diff options
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 6186 |
1 files changed, 3732 insertions, 2454 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index be9924f60ec..367a586d0c8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -73,13 +73,13 @@ */ #include <asm/uaccess.h> -#include <asm/system.h> #include <linux/bitops.h> #include <linux/capability.h> #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> @@ -97,23 +97,17 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <linux/rtnetlink.h> -#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> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> -#include <net/wext.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> @@ -129,6 +123,15 @@ #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 <linux/cpu_rmap.h> +#include <linux/static_key.h> +#include <linux/hashtable.h> +#include <linux/vmalloc.h> +#include <linux/if_macvlan.h> #include "net-sysfs.h" @@ -138,40 +141,16 @@ /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) -/* - * The list of packet types we will receive (as opposed to discard) - * and the routines to invoke. - * - * Why 16. Because with 16 the only overlap we get on a hash of the - * low nibble of the protocol value is RARP/SNAP/X.25. - * - * NOTE: That is no longer true with the addition of VLAN tags. Not - * sure which should go first, but I bet it won't make much - * difference if we are running VLANs. The good news is that - * this protocol won't be in the list unless compiled in, so - * the average user (w/out VLANs) will not be adversely affected. - * --BLG - * - * 0800 IP - * 8100 802.1Q VLAN - * 0001 802.3 - * 0002 AX.25 - * 0004 802.2 - * 8035 RARP - * 0005 SNAP - * 0805 X.25 - * 0806 ARP - * 8137 IPX - * 0009 Localtalk - * 86DD IPv6 - */ - -#define PTYPE_HASH_SIZE (16) -#define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) - static DEFINE_SPINLOCK(ptype_lock); -static struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; -static struct list_head ptype_all __read_mostly; /* Taps */ +static DEFINE_SPINLOCK(offload_lock); +struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; +struct list_head ptype_all __read_mostly; /* Taps */ +static struct list_head offload_base __read_mostly; + +static int netif_rx_internal(struct sk_buff *skb); +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info); /* * The @dev_base_head list is protected by @dev_base_lock and the rtnl @@ -195,9 +174,23 @@ static struct list_head ptype_all __read_mostly; /* Taps */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +/* protects napi_hash addition/deletion and napi_gen_id */ +static DEFINE_SPINLOCK(napi_hash_lock); + +static unsigned int napi_gen_id; +static DEFINE_HASHTABLE(napi_hash, 8); + +static seqcount_t devnet_rename_seq; + +static inline void dev_base_seq_inc(struct net *net) +{ + while (++net->dev_base_seq == 0); +} + static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { - unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + unsigned int hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); + return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } @@ -206,8 +199,22 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) 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 */ -static int list_netdevice(struct net_device *dev) +static void list_netdevice(struct net_device *dev) { struct net *net = dev_net(dev); @@ -219,7 +226,8 @@ static int list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); - return 0; + + dev_base_seq_inc(net); } /* Device list removal @@ -235,6 +243,8 @@ static void unlist_netdevice(struct net_device *dev) hlist_del_rcu(&dev->name_hlist); hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(dev_net(dev)); } /* @@ -248,7 +258,7 @@ 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 +279,9 @@ static const unsigned short netdev_lock_type[] = ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, 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_VOID, ARPHRD_NONE}; + ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, + ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, + ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", @@ -287,10 +296,9 @@ static const char *const netdev_lock_name[] = "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", - "_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211", - "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", - "_xmit_PHONET_PIPE", "_xmit_IEEE802154", - "_xmit_VOID", "_xmit_NONE"}; + "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", + "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", + "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -357,6 +365,14 @@ 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 @@ -372,16 +388,11 @@ 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); @@ -400,15 +411,10 @@ EXPORT_SYMBOL(dev_add_pack); */ 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) { @@ -417,9 +423,9 @@ void __dev_remove_pack(struct packet_type *pt) } } - printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); + pr_warn("dev_remove_pack: %p not found\n", pt); out: - spin_unlock_bh(&ptype_lock); + spin_unlock(&ptype_lock); } EXPORT_SYMBOL(__dev_remove_pack); @@ -443,6 +449,81 @@ void dev_remove_pack(struct packet_type *pt) } EXPORT_SYMBOL(dev_remove_pack); + +/** + * dev_add_offload - register offload handlers + * @po: protocol offload declaration + * + * Add protocol offload handlers to the networking stack. The passed + * &proto_offload is linked into kernel lists and may not be freed until + * it has been removed from the kernel lists. + * + * This call does not sleep therefore it can not + * guarantee all CPU's that are in middle of receiving packets + * will see the new offload handlers (until the next received packet). + */ +void dev_add_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + + spin_lock(&offload_lock); + list_add_rcu(&po->list, head); + spin_unlock(&offload_lock); +} +EXPORT_SYMBOL(dev_add_offload); + +/** + * __dev_remove_offload - remove offload handler + * @po: packet offload declaration + * + * Remove a protocol offload handler that was previously added to the + * kernel offload handlers by dev_add_offload(). The passed &offload_type + * is removed from the kernel lists and can be freed or reused once this + * function returns. + * + * The packet type might still be in use by receivers + * and must not be freed until after all the CPU's have gone + * through a quiescent state. + */ +static void __dev_remove_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + struct packet_offload *po1; + + spin_lock(&offload_lock); + + list_for_each_entry(po1, head, list) { + if (po == po1) { + list_del_rcu(&po->list); + goto out; + } + } + + pr_warn("dev_remove_offload: %p not found\n", po); +out: + spin_unlock(&offload_lock); +} + +/** + * dev_remove_offload - remove packet offload handler + * @po: packet offload declaration + * + * Remove a packet offload handler that was previously added to the kernel + * offload handlers by dev_add_offload(). The passed &offload_type is + * removed from the kernel lists and can be freed or reused once this + * function returns. + * + * This call sleeps to guarantee that no CPU is looking at the packet + * type after return. + */ +void dev_remove_offload(struct packet_offload *po) +{ + __dev_remove_offload(po); + + synchronize_net(); +} +EXPORT_SYMBOL(dev_remove_offload); + /****************************************************************************** Device Boot-time Settings Routines @@ -588,11 +669,10 @@ __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_entry(dev, p, head, name_hlist) + hlist_for_each_entry(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -614,11 +694,10 @@ EXPORT_SYMBOL(__dev_get_by_name); 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) + hlist_for_each_entry_rcu(dev, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; @@ -665,11 +744,10 @@ EXPORT_SYMBOL(dev_get_by_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_entry(dev, p, head, index_hlist) + hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -690,11 +768,10 @@ EXPORT_SYMBOL(__dev_get_by_index); 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) + hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; @@ -728,34 +805,66 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) EXPORT_SYMBOL(dev_get_by_index); /** - * dev_getbyhwaddr - find a device by its hardware address + * netdev_get_name - get a netdevice name, knowing its ifindex. + * @net: network namespace + * @name: a pointer to the buffer where the name will be stored. + * @ifindex: the ifindex of the interface to get the name from. + * + * The use of raw_seqcount_begin() and cond_resched() before + * retrying is required as we want to give the writers a chance + * to complete when CONFIG_PREEMPT is not set. + */ +int netdev_get_name(struct net *net, char *name, int ifindex) +{ + struct net_device *dev; + unsigned int seq; + +retry: + seq = raw_seqcount_begin(&devnet_rename_seq); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } + + strcpy(name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) { + cond_resched(); + goto retry; + } + + return 0; +} + +/** + * 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 or RTNL. + * 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) { @@ -772,47 +881,46 @@ 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, +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; - rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { - dev_hold(dev); ret = dev; break; } } - rcu_read_unlock(); return ret; } -EXPORT_SYMBOL(dev_get_by_flags); +EXPORT_SYMBOL(dev_get_by_flags_rcu); /** * dev_valid_name - check if name is okay for network device @@ -822,21 +930,21 @@ EXPORT_SYMBOL(dev_get_by_flags); * to allow sysfs to work. We also disallow any kind of * whitespace. */ -int dev_valid_name(const char *name) +bool dev_valid_name(const char *name) { if (*name == '\0') - return 0; + return false; if (strlen(name) >= IFNAMSIZ) - return 0; + return false; if (!strcmp(name, ".") || !strcmp(name, "..")) - return 0; + return false; while (*name) { if (*name == '/' || isspace(*name)) - return 0; + return false; name++; } - return 1; + return true; } EXPORT_SYMBOL(dev_valid_name); @@ -935,18 +1043,34 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -static int dev_get_valid_name(struct net *net, const char *name, char *buf, - bool fmt) +static int dev_alloc_name_ns(struct net *net, + struct net_device *dev, + const char *name) { + char buf[IFNAMSIZ]; + int ret; + + ret = __dev_alloc_name(net, name, buf); + if (ret >= 0) + strlcpy(dev->name, buf, IFNAMSIZ); + return ret; +} + +static int dev_get_valid_name(struct net *net, + struct net_device *dev, + const char *name) +{ + BUG_ON(!net); + if (!dev_valid_name(name)) return -EINVAL; - if (fmt && strchr(name, '%')) - return __dev_alloc_name(net, name, buf); + if (strchr(name, '%')) + return dev_alloc_name_ns(net, dev, name); else if (__dev_get_by_name(net, name)) return -EEXIST; - else if (buf != name) - strlcpy(buf, name, IFNAMSIZ); + else if (dev->name != name) + strlcpy(dev->name, name, IFNAMSIZ); return 0; } @@ -973,29 +1097,35 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) + write_seqcount_begin(&devnet_rename_seq); + + if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { + write_seqcount_end(&devnet_rename_seq); return 0; + } memcpy(oldname, dev->name, IFNAMSIZ); - err = dev_get_valid_name(net, newname, dev->name, 1); - if (err < 0) + err = dev_get_valid_name(net, dev, newname); + if (err < 0) { + write_seqcount_end(&devnet_rename_seq); return err; + } rollback: - /* For now only devices in the initial network namespace - * are in sysfs. - */ - if (net_eq(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); + write_seqcount_end(&devnet_rename_seq); + return ret; } + write_seqcount_end(&devnet_rename_seq); + + netdev_adjacent_rename_links(dev, oldname); + write_lock_bh(&dev_base_lock); - hlist_del(&dev->name_hlist); + hlist_del_rcu(&dev->name_hlist); write_unlock_bh(&dev_base_lock); synchronize_rcu(); @@ -1011,11 +1141,12 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; + write_seqcount_begin(&devnet_rename_seq); memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); goto rollback; } else { - printk(KERN_ERR - "%s: name change rollback failed: %d.\n", + pr_err("%s: name change rollback failed: %d\n", dev->name, ret); } } @@ -1033,22 +1164,23 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { + char *new_ifalias; + ASSERT_RTNL(); if (len >= IFALIASZ) return -EINVAL; if (!len) { - if (dev->ifalias) { - kfree(dev->ifalias); - dev->ifalias = NULL; - } + kfree(dev->ifalias); + dev->ifalias = NULL; return 0; } - dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!dev->ifalias) + new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); + if (!new_ifalias) return -ENOMEM; + dev->ifalias = new_ifalias; strlcpy(dev->ifalias, alias, len+1); return len; @@ -1078,81 +1210,55 @@ EXPORT_SYMBOL(netdev_features_change); void netdev_state_change(struct net_device *dev) { if (dev->flags & IFF_UP) { - call_netdevice_notifiers(NETDEV_CHANGE, dev); - rtmsg_ifinfo(RTM_NEWLINK, dev, 0); + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = 0; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); } } EXPORT_SYMBOL(netdev_state_change); -void netdev_bonding_change(struct net_device *dev, unsigned long event) -{ - call_netdevice_notifiers(event, dev); -} -EXPORT_SYMBOL(netdev_bonding_change); - /** - * dev_load - load a network module - * @net: the applicable net namespace - * @name: name of interface + * netdev_notify_peers - notify network peers about existence of @dev + * @dev: network device * - * If a network interface is not present and the process has suitable - * privileges this function loads the module. If module loading is not - * available in this kernel then it becomes a nop. + * Generate traffic such that interested network peers are aware of + * @dev, such as by generating a gratuitous ARP. This may be used when + * a device wants to inform the rest of the network about some sort of + * reconfiguration such as a failover event or virtual machine + * migration. */ - -void dev_load(struct net *net, const char *name) +void netdev_notify_peers(struct net_device *dev) { - struct net_device *dev; - - rcu_read_lock(); - dev = dev_get_by_name_rcu(net, name); - rcu_read_unlock(); - - if (!dev && capable(CAP_NET_ADMIN)) - request_module("%s", name); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); + rtnl_unlock(); } -EXPORT_SYMBOL(dev_load); +EXPORT_SYMBOL(netdev_notify_peers); -/** - * 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; ASSERT_RTNL(); - /* - * Is it already up? - */ - - if (dev->flags & IFF_UP) - return 0; - - /* - * Is it even present? - */ if (!netif_device_present(dev)) return -ENODEV; + /* Block netpoll from trying to do any rx path servicing. + * If we don't do this there is a chance ndo_poll_controller + * or ndo_poll may be running while we open the device + */ + netpoll_poll_disable(dev); + ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); ret = notifier_to_errno(ret); if (ret) return ret; - /* - * Call device private open method - */ set_bit(__LINK_STATE_START, &dev->state); if (ops->ndo_validate_addr) @@ -1161,108 +1267,150 @@ int dev_open(struct net_device *dev) if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); - /* - * If it went open OK then: - */ + netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { - /* - * Set the flags. - */ dev->flags |= IFF_UP; - - /* - * Enable NET_DMA - */ net_dmaengine_get(); - - /* - * Initialize multicasting status - */ dev_set_rx_mode(dev); - - /* - * Wakeup transmit queue engine - */ dev_activate(dev); - - /* - * ... and announce new interface. - */ - call_netdevice_notifiers(NETDEV_UP, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; } -EXPORT_SYMBOL(dev_open); /** - * 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(); + int ret; + if (dev->flags & IFF_UP) + return 0; + + ret = __dev_open(dev); + if (ret < 0) + return ret; + + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + call_netdevice_notifiers(NETDEV_UP, dev); + + return ret; +} +EXPORT_SYMBOL(dev_open); + +static int __dev_close_many(struct list_head *head) +{ + struct net_device *dev; + + ASSERT_RTNL(); might_sleep(); - if (!(dev->flags & IFF_UP)) - return 0; + list_for_each_entry(dev, head, close_list) { + /* Temporarily disable netpoll until the interface is down */ + netpoll_poll_disable(dev); - /* - * 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); + call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); + + clear_bit(__LINK_STATE_START, &dev->state); - 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_atomic(); /* Commit netif_running(). */ + } - /* 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); - dev_deactivate(dev); + list_for_each_entry(dev, head, close_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); + /* + * 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; + net_dmaengine_put(); + netpoll_poll_enable(dev); + } - dev->flags &= ~IFF_UP; + return 0; +} - /* - * Tell people we are down - */ - call_netdevice_notifiers(NETDEV_DOWN, dev); +static int __dev_close(struct net_device *dev) +{ + int retval; + LIST_HEAD(single); - /* - * Shutdown NET_DMA - */ - net_dmaengine_put(); + list_add(&dev->close_list, &single); + retval = __dev_close_many(&single); + list_del(&single); + + return retval; +} + +static int dev_close_many(struct list_head *head) +{ + struct net_device *dev, *tmp; + + /* Remove the devices that don't need to be closed */ + list_for_each_entry_safe(dev, tmp, head, close_list) + if (!(dev->flags & IFF_UP)) + list_del_init(&dev->close_list); + + __dev_close_many(head); + + list_for_each_entry_safe(dev, tmp, head, close_list) { + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + call_netdevice_notifiers(NETDEV_DOWN, dev); + list_del_init(&dev->close_list); + } 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) +{ + if (dev->flags & IFF_UP) { + LIST_HEAD(single); + + list_add(&dev->close_list, &single); + dev_close_many(&single); + list_del(&single); + } + return 0; +} EXPORT_SYMBOL(dev_close); @@ -1276,25 +1424,35 @@ EXPORT_SYMBOL(dev_close); */ void dev_disable_lro(struct net_device *dev) { - if (dev->ethtool_ops && dev->ethtool_ops->get_flags && - dev->ethtool_ops->set_flags) { - u32 flags = dev->ethtool_ops->get_flags(dev); - if (flags & ETH_FLAG_LRO) { - flags &= ~ETH_FLAG_LRO; - dev->ethtool_ops->set_flags(dev, flags); - } - } - WARN_ON(dev->features & NETIF_F_LRO); + /* + * If we're trying to disable lro on a vlan device + * use the underlying physical device instead + */ + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); + + /* the same for macvlan devices */ + if (netif_is_macvlan(dev)) + dev = macvlan_dev_real_dev(dev); + + dev->wanted_features &= ~NETIF_F_LRO; + netdev_update_features(dev); + + if (unlikely(dev->features & NETIF_F_LRO)) + netdev_WARN(dev, "failed to disable LRO!\n"); } EXPORT_SYMBOL(dev_disable_lro); +static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, + struct net_device *dev) +{ + struct netdev_notifier_info info; -static int dev_boot_phase = 1; + netdev_notifier_info_init(&info, dev); + return nb->notifier_call(nb, val, &info); +} -/* - * Device change register/unregister. These are not inline or static - * as we export them to the world. - */ +static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block @@ -1325,7 +1483,7 @@ int register_netdevice_notifier(struct notifier_block *nb) goto unlock; for_each_net(net) { for_each_netdev(net, dev) { - err = nb->notifier_call(nb, NETDEV_REGISTER, dev); + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) goto rollback; @@ -1333,7 +1491,7 @@ int register_netdevice_notifier(struct notifier_block *nb) if (!(dev->flags & IFF_UP)) continue; - nb->notifier_call(nb, NETDEV_UP, dev); + call_netdevice_notifier(nb, NETDEV_UP, dev); } } @@ -1346,17 +1504,18 @@ rollback: for_each_net(net) { for_each_netdev(net, dev) { if (dev == last) - break; + goto outroll; if (dev->flags & IFF_UP) { - nb->notifier_call(nb, NETDEV_GOING_DOWN, dev); - nb->notifier_call(nb, NETDEV_DOWN, dev); + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); } - nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } } +outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -1370,20 +1529,59 @@ EXPORT_SYMBOL(register_netdevice_notifier); * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { + struct net_device *dev; + struct net *net; int err; rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); + if (err) + goto unlock; + + for_each_net(net) { + for_each_netdev(net, dev) { + if (dev->flags & IFF_UP) { + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); + } + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); + } + } +unlock: rtnl_unlock(); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier); /** + * call_netdevice_notifiers_info - call all network notifier blocks + * @val: value passed unmodified to notifier function + * @dev: net_device pointer passed unmodified to notifier function + * @info: notifier information data + * + * Call all network notifier blocks. Parameters and return value + * are as for raw_notifier_call_chain(). + */ + +static int call_netdevice_notifiers_info(unsigned long val, + struct net_device *dev, + struct netdev_notifier_info *info) +{ + ASSERT_RTNL(); + netdev_notifier_info_init(info, dev); + return raw_notifier_call_chain(&netdev_chain, val, info); +} + +/** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function @@ -1394,32 +1592,105 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - return raw_notifier_call_chain(&netdev_chain, val, dev); + struct netdev_notifier_info info; + + return call_netdevice_notifiers_info(val, dev, &info); } +EXPORT_SYMBOL(call_netdevice_notifiers); -/* When > 0 there are consumers of rx skb time stamps */ -static atomic_t netstamp_needed = ATOMIC_INIT(0); +static struct static_key netstamp_needed __read_mostly; +#ifdef HAVE_JUMP_LABEL +/* We are not allowed to call static_key_slow_dec() from irq context + * If net_disable_timestamp() is called from irq context, defer the + * static_key_slow_dec() calls. + */ +static atomic_t netstamp_needed_deferred; +#endif void net_enable_timestamp(void) { - atomic_inc(&netstamp_needed); +#ifdef HAVE_JUMP_LABEL + int deferred = atomic_xchg(&netstamp_needed_deferred, 0); + + if (deferred) { + while (--deferred) + static_key_slow_dec(&netstamp_needed); + return; + } +#endif + static_key_slow_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { - atomic_dec(&netstamp_needed); +#ifdef HAVE_JUMP_LABEL + if (in_interrupt()) { + atomic_inc(&netstamp_needed_deferred); + return; + } +#endif + static_key_slow_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)) + skb->tstamp.tv64 = 0; + if (static_key_false(&netstamp_needed)) __net_timestamp(skb); - else - skb->tstamp.tv64 = 0; } +#define net_timestamp_check(COND, SKB) \ + if (static_key_false(&netstamp_needed)) { \ + if ((COND) && !(SKB)->tstamp.tv64) \ + __net_timestamp(SKB); \ + } \ + +bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) +{ + unsigned int len; + + if (!(dev->flags & IFF_UP)) + return false; + + len = dev->mtu + dev->hard_header_len + VLAN_HLEN; + if (skb->len <= len) + return true; + + /* if TSO is enabled, we don't care about the length as the packet + * could be forwarded without being segmented before + */ + if (skb_is_gso(skb)) + return true; + + return false; +} +EXPORT_SYMBOL_GPL(is_skb_forwardable); + +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, GFP_ATOMIC)) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + } + + if (unlikely(!is_skb_forwardable(dev, skb))) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + + skb_scrub_packet(skb, true); + skb->protocol = eth_type_trans(skb, dev); + + return 0; +} +EXPORT_SYMBOL_GPL(__dev_forward_skb); + /** * dev_forward_skb - loopback an skb to another netif * @@ -1428,7 +1699,7 @@ static inline void net_timestamp(struct sk_buff *skb) * * return values: * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) + * 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 @@ -1440,24 +1711,32 @@ static inline void net_timestamp(struct sk_buff *skb) */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - skb_orphan(skb); + return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); +} +EXPORT_SYMBOL_GPL(dev_forward_skb); - if (!(dev->flags & IFF_UP)) - return NET_RX_DROP; +static inline int deliver_skb(struct sk_buff *skb, + struct packet_type *pt_prev, + struct net_device *orig_dev) +{ + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + return -ENOMEM; + atomic_inc(&skb->users); + return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); +} - if (skb->len > (dev->mtu + dev->hard_header_len)) - return NET_RX_DROP; +static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) +{ + if (!ptype->af_packet_priv || !skb->sk) + return false; - skb_dst_drop(skb); - skb->tstamp.tv64 = 0; - skb->pkt_type = PACKET_HOST; - skb->protocol = eth_type_trans(skb, dev); - skb->mark = 0; - secpath_reset(skb); - nf_reset(skb); - return netif_rx(skb); + if (ptype->id_match) + return ptype->id_match(ptype, skb->sk); + else if ((struct sock *)ptype->af_packet_priv == skb->sk) + return true; + + return false; } -EXPORT_SYMBOL_GPL(dev_forward_skb); /* * Support routine. Sends outgoing frames to any network @@ -1467,13 +1746,8 @@ EXPORT_SYMBOL_GPL(dev_forward_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) { @@ -1481,12 +1755,19 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * they originated from - MvS (miquels@drinkel.ow.org) */ 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); + (!skb_loop_sk(ptype, skb))) { + 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. @@ -1494,22 +1775,366 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || - skb2->network_header > skb2->tail) { - if (net_ratelimit()) - printk(KERN_CRIT "protocol %04x is " - "buggy, dev %s\n", - skb2->protocol, dev->name); + skb_network_header(skb2) > skb_tail_pointer(skb2)) { + net_crit_ratelimited("protocol %04x is buggy, dev %s\n", + 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(); } +/** + * netif_setup_tc - Handle tc mappings on real_num_tx_queues change + * @dev: Network device + * @txq: number of queues available + * + * If real_num_tx_queues is changed the tc mappings may no longer be + * valid. To resolve this verify the tc mapping remains valid and if + * not NULL the mapping. With no priorities mapping to this + * offset/count pair it will no longer be used. In the worst case TC0 + * is invalid nothing can be done so disable priority mappings. If is + * expected that drivers will fix this mapping if they can before + * calling netif_set_real_num_tx_queues. + */ +static void netif_setup_tc(struct net_device *dev, unsigned int txq) +{ + int i; + struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; + + /* If TC0 is invalidated disable TC mapping */ + if (tc->offset + tc->count > txq) { + pr_warn("Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); + dev->num_tc = 0; + return; + } + + /* Invalidated prio to tc mappings set to TC0 */ + for (i = 1; i < TC_BITMASK + 1; i++) { + int q = netdev_get_prio_tc_map(dev, i); + + tc = &dev->tc_to_txq[q]; + if (tc->offset + tc->count > txq) { + pr_warn("Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", + i, q); + netdev_set_prio_tc_map(dev, i, 0); + } + } +} + +#ifdef CONFIG_XPS +static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) + +static struct xps_map *remove_xps_queue(struct xps_dev_maps *dev_maps, + int cpu, u16 index) +{ + struct xps_map *map = NULL; + int pos; + + if (dev_maps) + map = xmap_dereference(dev_maps->cpu_map[cpu]); + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] == index) { + if (map->len > 1) { + map->queues[pos] = map->queues[--map->len]; + } else { + RCU_INIT_POINTER(dev_maps->cpu_map[cpu], NULL); + kfree_rcu(map, rcu); + map = NULL; + } + break; + } + } + + return map; +} + +static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) +{ + struct xps_dev_maps *dev_maps; + int cpu, i; + bool active = false; + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (!dev_maps) + goto out_no_maps; + + for_each_possible_cpu(cpu) { + for (i = index; i < dev->num_tx_queues; i++) { + if (!remove_xps_queue(dev_maps, cpu, i)) + break; + } + if (i == dev->num_tx_queues) + active = true; + } + + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + + for (i = index; i < dev->num_tx_queues; i++) + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i), + NUMA_NO_NODE); + +out_no_maps: + mutex_unlock(&xps_map_mutex); +} + +static struct xps_map *expand_xps_map(struct xps_map *map, + int cpu, u16 index) +{ + struct xps_map *new_map; + int alloc_len = XPS_MIN_MAP_ALLOC; + int i, pos; + + for (pos = 0; map && pos < map->len; pos++) { + if (map->queues[pos] != index) + continue; + return map; + } + + /* Need to add queue to this CPU's existing map */ + if (map) { + if (pos < map->alloc_len) + return map; + + alloc_len = map->alloc_len * 2; + } + + /* Need to allocate new map to store queue on this CPU's map */ + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + return NULL; + + for (i = 0; i < pos; i++) + new_map->queues[i] = map->queues[i]; + new_map->alloc_len = alloc_len; + new_map->len = pos; + + return new_map; +} + +int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, + u16 index) +{ + struct xps_dev_maps *dev_maps, *new_dev_maps = NULL; + struct xps_map *map, *new_map; + int maps_sz = max_t(unsigned int, XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES); + int cpu, numa_node_id = -2; + bool active = false; + + mutex_lock(&xps_map_mutex); + + dev_maps = xmap_dereference(dev->xps_maps); + + /* allocate memory for queue storage */ + for_each_online_cpu(cpu) { + if (!cpumask_test_cpu(cpu, mask)) + continue; + + if (!new_dev_maps) + new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); + if (!new_dev_maps) { + mutex_unlock(&xps_map_mutex); + return -ENOMEM; + } + + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + + map = expand_xps_map(map, cpu, index); + if (!map) + goto error; + + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + if (!new_dev_maps) + goto out_no_new_maps; + + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) { + /* add queue to CPU maps */ + int pos = 0; + + map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + while ((pos < map->len) && (map->queues[pos] != index)) + pos++; + + if (pos == map->len) + map->queues[map->len++] = index; +#ifdef CONFIG_NUMA + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + numa_node_id = -1; +#endif + } else if (dev_maps) { + /* fill in the new device map from the old device map */ + map = xmap_dereference(dev_maps->cpu_map[cpu]); + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], map); + } + + } + + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + + /* Cleanup old maps */ + if (dev_maps) { + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = xmap_dereference(dev_maps->cpu_map[cpu]); + if (map && map != new_map) + kfree_rcu(map, rcu); + } + + kfree_rcu(dev_maps, rcu); + } + + dev_maps = new_dev_maps; + active = true; + +out_no_new_maps: + /* update Tx queue numa node */ + netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), + (numa_node_id >= 0) ? numa_node_id : + NUMA_NO_NODE); + + if (!dev_maps) + goto out_no_maps; + + /* removes queue from unused CPUs */ + for_each_possible_cpu(cpu) { + if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) + continue; + + if (remove_xps_queue(dev_maps, cpu, index)) + active = true; + } + + /* free map if not active */ + if (!active) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + kfree_rcu(dev_maps, rcu); + } + +out_no_maps: + mutex_unlock(&xps_map_mutex); + + return 0; +error: + /* remove any maps that we added */ + for_each_possible_cpu(cpu) { + new_map = xmap_dereference(new_dev_maps->cpu_map[cpu]); + map = dev_maps ? xmap_dereference(dev_maps->cpu_map[cpu]) : + NULL; + if (new_map && new_map != map) + kfree(new_map); + } + + mutex_unlock(&xps_map_mutex); + + kfree(new_dev_maps); + return -ENOMEM; +} +EXPORT_SYMBOL(netif_set_xps_queue); + +#endif +/* + * 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 || + dev->reg_state == NETREG_UNREGISTERING) { + ASSERT_RTNL(); + + rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, + txq); + if (rc) + return rc; + + if (dev->num_tc) + netif_setup_tc(dev, txq); + + if (txq < dev->real_num_tx_queues) { + qdisc_reset_all_tx_gt(dev, txq); +#ifdef CONFIG_XPS + netif_reset_xps_queues_gt(dev, txq); +#endif + } + } + + dev->real_num_tx_queues = txq; + return 0; +} +EXPORT_SYMBOL(netif_set_real_num_tx_queues); + +#ifdef CONFIG_SYSFS +/** + * 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 + +/** + * netif_get_num_default_rss_queues - default number of RSS queues + * + * This routine should set an upper limit on the number of RSS queues + * used by default by multiqueue devices. + */ +int netif_get_num_default_rss_queues(void) +{ + return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); +} +EXPORT_SYMBOL(netif_get_num_default_rss_queues); static inline void __netif_reschedule(struct Qdisc *q) { @@ -1518,8 +2143,9 @@ 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); } @@ -1531,30 +2157,42 @@ void __netif_schedule(struct Qdisc *q) } EXPORT_SYMBOL(__netif_schedule); -void dev_kfree_skb_irq(struct sk_buff *skb) +struct dev_kfree_skb_cb { + enum skb_free_reason reason; +}; + +static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { - if (atomic_dec_and_test(&skb->users)) { - struct softnet_data *sd; - unsigned long flags; + return (struct dev_kfree_skb_cb *)skb->cb; +} - local_irq_save(flags); - sd = &__get_cpu_var(softnet_data); - skb->next = sd->completion_queue; - sd->completion_queue = skb; - raise_softirq_irqoff(NET_TX_SOFTIRQ); - local_irq_restore(flags); +void __dev_kfree_skb_irq(struct sk_buff *skb, enum skb_free_reason reason) +{ + unsigned long flags; + + if (likely(atomic_read(&skb->users) == 1)) { + smp_rmb(); + atomic_set(&skb->users, 0); + } else if (likely(!atomic_dec_and_test(&skb->users))) { + return; } + get_kfree_skb_cb(skb)->reason = reason; + local_irq_save(flags); + skb->next = __this_cpu_read(softnet_data.completion_queue); + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); } -EXPORT_SYMBOL(dev_kfree_skb_irq); +EXPORT_SYMBOL(__dev_kfree_skb_irq); -void dev_kfree_skb_any(struct sk_buff *skb) +void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_irq() || irqs_disabled()) - dev_kfree_skb_irq(skb); + __dev_kfree_skb_irq(skb, reason); else dev_kfree_skb(skb); } -EXPORT_SYMBOL(dev_kfree_skb_any); +EXPORT_SYMBOL(__dev_kfree_skb_any); /** @@ -1588,30 +2226,24 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -static bool can_checksum_protocol(unsigned long features, __be16 protocol) +static void skb_warn_bad_offload(const struct sk_buff *skb) { - 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 const netdev_features_t null_features = 0; + struct net_device *dev = skb->dev; + const char *driver = ""; -static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) -{ - if (can_checksum_protocol(dev->features, skb->protocol)) - return true; + if (!net_ratelimit()) + return; - 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; - } + if (dev && dev->dev.parent) + driver = dev_driver_string(dev->dev.parent); - return false; + WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d " + "gso_type=%d ip_summed=%d\n", + driver, dev ? &dev->features : &null_features, + skb->sk ? &skb->sk->sk_route_caps : &null_features, + skb->len, skb->data_len, skb_shinfo(skb)->gso_size, + skb_shinfo(skb)->gso_type, skb->ip_summed); } /* @@ -1627,11 +2259,20 @@ int skb_checksum_help(struct sk_buff *skb) goto out_set_summed; if (unlikely(skb_shinfo(skb)->gso_size)) { - /* Let GSO fix up the checksum. */ - goto out_set_summed; + skb_warn_bad_offload(skb); + return -EINVAL; + } + + /* Before computing a checksum, we should make sure no frag could + * be modified by an external entity : checksum could be wrong. + */ + if (skb_has_shared_frag(skb)) { + ret = __skb_linearize(skb); + if (ret) + goto out; } - 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); @@ -1653,58 +2294,85 @@ out: } EXPORT_SYMBOL(skb_checksum_help); -/** - * skb_gso_segment - Perform segmentation on skb. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - * - * This function segments the given skb and returns a list of segments. - * - * It may return NULL if the skb requires no segmentation. This is - * only possible when GSO is used for verifying header integrity. - */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) +__be16 skb_network_protocol(struct sk_buff *skb, int *depth) { - struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_type *ptype; + unsigned int vlan_depth = skb->mac_len; __be16 type = skb->protocol; - int err; - skb_reset_mac_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; - __skb_pull(skb, skb->mac_len); + /* Tunnel gso handlers can set protocol to ethernet. */ + if (type == htons(ETH_P_TEB)) { + struct ethhdr *eth; - if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - struct net_device *dev = skb->dev; - struct ethtool_drvinfo info = {}; + if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) + return 0; - if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) - dev->ethtool_ops->get_drvinfo(dev, &info); + eth = (struct ethhdr *)skb_mac_header(skb); + type = eth->h_proto; + } - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d " - "ip_summed=%d", - info.driver, dev ? dev->features : 0L, - skb->sk ? skb->sk->sk_route_caps : 0L, - skb->len, skb->data_len, skb->ip_summed); + /* if skb->protocol is 802.1Q/AD then the header should already be + * present at mac_len - VLAN_HLEN (if mac_len > 0), or at + * ETH_HLEN otherwise + */ + if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { + if (vlan_depth) { + if (unlikely(WARN_ON(vlan_depth < VLAN_HLEN))) + return 0; + vlan_depth -= VLAN_HLEN; + } else { + vlan_depth = ETH_HLEN; + } + do { + struct vlan_hdr *vh; - if (skb_header_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) - return ERR_PTR(err); + if (unlikely(!pskb_may_pull(skb, + vlan_depth + VLAN_HLEN))) + return 0; + + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; + } while (type == htons(ETH_P_8021Q) || + type == htons(ETH_P_8021AD)); } + *depth = vlan_depth; + + return type; +} + +/** + * skb_mac_gso_segment - mac layer segmentation handler. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + */ +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); + struct packet_offload *ptype; + int vlan_depth = skb->mac_len; + __be16 type = skb_network_protocol(skb, &vlan_depth); + + if (unlikely(!type)) + return ERR_PTR(-EINVAL); + + __skb_pull(skb, vlan_depth); + rcu_read_lock(); - list_for_each_entry_rcu(ptype, - &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && !ptype->dev && ptype->gso_segment) { + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->callbacks.gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { - err = ptype->gso_send_check(skb); + int err; + + err = ptype->callbacks.gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) break; __skb_push(skb, (skb->data - skb_network_header(skb))); } - segs = ptype->gso_segment(skb, features); + segs = ptype->callbacks.gso_segment(skb, features); break; } } @@ -1714,15 +2382,59 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) return segs; } -EXPORT_SYMBOL(skb_gso_segment); +EXPORT_SYMBOL(skb_mac_gso_segment); + + +/* openvswitch calls this on rx path, so we need a different check. + */ +static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) +{ + if (tx_path) + return skb->ip_summed != CHECKSUM_PARTIAL; + else + return skb->ip_summed == CHECKSUM_NONE; +} + +/** + * __skb_gso_segment - Perform segmentation on skb. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + * @tx_path: whether it is called in TX path + * + * This function segments the given skb and returns a list of segments. + * + * It may return NULL if the skb requires no segmentation. This is + * only possible when GSO is used for verifying header integrity. + */ +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path) +{ + if (unlikely(skb_needs_check(skb, tx_path))) { + int err; + + skb_warn_bad_offload(skb); + + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); + SKB_GSO_CB(skb)->encap_level = 0; + + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return skb_mac_gso_segment(skb, features); +} +EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev) { if (net_ratelimit()) { - printk(KERN_ERR "%s: hw csum failure.\n", - dev ? dev->name : "<unknown>"); + pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); dump_stack(); } } @@ -1734,18 +2446,30 @@ 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++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + if (PageHighMem(skb_frag_page(frag))) + 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++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + dma_addr_t addr = page_to_phys(skb_frag_page(frag)); + if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) + return 1; + } + } #endif return 0; } @@ -1760,13 +2484,8 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) { struct dev_gso_cb *cb; - do { - struct sk_buff *nskb = skb->next; - - skb->next = nskb->next; - nskb->next = NULL; - kfree_skb(nskb); - } while (skb->next); + kfree_skb_list(skb->next); + skb->next = NULL; cb = DEV_GSO_CB(skb); if (cb->destructor) @@ -1776,16 +2495,14 @@ 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, netdev_features_t 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); @@ -1803,47 +2520,146 @@ static int dev_gso_segment(struct sk_buff *skb) return 0; } +/* If MPLS offload request, verify we are testing hardware MPLS features + * instead of standard features for the netdev. + */ +#ifdef CONFIG_NET_MPLS_GSO +static netdev_features_t net_mpls_features(struct sk_buff *skb, + netdev_features_t features, + __be16 type) +{ + if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC)) + features &= skb->dev->mpls_features; + + return features; +} +#else +static netdev_features_t net_mpls_features(struct sk_buff *skb, + netdev_features_t features, + __be16 type) +{ + return features; +} +#endif + +static netdev_features_t harmonize_features(struct sk_buff *skb, + netdev_features_t features) +{ + int tmp; + __be16 type; + + type = skb_network_protocol(skb, &tmp); + features = net_mpls_features(skb, features, type); + + if (skb->ip_summed != CHECKSUM_NONE && + !can_checksum_protocol(features, type)) { + features &= ~NETIF_F_ALL_CSUM; + } else if (illegal_highdma(skb->dev, skb)) { + features &= ~NETIF_F_SG; + } + + return features; +} + +netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + __be16 protocol = skb->protocol; + netdev_features_t features = skb->dev->features; + + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + features &= ~NETIF_F_GSO_MASK; + + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { + 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, features); + } + + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); + + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + + return harmonize_features(skb, features); +} +EXPORT_SYMBOL(netif_skb_features); + 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 = NETDEV_TX_OK; + unsigned int skb_len; 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; - } + netdev_features_t features; /* - * If device doesnt need skb->dst, release it right now while + * If device doesn't need skb->dst, release it right now while * its hot in this cpu cache */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); + features = netif_skb_features(skb); + + if (vlan_tx_tag_present(skb) && + !vlan_hw_offload_capable(features, skb->vlan_proto)) { + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); + if (unlikely(!skb)) + goto out; + + skb->vlan_tci = 0; + } + + /* If encapsulation offload request, verify we are testing + * hardware encapsulation features instead of standard + * features for the netdev + */ + if (skb->encapsulation) + features &= dev->hw_enc_features; + + 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) { + if (skb->encapsulation) + skb_set_inner_transport_header(skb, + skb_checksum_start_offset(skb)); + else + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); + if (!(features & NETIF_F_ALL_CSUM) && + skb_checksum_help(skb)) + goto out_kfree_skb; + } + } + + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + + skb_len = skb->len; + trace_net_dev_start_xmit(skb, dev); rc = ops->ndo_start_xmit(skb, dev); + trace_net_dev_xmit(skb, rc, dev, skb_len); 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; } @@ -1853,7 +2669,14 @@ gso: skb->next = nskb->next; nskb->next = NULL; + + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(nskb, dev); + + skb_len = nskb->len; + trace_net_dev_start_xmit(nskb, dev); rc = ops->ndo_start_xmit(nskb, dev); + trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) goto out_kfree_gso_skb; @@ -1862,82 +2685,51 @@ gso: return rc; } txq_trans_update(txq); - if (unlikely(netif_tx_queue_stopped(txq) && skb->next)) + if (unlikely(netif_xmit_stopped(txq) && skb->next)) return NETDEV_TX_BUSY; } while (skb->next); out_kfree_gso_skb: - if (likely(skb->next == NULL)) + if (likely(skb->next == NULL)) { skb->destructor = DEV_GSO_CB(skb)->destructor; + consume_skb(skb); + return rc; + } out_kfree_skb: kfree_skb(skb); +out: return rc; } +EXPORT_SYMBOL_GPL(dev_hard_start_xmit); -static u32 skb_tx_hashrnd; - -u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) +static void qdisc_pkt_len_init(struct sk_buff *skb) { - u32 hash; + const struct skb_shared_info *shinfo = skb_shinfo(skb); - 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; - return hash; - } - - if (skb->sk && skb->sk->sk_hash) - hash = skb->sk->sk_hash; - else - hash = skb->protocol; - - hash = jhash_1word(hash, skb_tx_hashrnd); + qdisc_skb_cb(skb)->pkt_len = skb->len; - return (u16) (((u64) hash * dev->real_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()) { - WARN(1, "%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; -} + /* To get more precise estimation of bytes sent on wire, + * we add to pkt_len the headers size of all segments + */ + if (shinfo->gso_size) { + unsigned int hdr_len; + u16 gso_segs = shinfo->gso_segs; -static struct netdev_queue *dev_pick_tx(struct net_device *dev, - struct sk_buff *skb) -{ - u16 queue_index; - struct sock *sk = skb->sk; + /* mac layer + network layer */ + hdr_len = skb_transport_header(skb) - skb_mac_header(skb); - if (sk_tx_queue_recorded(sk)) { - queue_index = sk_tx_queue_get(sk); - } else { - const struct net_device_ops *ops = dev->netdev_ops; + /* + transport layer */ + if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + hdr_len += tcp_hdrlen(skb); + else + hdr_len += sizeof(struct udphdr); - if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { - queue_index = 0; - if (dev->real_num_tx_queues > 1) - queue_index = skb_tx_hash(dev, skb); + if (shinfo->gso_type & SKB_GSO_DODGY) + gso_segs = DIV_ROUND_UP(skb->len - hdr_len, + shinfo->gso_size); - if (sk && sk->sk_dst_cache) - sk_tx_queue_set(sk, queue_index); - } + qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } - - 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, @@ -1945,38 +2737,104 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); + bool contended; int rc; + qdisc_pkt_len_init(skb); + qdisc_calculate_pkt_len(skb, q); + /* + * 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. + */ + contended = qdisc_is_running(q); + 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) && - !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { + 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. */ - __qdisc_update_bstats(q, skb->len); - if (sch_direct_xmit(skb, q, dev, txq, root_lock)) + if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) + skb_dst_force(skb); + + 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 - clear_bit(__QDISC_STATE_RUNNING, &q->state); + } else + qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { - rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); + skb_dst_force(skb); + rc = q->enqueue(skb, q) & NET_XMIT_MASK; + 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; } +#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) +static void skb_update_prio(struct sk_buff *skb) +{ + struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); + + if (!skb->priority && skb->sk && map) { + unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; + } +} +#else +#define skb_update_prio(skb) +#endif + +static DEFINE_PER_CPU(int, xmit_recursion); +#define RECURSION_LIMIT 10 + /** - * dev_queue_xmit - transmit a buffer + * dev_loopback_xmit - loop back @skb * @skb: buffer to transmit + */ +int dev_loopback_xmit(struct sk_buff *skb) +{ + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->pkt_type = PACKET_LOOPBACK; + skb->ip_summed = CHECKSUM_UNNECESSARY; + WARN_ON(!skb_dst(skb)); + skb_dst_force(skb); + netif_rx_ni(skb); + return 0; +} +EXPORT_SYMBOL(dev_loopback_xmit); + +/** + * __dev_queue_xmit - transmit a buffer + * @skb: buffer to transmit + * @accel_priv: private data used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling @@ -1999,53 +2857,29 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, * the BH enable code must have IRQs enabled so that it will not deadlock. * --BLG */ -int dev_queue_xmit(struct sk_buff *skb) +static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) { struct net_device *dev = skb->dev; struct netdev_queue *txq; 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; - } + skb_reset_mac_header(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); + skb_update_prio(skb); + + txq = netdev_pick_tx(dev, skb, accel_priv); + q = rcu_dereference_bh(txq->qdisc); #ifdef CONFIG_NET_CLS_ACT skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); #endif + trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; @@ -2068,113 +2902,449 @@ 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)) { + if (!netif_xmit_stopped(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; } } HARD_TX_UNLOCK(dev, txq); - if (net_ratelimit()) - printk(KERN_CRIT "Virtual device %s asks to " - "queue packet!\n", dev->name); + net_crit_ratelimited("Virtual device %s asks to queue packet!\n", + dev->name); } else { /* Recursion is detected! It is possible, - * unfortunately */ - if (net_ratelimit()) - printk(KERN_CRIT "Dead loop on virtual device " - "%s, fix it urgently!\n", dev->name); + * unfortunately + */ +recursion_alert: + net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", + dev->name); } } rc = -ENETDOWN; rcu_read_unlock_bh(); -out_kfree_skb: + atomic_long_inc(&dev->tx_dropped); kfree_skb(skb); return rc; out: rcu_read_unlock_bh(); return rc; } + +int dev_queue_xmit(struct sk_buff *skb) +{ + return __dev_queue_xmit(skb, NULL); +} EXPORT_SYMBOL(dev_queue_xmit); +int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) +{ + return __dev_queue_xmit(skb, accel_priv); +} +EXPORT_SYMBOL(dev_queue_xmit_accel); + /*======================================================================= Receiver routines =======================================================================*/ int netdev_max_backlog __read_mostly = 1000; +EXPORT_SYMBOL(netdev_max_backlog); + +int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; int weight_p __read_mostly = 64; /* old backlog weight */ -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); +} + +#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); + +struct static_key rps_needed __read_mostly; + +static struct rps_dev_flow * +set_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow *rflow, u16 next_cpu) +{ + if (next_cpu != RPS_NO_CPU) { +#ifdef CONFIG_RFS_ACCEL + struct netdev_rx_queue *rxqueue; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *old_rflow; + u32 flow_id; + u16 rxq_index; + int rc; + + /* Should we steer this flow to a different hardware queue? */ + if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || + !(dev->features & NETIF_F_NTUPLE)) + goto out; + rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); + if (rxq_index == skb_get_rx_queue(skb)) + goto out; + + rxqueue = dev->_rx + rxq_index; + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (!flow_table) + goto out; + flow_id = skb_get_hash(skb) & flow_table->mask; + rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, + rxq_index, flow_id); + if (rc < 0) + goto out; + old_rflow = rflow; + rflow = &flow_table->flows[flow_id]; + rflow->filter = rc; + if (old_rflow->filter == rflow->filter) + old_rflow->filter = RPS_NO_FILTER; + out: +#endif + rflow->last_qtail = + per_cpu(softnet_data, next_cpu).input_queue_head; + } + + rflow->cpu = next_cpu; + return rflow; +} + +/* + * 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; + u32 hash; + + 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 && + !rcu_access_pointer(rxqueue->rps_flow_table)) { + tcpu = map->cpus[0]; + if (cpu_online(tcpu)) + cpu = tcpu; + goto done; + } + } else if (!rcu_access_pointer(rxqueue->rps_flow_table)) { + goto done; + } + + skb_reset_network_header(skb); + hash = skb_get_hash(skb); + if (!hash) + 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[hash & flow_table->mask]; + tcpu = rflow->cpu; + + next_cpu = sock_flow_table->ents[hash & 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 = next_cpu; + rflow = set_rps_cpu(dev, skb, rflow, next_cpu); + } + + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + *rflowp = rflow; + cpu = tcpu; + goto done; + } + } + + if (map) { + tcpu = map->cpus[((u64) hash * map->len) >> 32]; + if (cpu_online(tcpu)) { + cpu = tcpu; + goto done; + } + } + +done: + return cpu; +} + +#ifdef CONFIG_RFS_ACCEL /** - * netif_rx - post buffer to the network code - * @skb: buffer to post - * - * This function receives a packet from a device driver and queues it for - * the upper (protocol) levels to process. It always succeeds. The buffer - * may be dropped during processing for congestion control or by the - * protocol layers. - * - * return values: - * NET_RX_SUCCESS (no congestion) - * NET_RX_DROP (packet was dropped) + * rps_may_expire_flow - check whether an RFS hardware filter may be removed + * @dev: Device on which the filter was set + * @rxq_index: RX queue index + * @flow_id: Flow ID passed to ndo_rx_flow_steer() + * @filter_id: Filter ID returned by ndo_rx_flow_steer() * + * Drivers that implement ndo_rx_flow_steer() should periodically call + * this function for each installed filter and remove the filters for + * which it returns %true. */ +bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id) +{ + struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *rflow; + bool expire = true; + int cpu; -int netif_rx(struct sk_buff *skb) + rcu_read_lock(); + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (flow_table && flow_id <= flow_table->mask) { + rflow = &flow_table->flows[flow_id]; + cpu = ACCESS_ONCE(rflow->cpu); + if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + ((int)(per_cpu(softnet_data, cpu).input_queue_head - + rflow->last_qtail) < + (int)(10 * flow_table->mask))) + expire = false; + } + rcu_read_unlock(); + return expire; +} +EXPORT_SYMBOL(rps_may_expire_flow); + +#endif /* CONFIG_RFS_ACCEL */ + +/* Called from hardirq (IPI) context */ +static void rps_trigger_softirq(void *data) { - struct softnet_data *queue; - unsigned long flags; + struct softnet_data *sd = data; - /* if netpoll wants it, pretend we never saw it */ - if (netpoll_rx(skb)) - return NET_RX_DROP; + ____napi_schedule(sd, &sd->backlog); + sd->received_rps++; +} - if (!skb->tstamp.tv64) - net_timestamp(skb); +#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; +} + +#ifdef CONFIG_NET_FLOW_LIMIT +int netdev_flow_limit_table_len __read_mostly = (1 << 12); +#endif + +static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) +{ +#ifdef CONFIG_NET_FLOW_LIMIT + struct sd_flow_limit *fl; + struct softnet_data *sd; + unsigned int old_flow, new_flow; + + if (qlen < (netdev_max_backlog >> 1)) + return false; + + sd = &__get_cpu_var(softnet_data); + + rcu_read_lock(); + fl = rcu_dereference(sd->flow_limit); + if (fl) { + new_flow = skb_get_hash(skb) & (fl->num_buckets - 1); + old_flow = fl->history[fl->history_head]; + fl->history[fl->history_head] = new_flow; + + fl->history_head++; + fl->history_head &= FLOW_LIMIT_HISTORY - 1; + + if (likely(fl->buckets[old_flow])) + fl->buckets[old_flow]--; + + if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { + fl->count++; + rcu_read_unlock(); + return true; + } + } + rcu_read_unlock(); +#endif + return false; +} + +/* + * 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; + unsigned int qlen; + + sd = &per_cpu(softnet_data, cpu); - /* - * 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); - __get_cpu_var(netdev_rx_stat).total++; - if (queue->input_pkt_queue.qlen <= netdev_max_backlog) { - if (queue->input_pkt_queue.qlen) { + rps_lock(sd); + qlen = skb_queue_len(&sd->input_pkt_queue); + if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) { + if (skb_queue_len(&sd->input_pkt_queue)) { enqueue: - __skb_queue_tail(&queue->input_pkt_queue, skb); + __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; } - napi_schedule(&queue->backlog); + /* 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; } - __get_cpu_var(netdev_rx_stat).dropped++; + sd->dropped++; + rps_unlock(sd); + local_irq_restore(flags); + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } + +static int netif_rx_internal(struct sk_buff *skb) +{ + int ret; + + net_timestamp_check(netdev_tstamp_prequeue, skb); + + trace_netif_rx(skb); +#ifdef CONFIG_RPS + if (static_key_false(&rps_needed)) { + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + + preempt_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); + if (cpu < 0) + cpu = smp_processor_id(); + + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); + preempt_enable(); + } else +#endif + { + unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); + } + return ret; +} + +/** + * netif_rx - post buffer to the network code + * @skb: buffer to post + * + * This function receives a packet from a device driver and queues it for + * the upper (protocol) levels to process. It always succeeds. The buffer + * may be dropped during processing for congestion control or by the + * protocol layers. + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + */ + +int netif_rx(struct sk_buff *skb) +{ + trace_netif_rx_entry(skb); + + return netif_rx_internal(skb); +} EXPORT_SYMBOL(netif_rx); int netif_rx_ni(struct sk_buff *skb) { int err; + trace_netif_rx_ni_entry(skb); + preempt_disable(); - err = netif_rx(skb); + err = netif_rx_internal(skb); if (local_softirq_pending()) do_softirq(); preempt_enable(); @@ -2200,6 +3370,10 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); + if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) + trace_consume_skb(skb); + else + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } @@ -2210,6 +3384,7 @@ 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) { @@ -2220,7 +3395,7 @@ static void net_tx_action(struct softirq_action *h) root_lock = qdisc_lock(q); if (spin_trylock(root_lock)) { - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); @@ -2230,7 +3405,7 @@ static void net_tx_action(struct softirq_action *h) &q->state)) { __netif_reschedule(q); } else { - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(__QDISC_STATE_SCHED, &q->state); } @@ -2239,103 +3414,39 @@ 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_GPL(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_GPL(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) -#endif - #ifdef CONFIG_NET_CLS_ACT /* TODO: Maybe we should just force sch_ingress to be compiled in * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions * a compare and 2 stores extra right now if we dont have it on * but have CONFIG_NET_CLS_ACT - * NOTE: This doesnt stop any functionality; if you dont have - * the ingress scheduler, you just cant add policies on ingress. + * NOTE: This doesn't stop any functionality; if you dont have + * the ingress scheduler, you just can't 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->skb_iif, dev->ifindex); + if (unlikely(MAX_RED_LOOP < ttl++)) { + net_warn_ratelimited("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)); @@ -2351,18 +3462,17 @@ 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); @@ -2375,88 +3485,114 @@ 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 handler 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. + * + * For a general description of rx_handler, see enum rx_handler_result. */ -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; + /* Note: rx_handler_data must be set before rx_handler */ + 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 + * netdev_rx_handler_unregister - unregister receive handler + * @dev: device to unregister a handler from * - * 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. + * Unregister a receive handler from a device. * - * 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 + * 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_INIT_POINTER(dev->rx_handler, NULL); + /* a reader seeing a non NULL rx_handler in a rcu_read_lock() + * section has a guarantee to see a non NULL rx_handler_data + * as well. + */ + synchronize_net(); + RCU_INIT_POINTER(dev->rx_handler_data, NULL); +} +EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); + +/* + * Limit the use of PFMEMALLOC reserves to those protocols that implement + * the special handling of PFMEMALLOC skbs. + */ +static bool skb_pfmemalloc_protocol(struct sk_buff *skb) +{ + switch (skb->protocol) { + case htons(ETH_P_ARP): + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_8021Q): + case htons(ETH_P_8021AD): + return true; + default: + return false; + } +} + +static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc) { struct packet_type *ptype, *pt_prev; + rx_handler_func_t *rx_handler; struct net_device *orig_dev; - struct net_device *null_or_orig; + struct net_device *null_or_dev; + bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; - if (!skb->tstamp.tv64) - net_timestamp(skb); - - if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb)) - return NET_RX_SUCCESS; - - /* if we've gotten here through NAPI, check netpoll */ - if (netpoll_receive_skb(skb)) - return NET_RX_DROP; + net_timestamp_check(!netdev_tstamp_prequeue, skb); - if (!skb->skb_iif) - skb->skb_iif = skb->dev->ifindex; + trace_netif_receive_skb(skb); - null_or_orig = NULL; orig_dev = skb->dev; - if (orig_dev->master) { - if (skb_bond_should_drop(skb)) - null_or_orig = orig_dev; /* deliver only exact match */ - else - skb->dev = orig_dev->master; - } - - __get_cpu_var(netdev_rx_stat).total++; skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; + if (!skb_transport_header_was_set(skb)) + skb_reset_transport_header(skb); + skb_reset_mac_len(skb); pt_prev = NULL; rcu_read_lock(); +another_round: + skb->skb_iif = skb->dev->ifindex; + + __this_cpu_inc(softnet_data.processed); + + if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || + skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + skb = vlan_untag(skb); + if (unlikely(!skb)) + goto unlock; + } + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -2464,34 +3600,78 @@ int netif_receive_skb(struct sk_buff *skb) } #endif + if (pfmemalloc) + goto skip_taps; + list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (ptype->dev == null_or_orig || ptype->dev == skb->dev || - ptype->dev == orig_dev) { + if (!ptype->dev || ptype->dev == skb->dev) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } } +skip_taps: #ifdef CONFIG_NET_CLS_ACT skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto out; + goto unlock; 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; + if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) + goto drop; + + if (vlan_tx_tag_present(skb)) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + if (vlan_do_receive(&skb)) + goto another_round; + else if (unlikely(!skb)) + goto unlock; + } + + 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; + } + switch (rx_handler(&skb)) { + case RX_HANDLER_CONSUMED: + ret = NET_RX_SUCCESS; + goto unlock; + case RX_HANDLER_ANOTHER: + goto another_round; + case RX_HANDLER_EXACT: + deliver_exact = true; + case RX_HANDLER_PASS: + break; + default: + BUG(); + } + } + + if (unlikely(vlan_tx_tag_present(skb))) { + if (vlan_tx_tag_get_id(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* Note: we might in the future use prio bits + * and set skb->priority like in vlan_do_receive() + * For the time being, just ignore Priority Code Point + */ + skb->vlan_tci = 0; + } + + /* deliver only exact match when indicated */ + null_or_dev = deliver_exact ? skb->dev : NULL; 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 == null_or_dev || ptype->dev == skb->dev || ptype->dev == orig_dev)) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); @@ -2500,8 +3680,13 @@ ncls: } if (pt_prev) { - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + goto drop; + else + ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { +drop: + 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. :-) @@ -2509,33 +3694,123 @@ ncls: ret = NET_RX_DROP; } -out: +unlock: rcu_read_unlock(); return ret; } + +static int __netif_receive_skb(struct sk_buff *skb) +{ + int ret; + + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { + unsigned long pflags = current->flags; + + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + current->flags |= PF_MEMALLOC; + ret = __netif_receive_skb_core(skb, true); + tsk_restore_flags(current, pflags, PF_MEMALLOC); + } else + ret = __netif_receive_skb_core(skb, false); + + return ret; +} + +static int netif_receive_skb_internal(struct sk_buff *skb) +{ + net_timestamp_check(netdev_tstamp_prequeue, skb); + + if (skb_defer_rx_timestamp(skb)) + return NET_RX_SUCCESS; + +#ifdef CONFIG_RPS + if (static_key_false(&rps_needed)) { + 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(); + return ret; + } + rcu_read_unlock(); + } +#endif + return __netif_receive_skb(skb); +} + +/** + * 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) +{ + trace_netif_receive_skb_entry(skb); + + return netif_receive_skb_internal(skb); +} EXPORT_SYMBOL(netif_receive_skb); -/* Network device is going away, flush any packets still pending */ +/* 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, &queue->input_pkt_queue); + __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, &sd->process_queue); + kfree_skb(skb); + input_queue_head_incr(sd); + } + } } static int napi_gro_complete(struct sk_buff *skb) { - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + struct list_head *head = &offload_base; int err = -ENOENT; + BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); + if (NAPI_GRO_CB(skb)->count == 1) { skb_shinfo(skb)->gso_size = 0; goto out; @@ -2543,10 +3818,10 @@ static int napi_gro_complete(struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_complete) + if (ptype->type != type || !ptype->callbacks.gro_complete) continue; - err = ptype->gro_complete(skb); + err = ptype->callbacks.gro_complete(skb, 0); break; } rcu_read_unlock(); @@ -2558,53 +3833,137 @@ static int napi_gro_complete(struct sk_buff *skb) } out: - return netif_receive_skb(skb); + return netif_receive_skb_internal(skb); } -void napi_gro_flush(struct napi_struct *napi) +/* napi->gro_list contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) { - struct sk_buff *skb, *next; + struct sk_buff *skb, *prev = NULL; + + /* scan list and build reverse chain */ + for (skb = napi->gro_list; skb != NULL; skb = skb->next) { + skb->prev = prev; + prev = skb; + } - for (skb = napi->gro_list; skb; skb = next) { - next = skb->next; + for (skb = prev; skb; skb = prev) { skb->next = NULL; + + if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) + return; + + prev = skb->prev; napi_gro_complete(skb); + napi->gro_count--; } - napi->gro_count = 0; napi->gro_list = NULL; } EXPORT_SYMBOL(napi_gro_flush); -enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) +{ + struct sk_buff *p; + unsigned int maclen = skb->dev->hard_header_len; + u32 hash = skb_get_hash_raw(skb); + + for (p = napi->gro_list; p; p = p->next) { + unsigned long diffs; + + NAPI_GRO_CB(p)->flush = 0; + + if (hash != skb_get_hash_raw(p)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= p->vlan_tci ^ skb->vlan_tci; + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_mac_header(skb), + maclen); + NAPI_GRO_CB(p)->same_flow = !diffs; + } +} + +static void skb_gro_reset_offset(struct sk_buff *skb) +{ + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (skb_mac_header(skb) == skb_tail_pointer(skb) && + pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0); + } +} + +static void gro_pull_from_frag0(struct sk_buff *skb, int grow) +{ + struct skb_shared_info *pinfo = skb_shinfo(skb); + + BUG_ON(skb->end - skb->tail < grow); + + memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); + + skb->data_len -= grow; + skb->tail += grow; + + pinfo->frags[0].page_offset += grow; + skb_frag_size_sub(&pinfo->frags[0], grow); + + if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { + skb_frag_unref(skb, 0); + memmove(pinfo->frags, pinfo->frags + 1, + --pinfo->nr_frags * sizeof(pinfo->frags[0])); + } +} + +static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; - struct packet_type *ptype; + struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; + struct list_head *head = &offload_base; int same_flow; - int mac_len; enum gro_result ret; + int grow; if (!(skb->dev->features & NETIF_F_GRO)) goto normal; - if (skb_is_gso(skb) || skb_has_frags(skb)) + if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; + gro_list_prepare(napi, skb); + NAPI_GRO_CB(skb)->csum = skb->csum; /* Needed for CHECKSUM_COMPLETE */ + rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || ptype->dev || !ptype->gro_receive) + if (ptype->type != type || !ptype->callbacks.gro_receive) continue; skb_set_network_header(skb, skb_gro_offset(skb)); - mac_len = skb->network_header - skb->mac_header; - skb->mac_len = mac_len; + skb_reset_mac_len(skb); NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->udp_mark = 0; - pp = ptype->gro_receive(&napi->gro_list, skb); + pp = ptype->callbacks.gro_receive(&napi->gro_list, skb); break; } rcu_read_unlock(); @@ -2627,38 +3986,35 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) if (same_flow) goto ok; - if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS) + if (NAPI_GRO_CB(skb)->flush) goto normal; - napi->gro_count++; + if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { + struct sk_buff *nskb = napi->gro_list; + + /* locate the end of the list to select the 'oldest' flow */ + while (nskb->next) { + pp = &nskb->next; + nskb = *pp; + } + *pp = NULL; + nskb->next = NULL; + napi_gro_complete(nskb); + } else { + napi->gro_count++; + } NAPI_GRO_CB(skb)->count = 1; + NAPI_GRO_CB(skb)->age = jiffies; + NAPI_GRO_CB(skb)->last = skb; skb_shinfo(skb)->gso_size = skb_gro_len(skb); skb->next = napi->gro_list; napi->gro_list = skb; ret = GRO_HELD; pull: - if (skb_headlen(skb) < skb_gro_offset(skb)) { - int grow = skb_gro_offset(skb) - skb_headlen(skb); - - BUG_ON(skb->end - skb->tail < grow); - - memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); - - skb->tail += grow; - skb->data_len -= grow; - - skb_shinfo(skb)->frags[0].page_offset += grow; - skb_shinfo(skb)->frags[0].size -= grow; - - if (unlikely(!skb_shinfo(skb)->frags[0].size)) { - put_page(skb_shinfo(skb)->frags[0].page); - memmove(skb_shinfo(skb)->frags, - skb_shinfo(skb)->frags + 1, - --skb_shinfo(skb)->nr_frags); - } - } - + grow = skb_gro_offset(skb) - skb_headlen(skb); + if (grow > 0) + gro_pull_from_frag0(skb, grow); ok: return ret; @@ -2666,40 +4022,54 @@ normal: ret = GRO_NORMAL; goto pull; } -EXPORT_SYMBOL(dev_gro_receive); -static gro_result_t -__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +struct packet_offload *gro_find_receive_by_type(__be16 type) { - struct sk_buff *p; - - if (netpoll_rx_on(skb)) - return GRO_NORMAL; + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; - 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)); - NAPI_GRO_CB(p)->flush = 0; + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + return ptype; } + return NULL; +} +EXPORT_SYMBOL(gro_find_receive_by_type); + +struct packet_offload *gro_find_complete_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; - return dev_gro_receive(napi, skb); + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + return ptype; + } + return NULL; } +EXPORT_SYMBOL(gro_find_complete_by_type); -gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb(skb)) + if (netif_receive_skb_internal(skb)) ret = GRO_DROP; break; case GRO_DROP: - case GRO_MERGED_FREE: kfree_skb(skb); break; + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + kmem_cache_free(skbuff_head_cache, skb); + else + __kfree_skb(skb); + break; + case GRO_HELD: case GRO_MERGED: break; @@ -2707,40 +4077,31 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) return ret; } -EXPORT_SYMBOL(napi_skb_finish); - -void skb_gro_reset_offset(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (skb->mac_header == skb->tail && - !PageHighMem(skb_shinfo(skb)->frags[0].page)) { - NAPI_GRO_CB(skb)->frag0 = - page_address(skb_shinfo(skb)->frags[0].page) + - skb_shinfo(skb)->frags[0].page_offset; - NAPI_GRO_CB(skb)->frag0_len = skb_shinfo(skb)->frags[0].size; - } -} -EXPORT_SYMBOL(skb_gro_reset_offset); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { + trace_napi_gro_receive_entry(skb); + skb_gro_reset_offset(skb); - return napi_skb_finish(__napi_gro_receive(napi, skb), skb); + return napi_skb_finish(dev_gro_receive(napi, skb), 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)); + /* restore the reserve we had after netdev_alloc_skb_ip_align() */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); + skb->vlan_tci = 0; + skb->dev = napi->dev; + skb->skb_iif = 0; + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); napi->skb = skb; } -EXPORT_SYMBOL(napi_reuse_skb); struct sk_buff *napi_get_frags(struct napi_struct *napi) { @@ -2748,24 +4109,22 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) if (!skb) { skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); - if (skb) - napi->skb = skb; + napi->skb = skb; } return skb; } EXPORT_SYMBOL(napi_get_frags); -gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, - gro_result_t ret) +static gro_result_t napi_frags_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) { switch (ret) { case GRO_NORMAL: case GRO_HELD: - skb->protocol = eth_type_trans(skb, napi->dev); - - if (ret == GRO_HELD) - skb_gro_pull(skb, -ETH_HLEN); - else if (netif_receive_skb(skb)) + __skb_push(skb, ETH_HLEN); + skb->protocol = eth_type_trans(skb, skb->dev); + if (ret == GRO_NORMAL && netif_receive_skb_internal(skb)) ret = GRO_DROP; break; @@ -2780,44 +4139,45 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, return ret; } -EXPORT_SYMBOL(napi_frags_finish); -struct sk_buff *napi_frags_skb(struct napi_struct *napi) +/* Upper GRO stack assumes network header starts at gro_offset=0 + * Drivers could call both napi_gro_frags() and napi_gro_receive() + * We copy ethernet header into skb->data to have a common layout. + */ +static struct sk_buff *napi_frags_skb(struct napi_struct *napi) { struct sk_buff *skb = napi->skb; - struct ethhdr *eth; - unsigned int hlen; - unsigned int off; + const struct ethhdr *eth; + unsigned int hlen = sizeof(*eth); napi->skb = NULL; skb_reset_mac_header(skb); skb_gro_reset_offset(skb); - off = skb_gro_offset(skb); - hlen = off + sizeof(*eth); - eth = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) { - eth = skb_gro_header_slow(skb, hlen, off); + eth = skb_gro_header_fast(skb, 0); + if (unlikely(skb_gro_header_hard(skb, hlen))) { + eth = skb_gro_header_slow(skb, hlen, 0); if (unlikely(!eth)) { napi_reuse_skb(napi, skb); - skb = NULL; - goto out; + return NULL; } + } else { + gro_pull_from_frag0(skb, hlen); + NAPI_GRO_CB(skb)->frag0 += hlen; + NAPI_GRO_CB(skb)->frag0_len -= hlen; } - - skb_gro_pull(skb, sizeof(*eth)); + __skb_pull(skb, hlen); /* * This works because the only protocols we care about don't require - * special handling. We'll fix it up properly at the end. + * special handling. + * We'll fix it up properly in napi_frags_finish() */ skb->protocol = eth->h_proto; -out: return skb; } -EXPORT_SYMBOL(napi_frags_skb); gro_result_t napi_gro_frags(struct napi_struct *napi) { @@ -2826,31 +4186,92 @@ gro_result_t napi_gro_frags(struct napi_struct *napi) if (!skb) return GRO_DROP; - return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb)); + trace_napi_gro_frags_entry(skb); + + return napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); } EXPORT_SYMBOL(napi_gro_frags); +/* + * net_rps_action_and_irq_enable 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_async(remsd->cpu, + &remsd->csd); + 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 (1) { struct sk_buff *skb; - 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(); + __netif_receive_skb(skb); + local_irq_disable(); + input_queue_head_incr(sd); + if (++work >= quota) { + local_irq_enable(); + return work; + } + } + + rps_lock(sd); + if (skb_queue_empty(&sd->input_pkt_queue)) { + /* + * 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; + rps_unlock(sd); + break; } - local_irq_enable(); - netif_receive_skb(skb); - } while (++work < quota && jiffies == start_time); + skb_queue_splice_tail_init(&sd->input_pkt_queue, + &sd->process_queue); + rps_unlock(sd); + } + local_irq_enable(); return work; } @@ -2866,8 +4287,7 @@ 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); @@ -2878,7 +4298,7 @@ void __napi_complete(struct napi_struct *n) BUG_ON(n->gro_list); list_del(&n->poll_list); - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); } EXPORT_SYMBOL(__napi_complete); @@ -2894,13 +4314,65 @@ void napi_complete(struct napi_struct *n) if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state))) return; - napi_gro_flush(n); + napi_gro_flush(n, false); local_irq_save(flags); __napi_complete(n); local_irq_restore(flags); } EXPORT_SYMBOL(napi_complete); +/* must be called under rcu_read_lock(), as we dont take a reference */ +struct napi_struct *napi_by_id(unsigned int napi_id) +{ + unsigned int hash = napi_id % HASH_SIZE(napi_hash); + struct napi_struct *napi; + + hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) + if (napi->napi_id == napi_id) + return napi; + + return NULL; +} +EXPORT_SYMBOL_GPL(napi_by_id); + +void napi_hash_add(struct napi_struct *napi) +{ + if (!test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) { + + spin_lock(&napi_hash_lock); + + /* 0 is not a valid id, we also skip an id that is taken + * we expect both events to be extremely rare + */ + napi->napi_id = 0; + while (!napi->napi_id) { + napi->napi_id = ++napi_gen_id; + if (napi_by_id(napi->napi_id)) + napi->napi_id = 0; + } + + hlist_add_head_rcu(&napi->napi_hash_node, + &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); + + spin_unlock(&napi_hash_lock); + } +} +EXPORT_SYMBOL_GPL(napi_hash_add); + +/* Warning : caller is responsible to make sure rcu grace period + * is respected before freeing memory containing @napi + */ +void napi_hash_del(struct napi_struct *napi) +{ + spin_lock(&napi_hash_lock); + + if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) + hlist_del_rcu(&napi->napi_hash_node); + + spin_unlock(&napi_hash_lock); +} +EXPORT_SYMBOL_GPL(napi_hash_del); + void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { @@ -2909,6 +4381,9 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->gro_list = NULL; napi->skb = NULL; napi->poll = poll; + if (weight > NAPI_POLL_WEIGHT) + pr_err_once("netif_napi_add() called with weight %d on device %s\n", + weight, dev->name); napi->weight = weight; list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; @@ -2922,33 +4397,25 @@ EXPORT_SYMBOL(netif_napi_add); void netif_napi_del(struct napi_struct *napi) { - struct sk_buff *skb, *next; - list_del_init(&napi->dev_list); napi_free_frags(napi); - for (skb = napi->gro_list; skb; skb = next) { - next = skb->next; - skb->next = NULL; - kfree_skb(skb); - } - + kfree_skb_list(napi->gro_list); napi->gro_list = NULL; napi->gro_count = 0; } 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; @@ -2956,7 +4423,7 @@ static void net_rx_action(struct softirq_action *h) * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ - if (unlikely(budget <= 0 || time_after(jiffies, time_limit))) + if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) goto softnet_break; local_irq_enable(); @@ -2966,7 +4433,7 @@ 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); @@ -2976,7 +4443,7 @@ static void net_rx_action(struct softirq_action *h) * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid - * accidently calling ->poll() when NAPI is not scheduled. + * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (test_bit(NAPI_STATE_SCHED, &n->state)) { @@ -3000,14 +4467,23 @@ static void net_rx_action(struct softirq_action *h) local_irq_enable(); napi_complete(n); local_irq_disable(); - } else - list_move_tail(&n->poll_list, list); + } else { + if (n->gro_list) { + /* flush too old packets + * If HZ < 1000, flush all packets. + */ + local_irq_enable(); + napi_gro_flush(n, HZ >= 1000); + local_irq_disable(); + } + 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 /* @@ -3020,493 +4496,726 @@ 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]; +struct netdev_adjacent { + struct net_device *dev; + + /* upper master flag, there can only be one master device per list */ + bool master; + + /* counter for the number of times this device was added to us */ + u16 ref_nr; + + /* private field for the users */ + void *private; + + struct list_head list; + struct rcu_head rcu; +}; + +static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *adj_list) +{ + struct netdev_adjacent *adj; + + list_for_each_entry(adj, adj_list, list) { + if (adj->dev == adj_dev) + return adj; + } + return NULL; +} /** - * register_gifconf - register a SIOCGIF handler - * @family: Address family - * @gifconf: Function handler + * netdev_has_upper_dev - Check if device is linked to an upper device + * @dev: device + * @upper_dev: upper device to check * - * Register protocol dependent address dumping routines. The handler - * that is passed must not be freed or reused until it has been replaced - * by another handler. + * Find out if a device is linked to specified upper device and return true + * in case it is. Note that this checks only immediate upper device, + * not through a complete stack of devices. The caller must hold the RTNL lock. */ -int register_gifconf(unsigned int family, gifconf_func_t *gifconf) +bool netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) { - if (family >= NPROTO) - return -EINVAL; - gifconf_list[family] = gifconf; - return 0; -} -EXPORT_SYMBOL(register_gifconf); + ASSERT_RTNL(); + return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper); +} +EXPORT_SYMBOL(netdev_has_upper_dev); -/* - * Map an interface index to its name (SIOCGIFNAME) +/** + * netdev_has_any_upper_dev - Check if device is linked to some device + * @dev: device + * + * Find out if a device is linked to an upper device and return true in case + * it is. The caller must hold the RTNL lock. */ +static bool netdev_has_any_upper_dev(struct net_device *dev) +{ + ASSERT_RTNL(); -/* - * We need this ioctl for efficient implementation of the - * if_indextoname() function required by the IPv6 API. Without - * it, we would have to search all the interfaces to find a - * match. --pb - */ + return !list_empty(&dev->all_adj_list.upper); +} -static int dev_ifname(struct net *net, struct ifreq __user *arg) +/** + * netdev_master_upper_dev_get - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RTNL lock. + */ +struct net_device *netdev_master_upper_dev_get(struct net_device *dev) { - struct net_device *dev; - struct ifreq ifr; + struct netdev_adjacent *upper; - /* - * Fetch the caller's info block. - */ + ASSERT_RTNL(); - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; + if (list_empty(&dev->adj_list.upper)) + return NULL; - rcu_read_lock(); - dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); - if (!dev) { - rcu_read_unlock(); - return -ENODEV; - } + upper = list_first_entry(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (likely(upper->master)) + return upper->dev; + return NULL; +} +EXPORT_SYMBOL(netdev_master_upper_dev_get); - strcpy(ifr.ifr_name, dev->name); - rcu_read_unlock(); +void *netdev_adjacent_get_private(struct list_head *adj_list) +{ + struct netdev_adjacent *adj; - if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) - return -EFAULT; - return 0; + adj = list_entry(adj_list, struct netdev_adjacent, list); + + return adj->private; } +EXPORT_SYMBOL(netdev_adjacent_get_private); -/* - * Perform a SIOCGIFCONF call. This structure will change - * size eventually, and there is nothing I can do about it. - * Thus we will need a 'compatibility mode'. +/** + * netdev_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. */ - -static int dev_ifconf(struct net *net, char __user *arg) +struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) { - struct ifconf ifc; - struct net_device *dev; - char __user *pos; - int len; - int total; - int i; + struct netdev_adjacent *upper; - /* - * Fetch the caller's info block. - */ + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - if (copy_from_user(&ifc, arg, sizeof(struct ifconf))) - return -EFAULT; - - pos = ifc.ifc_buf; - len = ifc.ifc_len; - - /* - * Loop over the interfaces, and write an info block for each. - */ + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); - total = 0; - for_each_netdev(net, dev) { - for (i = 0; i < NPROTO; i++) { - if (gifconf_list[i]) { - int done; - if (!pos) - done = gifconf_list[i](dev, NULL, 0); - else - done = gifconf_list[i](dev, pos + total, - len - total); - if (done < 0) - return -EFAULT; - total += done; - } - } - } + if (&upper->list == &dev->adj_list.upper) + return NULL; - /* - * All done. Write the updated control block back to the caller. - */ - ifc.ifc_len = total; + *iter = &upper->list; - /* - * Both BSD and Solaris return 0 here, so we do too. - */ - return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0; + return upper->dev; } +EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); -#ifdef CONFIG_PROC_FS -/* - * This is invoked by the /proc filesystem handler to display a device - * in detail. +/** + * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next device from the dev's upper list, starting from iter + * position. The caller must hold RCU read lock. */ -void *dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) +struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, + struct list_head **iter) { - struct net *net = seq_file_net(seq); - loff_t off; - struct net_device *dev; + struct netdev_adjacent *upper; - rcu_read_lock(); - if (!*pos) - return SEQ_START_TOKEN; + WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); - off = 1; - for_each_netdev_rcu(net, dev) - if (off++ == *pos) - return dev; + upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); - return NULL; -} + if (&upper->list == &dev->all_adj_list.upper) + return NULL; -void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct net_device *dev = (v == SEQ_START_TOKEN) ? - first_net_device(seq_file_net(seq)) : - next_net_device((struct net_device *)v); + *iter = &upper->list; - ++*pos; - return rcu_dereference(dev); + return upper->dev; } +EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu); -void dev_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) +/** + * netdev_lower_get_next_private - Get the next ->private from the + * lower neighbour list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold either hold the + * RTNL lock or its own locking that guarantees that the neighbour lower + * list will remain unchainged. + */ +void *netdev_lower_get_next_private(struct net_device *dev, + struct list_head **iter) { - rcu_read_unlock(); + struct netdev_adjacent *lower; + + lower = list_entry(*iter, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = lower->list.next; + + return lower->private; } +EXPORT_SYMBOL(netdev_lower_get_next_private); -static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) +/** + * netdev_lower_get_next_private_rcu - Get the next ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent->private from the dev's lower neighbour + * list, starting from iter position. The caller must hold RCU read lock. + */ +void *netdev_lower_get_next_private_rcu(struct net_device *dev, + struct list_head **iter) { - const struct net_device_stats *stats = dev_get_stats(dev); + struct netdev_adjacent *lower; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; - seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " - "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", - dev->name, stats->rx_bytes, stats->rx_packets, - stats->rx_errors, - stats->rx_dropped + stats->rx_missed_errors, - stats->rx_fifo_errors, - stats->rx_length_errors + stats->rx_over_errors + - stats->rx_crc_errors + stats->rx_frame_errors, - stats->rx_compressed, stats->multicast, - stats->tx_bytes, stats->tx_packets, - stats->tx_errors, stats->tx_dropped, - stats->tx_fifo_errors, stats->collisions, - stats->tx_carrier_errors + - stats->tx_aborted_errors + - stats->tx_window_errors + - stats->tx_heartbeat_errors, - stats->tx_compressed); + return lower->private; } +EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); -/* - * Called from the PROCfs module. This now uses the new arbitrary sized - * /proc/net interface to create /proc/net/dev +/** + * netdev_lower_get_next - Get the next device from the lower neighbour + * list + * @dev: device + * @iter: list_head ** of the current position + * + * Gets the next netdev_adjacent from the dev's lower neighbour + * list, starting from iter position. The caller must hold RTNL lock or + * its own locking that guarantees that the neighbour lower + * list will remain unchainged. */ -static int dev_seq_show(struct seq_file *seq, void *v) -{ - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Inter-| Receive " - " | Transmit\n" - " face |bytes packets errs drop fifo frame " - "compressed multicast|bytes packets errs " - "drop fifo colls carrier compressed\n"); - else - dev_seq_printf_stats(seq, v); - return 0; +void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + + return lower->dev; } +EXPORT_SYMBOL(netdev_lower_get_next); -static struct netif_rx_stats *softnet_get_online(loff_t *pos) +/** + * netdev_lower_get_first_private_rcu - Get the first ->private from the + * lower neighbour list, RCU + * variant + * @dev: device + * + * Gets the first netdev_adjacent->private from the dev's lower neighbour + * list. The caller must hold RCU read lock. + */ +void *netdev_lower_get_first_private_rcu(struct net_device *dev) { - struct netif_rx_stats *rc = NULL; + struct netdev_adjacent *lower; - while (*pos < nr_cpu_ids) - if (cpu_online(*pos)) { - rc = &per_cpu(netdev_rx_stat, *pos); - break; - } else - ++*pos; - return rc; + lower = list_first_or_null_rcu(&dev->adj_list.lower, + struct netdev_adjacent, list); + if (lower) + return lower->private; + return NULL; } +EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); -static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) +/** + * netdev_master_upper_dev_get_rcu - Get master upper device + * @dev: device + * + * Find a master upper device and return pointer to it or NULL in case + * it's not there. The caller must hold the RCU read lock. + */ +struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { - return softnet_get_online(pos); + struct netdev_adjacent *upper; + + upper = list_first_or_null_rcu(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (upper && likely(upper->master)) + return upper->dev; + return NULL; } +EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); -static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static int netdev_adjacent_sysfs_add(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) { - ++*pos; - return softnet_get_online(pos); + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", adj_dev->name); + return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), + linkname); } - -static void softnet_seq_stop(struct seq_file *seq, void *v) +static void netdev_adjacent_sysfs_del(struct net_device *dev, + char *name, + struct list_head *dev_list) { + char linkname[IFNAMSIZ+7]; + sprintf(linkname, dev_list == &dev->adj_list.upper ? + "upper_%s" : "lower_%s", name); + sysfs_remove_link(&(dev->dev.kobj), linkname); } -static int softnet_seq_show(struct seq_file *seq, void *v) +#define netdev_adjacent_is_neigh_list(dev, dev_list) \ + (dev_list == &dev->adj_list.upper || \ + dev_list == &dev->adj_list.lower) + +static int __netdev_adjacent_dev_insert(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list, + void *private, bool master) { - struct netif_rx_stats *s = v; + struct netdev_adjacent *adj; + int ret; + + adj = __netdev_find_adj(dev, adj_dev, dev_list); + + if (adj) { + adj->ref_nr++; + return 0; + } + + adj = kmalloc(sizeof(*adj), GFP_KERNEL); + if (!adj) + return -ENOMEM; + + adj->dev = adj_dev; + adj->master = master; + adj->ref_nr = 1; + adj->private = private; + dev_hold(adj_dev); + + pr_debug("dev_hold for %s, because of link added from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); + + if (netdev_adjacent_is_neigh_list(dev, dev_list)) { + ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); + if (ret) + goto free_adj; + } + + /* Ensure that master link is always the first item in list. */ + if (master) { + ret = sysfs_create_link(&(dev->dev.kobj), + &(adj_dev->dev.kobj), "master"); + if (ret) + goto remove_symlinks; + + list_add_rcu(&adj->list, dev_list); + } else { + list_add_tail_rcu(&adj->list, dev_list); + } - seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n", - s->total, s->dropped, s->time_squeeze, 0, - 0, 0, 0, 0, /* was fastroute */ - s->cpu_collision); return 0; -} -static const struct seq_operations dev_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_seq_show, -}; +remove_symlinks: + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); +free_adj: + kfree(adj); + dev_put(adj_dev); -static int dev_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_seq_ops, - sizeof(struct seq_net_private)); + return ret; } -static const struct file_operations dev_seq_fops = { - .owner = THIS_MODULE, - .open = dev_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; +static void __netdev_adjacent_dev_remove(struct net_device *dev, + struct net_device *adj_dev, + struct list_head *dev_list) +{ + struct netdev_adjacent *adj; -static const struct seq_operations softnet_seq_ops = { - .start = softnet_seq_start, - .next = softnet_seq_next, - .stop = softnet_seq_stop, - .show = softnet_seq_show, -}; + adj = __netdev_find_adj(dev, adj_dev, dev_list); -static int softnet_seq_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &softnet_seq_ops); -} + if (!adj) { + pr_err("tried to remove device %s from %s\n", + dev->name, adj_dev->name); + BUG(); + } -static const struct file_operations softnet_seq_fops = { - .owner = THIS_MODULE, - .open = softnet_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; + if (adj->ref_nr > 1) { + pr_debug("%s to %s ref_nr-- = %d\n", dev->name, adj_dev->name, + adj->ref_nr-1); + adj->ref_nr--; + return; + } + + if (adj->master) + sysfs_remove_link(&(dev->dev.kobj), "master"); + + if (netdev_adjacent_is_neigh_list(dev, dev_list)) + netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); + + list_del_rcu(&adj->list); + pr_debug("dev_put for %s, because link removed from %s to %s\n", + adj_dev->name, dev->name, adj_dev->name); + dev_put(adj_dev); + kfree_rcu(adj, rcu); +} -static void *ptype_get_idx(loff_t pos) +static int __netdev_adjacent_dev_link_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list, + void *private, bool master) { - struct packet_type *pt = NULL; - loff_t i = 0; - int t; + int ret; - list_for_each_entry_rcu(pt, &ptype_all, list) { - if (i == pos) - return pt; - ++i; - } + ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, + master); + if (ret) + return ret; - for (t = 0; t < PTYPE_HASH_SIZE; t++) { - list_for_each_entry_rcu(pt, &ptype_base[t], list) { - if (i == pos) - return pt; - ++i; - } + ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, + false); + if (ret) { + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + return ret; } - return NULL; + + return 0; } -static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(RCU) +static int __netdev_adjacent_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - rcu_read_lock(); - return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN; + return __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower, + NULL, false); } -static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) +static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, + struct net_device *upper_dev, + struct list_head *up_list, + struct list_head *down_list) { - struct packet_type *pt; - struct list_head *nxt; - int hash; + __netdev_adjacent_dev_remove(dev, upper_dev, up_list); + __netdev_adjacent_dev_remove(upper_dev, dev, down_list); +} - ++*pos; - if (v == SEQ_START_TOKEN) - return ptype_get_idx(0); +static void __netdev_adjacent_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->all_adj_list.upper, + &upper_dev->all_adj_list.lower); +} - pt = v; - nxt = pt->list.next; - if (pt->type == htons(ETH_P_ALL)) { - if (nxt != &ptype_all) - goto found; - hash = 0; - nxt = ptype_base[0].next; - } else - hash = ntohs(pt->type) & PTYPE_HASH_MASK; +static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, + struct net_device *upper_dev, + void *private, bool master) +{ + int ret = __netdev_adjacent_dev_link(dev, upper_dev); - while (nxt == &ptype_base[hash]) { - if (++hash >= PTYPE_HASH_SIZE) - return NULL; - nxt = ptype_base[hash].next; + if (ret) + return ret; + + ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower, + private, master); + if (ret) { + __netdev_adjacent_dev_unlink(dev, upper_dev); + return ret; } -found: - return list_entry(nxt, struct packet_type, list); + + return 0; } -static void ptype_seq_stop(struct seq_file *seq, void *v) - __releases(RCU) +static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, + struct net_device *upper_dev) { - rcu_read_unlock(); + __netdev_adjacent_dev_unlink(dev, upper_dev); + __netdev_adjacent_dev_unlink_lists(dev, upper_dev, + &dev->adj_list.upper, + &upper_dev->adj_list.lower); } -static int ptype_seq_show(struct seq_file *seq, void *v) +static int __netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev, bool master, + void *private) { - struct packet_type *pt = v; + struct netdev_adjacent *i, *j, *to_i, *to_j; + int ret = 0; - if (v == SEQ_START_TOKEN) - seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { - if (pt->type == htons(ETH_P_ALL)) - seq_puts(seq, "ALL "); - else - seq_printf(seq, "%04x", ntohs(pt->type)); + ASSERT_RTNL(); + + if (dev == upper_dev) + return -EBUSY; + + /* To prevent loops, check if dev is not upper device to upper_dev. */ + if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) + return -EBUSY; + + if (__netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper)) + return -EEXIST; + + if (master && netdev_master_upper_dev_get(dev)) + return -EBUSY; - seq_printf(seq, " %-8s %pF\n", - pt->dev ? pt->dev->name : "", pt->func); + ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private, + master); + if (ret) + return ret; + + /* Now that we linked these devs, make all the upper_dev's + * all_adj_list.upper visible to every dev's all_adj_list.lower an + * versa, and don't forget the devices itself. All of these + * links are non-neighbours. + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { + pr_debug("Interlinking %s with %s, non-neighbour\n", + i->dev->name, j->dev->name); + ret = __netdev_adjacent_dev_link(i->dev, j->dev); + if (ret) + goto rollback_mesh; + } + } + + /* add dev to every upper_dev's upper device */ + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { + pr_debug("linking %s's upper device %s with %s\n", + upper_dev->name, i->dev->name, dev->name); + ret = __netdev_adjacent_dev_link(dev, i->dev); + if (ret) + goto rollback_upper_mesh; + } + + /* add upper_dev to every dev's lower device */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + pr_debug("linking %s's lower device %s with %s\n", dev->name, + i->dev->name, upper_dev->name); + ret = __netdev_adjacent_dev_link(i->dev, upper_dev); + if (ret) + goto rollback_lower_mesh; } + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); return 0; -} -static const struct seq_operations ptype_seq_ops = { - .start = ptype_seq_start, - .next = ptype_seq_next, - .stop = ptype_seq_stop, - .show = ptype_seq_show, -}; +rollback_lower_mesh: + to_i = i; + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + if (i == to_i) + break; + __netdev_adjacent_dev_unlink(i->dev, upper_dev); + } -static int ptype_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &ptype_seq_ops, - sizeof(struct seq_net_private)); -} + i = NULL; -static const struct file_operations ptype_seq_fops = { - .owner = THIS_MODULE, - .open = ptype_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; +rollback_upper_mesh: + to_i = i; + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) { + if (i == to_i) + break; + __netdev_adjacent_dev_unlink(dev, i->dev); + } + i = j = NULL; -static int __net_init dev_proc_net_init(struct net *net) -{ - int rc = -ENOMEM; +rollback_mesh: + to_i = i; + to_j = j; + list_for_each_entry(i, &dev->all_adj_list.lower, list) { + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) { + if (i == to_i && j == to_j) + break; + __netdev_adjacent_dev_unlink(i->dev, j->dev); + } + if (i == to_i) + break; + } - if (!proc_net_fops_create(net, "dev", S_IRUGO, &dev_seq_fops)) - goto out; - if (!proc_net_fops_create(net, "softnet_stat", S_IRUGO, &softnet_seq_fops)) - goto out_dev; - if (!proc_net_fops_create(net, "ptype", S_IRUGO, &ptype_seq_fops)) - goto out_softnet; + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); - if (wext_proc_init(net)) - goto out_ptype; - rc = 0; -out: - return rc; -out_ptype: - proc_net_remove(net, "ptype"); -out_softnet: - proc_net_remove(net, "softnet_stat"); -out_dev: - proc_net_remove(net, "dev"); - goto out; + return ret; } -static void __net_exit dev_proc_net_exit(struct net *net) +/** + * netdev_upper_dev_link - Add a link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. The caller must hold + * the RTNL lock. On a failure a negative errno code is returned. + * On success the reference counts are adjusted and the function + * returns zero. + */ +int netdev_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - wext_proc_exit(net); - - proc_net_remove(net, "ptype"); - proc_net_remove(net, "softnet_stat"); - proc_net_remove(net, "dev"); + return __netdev_upper_dev_link(dev, upper_dev, false, NULL); } +EXPORT_SYMBOL(netdev_upper_dev_link); -static struct pernet_operations __net_initdata dev_proc_ops = { - .init = dev_proc_net_init, - .exit = dev_proc_net_exit, -}; - -static int __init dev_proc_init(void) +/** + * netdev_master_upper_dev_link - Add a master link to the upper device + * @dev: device + * @upper_dev: new upper device + * + * Adds a link to device which is upper to this one. In this case, only + * one master upper device can be linked, although other non-master devices + * might be linked as well. The caller must hold the RTNL lock. + * On a failure a negative errno code is returned. On success the reference + * counts are adjusted and the function returns zero. + */ +int netdev_master_upper_dev_link(struct net_device *dev, + struct net_device *upper_dev) { - return register_pernet_subsys(&dev_proc_ops); + return __netdev_upper_dev_link(dev, upper_dev, true, NULL); } -#else -#define dev_proc_init() 0 -#endif /* CONFIG_PROC_FS */ +EXPORT_SYMBOL(netdev_master_upper_dev_link); +int netdev_master_upper_dev_link_private(struct net_device *dev, + struct net_device *upper_dev, + void *private) +{ + return __netdev_upper_dev_link(dev, upper_dev, true, private); +} +EXPORT_SYMBOL(netdev_master_upper_dev_link_private); /** - * netdev_set_master - set up master/slave pair - * @slave: slave device - * @master: new master device - * - * Changes the master device of the slave. Pass %NULL to break the - * bonding. The caller must hold the RTNL semaphore. On a failure - * a negative errno code is returned. On success the reference counts - * are adjusted, %RTM_NEWLINK is sent to the routing socket and the - * function returns zero. + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device + * + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. */ -int netdev_set_master(struct net_device *slave, struct net_device *master) +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) { - struct net_device *old = slave->master; - + struct netdev_adjacent *i, *j; ASSERT_RTNL(); - if (master) { - if (old) - return -EBUSY; - dev_hold(master); + __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); + + /* Here is the tricky part. We must remove all dev's lower + * devices from all upper_dev's upper devices and vice + * versa, to maintain the graph relationship. + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) + list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) + __netdev_adjacent_dev_unlink(i->dev, j->dev); + + /* remove also the devices itself from lower/upper device + * list + */ + list_for_each_entry(i, &dev->all_adj_list.lower, list) + __netdev_adjacent_dev_unlink(i->dev, upper_dev); + + list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) + __netdev_adjacent_dev_unlink(dev, i->dev); + + call_netdevice_notifiers(NETDEV_CHANGEUPPER, dev); +} +EXPORT_SYMBOL(netdev_upper_dev_unlink); + +void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) +{ + struct netdev_adjacent *iter; + + list_for_each_entry(iter, &dev->adj_list.upper, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.lower); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.lower); } - slave->master = master; + list_for_each_entry(iter, &dev->adj_list.lower, list) { + netdev_adjacent_sysfs_del(iter->dev, oldname, + &iter->dev->adj_list.upper); + netdev_adjacent_sysfs_add(iter->dev, dev, + &iter->dev->adj_list.upper); + } +} - synchronize_net(); +void *netdev_lower_dev_get_private(struct net_device *dev, + struct net_device *lower_dev) +{ + struct netdev_adjacent *lower; - if (old) - dev_put(old); + if (!lower_dev) + return NULL; + lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower); + if (!lower) + return NULL; - if (master) - slave->flags |= IFF_SLAVE; - else - slave->flags &= ~IFF_SLAVE; + return lower->private; +} +EXPORT_SYMBOL(netdev_lower_dev_get_private); - rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE); - return 0; + +int dev_get_nest_level(struct net_device *dev, + bool (*type_check)(struct net_device *dev)) +{ + struct net_device *lower = NULL; + struct list_head *iter; + int max_nest = -1; + int nest; + + ASSERT_RTNL(); + + netdev_for_each_lower_dev(dev, lower, iter) { + nest = dev_get_nest_level(lower, type_check); + if (max_nest < nest) + max_nest = nest; + } + + if (type_check(dev)) + max_nest++; + + return max_nest; } -EXPORT_SYMBOL(netdev_set_master); +EXPORT_SYMBOL(dev_get_nest_level); static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; - if ((dev->flags & IFF_UP) && ops->ndo_change_rx_flags) + if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } -static int __dev_set_promiscuity(struct net_device *dev, int inc) +static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { - unsigned short old_flags = dev->flags; - uid_t uid; - gid_t gid; + unsigned int old_flags = dev->flags; + kuid_t uid; + kgid_t gid; ASSERT_RTNL(); @@ -3521,16 +5230,15 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) dev->flags &= ~IFF_PROMISC; else { dev->promiscuity -= inc; - printk(KERN_WARNING "%s: promiscuity touches roof, " - "set promiscuity failed, promiscuity feature " - "of device might be broken.\n", dev->name); + pr_warn("%s: promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n", + dev->name); return -EOVERFLOW; } } if (dev->flags != old_flags) { - printk(KERN_INFO "device %s %s promiscuous mode\n", - dev->name, (dev->flags & IFF_PROMISC) ? "entered" : - "left"); + pr_info("device %s %s promiscuous mode\n", + dev->name, + dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(current->audit_context, GFP_ATOMIC, @@ -3538,13 +5246,16 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), - audit_get_loginuid(current), - uid, gid, + from_kuid(&init_user_ns, audit_get_loginuid(current)), + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } dev_change_rx_flags(dev, IFF_PROMISC); } + if (notify) + __dev_notify_flags(dev, old_flags, IFF_PROMISC); return 0; } @@ -3561,10 +5272,10 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) */ int dev_set_promiscuity(struct net_device *dev, int inc) { - unsigned short old_flags = dev->flags; + unsigned int old_flags = dev->flags; int err; - err = __dev_set_promiscuity(dev, inc); + err = __dev_set_promiscuity(dev, inc, true); if (err < 0) return err; if (dev->flags != old_flags) @@ -3573,22 +5284,9 @@ int dev_set_promiscuity(struct net_device *dev, int inc) } EXPORT_SYMBOL(dev_set_promiscuity); -/** - * dev_set_allmulti - update allmulti count on a device - * @dev: device - * @inc: modifier - * - * Add or remove reception of all multicast frames to a device. While the - * count in the device remains above zero the interface remains listening - * to all interfaces. Once it hits zero the device reverts back to normal - * filtering operation. A negative @inc value is used to drop the counter - * when releasing a resource needing all multicasts. - * Return 0 if successful or a negative errno code on error. - */ - -int dev_set_allmulti(struct net_device *dev, int inc) +static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) { - unsigned short old_flags = dev->flags; + unsigned int old_flags = dev->flags, old_gflags = dev->gflags; ASSERT_RTNL(); @@ -3603,18 +5301,38 @@ int dev_set_allmulti(struct net_device *dev, int inc) dev->flags &= ~IFF_ALLMULTI; else { dev->allmulti -= inc; - printk(KERN_WARNING "%s: allmulti touches roof, " - "set allmulti failed, allmulti feature of " - "device might be broken.\n", dev->name); + pr_warn("%s: allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n", + dev->name); return -EOVERFLOW; } } if (dev->flags ^ old_flags) { dev_change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); + if (notify) + __dev_notify_flags(dev, old_flags, + dev->gflags ^ old_gflags); } return 0; } + +/** + * dev_set_allmulti - update allmulti count on a device + * @dev: device + * @inc: modifier + * + * Add or remove reception of all multicast frames to a device. While the + * count in the device remains above zero the interface remains listening + * to all interfaces. Once it hits zero the device reverts back to normal + * filtering operation. A negative @inc value is used to drop the counter + * when releasing a resource needing all multicasts. + * Return 0 if successful or a negative errno code on error. + */ + +int dev_set_allmulti(struct net_device *dev, int inc) +{ + return __dev_set_allmulti(dev, inc, true); +} EXPORT_SYMBOL(dev_set_allmulti); /* @@ -3634,23 +5352,21 @@ void __dev_set_rx_mode(struct net_device *dev) if (!netif_device_present(dev)) return; - if (ops->ndo_set_rx_mode) - ops->ndo_set_rx_mode(dev); - else { + if (!(dev->priv_flags & IFF_UNICAST_FLT)) { /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ - if (dev->uc.count > 0 && !dev->uc_promisc) { - __dev_set_promiscuity(dev, 1); - dev->uc_promisc = 1; - } else if (dev->uc.count == 0 && dev->uc_promisc) { - __dev_set_promiscuity(dev, -1); - dev->uc_promisc = 0; + if (!netdev_uc_empty(dev) && !dev->uc_promisc) { + __dev_set_promiscuity(dev, 1, false); + dev->uc_promisc = true; + } else if (netdev_uc_empty(dev) && dev->uc_promisc) { + __dev_set_promiscuity(dev, -1, false); + dev->uc_promisc = false; } - - if (ops->ndo_set_multicast_list) - ops->ndo_set_multicast_list(dev); } + + if (ops->ndo_set_rx_mode) + ops->ndo_set_rx_mode(dev); } void dev_set_rx_mode(struct net_device *dev) @@ -3660,571 +5376,15 @@ 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(); - - netif_addr_lock_bh(dev); - err = __hw_addr_del(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST); - if (!err) - __dev_set_rx_mode(dev); - netif_addr_unlock_bh(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(); - - netif_addr_lock_bh(dev); - err = __hw_addr_add(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST); - if (!err) - __dev_set_rx_mode(dev); - netif_addr_unlock_bh(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; -} -EXPORT_SYMBOL_GPL(__dev_addr_sync); - -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; - } -} -EXPORT_SYMBOL_GPL(__dev_addr_unsync); - -/** - * 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. The source device must be - * locked by netif_tx_lock_bh. - * - * 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; - - if (to->addr_len != from->addr_len) - return -EINVAL; - - netif_addr_lock_bh(to); - err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); - if (!err) - __dev_set_rx_mode(to); - netif_addr_unlock_bh(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) -{ - if (to->addr_len != from->addr_len) - return; - - netif_addr_lock_bh(from); - netif_addr_lock(to); - __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); - __dev_set_rx_mode(to); - netif_addr_unlock(to); - netif_addr_unlock_bh(from); -} -EXPORT_SYMBOL(dev_unicast_unsync); - -static void dev_unicast_flush(struct net_device *dev) -{ - netif_addr_lock_bh(dev); - __hw_addr_flush(&dev->uc); - netif_addr_unlock_bh(dev); -} - -static void dev_unicast_init(struct net_device *dev) -{ - __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 * * Get the combination of flag bits exported through APIs to userspace. */ -unsigned dev_get_flags(const struct net_device *dev) +unsigned int dev_get_flags(const struct net_device *dev) { - unsigned flags; + unsigned int flags; flags = (dev->flags & ~(IFF_PROMISC | IFF_ALLMULTI | @@ -4247,18 +5407,10 @@ unsigned dev_get_flags(const struct net_device *dev) } 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; + unsigned int old_flags = dev->flags; + int ret; ASSERT_RTNL(); @@ -4289,22 +5441,21 @@ 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; + unsigned int old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; - dev_set_promiscuity(dev, inc); + + if (__dev_set_promiscuity(dev, inc, false) >= 0) + if (dev->flags != old_flags) + dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI @@ -4315,18 +5466,71 @@ int dev_change_flags(struct net_device *dev, unsigned flags) int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; - dev_set_allmulti(dev, inc); + __dev_set_allmulti(dev, inc, false); + } + + return ret; +} + +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, + unsigned int gchanges) +{ + unsigned int changes = dev->flags ^ old_flags; + + if (gchanges) + rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); + + if (changes & IFF_UP) { + if (dev->flags & IFF_UP) + call_netdevice_notifiers(NETDEV_UP, dev); + else + call_netdevice_notifiers(NETDEV_DOWN, dev); } - /* Exclude state transition flags, already notified */ - changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING); - if (changes) - rtmsg_ifinfo(RTM_NEWLINK, dev, changes); + if (dev->flags & IFF_UP && + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { + struct netdev_notifier_change_info change_info; + + change_info.flags_changed = changes; + call_netdevice_notifiers_info(NETDEV_CHANGE, dev, + &change_info.info); + } +} + +/** + * 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 int flags) +{ + int ret; + unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; + + ret = __dev_change_flags(dev, flags); + if (ret < 0) + return ret; + changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); + __dev_notify_flags(dev, old_flags, changes); return ret; } EXPORT_SYMBOL(dev_change_flags); +static int __dev_set_mtu(struct net_device *dev, int new_mtu) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (ops->ndo_change_mtu) + return ops->ndo_change_mtu(dev, new_mtu); + + dev->mtu = new_mtu; + return 0; +} + /** * dev_set_mtu - Change maximum transfer unit * @dev: device @@ -4336,8 +5540,7 @@ EXPORT_SYMBOL(dev_change_flags); */ int dev_set_mtu(struct net_device *dev, int new_mtu) { - const struct net_device_ops *ops = dev->netdev_ops; - int err; + int err, orig_mtu; if (new_mtu == dev->mtu) return 0; @@ -4349,19 +5552,41 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) if (!netif_device_present(dev)) return -ENODEV; - err = 0; - if (ops->ndo_change_mtu) - err = ops->ndo_change_mtu(dev, new_mtu); - else - dev->mtu = new_mtu; + err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) + return err; - if (!err && dev->flags & IFF_UP) - call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + orig_mtu = dev->mtu; + err = __dev_set_mtu(dev, new_mtu); + + if (!err) { + err = call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + err = notifier_to_errno(err); + if (err) { + /* setting mtu back and notifying everyone again, + * so that they have a chance to revert changes. + */ + __dev_set_mtu(dev, orig_mtu); + call_netdevice_notifiers(NETDEV_CHANGEMTU, dev); + } + } return err; } EXPORT_SYMBOL(dev_set_mtu); /** + * dev_set_group - Change group this device belongs to + * @dev: device + * @new_group: group this device should belong to + */ +void dev_set_group(struct net_device *dev, int new_group) +{ + dev->group = new_group; +} +EXPORT_SYMBOL(dev_set_group); + +/** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address @@ -4380,367 +5605,51 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) if (!netif_device_present(dev)) return -ENODEV; err = ops->ndo_set_mac_address(dev, sa); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; + if (err) + return err; + dev->addr_assign_type = NET_ADDR_SET; + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); + return 0; } EXPORT_SYMBOL(dev_set_mac_address); -/* - * 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_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 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 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 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 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; - - } - return err; -} - -/* - * Perform the SIOCxIFxxx calls, inside rtnl_lock() +/** + * dev_change_carrier - Change device carrier + * @dev: device + * @new_carrier: new value + * + * Change device carrier */ -static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) +int dev_change_carrier(struct net_device *dev, bool new_carrier) { - int err; - struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); - const struct net_device_ops *ops; - - if (!dev) - return -ENODEV; - - ops = dev->netdev_ops; - - switch (cmd) { - case SIOCSIFFLAGS: /* Set interface flags */ - return dev_change_flags(dev, ifr->ifr_flags); + const struct net_device_ops *ops = dev->netdev_ops; - case SIOCSIFMETRIC: /* Set the metric on the interface - (currently unused) */ + if (!ops->ndo_change_carrier) return -EOPNOTSUPP; - - case SIOCSIFMTU: /* Set the MTU of a device */ - return dev_set_mtu(dev, ifr->ifr_mtu); - - case SIOCSIFHWADDR: - return dev_set_mac_address(dev, &ifr->ifr_hwaddr); - - 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 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 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(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); - - 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 SIOCSIFTXQLEN: - if (ifr->ifr_qlen < 0) - return -EINVAL; - dev->tx_queue_len = ifr->ifr_qlen; - return 0; - - case SIOCSIFNAME: - ifr->ifr_newname[IFNAMSIZ-1] = '\0'; - return dev_change_name(dev, ifr->ifr_newname); - - /* - * 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; + if (!netif_device_present(dev)) + return -ENODEV; + return ops->ndo_change_carrier(dev, new_carrier); } - -/* - * This function handles all "interface"-type I/O control requests. The actual - * 'doing' part of this is dev_ifsioc above. - */ +EXPORT_SYMBOL(dev_change_carrier); /** - * dev_ioctl - network device ioctl - * @net: the applicable net namespace - * @cmd: command to issue - * @arg: pointer to a struct ifreq in user space + * dev_get_phys_port_id - Get device physical port ID + * @dev: device + * @ppid: port ID * - * Issue ioctl functions to devices. This is normally called by the - * user space syscall interfaces but can sometimes be useful for - * other purposes. The return value is the return from the syscall if - * positive or a negative errno code on error. + * Get device physical port ID */ - -int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) +int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid) { - struct ifreq ifr; - int ret; - char *colon; - - /* One special case: SIOCGIFCONF takes ifconf argument - and requires shared lock, because it sleeps writing - to user space. - */ - - if (cmd == SIOCGIFCONF) { - rtnl_lock(); - ret = dev_ifconf(net, (char __user *) arg); - rtnl_unlock(); - return ret; - } - if (cmd == SIOCGIFNAME) - return dev_ifname(net, (struct ifreq __user *)arg); - - if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) - return -EFAULT; - - ifr.ifr_name[IFNAMSIZ-1] = 0; - - colon = strchr(ifr.ifr_name, ':'); - if (colon) - *colon = 0; - - /* - * See which interface the caller is talking about. - */ - - 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); - 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; - - /* - * 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: - 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; + const struct net_device_ops *ops = dev->netdev_ops; - /* - * 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; - } + if (!ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + return ops->ndo_get_phys_port_id(dev, ppid); } - +EXPORT_SYMBOL(dev_get_phys_port_id); /** * dev_new_index - allocate an ifindex @@ -4752,26 +5661,29 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) */ static int dev_new_index(struct net *net) { - static int ifindex; + int ifindex = net->ifindex; for (;;) { if (++ifindex <= 0) ifindex = 1; if (!__dev_get_by_index(net, ifindex)) - return ifindex; + return net->ifindex = ifindex; } } /* Delayed registration/unregisteration */ static LIST_HEAD(net_todo_list); +DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); + dev_net(dev)->dev_unreg_count++; } static void rollback_registered_many(struct list_head *head) { struct net_device *dev, *tmp; + LIST_HEAD(close_head); BUG_ON(dev_boot_phase); ASSERT_RTNL(); @@ -4782,19 +5694,23 @@ static void rollback_registered_many(struct list_head *head) * 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); + pr_debug("unregister_netdevice: device %s/%p never was registered\n", + dev->name, dev); WARN_ON(1); list_del(&dev->unreg_list); continue; } - + dev->dismantle = true; BUG_ON(dev->reg_state != NETREG_REGISTERED); + } - /* If device is running, close it first. */ - dev_close(dev); + /* If device is running, close it first. */ + list_for_each_entry(dev, head, unreg_list) + list_add_tail(&dev->close_list, &close_head); + dev_close_many(&close_head); + list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); @@ -4816,23 +5732,27 @@ static void rollback_registered_many(struct list_head *head) /* * Flush the unicast and multicast chains */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + dev_uc_flush(dev); + dev_mc_flush(dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + + /* Notifier chain MUST detach us all upper devices. */ + WARN_ON(netdev_has_any_upper_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); +#ifdef CONFIG_XPS + /* Remove XPS queueing entries */ + netif_reset_xps_queues_gt(dev, 0); +#endif } - /* Process any work delayed until the end of the batch */ - dev = list_entry(head->next, struct net_device, unreg_list); - call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - synchronize_net(); list_for_each_entry(dev, head, unreg_list) @@ -4845,62 +5765,144 @@ static void rollback_registered(struct net_device *dev) list_add(&dev->unreg_list, &single); rollback_registered_many(&single); + list_del(&single); } -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; -} - -static void netdev_init_queue_locks(struct net_device *dev) +static netdev_features_t netdev_fix_features(struct net_device *dev, + netdev_features_t features) { - netdev_for_each_tx_queue(dev, __netdev_init_queue_locks_one, NULL); - __netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL); -} - -unsigned long netdev_fix_features(unsigned long features, const char *name) -{ - /* Fix illegal SG+CSUM combinations. */ - if ((features & NETIF_F_SG) && - !(features & NETIF_F_ALL_CSUM)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no " - "checksum feature.\n", name); - features &= ~NETIF_F_SG; + /* Fix illegal checksum combinations */ + if ((features & NETIF_F_HW_CSUM) && + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_warn(dev, "mixed HW and IP checksum settings.\n"); + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } /* TSO requires that SG is present as well. */ - if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no " - "SG feature.\n", name); + if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); + features &= ~NETIF_F_ALL_TSO; + } + + if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IP_CSUM)) { + netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); features &= ~NETIF_F_TSO; + features &= ~NETIF_F_TSO_ECN; + } + + if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IPV6_CSUM)) { + netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO6; } + /* TSO ECN requires that TSO is present as well. */ + if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) + features &= ~NETIF_F_TSO_ECN; + + /* Software GSO depends on SG. */ + if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { + netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); + features &= ~NETIF_F_GSO; + } + + /* UFO needs SG and checksumming */ if (features & NETIF_F_UFO) { - if (!(features & NETIF_F_GEN_CSUM)) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_HW_CSUM feature.\n", - name); + /* 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))) { + netdev_dbg(dev, + "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; } if (!(features & NETIF_F_SG)) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_SG feature.\n", name); + netdev_dbg(dev, + "Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n"); features &= ~NETIF_F_UFO; } } +#ifdef CONFIG_NET_RX_BUSY_POLL + if (dev->netdev_ops->ndo_busy_poll) + features |= NETIF_F_BUSY_POLL; + else +#endif + features &= ~NETIF_F_BUSY_POLL; + return features; } -EXPORT_SYMBOL(netdev_fix_features); + +int __netdev_update_features(struct net_device *dev) +{ + netdev_features_t features; + int err = 0; + + ASSERT_RTNL(); + + features = netdev_get_wanted_features(dev); + + if (dev->netdev_ops->ndo_fix_features) + features = dev->netdev_ops->ndo_fix_features(dev, features); + + /* driver might be less strict about feature dependencies */ + features = netdev_fix_features(dev, features); + + if (dev->features == features) + return 0; + + netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", + &dev->features, &features); + + if (dev->netdev_ops->ndo_set_features) + err = dev->netdev_ops->ndo_set_features(dev, features); + + if (unlikely(err < 0)) { + netdev_err(dev, + "set_features() failed (%d); wanted %pNF, left %pNF\n", + err, &features, &dev->features); + return -1; + } + + if (!err) + dev->features = features; + + return 1; +} + +/** + * netdev_update_features - recalculate device features + * @dev: the device to check + * + * Recalculate dev->features set and send notifications if it + * has changed. Should be called after driver or hardware dependent + * conditions might have changed that influence the features. + */ +void netdev_update_features(struct net_device *dev) +{ + if (__netdev_update_features(dev)) + netdev_features_change(dev); +} +EXPORT_SYMBOL(netdev_update_features); + +/** + * netdev_change_features - recalculate device features + * @dev: the device to check + * + * Recalculate dev->features set and send notifications even + * if they have not changed. Should be called instead of + * netdev_update_features() if also dev->vlan_features might + * have changed to allow the changes to be propagated to stacked + * VLAN devices. + */ +void netdev_change_features(struct net_device *dev) +{ + __netdev_update_features(dev); + netdev_features_change(dev); +} +EXPORT_SYMBOL(netdev_change_features); /** * netif_stacked_transfer_operstate - transfer operstate @@ -4929,6 +5931,67 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); +#ifdef CONFIG_SYSFS +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) + 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; +#ifdef CONFIG_BQL + dql_init(&queue->dql, HZ); +#endif +} + +static void netif_free_tx_queues(struct net_device *dev) +{ + kvfree(dev->_tx); +} + +static int netif_alloc_netdev_queues(struct net_device *dev) +{ + unsigned int count = dev->num_tx_queues; + struct netdev_queue *tx; + size_t sz = count * sizeof(*tx); + + BUG_ON(count < 1 || count > 0xffff); + + tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!tx) { + tx = vzalloc(sz); + if (!tx) + 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 @@ -4962,10 +6025,13 @@ 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; + ret = dev_get_valid_name(net, dev, dev->name); + if (ret < 0) + goto out; + /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -4976,36 +6042,46 @@ int register_netdevice(struct net_device *dev) } } - ret = dev_get_valid_name(net, dev->name, dev->name, 0); - if (ret) + if (((dev->hw_features | dev->features) & + NETIF_F_HW_VLAN_CTAG_FILTER) && + (!dev->netdev_ops->ndo_vlan_rx_add_vid || + !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { + netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); + ret = -EINVAL; + goto err_uninit; + } + + ret = -EBUSY; + if (!dev->ifindex) + dev->ifindex = dev_new_index(net); + else if (__dev_get_by_index(net, dev->ifindex)) goto err_uninit; - dev->ifindex = dev_new_index(net); if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Fix illegal checksum combinations */ - if ((dev->features & NETIF_F_HW_CSUM) && - (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); - } + /* Transfer changeable features to wanted_features and enable + * software offloads (GSO and GRO). + */ + dev->hw_features |= NETIF_F_SOFT_FEATURES; + dev->features |= NETIF_F_SOFT_FEATURES; + dev->wanted_features = dev->features & dev->hw_features; - if ((dev->features & NETIF_F_NO_CSUM) && - (dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); + if (!(dev->flags & IFF_LOOPBACK)) { + dev->hw_features |= NETIF_F_NOCACHE_COPY; } - dev->features = netdev_fix_features(dev->features, dev->name); + /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. + */ + dev->vlan_features |= NETIF_F_HIGHDMA; - /* Enable software GSO if SG is supported. */ - if (dev->features & NETIF_F_SG) - dev->features |= NETIF_F_GSO; + /* Make NETIF_F_SG inheritable to tunnel devices. + */ + dev->hw_enc_features |= NETIF_F_SG; - netdev_initialize_kobject(dev); + /* Make NETIF_F_SG inheritable to MPLS. + */ + dev->mpls_features |= NETIF_F_SG; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); @@ -5017,6 +6093,8 @@ int register_netdevice(struct net_device *dev) goto err_uninit; dev->reg_state = NETREG_REGISTERED; + __netdev_update_features(dev); + /* * Default initial state at registry is that the * device is present. @@ -5024,9 +6102,19 @@ int register_netdevice(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); + linkwatch_init_dev(dev); + dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); + + /* If the device has permanent device address, driver should + * set dev_addr and also addr_assign_type should be set to + * NET_ADDR_PERM (default value). + */ + if (dev->addr_assign_type == NET_ADDR_PERM) + memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); @@ -5039,7 +6127,9 @@ int register_netdevice(struct net_device *dev) * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); out: return ret; @@ -5075,9 +6165,6 @@ 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); @@ -5085,6 +6172,11 @@ 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); @@ -5108,26 +6200,25 @@ int register_netdev(struct net_device *dev) int err; rtnl_lock(); - - /* - * If the name is a format string the caller wants us to do a - * name allocation. - */ - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto out; - } - err = register_netdevice(dev); -out: rtnl_unlock(); return err; } 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. + * @dev: target net_device * * This is called when unregistering network devices. * @@ -5140,19 +6231,25 @@ 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 */ + __rtnl_unlock(); + rcu_barrier(); + rtnl_lock(); + + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events @@ -5171,11 +6268,11 @@ 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)); + pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", + dev->name, refcnt); warning_time = jiffies; } } @@ -5214,13 +6311,22 @@ void netdev_run_todo(void) __rtnl_unlock(); + + /* Wait for rcu callbacks to finish before next phase */ + if (!list_empty(&list)) + rcu_barrier(); + 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); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + __rtnl_unlock(); + if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { - printk(KERN_ERR "network todo '%s' but state %d\n", + pr_err("network todo '%s' but state %d\n", dev->name, dev->reg_state); dump_stack(); continue; @@ -5233,100 +6339,145 @@ 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_access_pointer(dev->ip_ptr)); + WARN_ON(rcu_access_pointer(dev->ip6_ptr)); WARN_ON(dev->dn_ptr); if (dev->destructor) dev->destructor(dev); + /* Report a network device has been unregistered */ + rtnl_lock(); + dev_net(dev)->dev_unreg_count--; + __rtnl_unlock(); + wake_up(&netdev_unregistering_wq); + /* Free network device */ kobject_put(&dev->dev.kobj); } } -/** - * dev_txq_stats_fold - fold tx_queues stats - * @dev: device to get statistics from - * @stats: struct net_device_stats to hold results +/* Convert net_device_stats to rtnl_link_stats64. They have the same + * fields in the same order, with only the type differing. */ -void dev_txq_stats_fold(const struct net_device *dev, - struct net_device_stats *stats) +void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, + const struct net_device_stats *netdev_stats) { - unsigned long 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); - 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; - } +#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 } -EXPORT_SYMBOL(dev_txq_stats_fold); +EXPORT_SYMBOL(netdev_stats_to_stats64); /** * 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); - - dev_txq_stats_fold(dev, &dev->stats); - return &dev->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); + } + storage->rx_dropped += atomic_long_read(&dev->rx_dropped); + storage->tx_dropped += atomic_long_read(&dev->tx_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); + +#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; } -static void netdev_init_queues(struct net_device *dev) +static const struct ethtool_ops default_ethtool_ops; + +void netdev_set_default_ethtool_ops(struct net_device *dev, + const struct ethtool_ops *ops) { - 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); + if (dev->ethtool_ops == &default_ethtool_ops) + dev->ethtool_ops = ops; +} +EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); + +void netdev_freemem(struct net_device *dev) +{ + char *addr = (char *)dev - dev->padded; + + kvfree(addr); } /** - * 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. + * and performs basic initialization. Also allocates subqueue structs + * 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_SYSFS + 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 */ @@ -5336,53 +6487,70 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, /* ensure 32-byte alignment of whole construct */ alloc_size += NETDEV_ALIGN - 1; - p = kzalloc(alloc_size, GFP_KERNEL); - if (!p) { - printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n"); + p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!p) + p = vzalloc(alloc_size); + if (!p) 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_dev; + 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->gso_max_size = GSO_MAX_SIZE; - - netdev_init_queues(dev); + dev->gso_max_segs = GSO_MAX_SEGS; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->close_list); INIT_LIST_HEAD(&dev->link_watch_list); + INIT_LIST_HEAD(&dev->adj_list.upper); + INIT_LIST_HEAD(&dev->adj_list.lower); + INIT_LIST_HEAD(&dev->all_adj_list.upper); + INIT_LIST_HEAD(&dev->all_adj_list.lower); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); + + dev->num_tx_queues = txqs; + dev->real_num_tx_queues = txqs; + if (netif_alloc_netdev_queues(dev)) + goto free_all; + +#ifdef CONFIG_SYSFS + dev->num_rx_queues = rxqs; + dev->real_num_rx_queues = rxqs; + if (netif_alloc_rx_queues(dev)) + goto free_all; +#endif + strcpy(dev->name, name); + dev->group = INIT_NETDEV_GROUP; + if (!dev->ethtool_ops) + dev->ethtool_ops = &default_ethtool_ops; return dev; -free_tx: - kfree(tx); +free_all: + free_netdev(dev); + return NULL; -free_p: - kfree(p); +free_pcpu: + free_percpu(dev->pcpu_refcnt); +free_dev: + netdev_freemem(dev); return NULL; } -EXPORT_SYMBOL(alloc_netdev_mq); +EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device @@ -5398,7 +6566,12 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); - kfree(dev->_tx); + netif_free_tx_queues(dev); +#ifdef CONFIG_SYSFS + kfree(dev->_rx); +#endif + + kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */ dev_addr_flush(dev); @@ -5406,9 +6579,12 @@ void free_netdev(struct net_device *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); + netdev_freemem(dev); return; } @@ -5429,7 +6605,10 @@ EXPORT_SYMBOL(free_netdev); void synchronize_net(void) { might_sleep(); - synchronize_rcu(); + if (rtnl_is_locked()) + synchronize_rcu_expedited(); + else + synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); @@ -5463,6 +6642,9 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { @@ -5472,6 +6654,7 @@ void unregister_netdevice_many(struct list_head *head) rollback_registered_many(head); list_for_each_entry(dev, head, unreg_list) net_set_todo(dev); + list_del(head); } } EXPORT_SYMBOL(unregister_netdevice_many); @@ -5520,17 +6703,7 @@ 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) goto out; @@ -5547,7 +6720,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* We get here if we can't use the current device name */ if (!pat) goto out; - if (dev_get_valid_name(net, pat, dev->name, 1)) + if (dev_get_valid_name(net, dev, pat) < 0) goto out; } @@ -5569,17 +6742,24 @@ 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); + rcu_barrier(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); /* * Flush the unicast and multicast chains */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + dev_uc_flush(dev); + dev_mc_flush(dev); - netdev_unregister_kobject(dev); + /* Send a netdev-removed uevent to the old namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); /* Actually switch the network namespace */ dev_net_set(dev, net); @@ -5592,8 +6772,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char dev->iflink = dev->ifindex; } + /* Send a netdev-add uevent to the new namespace */ + kobject_uevent(&dev->dev.kobj, KOBJ_ADD); + /* Fixup kobjects */ - err = netdev_register_kobject(dev); + err = device_rename(&dev->dev, dev->name); WARN_ON(err); /* Add the device back in the hashes */ @@ -5606,7 +6789,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); synchronize_net(); err = 0; @@ -5620,7 +6803,6 @@ static int dev_cpu_callback(struct notifier_block *nfb, 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; @@ -5641,20 +6823,31 @@ 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; + } + /* Append NAPI poll list from offline CPU. */ + if (!list_empty(&oldsd->poll_list)) { + list_splice_init(&oldsd->poll_list, &sd->poll_list); + raise_softirq_irqoff(NET_RX_SOFTIRQ); + } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) - netif_rx(skb); + while ((skb = __skb_dequeue(&oldsd->process_queue))) { + netif_rx_internal(skb); + input_queue_head_incr(oldsd); + } + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + netif_rx_internal(skb); + input_queue_head_incr(oldsd); + } return NOTIFY_OK; } @@ -5670,38 +6863,25 @@ static int dev_cpu_callback(struct notifier_block *nfb, * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ -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)) - 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. */ - if (one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM) && - !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - } - - /* If one device supports hw checksumming, set for all. */ - if (one & NETIF_F_GEN_CSUM && !(all & NETIF_F_GEN_CSUM)) { - all &= ~NETIF_F_ALL_CSUM; - all |= NETIF_F_HW_CSUM; - } - } +netdev_features_t netdev_increment_features(netdev_features_t all, + netdev_features_t one, netdev_features_t mask) +{ + if (mask & NETIF_F_GEN_CSUM) + mask |= NETIF_F_ALL_CSUM; + mask |= NETIF_F_VLAN_CHALLENGED; - one |= NETIF_F_ALL_CSUM; + all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; + all &= one | ~NETIF_F_ALL_FOR_ALL; - one |= all & NETIF_F_ONE_FOR_ALL; - all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO; - all |= one & mask & NETIF_F_ONE_FOR_ALL; + /* If one device supports hw checksumming, set for all. */ + if (all & NETIF_F_GEN_CSUM) + all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); return all; } EXPORT_SYMBOL(netdev_increment_features); -static struct hlist_head *netdev_create_hash(void) +static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; @@ -5717,7 +6897,8 @@ static struct hlist_head *netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { - INIT_LIST_HEAD(&net->dev_base_head); + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) @@ -5738,31 +6919,94 @@ err_name: /** * netdev_drivername - network driver for the device * @dev: network device - * @buffer: buffer for resulting name - * @len: size of buffer * * Determine network driver for device. */ -char *netdev_drivername(const struct net_device *dev, char *buffer, int len) +const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; - - if (len <= 0 || !buffer) - return buffer; - buffer[0] = 0; + const char *empty = ""; parent = dev->dev.parent; - if (!parent) - return buffer; + return empty; driver = parent->driver; if (driver && driver->name) - strlcpy(buffer, driver->name, len); - return buffer; + return driver->name; + return empty; +} + +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_emit(level[1] - '0', + dev->dev.parent, + "%s %s %s: %pV", + dev_driver_string(dev->dev.parent), + dev_name(dev->dev.parent), + 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); @@ -5794,22 +7038,50 @@ static void __net_exit default_device_exit(struct net *net) if (dev->rtnl_link_ops) continue; - /* Push remaing network devices to init_net */ + /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { - printk(KERN_EMERG "%s: failed to move %s to init_net: %d\n", - __func__, dev->name, err); + pr_emerg("%s: failed to move %s to init_net: %d\n", + __func__, dev->name, err); BUG(); } } rtnl_unlock(); } +static void __net_exit rtnl_lock_unregistering(struct list_head *net_list) +{ + /* Return with the rtnl_lock held when there are no network + * devices unregistering in any network namespace in net_list. + */ + struct net *net; + bool unregistering; + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait(&netdev_unregistering_wq, &wait, + TASK_UNINTERRUPTIBLE); + unregistering = false; + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + if (net->dev_unreg_count > 0) { + unregistering = true; + break; + } + } + if (!unregistering) + break; + __rtnl_unlock(); + schedule(); + } + finish_wait(&netdev_unregistering_wq, &wait); +} + 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. + * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ @@ -5817,7 +7089,18 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) struct net *net; LIST_HEAD(dev_kill_list); - rtnl_lock(); + /* To prevent network device cleanup code from dereferencing + * loopback devices or network devices that have been freed + * wait here for all pending unregistrations to complete, + * before unregistring the loopback device and allowing the + * network namespace be freed. + * + * The netdev todo list containing all network devices + * unregistrations that happen in default_device_exit_batch + * will run in the rtnl_unlock() at the end of + * default_device_exit_batch. + */ + rtnl_lock_unregistering(net_list); list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops) @@ -5862,6 +7145,8 @@ static int __init net_dev_init(void) for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); + INIT_LIST_HEAD(&offload_base); + if (register_pernet_subsys(&netdev_net_ops)) goto out; @@ -5870,17 +7155,20 @@ static int __init net_dev_init(void) */ for_each_possible_cpu(i) { - struct softnet_data *queue; - - queue = &per_cpu(softnet_data, i); - skb_queue_head_init(&queue->input_pkt_queue); - queue->completion_queue = NULL; - INIT_LIST_HEAD(&queue->poll_list); + struct softnet_data *sd = &per_cpu(softnet_data, i); + + skb_queue_head_init(&sd->input_pkt_queue); + skb_queue_head_init(&sd->process_queue); + INIT_LIST_HEAD(&sd->poll_list); + sd->output_queue_tailp = &sd->output_queue; +#ifdef CONFIG_RPS + sd->csd.func = rps_trigger_softirq; + sd->csd.info = sd; + 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; } dev_boot_phase = 0; @@ -5905,19 +7193,9 @@ static int __init net_dev_init(void) hotcpu_notifier(dev_cpu_callback, 0); dst_init(); - dev_mcast_init(); rc = 0; out: return rc; } subsys_initcall(net_dev_init); - -static int __init initialize_hashrnd(void) -{ - get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd)); - return 0; -} - -late_initcall_sync(initialize_hashrnd); - |