diff options
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 1312 |
1 files changed, 964 insertions, 348 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index fdcff29df915..46580b290450 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1,11 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 Protocol independent device support routines. * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * * Derived from the non IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> @@ -131,7 +127,6 @@ #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> @@ -146,10 +141,12 @@ #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> +#include <net/devlink.h> #include "net-sysfs.h" #define MAX_GRO_SKBS 8 +#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -232,6 +229,122 @@ static inline void rps_unlock(struct softnet_data *sd) #endif } +static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, + const char *name) +{ + struct netdev_name_node *name_node; + + name_node = kmalloc(sizeof(*name_node), GFP_KERNEL); + if (!name_node) + return NULL; + INIT_HLIST_NODE(&name_node->hlist); + name_node->dev = dev; + name_node->name = name; + return name_node; +} + +static struct netdev_name_node * +netdev_name_node_head_alloc(struct net_device *dev) +{ + struct netdev_name_node *name_node; + + name_node = netdev_name_node_alloc(dev, dev->name); + if (!name_node) + return NULL; + INIT_LIST_HEAD(&name_node->list); + return name_node; +} + +static void netdev_name_node_free(struct netdev_name_node *name_node) +{ + kfree(name_node); +} + +static void netdev_name_node_add(struct net *net, + struct netdev_name_node *name_node) +{ + hlist_add_head_rcu(&name_node->hlist, + dev_name_hash(net, name_node->name)); +} + +static void netdev_name_node_del(struct netdev_name_node *name_node) +{ + hlist_del_rcu(&name_node->hlist); +} + +static struct netdev_name_node *netdev_name_node_lookup(struct net *net, + const char *name) +{ + struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *name_node; + + hlist_for_each_entry(name_node, head, hlist) + if (!strcmp(name_node->name, name)) + return name_node; + return NULL; +} + +static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, + const char *name) +{ + struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *name_node; + + hlist_for_each_entry_rcu(name_node, head, hlist) + if (!strcmp(name_node->name, name)) + return name_node; + return NULL; +} + +int netdev_name_node_alt_create(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (name_node) + return -EEXIST; + name_node = netdev_name_node_alloc(dev, name); + if (!name_node) + return -ENOMEM; + netdev_name_node_add(net, name_node); + /* The node that holds dev->name acts as a head of per-device list. */ + list_add_tail(&name_node->list, &dev->name_node->list); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_create); + +static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) +{ + list_del(&name_node->list); + netdev_name_node_del(name_node); + kfree(name_node->name); + netdev_name_node_free(name_node); +} + +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (!name_node) + return -ENOENT; + __netdev_name_node_alt_destroy(name_node); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_destroy); + +static void netdev_name_node_alt_flush(struct net_device *dev) +{ + struct netdev_name_node *name_node, *tmp; + + list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) + __netdev_name_node_alt_destroy(name_node); +} + /* Device list insertion */ static void list_netdevice(struct net_device *dev) { @@ -241,7 +354,7 @@ static void list_netdevice(struct net_device *dev) write_lock_bh(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); - hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); @@ -259,7 +372,7 @@ static void unlist_netdevice(struct net_device *dev) /* Unlink dev from the device chain */ write_lock_bh(&dev_base_lock); list_del_rcu(&dev->dev_list); - hlist_del_rcu(&dev->name_hlist); + netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); @@ -280,88 +393,6 @@ static RAW_NOTIFIER_HEAD(netdev_chain); DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); -#ifdef CONFIG_LOCKDEP -/* - * register_netdevice() inits txq->_xmit_lock and sets lockdep class - * according to dev->type - */ -static const unsigned short netdev_lock_type[] = { - ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, - ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, - ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, - ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, - ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, - ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, - ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, - ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, - ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, - 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_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", - "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", - "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", - "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", - "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", - "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", - "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", - "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", - "_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_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)]; - -static inline unsigned short netdev_lock_pos(unsigned short dev_type) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) - if (netdev_lock_type[i] == dev_type) - return i; - /* the last key is used by default */ - return ARRAY_SIZE(netdev_lock_type) - 1; -} - -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ - int i; - - i = netdev_lock_pos(dev_type); - lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], - netdev_lock_name[i]); -} - -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ - int i; - - i = netdev_lock_pos(dev->type); - lockdep_set_class_and_name(&dev->addr_list_lock, - &netdev_addr_lock_key[i], - netdev_lock_name[i]); -} -#else -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ -} -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ -} -#endif - /******************************************************************************* * * Protocol management and registration routines @@ -737,14 +768,10 @@ EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); struct net_device *__dev_get_by_name(struct net *net, const char *name) { - struct net_device *dev; - struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *node_name; - hlist_for_each_entry(dev, head, name_hlist) - if (!strncmp(dev->name, name, IFNAMSIZ)) - return dev; - - return NULL; + node_name = netdev_name_node_lookup(net, name); + return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); @@ -762,14 +789,10 @@ EXPORT_SYMBOL(__dev_get_by_name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { - struct net_device *dev; - struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *node_name; - hlist_for_each_entry_rcu(dev, head, name_hlist) - if (!strncmp(dev->name, name, IFNAMSIZ)) - return dev; - - return NULL; + node_name = netdev_name_node_lookup_rcu(net, name); + return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu); @@ -1145,8 +1168,8 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); -int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name) +static int dev_get_valid_name(struct net *net, struct net_device *dev, + const char *name) { BUG_ON(!net); @@ -1162,7 +1185,6 @@ int dev_get_valid_name(struct net *net, struct net_device *dev, return 0; } -EXPORT_SYMBOL(dev_get_valid_name); /** * dev_change_name - change name of a device @@ -1184,7 +1206,21 @@ int dev_change_name(struct net_device *dev, const char *newname) BUG_ON(!dev_net(dev)); net = dev_net(dev); - if (dev->flags & IFF_UP) + + /* Some auto-enslaved devices e.g. failover slaves are + * special, as userspace might rename the device after + * the interface had been brought up and running since + * the point kernel initiated auto-enslavement. Allow + * live name change even when these slave devices are + * up and running. + * + * Typically, users of these auto-enslaving devices + * don't actually care about slave name change, as + * they are supposed to operate on master interface + * directly. + */ + if (dev->flags & IFF_UP && + likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; write_seqcount_begin(&devnet_rename_seq); @@ -1222,13 +1258,13 @@ rollback: netdev_adjacent_rename_links(dev, oldname); write_lock_bh(&dev_base_lock); - hlist_del_rcu(&dev->name_hlist); + netdev_name_node_del(dev->name_node); write_unlock_bh(&dev_base_lock); synchronize_rcu(); write_lock_bh(&dev_base_lock); - hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + netdev_name_node_add(net, dev->name_node); write_unlock_bh(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); @@ -1278,8 +1314,8 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) } mutex_lock(&ifalias_mutex); - rcu_swap_protected(dev->ifalias, new_alias, - mutex_is_locked(&ifalias_mutex)); + new_alias = rcu_replace_pointer(dev->ifalias, new_alias, + mutex_is_locked(&ifalias_mutex)); mutex_unlock(&ifalias_mutex); if (new_alias) @@ -1607,6 +1643,62 @@ static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, return nb->notifier_call(nb, val, &info); } +static int call_netdevice_register_notifiers(struct notifier_block *nb, + struct net_device *dev) +{ + int err; + + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); + err = notifier_to_errno(err); + if (err) + return err; + + if (!(dev->flags & IFF_UP)) + return 0; + + call_netdevice_notifier(nb, NETDEV_UP, dev); + return 0; +} + +static void call_netdevice_unregister_notifiers(struct notifier_block *nb, + struct net_device *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); +} + +static int call_netdevice_register_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + err = call_netdevice_register_notifiers(nb, dev); + if (err) + goto rollback; + } + return 0; + +rollback: + for_each_netdev_continue_reverse(net, dev) + call_netdevice_unregister_notifiers(nb, dev); + return err; +} + +static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + + for_each_netdev(net, dev) + call_netdevice_unregister_notifiers(nb, dev); +} + static int dev_boot_phase = 1; /** @@ -1625,8 +1717,6 @@ static int dev_boot_phase = 1; int register_netdevice_notifier(struct notifier_block *nb) { - struct net_device *dev; - struct net_device *last; struct net *net; int err; @@ -1639,17 +1729,9 @@ int register_netdevice_notifier(struct notifier_block *nb) if (dev_boot_phase) goto unlock; for_each_net(net) { - for_each_netdev(net, dev) { - err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); - err = notifier_to_errno(err); - if (err) - goto rollback; - - if (!(dev->flags & IFF_UP)) - continue; - - call_netdevice_notifier(nb, NETDEV_UP, dev); - } + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto rollback; } unlock: @@ -1658,22 +1740,9 @@ unlock: return err; rollback: - last = dev; - for_each_net(net) { - for_each_netdev(net, dev) { - if (dev == last) - goto outroll; + for_each_net_continue_reverse(net) + call_netdevice_unregister_net_notifiers(nb, net); - 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); - } - } - -outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -1724,6 +1793,80 @@ unlock: EXPORT_SYMBOL(unregister_netdevice_notifier); /** + * register_netdevice_notifier_net - register a per-netns network notifier block + * @net: network namespace + * @nb: notifier + * + * Register a notifier to be called when network device events occur. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. + * + * When registered all registration and up events are replayed + * to the new notifier to allow device to have a race free + * view of the network device list. + */ + +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_register(&net->netdev_chain, nb); + if (err) + goto unlock; + if (dev_boot_phase) + goto unlock; + + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto chain_unregister; + +unlock: + rtnl_unlock(); + return err; + +chain_unregister: + raw_notifier_chain_unregister(&netdev_chain, nb); + goto unlock; +} +EXPORT_SYMBOL(register_netdevice_notifier_net); + +/** + * unregister_netdevice_notifier_net - unregister a per-netns + * network notifier block + * @net: network namespace + * @nb: notifier + * + * Unregister a notifier previously registered by + * 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_net(struct net *net, + struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_unregister(&net->netdev_chain, nb); + if (err) + goto unlock; + + call_netdevice_unregister_net_notifiers(nb, net); + +unlock: + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier_net); + +/** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function * @info: notifier information data @@ -1735,7 +1878,18 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); static int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { + struct net *net = dev_net(info->dev); + int ret; + ASSERT_RTNL(); + + /* Run per-netns notifier block chain first, then run the global one. + * Hopefully, one day, the global one is going to be removed after + * all notifier block registrators get converted to be per-netns. + */ + ret = raw_notifier_call_chain(&net->netdev_chain, val, info); + if (ret & NOTIFY_STOP_MASK) + return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } @@ -2761,7 +2915,7 @@ static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) void netif_schedule_queue(struct netdev_queue *txq) { rcu_read_lock(); - if (!(txq->state & QUEUE_STATE_ANY_XOFF)) { + if (!netif_xmit_stopped(txq)) { struct Qdisc *q = rcu_dereference(txq->qdisc); __netif_schedule(q); @@ -2890,12 +3044,10 @@ static void skb_warn_bad_offload(const struct sk_buff *skb) else name = netdev_name(dev); } - WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d gso_size=%d " - "gso_type=%d ip_summed=%d\n", + skb_dump(KERN_WARNING, skb, false); + WARN(1, "%s: caps=(%pNF, %pNF)\n", name, 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); + skb->sk ? &skb->sk->sk_route_caps : &null_features); } /* @@ -2931,12 +3083,9 @@ int skb_checksum_help(struct sk_buff *skb) offset += skb->csum_offset; BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb)); - if (skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(__sum16))) { - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (ret) - goto out; - } + ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); + if (ret) + goto out; *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: @@ -2971,12 +3120,11 @@ int skb_crc32c_csum_help(struct sk_buff *skb) ret = -EINVAL; goto out; } - if (skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(__le32))) { - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (ret) - goto out; - } + + ret = skb_ensure_writable(skb, offset + sizeof(__le32)); + if (ret) + goto out; + crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, skb->len - start, ~(__u32)0, crc32c_csum_stub)); @@ -3114,13 +3262,7 @@ void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { if (net_ratelimit()) { pr_err("%s: hw csum failure\n", dev ? dev->name : "<unknown>"); - if (dev) - pr_err("dev features: %pNF\n", &dev->features); - pr_err("skb len=%u data_len=%u pkt_type=%u gso_size=%u gso_type=%u nr_frags=%u ip_summed=%u csum=%x csum_complete_sw=%d csum_valid=%d csum_level=%u\n", - skb->len, skb->data_len, skb->pkt_type, - skb_shinfo(skb)->gso_size, skb_shinfo(skb)->gso_type, - skb_shinfo(skb)->nr_frags, skb->ip_summed, skb->csum, - skb->csum_complete_sw, skb->csum_valid, skb->csum_level); + skb_dump(KERN_ERR, skb, true); dump_stack(); } } @@ -3465,9 +3607,22 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; + if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && + qdisc_run_begin(q)) { + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, + &q->state))) { + __qdisc_drop(skb, &to_free); + rc = NET_XMIT_DROP; + goto end_run; + } + qdisc_bstats_cpu_update(q, skb); + + rc = NET_XMIT_SUCCESS; + if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) + __qdisc_run(q); + +end_run: + qdisc_run_end(q); } else { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; qdisc_run(q); @@ -3556,9 +3711,6 @@ static void skb_update_prio(struct sk_buff *skb) #define skb_update_prio(skb) #endif -DEFINE_PER_CPU(int, xmit_recursion); -EXPORT_SYMBOL(xmit_recursion); - /** * dev_loopback_xmit - loop back @skb * @net: network namespace this loopback is happening in @@ -3689,23 +3841,21 @@ get_cpus_map: } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev, - select_queue_fallback_t fallback) + struct net_device *sb_dev) { return (u16)raw_smp_processor_id() % dev->real_num_tx_queues; } EXPORT_SYMBOL(dev_pick_tx_cpu_id); -static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, - struct net_device *sb_dev) +u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -3729,10 +3879,11 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, return queue_index; } +EXPORT_SYMBOL(netdev_pick_tx); -struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb, - struct net_device *sb_dev) +struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, + struct sk_buff *skb, + struct net_device *sb_dev) { int queue_index = 0; @@ -3747,10 +3898,9 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, sb_dev, - __netdev_pick_tx); + queue_index = ops->ndo_select_queue(dev, skb, sb_dev); else - queue_index = __netdev_pick_tx(dev, skb, sb_dev); + queue_index = netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } @@ -3824,7 +3974,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) else skb_dst_force(skb); - txq = netdev_pick_tx(dev, skb, sb_dev); + txq = netdev_core_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); @@ -3849,8 +3999,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) int cpu = smp_processor_id(); /* ok because BHs are off */ if (txq->xmit_lock_owner != cpu) { - if (unlikely(__this_cpu_read(xmit_recursion) > - XMIT_RECURSION_LIMIT)) + if (dev_xmit_recursion()) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); @@ -3860,9 +4009,9 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { - __this_cpu_inc(xmit_recursion); + dev_xmit_recursion_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); - __this_cpu_dec(xmit_recursion); + dev_xmit_recursion_dec(); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; @@ -3958,6 +4107,8 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; +/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ +int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -3975,9 +4126,9 @@ EXPORT_SYMBOL(rps_sock_flow_table); u32 rps_cpu_mask __read_mostly; EXPORT_SYMBOL(rps_cpu_mask); -struct static_key rps_needed __read_mostly; +struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); -struct static_key rfs_needed __read_mostly; +struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); static struct rps_dev_flow * @@ -4369,12 +4520,17 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, act = bpf_prog_run_xdp(xdp_prog, xdp); + /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; - if (off > 0) - __skb_pull(skb, off); - else if (off < 0) - __skb_push(skb, -off); - skb->mac_header += off; + if (off) { + if (off > 0) + __skb_pull(skb, off); + else if (off < 0) + __skb_push(skb, -off); + + skb->mac_header += off; + skb_reset_network_header(skb); + } /* check if bpf_xdp_adjust_tail was used. it can only "shrink" * pckt. @@ -4429,7 +4585,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) bool free_skb = true; int cpu, rc; - txq = netdev_pick_tx(dev, skb, NULL); + txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { @@ -4485,25 +4641,8 @@ static int netif_rx_internal(struct sk_buff *skb) trace_netif_rx(skb); - if (static_branch_unlikely(&generic_xdp_needed_key)) { - int ret; - - preempt_disable(); - rcu_read_lock(); - ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); - rcu_read_unlock(); - preempt_enable(); - - /* Consider XDP consuming the packet a success from - * the netdev point of view we do not want to count - * this as an error. - */ - if (ret != XDP_PASS) - return NET_RX_SUCCESS; - } - #ifdef CONFIG_RPS - if (static_key_false(&rps_needed)) { + if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; @@ -4693,9 +4832,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, __skb_push(skb, skb->mac_len); skb_do_redirect(skb); return NULL; - case TC_ACT_REINSERT: - /* this does not scrub the packet, and updates stats on error */ - skb_tc_reinsert(skb, &cl_res); + case TC_ACT_CONSUMED: return NULL; default: break; @@ -4841,6 +4978,18 @@ another_round: __this_cpu_inc(softnet_data.processed); + if (static_branch_unlikely(&generic_xdp_needed_key)) { + int ret2; + + preempt_disable(); + ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); + preempt_enable(); + + if (ret2 != XDP_PASS) + return NET_RX_DROP; + skb_reset_mac_len(skb); + } + if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || skb->protocol == cpu_to_be16(ETH_P_8021AD)) { skb = skb_vlan_untag(skb); @@ -4915,8 +5064,36 @@ skip_classify: } if (unlikely(skb_vlan_tag_present(skb))) { - if (skb_vlan_tag_get_id(skb)) +check_vlan_id: + if (skb_vlan_tag_get_id(skb)) { + /* Vlan id is non 0 and vlan_do_receive() above couldn't + * find vlan device. + */ skb->pkt_type = PACKET_OTHERHOST; + } else if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || + skb->protocol == cpu_to_be16(ETH_P_8021AD)) { + /* Outer header is 802.1P with vlan 0, inner header is + * 802.1Q or 802.1AD and vlan_do_receive() above could + * not find vlan dev for vlan id 0. + */ + __vlan_hwaccel_clear_tag(skb); + skb = skb_vlan_untag(skb); + if (unlikely(!skb)) + goto out; + if (vlan_do_receive(&skb)) + /* After stripping off 802.1P header with vlan 0 + * vlan dev is found for inner header. + */ + goto another_round; + else if (unlikely(!skb)) + goto out; + else + /* We have stripped outer 802.1P vlan 0 header. + * But could not find vlan dev. + * check again for vlan id to set OTHERHOST. + */ + goto check_vlan_id; + } /* 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 @@ -4970,7 +5147,8 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); if (pt_prev) - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, + skb->dev, pt_prev, orig_dev); return ret; } @@ -5012,7 +5190,8 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head, if (list_empty(head)) return; if (pt_prev->list_func != NULL) - pt_prev->list_func(head, pt_prev, orig_dev); + INDIRECT_CALL_INET(pt_prev->list_func, ipv6_list_rcv, + ip_list_rcv, head, pt_prev, orig_dev); else list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); @@ -5159,22 +5338,9 @@ static int netif_receive_skb_internal(struct sk_buff *skb) if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; - if (static_branch_unlikely(&generic_xdp_needed_key)) { - int ret; - - preempt_disable(); - rcu_read_lock(); - ret = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); - rcu_read_unlock(); - preempt_enable(); - - if (ret != XDP_PASS) - return NET_RX_DROP; - } - rcu_read_lock(); #ifdef CONFIG_RPS - if (static_key_false(&rps_needed)) { + if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -5192,7 +5358,6 @@ static int netif_receive_skb_internal(struct sk_buff *skb) static void netif_receive_skb_list_internal(struct list_head *head) { - struct bpf_prog *xdp_prog = NULL; struct sk_buff *skb, *next; struct list_head sublist; @@ -5205,24 +5370,9 @@ static void netif_receive_skb_list_internal(struct list_head *head) } list_splice_init(&sublist, head); - if (static_branch_unlikely(&generic_xdp_needed_key)) { - preempt_disable(); - rcu_read_lock(); - list_for_each_entry_safe(skb, next, head, list) { - xdp_prog = rcu_dereference(skb->dev->xdp_prog); - skb_list_del_init(skb); - if (do_xdp_generic(xdp_prog, skb) == XDP_PASS) - list_add_tail(&skb->list, &sublist); - } - rcu_read_unlock(); - preempt_enable(); - /* Put passed packets back on main list */ - list_splice_init(&sublist, head); - } - rcu_read_lock(); #ifdef CONFIG_RPS - if (static_key_false(&rps_needed)) { + if (static_branch_unlikely(&rps_needed)) { list_for_each_entry_safe(skb, next, head, list) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -5436,7 +5586,7 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi, diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); if (skb_vlan_tag_present(p)) - diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); diffs |= skb_metadata_dst_cmp(p, skb); diffs |= skb_metadata_differs(p, skb); if (maclen == ETH_HLEN) @@ -5461,8 +5611,7 @@ static void skb_gro_reset_offset(struct sk_buff *skb) 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 && + if (!skb_headlen(skb) && pinfo->nr_frags && !PageHighMem(skb_frag_page(frag0))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, @@ -5482,7 +5631,7 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow) skb->data_len -= grow; skb->tail += grow; - pinfo->frags[0].page_offset += grow; + skb_frag_off_add(&pinfo->frags[0], grow); skb_frag_size_sub(&pinfo->frags[0], grow); if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { @@ -5653,19 +5802,40 @@ struct packet_offload *gro_find_complete_by_type(__be16 type) } EXPORT_SYMBOL(gro_find_complete_by_type); +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + static void napi_skb_free_stolen_head(struct sk_buff *skb) { skb_dst_drop(skb); - secpath_reset(skb); + skb_ext_put(skb); kmem_cache_free(skbuff_head_cache, skb); } -static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +static gro_result_t napi_skb_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb_internal(skb)) - ret = GRO_DROP; + gro_normal_one(napi, skb); break; case GRO_DROP: @@ -5697,7 +5867,7 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) skb_gro_reset_offset(skb); - ret = napi_skb_finish(dev_gro_receive(napi, skb), skb); + ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); trace_napi_gro_receive_exit(ret); return ret; @@ -5723,7 +5893,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->encapsulation = 0; skb_shinfo(skb)->gso_type = 0; skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - secpath_reset(skb); + skb_ext_reset(skb); napi->skb = skb; } @@ -5752,8 +5922,8 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi, case GRO_HELD: __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; + if (ret == GRO_NORMAL) + gro_normal_one(napi, skb); break; case GRO_DROP: @@ -5790,7 +5960,6 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) skb_reset_mac_header(skb); skb_gro_reset_offset(skb); - 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)) { @@ -5800,6 +5969,7 @@ static struct sk_buff *napi_frags_skb(struct napi_struct *napi) return NULL; } } else { + eth = (const struct ethhdr *)skb->data; gro_pull_from_frag0(skb, hlen); NAPI_GRO_CB(skb)->frag0 += hlen; NAPI_GRO_CB(skb)->frag0_len -= hlen; @@ -6030,6 +6200,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) NAPIF_STATE_IN_BUSY_POLL))) return false; + gro_normal_list(n); + if (n->gro_bitmask) { unsigned long timeout = 0; @@ -6115,10 +6287,19 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, BUSY_POLL_BUDGET); + /* We can't gro_normal_list() here, because napi->poll() might have + * rearmed the napi (napi_complete_done()) in which case it could + * already be running on another CPU. + */ trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) + if (rc == BUSY_POLL_BUDGET) { + /* As the whole budget was spent, we still own the napi so can + * safely handle the rx_list. + */ + gro_normal_list(napi); __napi_schedule(napi); + } local_bh_enable(); } @@ -6163,6 +6344,7 @@ restart: } work = napi_poll(napi, BUSY_POLL_BUDGET); trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + gro_normal_list(napi); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), @@ -6268,6 +6450,8 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->timer.function = napi_watchdog; init_gro_hash(napi); napi->skb = NULL; + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, @@ -6364,6 +6548,8 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } + gro_normal_list(n); + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. @@ -6443,6 +6629,9 @@ struct netdev_adjacent { /* upper master flag, there can only be one master device per list */ bool master; + /* lookup ignore flag */ + bool ignore; + /* counter for the number of times this device was added to us */ u16 ref_nr; @@ -6465,7 +6654,7 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, return NULL; } -static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data) +static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) { struct net_device *dev = data; @@ -6486,7 +6675,7 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -6504,7 +6693,7 @@ EXPORT_SYMBOL(netdev_has_upper_dev); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { - return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); @@ -6548,6 +6737,22 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) } EXPORT_SYMBOL(netdev_master_upper_dev_get); +static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_adjacent *upper; + + ASSERT_RTNL(); + + if (list_empty(&dev->adj_list.upper)) + return NULL; + + upper = list_first_entry(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (likely(upper->master) && !upper->ignore) + return upper->dev; + return NULL; +} + /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device @@ -6598,6 +6803,23 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); +static struct net_device *__netdev_next_upper_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) +{ + struct netdev_adjacent *upper; + + upper = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + *ignore = upper->ignore; + + return upper->dev; +} + static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { @@ -6615,34 +6837,111 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, return upper->dev; } +static int __netdev_walk_all_upper_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + bool ignore; + + now = dev; + iter = &dev->adj_list.upper; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = __netdev_next_upper_dev(now, &iter, &ignore); + if (!udev) + break; + if (ignore) + continue; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *udev; - struct list_head *iter; - int ret; + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.upper, - udev = netdev_next_upper_dev_rcu(dev, &iter); - udev; - udev = netdev_next_upper_dev_rcu(dev, &iter)) { - /* first is the upper device itself */ - ret = fn(udev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.upper; - /* then look at all of its upper devices */ - ret = netdev_walk_all_upper_dev_rcu(udev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = netdev_next_upper_dev_rcu(now, &iter); + if (!udev) + break; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); +static bool __netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + ASSERT_RTNL(); + + return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, + upper_dev); +} + /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list @@ -6739,34 +7038,119 @@ static struct net_device *netdev_next_lower_dev(struct net_device *dev, return lower->dev; } +static struct net_device *__netdev_next_lower_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) +{ + 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; + *ignore = lower->ignore; + + return lower->dev; +} + int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *ldev; - struct list_head *iter; - int ret; + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev(dev, &iter); - ldev; - ldev = netdev_next_lower_dev(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.lower; - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev(ldev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); +static int __netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + bool ignore; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = __netdev_next_lower_dev(now, &iter, &ignore); + if (!ldev) + break; + if (ignore) + continue; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { @@ -6781,28 +7165,99 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } -int netdev_walk_all_lower_dev_rcu(struct net_device *dev, - int (*fn)(struct net_device *dev, - void *data), - void *data) +static u8 __netdev_upper_depth(struct net_device *dev) +{ + struct net_device *udev; + struct list_head *iter; + u8 max_depth = 0; + bool ignore; + + for (iter = &dev->adj_list.upper, + udev = __netdev_next_upper_dev(dev, &iter, &ignore); + udev; + udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { + if (ignore) + continue; + if (max_depth < udev->upper_level) + max_depth = udev->upper_level; + } + + return max_depth; +} + +static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; - int ret; + u8 max_depth = 0; + bool ignore; for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev_rcu(dev, &iter); + ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; - ldev = netdev_next_lower_dev_rcu(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { + if (ignore) + continue; + if (max_depth < ldev->lower_level) + max_depth = ldev->lower_level; + } - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data); - if (ret) - return ret; + return max_depth; +} + +static int __netdev_update_upper_level(struct net_device *dev, void *data) +{ + dev->upper_level = __netdev_upper_depth(dev) + 1; + return 0; +} + +static int __netdev_update_lower_level(struct net_device *dev, void *data) +{ + dev->lower_level = __netdev_lower_depth(dev) + 1; + return 0; +} + +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; @@ -6906,6 +7361,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, adj->master = master; adj->ref_nr = 1; adj->private = private; + adj->ignore = false; dev_hold(adj_dev); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", @@ -7056,14 +7512,17 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (netdev_has_upper_dev(upper_dev, dev)) + if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; + if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) + return -EMLINK; + if (!master) { - if (netdev_has_upper_dev(dev, upper_dev)) + if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { - master_dev = netdev_master_upper_dev_get(dev); + master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } @@ -7085,6 +7544,13 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) goto rollback; + __netdev_update_upper_level(dev, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); + return 0; rollback: @@ -7167,9 +7633,96 @@ void netdev_upper_dev_unlink(struct net_device *dev, call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); + + __netdev_update_upper_level(dev, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); } EXPORT_SYMBOL(netdev_upper_dev_unlink); +static void __netdev_adjacent_dev_set(struct net_device *upper_dev, + struct net_device *lower_dev, + bool val) +{ + struct netdev_adjacent *adj; + + adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); + if (adj) + adj->ignore = val; + + adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); + if (adj) + adj->ignore = val; +} + +static void netdev_adjacent_dev_disable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, true); +} + +static void netdev_adjacent_dev_enable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, false); +} + +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack) +{ + int err; + + if (!new_dev) + return 0; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_disable(dev, old_dev); + + err = netdev_upper_dev_link(new_dev, dev, extack); + if (err) { + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + return err; + } + + return 0; +} +EXPORT_SYMBOL(netdev_adjacent_change_prepare); + +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev || !old_dev) + return; + + if (new_dev == old_dev) + return; + + netdev_adjacent_dev_enable(dev, old_dev); + netdev_upper_dev_unlink(old_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_commit); + +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev) + return; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + + netdev_upper_dev_unlink(new_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_abort); + /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device @@ -7283,25 +7836,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(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); - if (max_nest < nest) - max_nest = nest; - } - - return max_nest + 1; -} -EXPORT_SYMBOL(dev_get_nest_level); - /** * netdev_lower_change - Dispatch event about lower device state change * @lower_dev: device @@ -7872,10 +8406,14 @@ int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len) { const struct net_device_ops *ops = dev->netdev_ops; + int err; - if (!ops->ndo_get_phys_port_name) - return -EOPNOTSUPP; - return ops->ndo_get_phys_port_name(dev, name, len); + if (ops->ndo_get_phys_port_name) { + err = ops->ndo_get_phys_port_name(dev, name, len); + if (err != -EOPNOTSUPP) + return err; + } + return devlink_compat_phys_port_name_get(dev, name, len); } EXPORT_SYMBOL(dev_get_phys_port_name); @@ -7895,14 +8433,21 @@ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id first = { }; struct net_device *lower_dev; struct list_head *iter; - int err = -EOPNOTSUPP; + int err; - if (ops->ndo_get_port_parent_id) - return ops->ndo_get_port_parent_id(dev, ppid); + if (ops->ndo_get_port_parent_id) { + err = ops->ndo_get_port_parent_id(dev, ppid); + if (err != -EOPNOTSUPP) + return err; + } - if (!recurse) + err = devlink_compat_switch_id_get(dev, ppid); + if (!err || err != -EOPNOTSUPP) return err; + if (!recurse) + return -EOPNOTSUPP; + netdev_for_each_lower_dev(dev, lower_dev, iter) { err = dev_get_port_parent_id(lower_dev, ppid, recurse); if (err) @@ -8073,12 +8618,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, bpf_chk = generic_xdp_install; if (fd >= 0) { + u32 prog_id; + if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) { NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time"); return -EEXIST; } - if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_query(dev, bpf_op, query)) { + + prog_id = __dev_xdp_query(dev, bpf_op, query); + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && prog_id) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } @@ -8093,6 +8641,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, bpf_prog_put(prog); return -EINVAL; } + + /* prog->aux->id may be 0 for orphaned device-bound progs */ + if (prog->aux->id && prog->aux->id == prog_id) { + bpf_prog_put(prog); + return 0; + } + } else { + if (!__dev_xdp_query(dev, bpf_op, query)) + return 0; } err = dev_xdp_install(dev, bpf_op, extack, flags, prog); @@ -8196,6 +8753,9 @@ static void rollback_registered_many(struct list_head *head) dev_uc_flush(dev); dev_mc_flush(dev); + netdev_name_node_alt_flush(dev); + netdev_name_node_free(dev->name_node); + if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -8551,7 +9111,7 @@ static void netdev_init_one_queue(struct net_device *dev, { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; @@ -8598,6 +9158,43 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); +static void netdev_register_lockdep_key(struct net_device *dev) +{ + lockdep_register_key(&dev->qdisc_tx_busylock_key); + lockdep_register_key(&dev->qdisc_running_key); + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); +} + +static void netdev_unregister_lockdep_key(struct net_device *dev) +{ + lockdep_unregister_key(&dev->qdisc_tx_busylock_key); + lockdep_unregister_key(&dev->qdisc_running_key); + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); +} + +void netdev_update_lockdep_key(struct net_device *dev) +{ + struct netdev_queue *queue; + int i; + + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); + + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); + + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); + for (i = 0; i < dev->num_tx_queues; i++) { + queue = netdev_get_tx_queue(dev, i); + + lockdep_set_class(&queue->_xmit_lock, + &dev->qdisc_xmit_lock_key); + } +} +EXPORT_SYMBOL(netdev_update_lockdep_key); + /** * register_netdevice - register a network device * @dev: device to register @@ -8632,12 +9229,17 @@ int register_netdevice(struct net_device *dev) BUG_ON(!net); spin_lock_init(&dev->addr_list_lock); - netdev_set_addr_lockdep_class(dev); + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; + ret = -ENOMEM; + dev->name_node = netdev_name_node_head_alloc(dev); + if (!dev->name_node) + goto out; + /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -8743,6 +9345,8 @@ int register_netdevice(struct net_device *dev) ret = notifier_to_errno(ret); if (ret) { rollback_registered(dev); + rcu_barrier(); + dev->reg_state = NETREG_UNREGISTERED; } /* @@ -8757,6 +9361,8 @@ out: return ret; err_uninit: + if (dev->name_node) + netdev_name_node_free(dev->name_node); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) @@ -8897,7 +9503,7 @@ static void netdev_wait_allrefs(struct net_device *dev) refcnt = netdev_refcnt_read(dev); - if (time_after(jiffies, warning_time + 10 * HZ)) { + if (refcnt && time_after(jiffies, warning_time + 10 * HZ)) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, refcnt); warning_time = jiffies; @@ -9140,8 +9746,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); + netdev_register_lockdep_key(dev); + dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->upper_level = 1; + dev->lower_level = 1; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); @@ -9222,6 +9832,8 @@ void free_netdev(struct net_device *dev) free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; + netdev_unregister_lockdep_key(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); @@ -9390,7 +10002,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); - new_nsid = peernet2id_alloc(dev_net(dev), net); + new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); /* If there is an ifindex conflict assign a new one */ if (__dev_get_by_index(net, dev->ifindex)) new_ifindex = dev_new_index(net); @@ -9565,6 +10177,8 @@ static int __net_init netdev_init(struct net *net) if (net->dev_index_head == NULL) goto err_idx; + RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); + return 0; err_idx: @@ -9691,6 +10305,8 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); + if (__dev_get_by_name(&init_net, fb_name)) + snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", |