev_addr_add - Add a device address - * @dev: device - * @addr: address to add - * @addr_type: address type - * - * Add a device address to the device or increase the reference count if - * it already exists. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_add(struct net_device *dev, unsigned char *addr, - unsigned char addr_type) -{ - int err; - - ASSERT_RTNL(); - - err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; -} -EXPORT_SYMBOL(dev_addr_add); - -/** - * dev_addr_del - Release a device address. - * @dev: device - * @addr: address to delete - * @addr_type: address type - * - * Release reference to a device address and remove it from the device - * if the reference count drops to zero. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_del(struct net_device *dev, unsigned char *addr, - unsigned char addr_type) -{ - int err; - struct netdev_hw_addr *ha; - - ASSERT_RTNL(); - - /* - * We can not remove the first address from the list because - * dev->dev_addr points to that. - */ - ha = list_first_entry(&dev->dev_addrs.list, - struct netdev_hw_addr, list); - if (ha->addr == dev->dev_addr && ha->refcount == 1) - return -ENOENT; - - err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, - addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; -} -EXPORT_SYMBOL(dev_addr_del); - -/** - * dev_addr_add_multiple - Add device addresses from another device - * @to_dev: device to which addresses will be added - * @from_dev: device from which addresses will be added - * @addr_type: address type - 0 means type will be used from from_dev - * - * Add device addresses of the one device to another. - ** - * The caller must hold the rtnl_mutex. - */ -int dev_addr_add_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - int err; - - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return err; -} -EXPORT_SYMBOL(dev_addr_add_multiple); - -/** - * dev_addr_del_multiple - Delete device addresses by another device - * @to_dev: device where the addresses will be deleted - * @from_dev: device by which addresses the addresses will be deleted - * @addr_type: address type - 0 means type will used from from_dev - * - * Deletes addresses in to device by the list of addresses in from device. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_del_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return 0; -} -EXPORT_SYMBOL(dev_addr_del_multiple); - -/* multicast addresses handling functions */ - -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 = kzalloc(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 - * - * 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 err; - - ASSERT_RTNL(); - - err = __hw_addr_del(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST); - if (!err) - __dev_set_rx_mode(dev); - return err; -} -EXPORT_SYMBOL(dev_unicast_delete); - -/** - * dev_unicast_add - add a secondary unicast address - * @dev: device - * @addr: address to add - * - * 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 err; - - ASSERT_RTNL(); - - err = __hw_addr_add(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST); - if (!err) - __dev_set_rx_mode(dev); - return err; -} -EXPORT_SYMBOL(dev_unicast_add); - -int __dev_addr_sync(struct dev_addr_list **to, int *to_count, - struct dev_addr_list **from, int *from_count) -{ - struct dev_addr_list *da, *next; - int err = 0; - - da = *from; - while (da != NULL) { - next = da->next; - if (!da->da_synced) { - err = __dev_addr_add(to, to_count, - da->da_addr, da->da_addrlen, 0); - if (err < 0) - break; - da->da_synced = 1; - da->da_users++; - } else if (da->da_users == 1) { - __dev_addr_delete(to, to_count, - da->da_addr, da->da_addrlen, 0); - __dev_addr_delete(from, from_count, - da->da_addr, da->da_addrlen, 0); - } - da = next; - } - return err; -} - -void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, - struct dev_addr_list **from, int *from_count) -{ - struct dev_addr_list *da, *next; - - da = *from; - while (da != NULL) { - next = da->next; - if (da->da_synced) { - __dev_addr_delete(to, to_count, - da->da_addr, da->da_addrlen, 0); - da->da_synced = 0; - __dev_addr_delete(from, from_count, - da->da_addr, da->da_addrlen, 0); - } - da = next; - } -} - -/** - * dev_unicast_sync - Synchronize device's unicast list to another device - * @to: destination device - * @from: source device - * - * Add newly added addresses to the destination device and release - * addresses that have no users left. - * - * This function is intended to be called from the dev->set_rx_mode - * function of layered software devices. - */ -int dev_unicast_sync(struct net_device *to, struct net_device *from) -{ - int err = 0; - - ASSERT_RTNL(); - - if (to->addr_len != from->addr_len) - return -EINVAL; - - err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); - if (!err) - __dev_set_rx_mode(to); - return err; -} -EXPORT_SYMBOL(dev_unicast_sync); - -/** - * dev_unicast_unsync - Remove synchronized addresses from the destination device - * @to: destination device - * @from: source device - * - * Remove all addresses that were added to the destination device by - * dev_unicast_sync(). This function is intended to be called from the - * dev->stop function of layered software devices. - */ -void dev_unicast_unsync(struct net_device *to, struct net_device *from) -{ - ASSERT_RTNL(); - - if (to->addr_len != from->addr_len) - return; - - __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); - __dev_set_rx_mode(to); -} -EXPORT_SYMBOL(dev_unicast_unsync); - -static void dev_unicast_flush(struct net_device *dev) -{ - /* rtnl_mutex must be held here */ - - __hw_addr_flush(&dev->uc); -} - -static void dev_unicast_init(struct net_device *dev) -{ - /* rtnl_mutex must be held here */ - - __hw_addr_init(&dev->uc); -} - - -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_addr_lock_bh(dev); - - __dev_addr_discard(&dev->mc_list); - dev->mc_count = 0; - - netif_addr_unlock_bh(dev); -} - /** * dev_get_flags - get flags reported to userspace * @dev: device @@ -4059,19 +4432,12 @@ unsigned dev_get_flags(const struct net_device *dev) return flags; } +EXPORT_SYMBOL(dev_get_flags); -/** - * dev_change_flags - change device settings - * @dev: device - * @flags: device state flags - * - * Change settings on device based state flags. The flags are - * in the userspace exported format. - */ -int dev_change_flags(struct net_device *dev, unsigned flags) +int __dev_change_flags(struct net_device *dev, unsigned int flags) { - int ret, changes; int old_flags = dev->flags; + int ret; ASSERT_RTNL(); @@ -4102,19 +4468,15 @@ int dev_change_flags(struct net_device *dev, unsigned flags) ret = 0; if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */ - ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev); + ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev); if (!ret) dev_set_rx_mode(dev); } - if (dev->flags & IFF_UP && - ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI | - IFF_VOLATILE))) - call_netdevice_notifiers(NETDEV_CHANGE, dev); - if ((flags ^ dev->gflags) & IFF_PROMISC) { - int inc = (flags & IFF_PROMISC) ? +1 : -1; + int inc = (flags & IFF_PROMISC) ? 1 : -1; + dev->gflags ^= IFF_PROMISC; dev_set_promiscuity(dev, inc); } @@ -4124,18 +4486,56 @@ int dev_change_flags(struct net_device *dev, unsigned flags) IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { - int inc = (flags & IFF_ALLMULTI) ? +1 : -1; + int inc = (flags & IFF_ALLMULTI) ? 1 : -1; + dev->gflags ^= IFF_ALLMULTI; dev_set_allmulti(dev, inc); } - /* Exclude state transition flags, already notified */ - changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING); + return ret; +} + +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) +{ + unsigned int changes = dev->flags ^ old_flags; + + if (changes & IFF_UP) { + if (dev->flags & IFF_UP) + call_netdevice_notifiers(NETDEV_UP, dev); + else + call_netdevice_notifiers(NETDEV_DOWN, dev); + } + + if (dev->flags & IFF_UP && + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) + call_netdevice_notifiers(NETDEV_CHANGE, dev); +} + +/** + * dev_change_flags - change device settings + * @dev: device + * @flags: device state flags + * + * Change settings on device based state flags. The flags are + * in the userspace exported format. + */ +int dev_change_flags(struct net_device *dev, unsigned flags) +{ + int ret, changes; + int old_flags = dev->flags; + + ret = __dev_change_flags(dev, flags); + if (ret < 0) + return ret; + + changes = old_flags ^ dev->flags; if (changes) rtmsg_ifinfo(RTM_NEWLINK, dev, changes); + __dev_notify_flags(dev, old_flags); return ret; } +EXPORT_SYMBOL(dev_change_flags); /** * dev_set_mtu - Change maximum transfer unit @@ -4169,6 +4569,7 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); return err; } +EXPORT_SYMBOL(dev_set_mtu); /** * dev_set_mac_address - Change Media Access Control Address @@ -4193,69 +4594,70 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; } +EXPORT_SYMBOL(dev_set_mac_address); /* - * Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock) + * Perform the SIOCxIFxxx calls, inside rcu_read_lock() */ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) { int err; - struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); + struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); if (!dev) return -ENODEV; switch (cmd) { - case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = (short) dev_get_flags(dev); - return 0; + case SIOCGIFFLAGS: /* Get interface flags */ + ifr->ifr_flags = (short) dev_get_flags(dev); + return 0; - case SIOCGIFMETRIC: /* Get the metric on the interface - (currently unused) */ - ifr->ifr_metric = 0; - return 0; + case SIOCGIFMETRIC: /* Get the metric on the interface + (currently unused) */ + ifr->ifr_metric = 0; + return 0; - case SIOCGIFMTU: /* Get the MTU of a device */ - ifr->ifr_mtu = dev->mtu; - return 0; + case SIOCGIFMTU: /* Get the MTU of a device */ + ifr->ifr_mtu = dev->mtu; + return 0; - case SIOCGIFHWADDR: - if (!dev->addr_len) - memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); - else - memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - ifr->ifr_hwaddr.sa_family = dev->type; - return 0; + case SIOCGIFHWADDR: + if (!dev->addr_len) + memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data); + else + memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + ifr->ifr_hwaddr.sa_family = dev->type; + return 0; - case SIOCGIFSLAVE: - err = -EINVAL; - break; + case SIOCGIFSLAVE: + err = -EINVAL; + break; - case SIOCGIFMAP: - ifr->ifr_map.mem_start = dev->mem_start; - ifr->ifr_map.mem_end = dev->mem_end; - ifr->ifr_map.base_addr = dev->base_addr; - ifr->ifr_map.irq = dev->irq; - ifr->ifr_map.dma = dev->dma; - ifr->ifr_map.port = dev->if_port; - return 0; + case SIOCGIFMAP: + ifr->ifr_map.mem_start = dev->mem_start; + ifr->ifr_map.mem_end = dev->mem_end; + ifr->ifr_map.base_addr = dev->base_addr; + ifr->ifr_map.irq = dev->irq; + ifr->ifr_map.dma = dev->dma; + ifr->ifr_map.port = dev->if_port; + return 0; - case SIOCGIFINDEX: - ifr->ifr_ifindex = dev->ifindex; - return 0; + case SIOCGIFINDEX: + ifr->ifr_ifindex = dev->ifindex; + return 0; - case SIOCGIFTXQLEN: - ifr->ifr_qlen = dev->tx_queue_len; - return 0; + case SIOCGIFTXQLEN: + ifr->ifr_qlen = dev->tx_queue_len; + return 0; - default: - /* dev_ioctl() should ensure this case - * is never reached - */ - WARN_ON(1); - err = -EINVAL; - break; + default: + /* dev_ioctl() should ensure this case + * is never reached + */ + WARN_ON(1); + err = -EINVAL; + break; } return err; @@ -4276,92 +4678,89 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) ops = dev->netdev_ops; switch (cmd) { - case SIOCSIFFLAGS: /* Set interface flags */ - return dev_change_flags(dev, ifr->ifr_flags); - - case SIOCSIFMETRIC: /* Set the metric on the interface - (currently unused) */ - return -EOPNOTSUPP; + case SIOCSIFFLAGS: /* Set interface flags */ + return dev_change_flags(dev, ifr->ifr_flags); - case SIOCSIFMTU: /* Set the MTU of a device */ - return dev_set_mtu(dev, ifr->ifr_mtu); + case SIOCSIFMETRIC: /* Set the metric on the interface + (currently unused) */ + return -EOPNOTSUPP; - case SIOCSIFHWADDR: - return dev_set_mac_address(dev, &ifr->ifr_hwaddr); + case SIOCSIFMTU: /* Set the MTU of a device */ + return dev_set_mtu(dev, ifr->ifr_mtu); - case SIOCSIFHWBROADCAST: - if (ifr->ifr_hwaddr.sa_family != dev->type) - return -EINVAL; - memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return 0; + case SIOCSIFHWADDR: + return dev_set_mac_address(dev, &ifr->ifr_hwaddr); - case SIOCSIFMAP: - if (ops->ndo_set_config) { - if (!netif_device_present(dev)) - return -ENODEV; - return ops->ndo_set_config(dev, &ifr->ifr_map); - } - return -EOPNOTSUPP; + case SIOCSIFHWBROADCAST: + if (ifr->ifr_hwaddr.sa_family != dev->type) + return -EINVAL; + memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, + min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len)); + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return 0; - case SIOCADDMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; + case SIOCSIFMAP: + if (ops->ndo_set_config) { if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + return ops->ndo_set_config(dev, &ifr->ifr_map); + } + return -EOPNOTSUPP; - case SIOCDELMULTI: - if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || - ifr->ifr_hwaddr.sa_family != AF_UNSPEC) - return -EINVAL; - if (!netif_device_present(dev)) - return -ENODEV; - return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + case SIOCADDMULTI: + if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); - case SIOCSIFTXQLEN: - if (ifr->ifr_qlen < 0) - return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; - return 0; + case SIOCDELMULTI: + if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || + ifr->ifr_hwaddr.sa_family != AF_UNSPEC) + return -EINVAL; + if (!netif_device_present(dev)) + return -ENODEV; + return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); - case SIOCSIFNAME: - ifr->ifr_newname[IFNAMSIZ-1] = '\0'; - return dev_change_name(dev, ifr->ifr_newname); + case SIOCSIFTXQLEN: + if (ifr->ifr_qlen < 0) + return -EINVAL; + dev->tx_queue_len = ifr->ifr_qlen; + return 0; - /* - * Unknown or private ioctl - */ + case SIOCSIFNAME: + ifr->ifr_newname[IFNAMSIZ-1] = '\0'; + return dev_change_name(dev, ifr->ifr_newname); - default: - if ((cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15) || - cmd == SIOCBONDENSLAVE || - cmd == SIOCBONDRELEASE || - cmd == SIOCBONDSETHWADDR || - cmd == SIOCBONDSLAVEINFOQUERY || - cmd == SIOCBONDINFOQUERY || - cmd == SIOCBONDCHANGEACTIVE || - cmd == SIOCGMIIPHY || - cmd == SIOCGMIIREG || - cmd == SIOCSMIIREG || - cmd == SIOCBRADDIF || - cmd == SIOCBRDELIF || - cmd == SIOCSHWTSTAMP || - cmd == SIOCWANDEV) { - err = -EOPNOTSUPP; - if (ops->ndo_do_ioctl) { - if (netif_device_present(dev)) - err = ops->ndo_do_ioctl(dev, ifr, cmd); - else - err = -ENODEV; - } - } else - err = -EINVAL; + /* + * Unknown or private ioctl + */ + default: + if ((cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15) || + cmd == SIOCBONDENSLAVE || + cmd == SIOCBONDRELEASE || + cmd == SIOCBONDSETHWADDR || + cmd == SIOCBONDSLAVEINFOQUERY || + cmd == SIOCBONDINFOQUERY || + cmd == SIOCBONDCHANGEACTIVE || + cmd == SIOCGMIIPHY || + cmd == SIOCGMIIREG || + cmd == SIOCSMIIREG || + cmd == SIOCBRADDIF || + cmd == SIOCBRDELIF || + cmd == SIOCSHWTSTAMP || + cmd == SIOCWANDEV) { + err = -EOPNOTSUPP; + if (ops->ndo_do_ioctl) { + if (netif_device_present(dev)) + err = ops->ndo_do_ioctl(dev, ifr, cmd); + else + err = -ENODEV; + } + } else + err = -EINVAL; } return err; @@ -4418,135 +4817,135 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) */ switch (cmd) { - /* - * These ioctl calls: - * - can be done by all. - * - atomic and do not require locking. - * - return a value - */ - case SIOCGIFFLAGS: - case SIOCGIFMETRIC: - case SIOCGIFMTU: - case SIOCGIFHWADDR: - case SIOCGIFSLAVE: - case SIOCGIFMAP: - case SIOCGIFINDEX: - case SIOCGIFTXQLEN: - dev_load(net, ifr.ifr_name); - read_lock(&dev_base_lock); - ret = dev_ifsioc_locked(net, &ifr, cmd); - read_unlock(&dev_base_lock); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + /* + * These ioctl calls: + * - can be done by all. + * - atomic and do not require locking. + * - return a value + */ + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFHWADDR: + case SIOCGIFSLAVE: + case SIOCGIFMAP: + case SIOCGIFINDEX: + case SIOCGIFTXQLEN: + dev_load(net, ifr.ifr_name); + rcu_read_lock(); + ret = dev_ifsioc_locked(net, &ifr, cmd); + rcu_read_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; - case SIOCETHTOOL: - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ethtool(net, &ifr); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + case SIOCETHTOOL: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ethtool(net, &ifr); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - return a value - */ - case SIOCGMIIPHY: - case SIOCGMIIREG: - case SIOCSIFNAME: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret) { - if (colon) - *colon = ':'; - if (copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - } - return ret; + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - return a value + */ + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCSIFNAME: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + if (!ret) { + if (colon) + *colon = ':'; + if (copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; + } + return ret; - /* - * These ioctl calls: - * - require superuser power. - * - require strict serialization. - * - do not return a value - */ - case SIOCSIFFLAGS: - case SIOCSIFMETRIC: - case SIOCSIFMTU: - case SIOCSIFMAP: - case SIOCSIFHWADDR: - case SIOCSIFSLAVE: - case SIOCADDMULTI: - case SIOCDELMULTI: - case SIOCSIFHWBROADCAST: - case SIOCSIFTXQLEN: - case SIOCSMIIREG: - case SIOCBONDENSLAVE: - case SIOCBONDRELEASE: - case SIOCBONDSETHWADDR: - case SIOCBONDCHANGEACTIVE: - case SIOCBRADDIF: - case SIOCBRDELIF: - case SIOCSHWTSTAMP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - /* fall through */ - case SIOCBONDSLAVEINFOQUERY: - case SIOCBONDINFOQUERY: + /* + * These ioctl calls: + * - require superuser power. + * - require strict serialization. + * - do not return a value + */ + case SIOCSIFFLAGS: + case SIOCSIFMETRIC: + case SIOCSIFMTU: + case SIOCSIFMAP: + case SIOCSIFHWADDR: + case SIOCSIFSLAVE: + case SIOCADDMULTI: + case SIOCDELMULTI: + case SIOCSIFHWBROADCAST: + case SIOCSIFTXQLEN: + case SIOCSMIIREG: + case SIOCBONDENSLAVE: + case SIOCBONDRELEASE: + case SIOCBONDSETHWADDR: + case SIOCBONDCHANGEACTIVE: + case SIOCBRADDIF: + case SIOCBRDELIF: + case SIOCSHWTSTAMP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* fall through */ + case SIOCBONDSLAVEINFOQUERY: + case SIOCBONDINFOQUERY: + dev_load(net, ifr.ifr_name); + rtnl_lock(); + ret = dev_ifsioc(net, &ifr, cmd); + rtnl_unlock(); + return ret; + + case SIOCGIFMEM: + /* Get the per device memory space. We can add this but + * currently do not support it */ + case SIOCSIFMEM: + /* Set the per device memory buffer space. + * Not applicable in our case */ + case SIOCSIFLINK: + return -EINVAL; + + /* + * Unknown or private ioctl. + */ + default: + if (cmd == SIOCWANDEV || + (cmd >= SIOCDEVPRIVATE && + cmd <= SIOCDEVPRIVATE + 15)) { dev_load(net, ifr.ifr_name); rtnl_lock(); ret = dev_ifsioc(net, &ifr, cmd); rtnl_unlock(); + if (!ret && copy_to_user(arg, &ifr, + sizeof(struct ifreq))) + ret = -EFAULT; return ret; - - case SIOCGIFMEM: - /* Get the per device memory space. We can add this but - * currently do not support it */ - case SIOCSIFMEM: - /* Set the per device memory buffer space. - * Not applicable in our case */ - case SIOCSIFLINK: - return -EINVAL; - - /* - * Unknown or private ioctl. - */ - default: - if (cmd == SIOCWANDEV || - (cmd >= SIOCDEVPRIVATE && - cmd <= SIOCDEVPRIVATE + 15)) { - dev_load(net, ifr.ifr_name); - rtnl_lock(); - ret = dev_ifsioc(net, &ifr, cmd); - rtnl_unlock(); - if (!ret && copy_to_user(arg, &ifr, - sizeof(struct ifreq))) - ret = -EFAULT; - return ret; - } - /* Take care of Wireless Extensions */ - if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) - return wext_handle_ioctl(net, &ifr, cmd, arg); - return -EINVAL; + } + /* Take care of Wireless Extensions */ + if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) + return wext_handle_ioctl(net, &ifr, cmd, arg); + return -EINVAL; } } @@ -4578,74 +4977,88 @@ static void net_set_todo(struct net_device *dev) list_add_tail(&dev->todo_list, &net_todo_list); } -static void rollback_registered(struct net_device *dev) +static void rollback_registered_many(struct list_head *head) { + struct net_device *dev, *tmp; + BUG_ON(dev_boot_phase); ASSERT_RTNL(); - /* Some devices call without registering for initialization unwind. */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - printk(KERN_DEBUG "unregister_netdevice: device %s/%p never " - "was registered\n", dev->name, dev); + list_for_each_entry_safe(dev, tmp, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. Remove those + * devices and proceed with the remaining. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never " + "was registered\n", dev->name, dev); - WARN_ON(1); - return; - } + WARN_ON(1); + list_del(&dev->unreg_list); + continue; + } - BUG_ON(dev->reg_state != NETREG_REGISTERED); + BUG_ON(dev->reg_state != NETREG_REGISTERED); + } /* If device is running, close it first. */ - dev_close(dev); + dev_close_many(head); - /* And unlink it from device chain. */ - unlist_netdevice(dev); + list_for_each_entry(dev, head, unreg_list) { + /* And unlink it from device chain. */ + unlist_netdevice(dev); - dev->reg_state = NETREG_UNREGISTERING; + dev->reg_state = NETREG_UNREGISTERING; + } synchronize_net(); - /* Shutdown queueing discipline. */ - dev_shutdown(dev); + list_for_each_entry(dev, head, unreg_list) { + /* Shutdown queueing discipline. */ + dev_shutdown(dev); - /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + /* Notify protocols, that we are about to destroy + this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* - * Flush the unicast and multicast chains - */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); - if (dev->netdev_ops->ndo_uninit) - dev->netdev_ops->ndo_uninit(dev); + /* + * Flush the unicast and multicast chains + */ + dev_uc_flush(dev); + dev_mc_flush(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); - /* Remove entries from kobject tree */ - netdev_unregister_kobject(dev); + /* Notifier chain MUST detach us from master device. */ + WARN_ON(dev->master); - synchronize_net(); + /* Remove entries from kobject tree */ + netdev_unregister_kobject(dev); + } - dev_put(dev); -} + /* Process any work delayed until the end of the batch */ + dev = list_first_entry(head, struct net_device, unreg_list); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); -static void __netdev_init_queue_locks_one(struct net_device *dev, - struct netdev_queue *dev_queue, - void *_unused) -{ - spin_lock_init(&dev_queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type); - dev_queue->xmit_lock_owner = -1; + rcu_barrier(); + + list_for_each_entry(dev, head, unreg_list) + dev_put(dev); } -static void netdev_init_queue_locks(struct net_device *dev) +static void rollback_registered(struct net_device *dev) { - netdev_for_each_tx_queue(dev, __netdev_init_queue_locks_one, NULL); - __netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL); + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + rollback_registered_many(&single); } unsigned long netdev_fix_features(unsigned long features, const char *name) @@ -4668,10 +5081,13 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } if (features & NETIF_F_UFO) { - if (!(features & NETIF_F_GEN_CSUM)) { + /* maybe split UFO into V4 and V6? */ + if (!((features & NETIF_F_GEN_CSUM) || + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) + == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { if (name) printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_HW_CSUM feature.\n", + "since no checksum offload features.\n", name); features &= ~NETIF_F_UFO; } @@ -4689,6 +5105,86 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) EXPORT_SYMBOL(netdev_fix_features); /** + * netif_stacked_transfer_operstate - transfer operstate + * @rootdev: the root or lower level device to transfer state from + * @dev: the device to transfer operstate to + * + * Transfer operational state from root to device. This is normally + * called when a stacking relationship exists between the root + * device and the device(a leaf device). + */ +void netif_stacked_transfer_operstate(const struct net_device *rootdev, + struct net_device *dev) +{ + if (rootdev->operstate == IF_OPER_DORMANT) + netif_dormant_on(dev); + else + netif_dormant_off(dev); + + if (netif_carrier_ok(rootdev)) { + if (!netif_carrier_ok(dev)) + netif_carrier_on(dev); + } else { + if (netif_carrier_ok(dev)) + netif_carrier_off(dev); + } +} +EXPORT_SYMBOL(netif_stacked_transfer_operstate); + +#ifdef CONFIG_RPS +static int netif_alloc_rx_queues(struct net_device *dev) +{ + unsigned int i, count = dev->num_rx_queues; + struct netdev_rx_queue *rx; + + BUG_ON(count < 1); + + rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); + if (!rx) { + pr_err("netdev: Unable to allocate %u rx queues.\n", count); + return -ENOMEM; + } + dev->_rx = rx; + + for (i = 0; i < count; i++) + rx[i].dev = dev; + return 0; +} +#endif + +static void netdev_init_one_queue(struct net_device *dev, + struct netdev_queue *queue, void *_unused) +{ + /* Initialize queue lock */ + spin_lock_init(&queue->_xmit_lock); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + queue->xmit_lock_owner = -1; + netdev_queue_numa_node_write(queue, NUMA_NO_NODE); + queue->dev = dev; +} + +static int netif_alloc_netdev_queues(struct net_device *dev) +{ + unsigned int count = dev->num_tx_queues; + struct netdev_queue *tx; + + BUG_ON(count < 1); + + tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); + if (!tx) { + pr_err("netdev: Unable to allocate %u tx queues.\n", + count); + return -ENOMEM; + } + dev->_tx = tx; + + netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); + spin_lock_init(&dev->tx_global_lock); + + return 0; +} + +/** * register_netdevice - register a network device * @dev: device to register * @@ -4707,8 +5203,6 @@ EXPORT_SYMBOL(netdev_fix_features); int register_netdevice(struct net_device *dev) { - struct hlist_head *head; - struct hlist_node *p; int ret; struct net *net = dev_net(dev); @@ -4723,7 +5217,6 @@ int register_netdevice(struct net_device *dev) spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); - netdev_init_queue_locks(dev); dev->iflink = -1; @@ -4737,26 +5230,14 @@ int register_netdevice(struct net_device *dev) } } - if (!dev_valid_name(dev->name)) { - ret = -EINVAL; + ret = dev_get_valid_name(dev, dev->name, 0); + if (ret) goto err_uninit; - } dev->ifindex = dev_new_index(net); if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Check for existence of name */ - head = dev_name_hash(net, dev->name); - hlist_for_each(p, head) { - struct net_device *d - = hlist_entry(p, struct net_device, name_hlist); - if (!strncmp(d->name, dev->name, IFNAMSIZ)) { - ret = -EEXIST; - goto err_uninit; - } - } - /* Fix illegal checksum combinations */ if ((dev->features & NETIF_F_HW_CSUM) && (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { @@ -4778,7 +5259,17 @@ int register_netdevice(struct net_device *dev) if (dev->features & NETIF_F_SG) dev->features |= NETIF_F_GSO; - netdev_initialize_kobject(dev); + /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, + * vlan_dev_init() will do the dev->features check, so these features + * are enabled only if supported by underlying device. + */ + dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA); + + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); + ret = notifier_to_errno(ret); + if (ret) + goto err_uninit; + ret = netdev_register_kobject(dev); if (ret) goto err_uninit; @@ -4802,6 +5293,13 @@ int register_netdevice(struct net_device *dev) rollback_registered(dev); dev->reg_state = NETREG_UNREGISTERED; } + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); out: return ret; @@ -4811,6 +5309,7 @@ err_uninit: dev->netdev_ops->ndo_uninit(dev); goto out; } +EXPORT_SYMBOL(register_netdevice); /** * init_dummy_netdev - init a dummy network device for NAPI @@ -4836,9 +5335,6 @@ int init_dummy_netdev(struct net_device *dev) */ dev->reg_state = NETREG_DUMMY; - /* initialize the ref count */ - atomic_set(&dev->refcnt, 1); - /* NAPI wants this */ INIT_LIST_HEAD(&dev->napi_list); @@ -4846,6 +5342,11 @@ int init_dummy_netdev(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); + /* Note : We dont allocate pcpu_refcnt for dummy devices, + * because users of this 'device' dont need to change + * its refcount. + */ + return 0; } EXPORT_SYMBOL_GPL(init_dummy_netdev); @@ -4887,6 +5388,16 @@ out: } EXPORT_SYMBOL(register_netdev); +int netdev_refcnt_read(const struct net_device *dev) +{ + int i, refcnt = 0; + + for_each_possible_cpu(i) + refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); + return refcnt; +} +EXPORT_SYMBOL(netdev_refcnt_read); + /* * netdev_wait_allrefs - wait until all references are gone. * @@ -4901,14 +5412,21 @@ EXPORT_SYMBOL(register_netdev); static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; + int refcnt; + + linkwatch_forget_dev(dev); rebroadcast_time = warning_time = jiffies; - while (atomic_read(&dev->refcnt) != 0) { + refcnt = netdev_refcnt_read(dev); + + while (refcnt != 0) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users + * should have already handle it the first time */ if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { @@ -4928,11 +5446,13 @@ static void netdev_wait_allrefs(struct net_device *dev) msleep(250); + refcnt = netdev_refcnt_read(dev); + if (time_after(jiffies, warning_time + 10 * HZ)) { printk(KERN_EMERG "unregister_netdevice: " "waiting for %s to become free. Usage " "count = %d\n", - dev->name, atomic_read(&dev->refcnt)); + dev->name, refcnt); warning_time = jiffies; } } @@ -4973,7 +5493,7 @@ void netdev_run_todo(void) while (!list_empty(&list)) { struct net_device *dev - = list_entry(list.next, struct net_device, todo_list); + = list_first_entry(&list, struct net_device, todo_list); list_del(&dev->todo_list); if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { @@ -4990,9 +5510,9 @@ void netdev_run_todo(void) netdev_wait_allrefs(dev); /* paranoia */ - BUG_ON(atomic_read(&dev->refcnt)); - WARN_ON(dev->ip_ptr); - WARN_ON(dev->ip6_ptr); + BUG_ON(netdev_refcnt_read(dev)); + WARN_ON(rcu_dereference_raw(dev->ip_ptr)); + WARN_ON(rcu_dereference_raw(dev->ip6_ptr)); WARN_ON(dev->dn_ptr); if (dev->destructor) @@ -5004,76 +5524,137 @@ void netdev_run_todo(void) } /** + * dev_txq_stats_fold - fold tx_queues stats + * @dev: device to get statistics from + * @stats: struct rtnl_link_stats64 to hold results + */ +void dev_txq_stats_fold(const struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + u64 tx_bytes = 0, tx_packets = 0, tx_dropped = 0; + unsigned int i; + struct netdev_queue *txq; + + for (i = 0; i < dev->num_tx_queues; i++) { + txq = netdev_get_tx_queue(dev, i); + spin_lock_bh(&txq->_xmit_lock); + tx_bytes += txq->tx_bytes; + tx_packets += txq->tx_packets; + tx_dropped += txq->tx_dropped; + spin_unlock_bh(&txq->_xmit_lock); + } + if (tx_bytes || tx_packets || tx_dropped) { + stats->tx_bytes = tx_bytes; + stats->tx_packets = tx_packets; + stats->tx_dropped = tx_dropped; + } +} +EXPORT_SYMBOL(dev_txq_stats_fold); + +/* Convert net_device_stats to rtnl_link_stats64. They have the same + * fields in the same order, with only the type differing. + */ +static void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, + const struct net_device_stats *netdev_stats) +{ +#if BITS_PER_LONG == 64 + BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats)); + memcpy(stats64, netdev_stats, sizeof(*stats64)); +#else + size_t i, n = sizeof(*stats64) / sizeof(u64); + const unsigned long *src = (const unsigned long *)netdev_stats; + u64 *dst = (u64 *)stats64; + + BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) != + sizeof(*stats64) / sizeof(u64)); + for (i = 0; i < n; i++) + dst[i] = src[i]; +#endif +} + +/** * dev_get_stats - get network device statistics * @dev: device to get statistics from + * @storage: place to store stats * - * Get network statistics from device. The device driver may provide - * its own method by setting dev->netdev_ops->get_stats; otherwise - * the internal statistics structure is used. + * Get network statistics from device. Return @storage. + * The device driver may provide its own method by setting + * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; + * otherwise the internal statistics structure is used. */ -const struct net_device_stats *dev_get_stats(struct net_device *dev) +struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_get_stats) - return ops->ndo_get_stats(dev); - else { - unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0; - struct net_device_stats *stats = &dev->stats; - unsigned int i; - struct netdev_queue *txq; - - for (i = 0; i < dev->num_tx_queues; i++) { - txq = netdev_get_tx_queue(dev, i); - tx_bytes += txq->tx_bytes; - tx_packets += txq->tx_packets; - tx_dropped += txq->tx_dropped; - } - if (tx_bytes || tx_packets || tx_dropped) { - stats->tx_bytes = tx_bytes; - stats->tx_packets = tx_packets; - stats->tx_dropped = tx_dropped; - } - return stats; + if (ops->ndo_get_stats64) { + memset(storage, 0, sizeof(*storage)); + ops->ndo_get_stats64(dev, storage); + } else if (ops->ndo_get_stats) { + netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); + } else { + netdev_stats_to_stats64(storage, &dev->stats); + dev_txq_stats_fold(dev, storage); } + storage->rx_dropped += atomic_long_read(&dev->rx_dropped); + return storage; } EXPORT_SYMBOL(dev_get_stats); -static void netdev_init_one_queue(struct net_device *dev, - struct netdev_queue *queue, - void *_unused) +struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { - queue->dev = dev; -} + struct netdev_queue *queue = dev_ingress_queue(dev); -static void netdev_init_queues(struct net_device *dev) -{ - netdev_init_one_queue(dev, &dev->rx_queue, NULL); - netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); - spin_lock_init(&dev->tx_global_lock); +#ifdef CONFIG_NET_CLS_ACT + if (queue) + return queue; + queue = kzalloc(sizeof(*queue), GFP_KERNEL); + if (!queue) + return NULL; + netdev_init_one_queue(dev, queue, NULL); + queue->qdisc = &noop_qdisc; + queue->qdisc_sleeping = &noop_qdisc; + rcu_assign_pointer(dev->ingress_queue, queue); +#endif + return queue; } /** - * alloc_netdev_mq - allocate network device + * alloc_netdev_mqs - 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 + * @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 subquue structs - * for each queue on the device at the end of the netdevice. + * for each queue on the device. */ -struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, - void (*setup)(struct net_device *), unsigned int queue_count) +struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + void (*setup)(struct net_device *), + unsigned int txqs, unsigned int rxqs) { - struct netdev_queue *tx; struct net_device *dev; size_t alloc_size; struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); + if (txqs < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero queues.\n"); + return NULL; + } + +#ifdef CONFIG_RPS + if (rxqs < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero RX queues.\n"); + return NULL; + } +#endif + alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ @@ -5089,45 +5670,57 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, return NULL; } - tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL); - if (!tx) { - printk(KERN_ERR "alloc_netdev: Unable to allocate " - "tx qdiscs.\n"); - goto free_p; - } - dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; + dev->pcpu_refcnt = alloc_percpu(int); + if (!dev->pcpu_refcnt) + goto free_p; + if (dev_addr_init(dev)) - goto free_tx; + goto free_pcpu; - dev_unicast_init(dev); + dev_mc_init(dev); + dev_uc_init(dev); dev_net_set(dev, &init_net); - dev->_tx = tx; - dev->num_tx_queues = queue_count; - dev->real_num_tx_queues = queue_count; + dev->num_tx_queues = txqs; + dev->real_num_tx_queues = txqs; + if (netif_alloc_netdev_queues(dev)) + goto free_pcpu; - dev->gso_max_size = GSO_MAX_SIZE; +#ifdef CONFIG_RPS + dev->num_rx_queues = rxqs; + dev->real_num_rx_queues = rxqs; + if (netif_alloc_rx_queues(dev)) + goto free_pcpu; +#endif - netdev_init_queues(dev); + dev->gso_max_size = GSO_MAX_SIZE; + INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); + dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); + INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->link_watch_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); strcpy(dev->name, name); return dev; -free_tx: - kfree(tx); +free_pcpu: + free_percpu(dev->pcpu_refcnt); + kfree(dev->_tx); +#ifdef CONFIG_RPS + kfree(dev->_rx); +#endif free_p: kfree(p); return NULL; } -EXPORT_SYMBOL(alloc_netdev_mq); +EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device @@ -5144,13 +5737,24 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); kfree(dev->_tx); +#ifdef CONFIG_RPS + kfree(dev->_rx); +#endif + + kfree(rcu_dereference_raw(dev->ingress_queue)); /* Flush device addresses */ dev_addr_flush(dev); + /* Clear ethtool n-tuple list */ + ethtool_ntuple_flush(dev); + list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); + free_percpu(dev->pcpu_refcnt); + dev->pcpu_refcnt = NULL; + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { kfree((char *)dev - dev->padded); @@ -5163,6 +5767,7 @@ void free_netdev(struct net_device *dev) /* will free via device release */ put_device(&dev->dev); } +EXPORT_SYMBOL(free_netdev); /** * synchronize_net - Synchronize with packet receive processing @@ -5175,26 +5780,50 @@ void synchronize_net(void) might_sleep(); synchronize_rcu(); } +EXPORT_SYMBOL(synchronize_net); /** - * unregister_netdevice - remove device from the kernel + * unregister_netdevice_queue - remove device from the kernel * @dev: device + * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. + * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ -void unregister_netdevice(struct net_device *dev) +void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); - rollback_registered(dev); - /* Finish processing unregister after unlock */ - net_set_todo(dev); + if (head) { + list_move_tail(&dev->unreg_list, head); + } else { + rollback_registered(dev); + /* Finish processing unregister after unlock */ + net_set_todo(dev); + } +} +EXPORT_SYMBOL(unregister_netdevice_queue); + +/** + * unregister_netdevice_many - unregister many devices + * @head: list of devices + */ +void unregister_netdevice_many(struct list_head *head) +{ + struct net_device *dev; + + if (!list_empty(head)) { + rollback_registered_many(head); + list_for_each_entry(dev, head, unreg_list) + net_set_todo(dev); + } } +EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel @@ -5213,7 +5842,6 @@ void unregister_netdev(struct net_device *dev) unregister_netdevice(dev); rtnl_unlock(); } - EXPORT_SYMBOL(unregister_netdev); /** @@ -5232,8 +5860,6 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - char buf[IFNAMSIZ]; - const char *destname; int err; ASSERT_RTNL(); @@ -5243,15 +5869,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char if (dev->features & NETIF_F_NETNS_LOCAL) goto out; -#ifdef CONFIG_SYSFS - /* Don't allow real devices to be moved when sysfs - * is enabled. - */ - err = -EINVAL; - if (dev->dev.parent) - goto out; -#endif - /* Ensure the device has been registrered */ err = -EINVAL; if (dev->reg_state != NETREG_REGISTERED) @@ -5266,20 +5883,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char * we can use it in the destination network namespace. */ err = -EEXIST; - destname = dev->name; - if (__dev_get_by_name(net, destname)) { + if (__dev_get_by_name(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; - if (!dev_valid_name(pat)) - goto out; - if (strchr(pat, '%')) { - if (__dev_alloc_name(net, pat, buf) < 0) - goto out; - destname = buf; - } else - destname = pat; - if (__dev_get_by_name(net, destname)) + if (dev_get_valid_name(dev, pat, 1)) goto out; } @@ -5301,24 +5909,23 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* 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. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); /* * Flush the unicast and multicast chains */ - dev_unicast_flush(dev); - dev_addr_discard(dev); - - netdev_unregister_kobject(dev); + dev_uc_flush(dev); + dev_mc_flush(dev); /* Actually switch the network namespace */ dev_net_set(dev, net); - /* Assign the new device name */ - if (destname != dev->name) - strcpy(dev->name, destname); - /* If there is an ifindex conflict assign a new one */ if (__dev_get_by_index(net, dev->ifindex)) { int iflink = (dev->iflink == dev->ifindex); @@ -5328,7 +5935,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char } /* Fixup kobjects */ - err = netdev_register_kobject(dev); + err = device_rename(&dev->dev, dev->name); WARN_ON(err); /* Add the device back in the hashes */ @@ -5337,18 +5944,24 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); + /* + * Prevent userspace races by waiting until the network + * device is fully setup before sending notifications. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + synchronize_net(); err = 0; out: return err; } +EXPORT_SYMBOL_GPL(dev_change_net_namespace); static int dev_cpu_callback(struct notifier_block *nfb, unsigned long action, void *ocpu) { struct sk_buff **list_skb; - struct Qdisc **list_net; struct sk_buff *skb; unsigned int cpu, oldcpu = (unsigned long)ocpu; struct softnet_data *sd, *oldsd; @@ -5369,20 +5982,26 @@ static int dev_cpu_callback(struct notifier_block *nfb, *list_skb = oldsd->completion_queue; oldsd->completion_queue = NULL; - /* Find end of our output_queue. */ - list_net = &sd->output_queue; - while (*list_net) - list_net = &(*list_net)->next_sched; /* Append output queue from offline CPU. */ - *list_net = oldsd->output_queue; - oldsd->output_queue = NULL; + if (oldsd->output_queue) { + *sd->output_queue_tailp = oldsd->output_queue; + sd->output_queue_tailp = oldsd->output_queue_tailp; + oldsd->output_queue = NULL; + oldsd->output_queue_tailp = &oldsd->output_queue; + } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) + while ((skb = __skb_dequeue(&oldsd->process_queue))) { + netif_rx(skb); + input_queue_head_incr(oldsd); + } + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); + input_queue_head_incr(oldsd); + } return NOTIFY_OK; } @@ -5402,7 +6021,7 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one, unsigned long mask) { /* If device needs checksumming, downgrade to it. */ - if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) + if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM); else if (mask & NETIF_F_ALL_CSUM) { /* If one device supports v4/v6 checksumming, set for all. */ @@ -5422,7 +6041,7 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one, one |= NETIF_F_ALL_CSUM; one |= all & NETIF_F_ONE_FOR_ALL; - all &= one | NETIF_F_LLTX | NETIF_F_GSO; + all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO; all |= one & mask & NETIF_F_ONE_FOR_ALL; return all; @@ -5491,6 +6110,68 @@ char *netdev_drivername(const struct net_device *dev, char *buffer, int len) return buffer; } +static int __netdev_printk(const char *level, const struct net_device *dev, + struct va_format *vaf) +{ + int r; + + if (dev && dev->dev.parent) + r = dev_printk(level, dev->dev.parent, "%s: %pV", + netdev_name(dev), vaf); + else if (dev) + r = printk("%s%s: %pV", level, netdev_name(dev), vaf); + else + r = printk("%s(NULL net_device): %pV", level, vaf); + + return r; +} + +int netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...) +{ + struct va_format vaf; + va_list args; + int r; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + r = __netdev_printk(level, dev, &vaf); + va_end(args); + + return r; +} +EXPORT_SYMBOL(netdev_printk); + +#define define_netdev_printk_level(func, level) \ +int func(const struct net_device *dev, const char *fmt, ...) \ +{ \ + int r; \ + struct va_format vaf; \ + va_list args; \ + \ + va_start(args, fmt); \ + \ + vaf.fmt = fmt; \ + vaf.va = &args; \ + \ + r = __netdev_printk(level, dev, &vaf); \ + va_end(args); \ + \ + return r; \ +} \ +EXPORT_SYMBOL(func); + +define_netdev_printk_level(netdev_emerg, KERN_EMERG); +define_netdev_printk_level(netdev_alert, KERN_ALERT); +define_netdev_printk_level(netdev_crit, KERN_CRIT); +define_netdev_printk_level(netdev_err, KERN_ERR); +define_netdev_printk_level(netdev_warn, KERN_WARNING); +define_netdev_printk_level(netdev_notice, KERN_NOTICE); +define_netdev_printk_level(netdev_info, KERN_INFO); + static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); @@ -5504,14 +6185,13 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit(struct net *net) { - struct net_device *dev; + struct net_device *dev, *aux; /* - * Push all migratable of the network devices back to the + * Push all migratable network devices back to the * initial network namespace */ rtnl_lock(); -restart: - for_each_netdev(net, dev) { + for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -5519,11 +6199,9 @@ restart: if (dev->features & NETIF_F_NETNS_LOCAL) continue; - /* Delete virtual devices */ - if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) { - dev->rtnl_link_ops->dellink(dev); - goto restart; - } + /* Leave virtual devices for the generic cleanup */ + if (dev->rtnl_link_ops) + continue; /* Push remaing network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); @@ -5533,13 +6211,37 @@ restart: __func__, dev->name, err); BUG(); } - goto restart; } rtnl_unlock(); } +static void __net_exit default_device_exit_batch(struct list_head *net_list) +{ + /* At exit all network devices most be removed from a network + * namespace. Do this in the reverse order of registeration. + * Do this across as many network namespaces as possible to + * improve batching efficiency. + */ + struct net_device *dev; + struct net *net; + LIST_HEAD(dev_kill_list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + for_each_netdev_reverse(net, dev) { + if (dev->rtnl_link_ops) + dev->rtnl_link_ops->dellink(dev, &dev_kill_list); + else + unregister_netdevice_queue(dev, &dev_kill_list); + } + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); +} + static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, + .exit_batch = default_device_exit_batch, }; /* @@ -5577,17 +6279,26 @@ static int __init net_dev_init(void) */ for_each_possible_cpu(i) { - struct softnet_data *queue; + struct softnet_data *sd = &per_cpu(softnet_data, i); - queue = &per_cpu(softnet_data, i); - skb_queue_head_init(&queue->input_pkt_queue); - queue->completion_queue = NULL; - INIT_LIST_HEAD(&queue->poll_list); + memset(sd, 0, sizeof(*sd)); + skb_queue_head_init(&sd->input_pkt_queue); + skb_queue_head_init(&sd->process_queue); + sd->completion_queue = NULL; + INIT_LIST_HEAD(&sd->poll_list); + sd->output_queue = NULL; + sd->output_queue_tailp = &sd->output_queue; +#ifdef CONFIG_RPS + sd->csd.func = rps_trigger_softirq; + sd->csd.info = sd; + sd->csd.flags = 0; + sd->cpu = i; +#endif - queue->backlog.poll = process_backlog; - queue->backlog.weight = weight_p; - queue->backlog.gro_list = NULL; - queue->backlog.gro_count = 0; + sd->backlog.poll = process_backlog; + sd->backlog.weight = weight_p; + sd->backlog.gro_list = NULL; + sd->backlog.gro_count = 0; } dev_boot_phase = 0; @@ -5622,47 +6333,9 @@ subsys_initcall(net_dev_init); static int __init initialize_hashrnd(void) { - get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd)); + get_random_bytes(&hashrnd, sizeof(hashrnd)); return 0; } late_initcall_sync(initialize_hashrnd); -EXPORT_SYMBOL(__dev_get_by_index); -EXPORT_SYMBOL(__dev_get_by_name); -EXPORT_SYMBOL(__dev_remove_pack); -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_open); -EXPORT_SYMBOL(dev_queue_xmit); -EXPORT_SYMBOL(dev_remove_pack); -EXPORT_SYMBOL(dev_set_allmulti); -EXPORT_SYMBOL(dev_set_promiscuity); -EXPORT_SYMBOL(dev_change_flags); -EXPORT_SYMBOL(dev_set_mtu); -EXPORT_SYMBOL(dev_set_mac_address); -EXPORT_SYMBOL(free_netdev); -EXPORT_SYMBOL(netdev_boot_setup_check); -EXPORT_SYMBOL(netdev_set_master); -EXPORT_SYMBOL(netdev_state_change); -EXPORT_SYMBOL(netif_receive_skb); -EXPORT_SYMBOL(netif_rx); -EXPORT_SYMBOL(register_gifconf); -EXPORT_SYMBOL(register_netdevice); -EXPORT_SYMBOL(register_netdevice_notifier); -EXPORT_SYMBOL(skb_checksum_help); -EXPORT_SYMBOL(synchronize_net); -EXPORT_SYMBOL(unregister_netdevice); -EXPORT_SYMBOL(unregister_netdevice_notifier); -EXPORT_SYMBOL(net_enable_timestamp); -EXPORT_SYMBOL(net_disable_timestamp); -EXPORT_SYMBOL(dev_get_flags); - -EXPORT_SYMBOL(dev_load); - -EXPORT_PER_CPU_SYMBOL(softnet_data); |