diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/bpf_sk_storage.c | 2 | ||||
| -rw-r--r-- | net/core/datagram.c | 10 | ||||
| -rw-r--r-- | net/core/dev.c | 1036 | ||||
| -rw-r--r-- | net/core/dev_addr_lists.c | 12 | ||||
| -rw-r--r-- | net/core/devlink.c | 362 | ||||
| -rw-r--r-- | net/core/ethtool.c | 4 | ||||
| -rw-r--r-- | net/core/fib_notifier.c | 95 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 23 | ||||
| -rw-r--r-- | net/core/filter.c | 41 | ||||
| -rw-r--r-- | net/core/flow_dissector.c | 191 | ||||
| -rw-r--r-- | net/core/gen_estimator.c | 4 | ||||
| -rw-r--r-- | net/core/gen_stats.c | 12 | ||||
| -rw-r--r-- | net/core/lwt_bpf.c | 7 | ||||
| -rw-r--r-- | net/core/neighbour.c | 8 | ||||
| -rw-r--r-- | net/core/net-procfs.c | 4 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 25 | ||||
| -rw-r--r-- | net/core/net_namespace.c | 23 | ||||
| -rw-r--r-- | net/core/netprio_cgroup.c | 8 | ||||
| -rw-r--r-- | net/core/page_pool.c | 189 | ||||
| -rw-r--r-- | net/core/pktgen.c | 1 | ||||
| -rw-r--r-- | net/core/request_sock.c | 2 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 246 | ||||
| -rw-r--r-- | net/core/skbuff.c | 25 | ||||
| -rw-r--r-- | net/core/skmsg.c | 33 | ||||
| -rw-r--r-- | net/core/sock.c | 67 | ||||
| -rw-r--r-- | net/core/xdp.c | 128 |
26 files changed, 1841 insertions, 717 deletions
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index da5639a5bd3b..458be6b3eda9 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -798,7 +798,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ - map = bpf_map_inc_not_zero(&smap->map, false); + map = bpf_map_inc_not_zero(&smap->map); if (IS_ERR(map)) continue; diff --git a/net/core/datagram.c b/net/core/datagram.c index 4cc8dc5db2b7..da3c24ed129c 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -97,7 +97,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, if (error) goto out_err; - if (sk->sk_receive_queue.prev != skb) + if (READ_ONCE(sk->sk_receive_queue.prev) != skb) goto out; /* Socket shut down? */ @@ -278,7 +278,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (sk->sk_receive_queue.prev != *last); + } while (READ_ONCE(sk->sk_receive_queue.prev) != *last); error = -EAGAIN; @@ -640,7 +640,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->len += copied; skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { - sk->sk_wmem_queued += truesize; + sk_wmem_queued_add(sk, truesize); sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); @@ -767,7 +767,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); @@ -777,7 +777,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ diff --git a/net/core/dev.c b/net/core/dev.c index bf3ed413abaf..c7fc902ccbdc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,6 +146,7 @@ #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) @@ -228,6 +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) { @@ -237,7 +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); @@ -255,7 +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); @@ -276,88 +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 @@ -733,14 +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); - - hlist_for_each_entry(dev, head, name_hlist) - if (!strncmp(dev->name, name, IFNAMSIZ)) - return dev; + struct netdev_name_node *node_name; - return NULL; + node_name = netdev_name_node_lookup(net, name); + return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); @@ -758,14 +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); @@ -1141,8 +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); @@ -1158,7 +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 @@ -1232,13 +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); @@ -1617,6 +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; /** @@ -1635,8 +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; @@ -1649,17 +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: @@ -1668,22 +1740,9 @@ unlock: return err; rollback: - last = dev; - for_each_net(net) { - for_each_netdev(net, dev) { - if (dev == last) - goto outroll; - - 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); - } - } + for_each_net_continue_reverse(net) + call_netdevice_unregister_net_notifiers(nb, net); -outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@ -1734,6 +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 @@ -1745,7 +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); } @@ -2771,7 +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); @@ -2939,12 +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: @@ -2979,12 +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)); @@ -3467,7 +3607,7 @@ 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 ((q->flags & TCQ_F_CAN_BYPASS) && q->empty && + if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && qdisc_run_begin(q)) { if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { @@ -5446,7 +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) @@ -5471,8 +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, @@ -5663,6 +5802,26 @@ 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); @@ -5670,12 +5829,13 @@ static void napi_skb_free_stolen_head(struct sk_buff *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: @@ -5707,7 +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; @@ -5753,26 +5913,6 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi) } EXPORT_SYMBOL(napi_get_frags); -/* 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 gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@ -6489,6 +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; @@ -6511,7 +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; @@ -6532,7 +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); @@ -6550,7 +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); @@ -6594,6 +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 @@ -6644,6 +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) { @@ -6661,34 +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 @@ -6785,34 +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) { @@ -6827,28 +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; @@ -6952,6 +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", @@ -7102,14 +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; } @@ -7131,6 +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: @@ -7213,9 +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 @@ -7329,25 +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 @@ -8154,7 +8642,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, return -EINVAL; } - if (prog->aux->id == prog_id) { + /* 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; } @@ -8264,6 +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); @@ -8619,7 +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; @@ -8666,6 +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 @@ -8700,12 +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); @@ -8827,6 +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) @@ -9210,8 +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); @@ -9292,6 +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); @@ -9460,7 +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); @@ -9635,6 +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: diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 6393ba930097..2f949b5a1eb9 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) return; netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/core/devlink.c b/net/core/devlink.c index e48680efe54a..4c63c9a4c09e 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -95,16 +95,25 @@ static LIST_HEAD(devlink_list); */ static DEFINE_MUTEX(devlink_mutex); -static struct net *devlink_net(const struct devlink *devlink) +struct net *devlink_net(const struct devlink *devlink) { return read_pnet(&devlink->_net); } +EXPORT_SYMBOL_GPL(devlink_net); -static void devlink_net_set(struct devlink *devlink, struct net *net) +static void __devlink_net_set(struct devlink *devlink, struct net *net) { write_pnet(&devlink->_net, net); } +void devlink_net_set(struct devlink *devlink, struct net *net) +{ + if (WARN_ON(devlink->registered)) + return; + __devlink_net_set(devlink, net); +} +EXPORT_SYMBOL_GPL(devlink_net_set); + static struct devlink *devlink_get_from_attrs(struct net *net, struct nlattr **attrs) { @@ -434,8 +443,16 @@ static void devlink_nl_post_doit(const struct genl_ops *ops, { struct devlink *devlink; - devlink = devlink_get_from_info(info); - if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) + /* When devlink changes netns, it would not be found + * by devlink_get_from_info(). So try if it is stored first. + */ + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) { + devlink = info->user_ptr[0]; + } else { + devlink = devlink_get_from_info(info); + WARN_ON(IS_ERR(devlink)); + } + if (!IS_ERR(devlink) && ~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); } @@ -1035,7 +1052,7 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -1058,6 +1075,9 @@ static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -1233,7 +1253,7 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -1256,6 +1276,9 @@ static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -1460,7 +1483,7 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -1485,6 +1508,9 @@ devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -2674,6 +2700,72 @@ devlink_resources_validate(struct devlink *devlink, return err; } +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, + struct devlink_param_item *param_item, + enum devlink_command cmd); + +static void devlink_reload_netns_change(struct devlink *devlink, + struct net *dest_net) +{ + struct devlink_param_item *param_item; + + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + devlink_notify(devlink, DEVLINK_CMD_DEL); + + __devlink_net_set(devlink, dest_net); + + devlink_notify(devlink, DEVLINK_CMD_NEW); + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); +} + static bool devlink_reload_supported(struct devlink *devlink) { return devlink->ops->reload_down && devlink->ops->reload_up; @@ -2694,12 +2786,33 @@ bool devlink_is_reload_failed(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_is_reload_failed); +static int devlink_reload(struct devlink *devlink, struct net *dest_net, + struct netlink_ext_ack *extack) +{ + int err; + + if (!devlink->reload_enabled) + return -EOPNOTSUPP; + + err = devlink->ops->reload_down(devlink, !!dest_net, extack); + if (err) + return err; + + if (dest_net && !net_eq(dest_net, devlink_net(devlink))) + devlink_reload_netns_change(devlink, dest_net); + + err = devlink->ops->reload_up(devlink, extack); + devlink_reload_failed_set(devlink, !!err); + return err; +} + static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + struct net *dest_net = NULL; int err; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink) || !devlink->reload_enabled) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -2707,11 +2820,20 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); return err; } - err = devlink->ops->reload_down(devlink, info->extack); - if (err) - return err; - err = devlink->ops->reload_up(devlink, info->extack); - devlink_reload_failed_set(devlink, !!err); + + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, info->extack); + + if (dest_net) + put_net(dest_net); + return err; } @@ -2884,6 +3006,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME, .type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) @@ -3155,7 +3282,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, struct devlink *devlink; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -3172,7 +3299,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { + if (err && err != -EOPNOTSUPP) { mutex_unlock(&devlink->lock); goto out; } @@ -3183,6 +3310,9 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -3411,7 +3541,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, struct devlink *devlink; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -3432,7 +3562,7 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); - if (err) { + if (err && err != -EOPNOTSUPP) { mutex_unlock(&devlink->lock); goto out; } @@ -3444,6 +3574,9 @@ static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, out: mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -3818,29 +3951,19 @@ static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb, static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { + const struct genl_dumpit_info *info = genl_dumpit_info(cb); u64 ret_offset, start_offset, end_offset = 0; + struct nlattr **attrs = info->attrs; struct devlink_region *region; struct nlattr *chunks_attr; const char *region_name; struct devlink *devlink; - struct nlattr **attrs; bool dump = true; void *hdr; int err; start_offset = *((u64 *)&cb->args[0]); - attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL); - if (!attrs) - return -ENOMEM; - - err = nlmsg_parse_deprecated(cb->nlh, - GENL_HDRLEN + devlink_nl_family.hdrsize, - attrs, DEVLINK_ATTR_MAX, - devlink_nl_family.policy, cb->extack); - if (err) - goto out_free; - mutex_lock(&devlink_mutex); devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); if (IS_ERR(devlink)) { @@ -3917,7 +4040,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, genlmsg_end(skb, hdr); mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); - kfree(attrs); return skb->len; @@ -3927,8 +4049,6 @@ out_unlock: mutex_unlock(&devlink->lock); out_dev: mutex_unlock(&devlink_mutex); -out_free: - kfree(attrs); return err; } @@ -4066,7 +4186,7 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, struct devlink *devlink; int start = cb->args[0]; int idx = 0; - int err; + int err = 0; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { @@ -4088,12 +4208,15 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->extack); mutex_unlock(&devlink->lock); - if (err) + if (err && err != -EOPNOTSUPP) break; idx++; } mutex_unlock(&devlink_mutex); + if (err != -EMSGSIZE) + return err; + cb->args[0] = idx; return msg->len; } @@ -4296,12 +4419,11 @@ int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) +static int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) { return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } -EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value) @@ -4409,19 +4531,26 @@ int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u16 value_len) + const void *value, u32 value_len) { + u32 data_size; + u32 offset; int err; - err = devlink_fmsg_pair_nest_start(fmsg, name); + err = devlink_fmsg_arr_pair_nest_start(fmsg, name); if (err) return err; - err = devlink_fmsg_binary_put(fmsg, value, value_len); - if (err) - return err; + for (offset = 0; offset < value_len; offset += data_size) { + data_size = value_len - offset; + if (data_size > DEVLINK_FMSG_MAX_SIZE) + data_size = DEVLINK_FMSG_MAX_SIZE; + err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); + if (err) + return err; + } - err = devlink_fmsg_pair_nest_end(fmsg); + err = devlink_fmsg_arr_pair_nest_end(fmsg); if (err) return err; @@ -4618,6 +4747,7 @@ struct devlink_health_reporter { bool auto_recover; u8 health_state; u64 dump_ts; + u64 dump_real_ts; u64 error_count; u64 recovery_count; u64 last_recovery_ts; @@ -4732,14 +4862,17 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); static int devlink_health_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, struct netlink_ext_ack *extack) { int err; + if (reporter->health_state == DEVLINK_HEALTH_REPORTER_STATE_HEALTHY) + return 0; + if (!reporter->ops->recover) return -EOPNOTSUPP; - err = reporter->ops->recover(reporter, priv_ctx); + err = reporter->ops->recover(reporter, priv_ctx, extack); if (err) return err; @@ -4760,7 +4893,8 @@ devlink_health_dump_clear(struct devlink_health_reporter *reporter) } static int devlink_health_do_dump(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { int err; @@ -4781,7 +4915,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, goto dump_err; err = reporter->ops->dump(reporter, reporter->dump_fmsg, - priv_ctx); + priv_ctx, extack); if (err) goto dump_err; @@ -4790,6 +4924,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, goto dump_err; reporter->dump_ts = jiffies; + reporter->dump_real_ts = ktime_get_real_ns(); return 0; @@ -4828,11 +4963,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, mutex_lock(&reporter->dump_lock); /* store current dump of current error, for later analysis */ - devlink_health_do_dump(reporter, priv_ctx); + devlink_health_do_dump(reporter, priv_ctx, NULL); mutex_unlock(&reporter->dump_lock); if (reporter->auto_recover) - return devlink_health_reporter_recover(reporter, priv_ctx); + return devlink_health_reporter_recover(reporter, + priv_ctx, NULL); return 0; } @@ -4867,21 +5003,10 @@ devlink_health_reporter_get_from_info(struct devlink *devlink, static struct devlink_health_reporter * devlink_health_reporter_get_from_cb(struct netlink_callback *cb) { + const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_health_reporter *reporter; + struct nlattr **attrs = info->attrs; struct devlink *devlink; - struct nlattr **attrs; - int err; - - attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL); - if (!attrs) - return NULL; - - err = nlmsg_parse_deprecated(cb->nlh, - GENL_HDRLEN + devlink_nl_family.hdrsize, - attrs, DEVLINK_ATTR_MAX, - devlink_nl_family.policy, cb->extack); - if (err) - goto free; mutex_lock(&devlink_mutex); devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); @@ -4890,12 +5015,9 @@ devlink_health_reporter_get_from_cb(struct netlink_callback *cb) reporter = devlink_health_reporter_get_from_attrs(devlink, attrs); mutex_unlock(&devlink_mutex); - kfree(attrs); return reporter; unlock: mutex_unlock(&devlink_mutex); -free: - kfree(attrs); return NULL; } @@ -4952,6 +5074,10 @@ devlink_nl_health_reporter_fill(struct sk_buff *msg, jiffies_to_msecs(reporter->dump_ts), DEVLINK_ATTR_PAD)) goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS_NS, + reporter->dump_real_ts, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; nla_nest_end(msg, reporter_attr); genlmsg_end(msg, hdr); @@ -5084,7 +5210,7 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, if (!reporter) return -EINVAL; - err = devlink_health_reporter_recover(reporter, NULL); + err = devlink_health_reporter_recover(reporter, NULL, info->extack); devlink_health_reporter_put(reporter); return err; @@ -5117,7 +5243,7 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, if (err) goto out; - err = reporter->ops->diagnose(reporter, fmsg); + err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) goto out; @@ -5152,7 +5278,7 @@ devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, } mutex_lock(&reporter->dump_lock); if (!start) { - err = devlink_health_do_dump(reporter, NULL); + err = devlink_health_do_dump(reporter, NULL, cb->extack); if (err) goto unlock; cb->args[1] = reporter->dump_ts; @@ -5793,6 +5919,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -6023,7 +6152,8 @@ static const struct genl_ops devlink_nl_ops[] = { }, { .cmd = DEVLINK_CMD_REGION_READ, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT | + GENL_DONT_VALIDATE_DUMP_STRICT, .dumpit = devlink_nl_cmd_region_read_dumpit, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, @@ -6071,7 +6201,8 @@ static const struct genl_ops devlink_nl_ops[] = { }, { .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT | + GENL_DONT_VALIDATE_DUMP_STRICT, .dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | @@ -6155,7 +6286,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) if (!devlink) return NULL; devlink->ops = ops; - devlink_net_set(devlink, &init_net); + __devlink_net_set(devlink, &init_net); INIT_LIST_HEAD(&devlink->port_list); INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); @@ -6181,6 +6312,7 @@ int devlink_register(struct devlink *devlink, struct device *dev) { mutex_lock(&devlink_mutex); devlink->dev = dev; + devlink->registered = true; list_add_tail(&devlink->list, &devlink_list); devlink_notify(devlink, DEVLINK_CMD_NEW); mutex_unlock(&devlink_mutex); @@ -6196,6 +6328,8 @@ EXPORT_SYMBOL_GPL(devlink_register); void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); + WARN_ON(devlink_reload_supported(devlink) && + devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); mutex_unlock(&devlink_mutex); @@ -6203,6 +6337,41 @@ void devlink_unregister(struct devlink *devlink) EXPORT_SYMBOL_GPL(devlink_unregister); /** + * devlink_reload_enable - Enable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at end of device initialization + * process when reload operation is supported. + */ +void devlink_reload_enable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink->reload_enabled = true; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_enable); + +/** + * devlink_reload_disable - Disable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at the beginning of device cleanup + * process when reload operation is supported. + */ +void devlink_reload_disable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + /* Mutex is taken which ensures that no reload operation is in + * progress while setting up forbidded flag. + */ + devlink->reload_enabled = false; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_disable); + +/** * devlink_free - Free devlink instance resources * * @devlink: devlink @@ -7490,6 +7659,21 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), DEVLINK_TRAP(TTL_ERROR, EXCEPTION), DEVLINK_TRAP(TAIL_DROP, DROP), + DEVLINK_TRAP(NON_IP_PACKET, DROP), + DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP), + DEVLINK_TRAP(DIP_LB, DROP), + DEVLINK_TRAP(SIP_MC, DROP), + DEVLINK_TRAP(SIP_LB, DROP), + DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP), + DEVLINK_TRAP(IPV4_SIP_BC, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP), + DEVLINK_TRAP(MTU_ERROR, EXCEPTION), + DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION), + DEVLINK_TRAP(RPF, EXCEPTION), + DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), + DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), + DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -8060,9 +8244,43 @@ int devlink_compat_switch_id_get(struct net_device *dev, return 0; } +static void __net_exit devlink_pernet_pre_exit(struct net *net) +{ + struct devlink *devlink; + int err; + + /* In case network namespace is getting destroyed, reload + * all devlink instances from this namespace into init_net. + */ + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (net_eq(devlink_net(devlink), net)) { + if (WARN_ON(!devlink_reload_supported(devlink))) + continue; + err = devlink_reload(devlink, &init_net, NULL); + if (err && err != -EOPNOTSUPP) + pr_warn("Failed to reload devlink instance into init_net\n"); + } + } + mutex_unlock(&devlink_mutex); +} + +static struct pernet_operations devlink_pernet_ops __net_initdata = { + .pre_exit = devlink_pernet_pre_exit, +}; + static int __init devlink_init(void) { - return genl_register_family(&devlink_nl_family); + int err; + + err = genl_register_family(&devlink_nl_family); + if (err) + goto out; + err = register_pernet_subsys(&devlink_pernet_ops); + +out: + WARN_ON(err); + return err; } subsys_initcall(devlink_init); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c763106c73fc..cd9bc67381b2 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1396,11 +1396,13 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr) static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + struct ethtool_wolinfo wol; if (!dev->ethtool_ops->get_wol) return -EOPNOTSUPP; + memset(&wol, 0, sizeof(struct ethtool_wolinfo)); + wol.cmd = ETHTOOL_GWOL; dev->ethtool_ops->get_wol(dev, &wol); if (copy_to_user(useraddr, &wol, sizeof(wol))) diff --git a/net/core/fib_notifier.c b/net/core/fib_notifier.c index 470a606d5e8d..fc96259807b6 100644 --- a/net/core/fib_notifier.c +++ b/net/core/fib_notifier.c @@ -12,17 +12,15 @@ static unsigned int fib_notifier_net_id; struct fib_notifier_net { struct list_head fib_notifier_ops; + struct atomic_notifier_head fib_chain; }; -static ATOMIC_NOTIFIER_HEAD(fib_chain); - -int call_fib_notifier(struct notifier_block *nb, struct net *net, +int call_fib_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { int err; - info->net = net; err = nb->notifier_call(nb, event_type, info); return notifier_to_errno(err); } @@ -31,106 +29,100 @@ EXPORT_SYMBOL(call_fib_notifier); int call_fib_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info) { + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); int err; - info->net = net; - err = atomic_notifier_call_chain(&fib_chain, event_type, info); + err = atomic_notifier_call_chain(&fn_net->fib_chain, event_type, info); return notifier_to_errno(err); } EXPORT_SYMBOL(call_fib_notifiers); -static unsigned int fib_seq_sum(void) +static unsigned int fib_seq_sum(struct net *net) { - struct fib_notifier_net *fn_net; + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; unsigned int fib_seq = 0; - struct net *net; rtnl_lock(); - down_read(&net_rwsem); - for_each_net(net) { - fn_net = net_generic(net, fib_notifier_net_id); - rcu_read_lock(); - list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { - if (!try_module_get(ops->owner)) - continue; - fib_seq += ops->fib_seq_read(net); - module_put(ops->owner); - } - rcu_read_unlock(); + rcu_read_lock(); + list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { + if (!try_module_get(ops->owner)) + continue; + fib_seq += ops->fib_seq_read(net); + module_put(ops->owner); } - up_read(&net_rwsem); + rcu_read_unlock(); rtnl_unlock(); return fib_seq; } -static int fib_net_dump(struct net *net, struct notifier_block *nb) +static int fib_net_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); struct fib_notifier_ops *ops; + int err = 0; + rcu_read_lock(); list_for_each_entry_rcu(ops, &fn_net->fib_notifier_ops, list) { - int err; - if (!try_module_get(ops->owner)) continue; - err = ops->fib_dump(net, nb); + err = ops->fib_dump(net, nb, extack); module_put(ops->owner); if (err) - return err; + goto unlock; } - return 0; +unlock: + rcu_read_unlock(); + + return err; } -static bool fib_dump_is_consistent(struct notifier_block *nb, +static bool fib_dump_is_consistent(struct net *net, struct notifier_block *nb, void (*cb)(struct notifier_block *nb), unsigned int fib_seq) { - atomic_notifier_chain_register(&fib_chain, nb); - if (fib_seq == fib_seq_sum()) + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); + + atomic_notifier_chain_register(&fn_net->fib_chain, nb); + if (fib_seq == fib_seq_sum(net)) return true; - atomic_notifier_chain_unregister(&fib_chain, nb); + atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); if (cb) cb(nb); return false; } #define FIB_DUMP_MAX_RETRIES 5 -int register_fib_notifier(struct notifier_block *nb, - void (*cb)(struct notifier_block *nb)) +int register_fib_notifier(struct net *net, struct notifier_block *nb, + void (*cb)(struct notifier_block *nb), + struct netlink_ext_ack *extack) { int retries = 0; int err; do { - unsigned int fib_seq = fib_seq_sum(); - struct net *net; - - rcu_read_lock(); - for_each_net_rcu(net) { - err = fib_net_dump(net, nb); - if (err) - goto err_fib_net_dump; - } - rcu_read_unlock(); - - if (fib_dump_is_consistent(nb, cb, fib_seq)) + unsigned int fib_seq = fib_seq_sum(net); + + err = fib_net_dump(net, nb, extack); + if (err) + return err; + + if (fib_dump_is_consistent(net, nb, cb, fib_seq)) return 0; } while (++retries < FIB_DUMP_MAX_RETRIES); return -EBUSY; - -err_fib_net_dump: - rcu_read_unlock(); - return err; } EXPORT_SYMBOL(register_fib_notifier); -int unregister_fib_notifier(struct notifier_block *nb) +int unregister_fib_notifier(struct net *net, struct notifier_block *nb) { - return atomic_notifier_chain_unregister(&fib_chain, nb); + struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); + + return atomic_notifier_chain_unregister(&fn_net->fib_chain, nb); } EXPORT_SYMBOL(unregister_fib_notifier); @@ -181,6 +173,7 @@ static int __net_init fib_notifier_net_init(struct net *net) struct fib_notifier_net *fn_net = net_generic(net, fib_notifier_net_id); INIT_LIST_HEAD(&fn_net->fib_notifier_ops); + ATOMIC_INIT_NOTIFIER_HEAD(&fn_net->fib_chain); return 0; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index dd220ce7ca7a..3e7e15278c46 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -321,16 +321,18 @@ out: } EXPORT_SYMBOL_GPL(fib_rules_lookup); -static int call_fib_rule_notifier(struct notifier_block *nb, struct net *net, +static int call_fib_rule_notifier(struct notifier_block *nb, enum fib_event_type event_type, - struct fib_rule *rule, int family) + struct fib_rule *rule, int family, + struct netlink_ext_ack *extack) { struct fib_rule_notifier_info info = { .info.family = family, + .info.extack = extack, .rule = rule, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static int call_fib_rule_notifiers(struct net *net, @@ -350,20 +352,25 @@ static int call_fib_rule_notifiers(struct net *net, } /* Called with rcu_read_lock() */ -int fib_rules_dump(struct net *net, struct notifier_block *nb, int family) +int fib_rules_dump(struct net *net, struct notifier_block *nb, int family, + struct netlink_ext_ack *extack) { struct fib_rules_ops *ops; struct fib_rule *rule; + int err = 0; ops = lookup_rules_ops(net, family); if (!ops) return -EAFNOSUPPORT; - list_for_each_entry_rcu(rule, &ops->rules_list, list) - call_fib_rule_notifier(nb, net, FIB_EVENT_RULE_ADD, rule, - family); + list_for_each_entry_rcu(rule, &ops->rules_list, list) { + err = call_fib_rule_notifier(nb, FIB_EVENT_RULE_ADD, + rule, family, extack); + if (err) + break; + } rules_ops_put(ops); - return 0; + return err; } EXPORT_SYMBOL_GPL(fib_rules_dump); diff --git a/net/core/filter.c b/net/core/filter.c index ed6563622ce3..b0ed048585ba 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2245,7 +2245,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!msg->sg.copy[i] && bytes_sg_total <= len) + if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist @@ -2450,7 +2450,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; - msg->sg.copy[new] = false; + __clear_bit(new, &msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); @@ -3798,7 +3798,7 @@ BPF_CALL_5(bpf_skb_event_output, struct sk_buff *, skb, struct bpf_map *, map, if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; - if (unlikely(skb_size > skb->len)) + if (unlikely(!skb || skb_size > skb->len)) return -EFAULT; return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, @@ -3816,6 +3816,19 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; +static int bpf_skb_output_btf_ids[5]; +const struct bpf_func_proto bpf_skb_output_proto = { + .func = bpf_skb_event_output, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_skb_output_btf_ids, +}; + static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; @@ -4089,7 +4102,7 @@ BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return cgrp->kn->id.id; + return cgroup_id(cgrp); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4114,7 +4127,7 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, if (!ancestor) return 0; - return ancestor->kn->id.id; + return cgroup_id(ancestor); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { @@ -4252,12 +4265,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, case SO_RCVBUF: val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); break; case SO_MAX_PACING_RATE: /* 32bit version */ if (val != ~0U) @@ -4274,7 +4289,7 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_MARK: if (sk->sk_mark != val) { @@ -8669,16 +8684,6 @@ out: } #ifdef CONFIG_INET -struct sk_reuseport_kern { - struct sk_buff *skb; - struct sock *sk; - struct sock *selected_sk; - void *data_end; - u32 hash; - u32 reuseport_id; - bool bind_inany; -}; - static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern, struct sock_reuseport *reuse, struct sock *sk, struct sk_buff *skb, diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7c09d87d3269..ca871657a4c4 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -114,19 +114,50 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, { struct bpf_prog *attached; struct net *net; + int ret = 0; net = current->nsproxy->net_ns; mutex_lock(&flow_dissector_mutex); + + if (net == &init_net) { + /* BPF flow dissector in the root namespace overrides + * any per-net-namespace one. When attaching to root, + * make sure we don't have any BPF program attached + * to the non-root namespaces. + */ + struct net *ns; + + for_each_net(ns) { + if (ns == &init_net) + continue; + if (rcu_access_pointer(ns->flow_dissector_prog)) { + ret = -EEXIST; + goto out; + } + } + } else { + /* Make sure root flow dissector is not attached + * when attaching to the non-root namespace. + */ + if (rcu_access_pointer(init_net.flow_dissector_prog)) { + ret = -EEXIST; + goto out; + } + } + attached = rcu_dereference_protected(net->flow_dissector_prog, lockdep_is_held(&flow_dissector_mutex)); - if (attached) { - /* Only one BPF program can be attached at a time */ - mutex_unlock(&flow_dissector_mutex); - return -EEXIST; + if (attached == prog) { + /* The same program cannot be attached twice */ + ret = -EINVAL; + goto out; } rcu_assign_pointer(net->flow_dissector_prog, prog); + if (attached) + bpf_prog_put(attached); +out: mutex_unlock(&flow_dissector_mutex); - return 0; + return ret; } int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) @@ -147,27 +178,6 @@ int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) mutex_unlock(&flow_dissector_mutex); return 0; } -/** - * skb_flow_get_be16 - extract be16 entity - * @skb: sk_buff to extract from - * @poff: offset to extract at - * @data: raw buffer pointer to the packet - * @hlen: packet header length - * - * The function will try to retrieve a be32 entity at - * offset poff - */ -static __be16 skb_flow_get_be16(const struct sk_buff *skb, int poff, - void *data, int hlen) -{ - __be16 *u, _u; - - u = __skb_header_pointer(skb, poff, sizeof(_u), data, hlen, &_u); - if (u) - return *u; - - return 0; -} /** * __skb_flow_get_ports - extract the upper layer ports and return them @@ -203,6 +213,72 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, } EXPORT_SYMBOL(__skb_flow_get_ports); +static bool icmp_has_id(u8 type) +{ + switch (type) { + case ICMP_ECHO: + case ICMP_ECHOREPLY: + case ICMP_TIMESTAMP: + case ICMP_TIMESTAMPREPLY: + case ICMPV6_ECHO_REQUEST: + case ICMPV6_ECHO_REPLY: + return true; + } + + return false; +} + +/** + * skb_flow_get_icmp_tci - extract ICMP(6) Type, Code and Identifier fields + * @skb: sk_buff to extract from + * @key_icmp: struct flow_dissector_key_icmp to fill + * @data: raw buffer pointer to the packet + * @toff: offset to extract at + * @hlen: packet header length + */ +void skb_flow_get_icmp_tci(const struct sk_buff *skb, + struct flow_dissector_key_icmp *key_icmp, + void *data, int thoff, int hlen) +{ + struct icmphdr *ih, _ih; + + ih = __skb_header_pointer(skb, thoff, sizeof(_ih), data, hlen, &_ih); + if (!ih) + return; + + key_icmp->type = ih->type; + key_icmp->code = ih->code; + + /* As we use 0 to signal that the Id field is not present, + * avoid confusion with packets without such field + */ + if (icmp_has_id(ih->type)) + key_icmp->id = ih->un.echo.id ? : 1; + else + key_icmp->id = 0; +} +EXPORT_SYMBOL(skb_flow_get_icmp_tci); + +/* If FLOW_DISSECTOR_KEY_ICMP is set, dissect an ICMP packet + * using skb_flow_get_icmp_tci(). + */ +static void __skb_flow_dissect_icmp(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container, + void *data, int thoff, int hlen) +{ + struct flow_dissector_key_icmp *key_icmp; + + if (!dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ICMP)) + return; + + key_icmp = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_ICMP, + target_container); + + skb_flow_get_icmp_tci(skb, key_icmp, data, thoff, hlen); +} + void skb_flow_dissect_meta(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container) @@ -853,7 +929,6 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_basic *key_basic; struct flow_dissector_key_addrs *key_addrs; struct flow_dissector_key_ports *key_ports; - struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; struct bpf_prog *attached = NULL; @@ -910,7 +985,10 @@ bool __skb_flow_dissect(const struct net *net, WARN_ON_ONCE(!net); if (net) { rcu_read_lock(); - attached = rcu_dereference(net->flow_dissector_prog); + attached = rcu_dereference(init_net.flow_dissector_prog); + + if (!attached) + attached = rcu_dereference(net->flow_dissector_prog); if (attached) { struct bpf_flow_keys flow_keys; @@ -1295,6 +1373,12 @@ ip_proto_again: data, nhoff, hlen); break; + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: + __skb_flow_dissect_icmp(skb, flow_dissector, target_container, + data, nhoff, hlen); + break; + default: break; } @@ -1308,14 +1392,6 @@ ip_proto_again: data, hlen); } - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_ICMP)) { - key_icmp = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_ICMP, - target_container); - key_icmp->icmp = skb_flow_get_be16(skb, nhoff, data, hlen); - } - /* Process result of IP proto processing */ switch (fdret) { case FLOW_DISSECT_RET_PROTO_AGAIN: @@ -1350,32 +1426,23 @@ out_bad: } EXPORT_SYMBOL(__skb_flow_dissect); -static u32 hashrnd __read_mostly; +static siphash_key_t hashrnd __read_mostly; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } -static __always_inline u32 __flow_hash_words(const u32 *words, u32 length, - u32 keyval) -{ - return jhash2(words, length, keyval); -} - -static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow) +static const void *flow_keys_hash_start(const struct flow_keys *flow) { - const void *p = flow; - - BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32)); - return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET); + BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); + return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); + BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); - BUILD_BUG_ON(offsetof(typeof(*flow), addrs) != - sizeof(*flow) - sizeof(flow->addrs)); switch (flow->control.addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: @@ -1388,7 +1455,7 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow) diff -= sizeof(flow->addrs.tipckey); break; } - return (sizeof(*flow) - diff) / sizeof(u32); + return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) @@ -1421,6 +1488,9 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow) } EXPORT_SYMBOL(flow_get_u32_dst); +/* Sort the source and destination IP (and the ports if the IP are the same), + * to have consistent hash within the two directions + */ static inline void __flow_hash_consistentify(struct flow_keys *keys) { int addr_diff, i; @@ -1454,14 +1524,15 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) } } -static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) +static inline u32 __flow_hash_from_keys(struct flow_keys *keys, + const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); - hash = __flow_hash_words(flow_keys_hash_start(keys), - flow_keys_hash_length(keys), keyval); + hash = siphash(flow_keys_hash_start(keys), + flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; @@ -1471,12 +1542,13 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); - return __flow_hash_from_keys(keys, hashrnd); + return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); static inline u32 ___skb_get_hash(const struct sk_buff *skb, - struct flow_keys *keys, u32 keyval) + struct flow_keys *keys, + const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); @@ -1524,7 +1596,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb) &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); - return __flow_hash_from_keys(&keys, hashrnd); + return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); @@ -1544,13 +1616,14 @@ void __skb_get_hash(struct sk_buff *skb) __flow_hash_secret_init(); - hash = ___skb_get_hash(skb, &keys, hashrnd); + hash = ___skb_get_hash(skb, &keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); -__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) +__u32 skb_get_hash_perturb(const struct sk_buff *skb, + const siphash_key_t *perturb) { struct flow_keys keys; diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index bfe7bdd4c340..80dbf2f4016e 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -48,7 +48,7 @@ struct net_rate_estimator { u8 intvl_log; /* period : (250ms << intvl_log) */ seqcount_t seq; - u32 last_packets; + u64 last_packets; u64 last_bytes; u64 avpps; @@ -83,7 +83,7 @@ static void est_timer(struct timer_list *t) brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log); brate -= (est->avbps >> est->ewma_log); - rate = (u64)(b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log); + rate = (b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log); rate -= (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 36888f5e09eb..1d653fbfcf52 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -123,8 +123,7 @@ __gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats, for_each_possible_cpu(i) { struct gnet_stats_basic_cpu *bcpu = per_cpu_ptr(cpu, i); unsigned int start; - u64 bytes; - u32 packets; + u64 bytes, packets; do { start = u64_stats_fetch_begin_irq(&bcpu->syncp); @@ -176,12 +175,17 @@ ___gnet_stats_copy_basic(const seqcount_t *running, if (d->tail) { struct gnet_stats_basic sb; + int res; memset(&sb, 0, sizeof(sb)); sb.bytes = bstats.bytes; sb.packets = bstats.packets; - return gnet_stats_copy(d, type, &sb, sizeof(sb), - TCA_STATS_PAD); + res = gnet_stats_copy(d, type, &sb, sizeof(sb), TCA_STATS_PAD); + if (res < 0 || sb.packets == bstats.packets) + return res; + /* emit 64bit stats only if needed */ + return gnet_stats_copy(d, TCA_STATS_PKT64, &bstats.packets, + sizeof(bstats.packets), TCA_STATS_PAD); } return 0; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index f93785e5833c..74cfb8b5ab33 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -88,11 +88,16 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb) int err = -EINVAL; if (skb->protocol == htons(ETH_P_IP)) { + struct net_device *dev = skb_dst(skb)->dev; struct iphdr *iph = ip_hdr(skb); + dev_hold(dev); + skb_dst_drop(skb); err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, skb_dst(skb)->dev); + iph->tos, dev); + dev_put(dev); } else if (skb->protocol == htons(ETH_P_IPV6)) { + skb_dst_drop(skb); err = ipv6_stub->ipv6_route_input(skb); } else { err = -EAFNOSUPPORT; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5480edff0c86..652da6369037 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1197,7 +1197,7 @@ static void neigh_update_hhs(struct neighbour *neigh) if (update) { hh = &neigh->hh; - if (hh->hh_len) { + if (READ_ONCE(hh->hh_len)) { write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); write_sequnlock_bh(&hh->hh_lock); @@ -1476,7 +1476,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) struct net_device *dev = neigh->dev; unsigned int seq; - if (dev->header_ops->cache && !neigh->hh.hh_len) + if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len)) neigh_hh_init(neigh); do { @@ -2052,8 +2052,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, goto nla_put_failure; { unsigned long now = jiffies; - unsigned int flush_delta = now - tbl->last_flush; - unsigned int rand_delta = now - tbl->last_rand; + long flush_delta = now - tbl->last_flush; + long rand_delta = now - tbl->last_rand; struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 36347933ec3a..6bbd06f7dc7d 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -20,8 +20,8 @@ static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff struct hlist_head *h; unsigned int count = 0, offset = get_offset(*pos); - h = &net->dev_name_head[get_bucket(*pos)]; - hlist_for_each_entry_rcu(dev, h, name_hlist) { + h = &net->dev_index_head[get_bucket(*pos)]; + hlist_for_each_entry_rcu(dev, h, index_hlist) { if (++count == offset) return dev; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 865ba6ca16eb..ae3bcb1540ec 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -923,21 +923,23 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, "rx-%u", index); if (error) - return error; + goto err; dev_hold(queue->dev); if (dev->sysfs_rx_queue_group) { error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group); - if (error) { - kobject_put(kobj); - return error; - } + if (error) + goto err; } kobject_uevent(kobj, KOBJ_ADD); return error; + +err: + kobject_put(kobj); + return error; } #endif /* CONFIG_SYSFS */ @@ -1461,21 +1463,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, "tx-%u", index); if (error) - return error; + goto err; dev_hold(queue->dev); #ifdef CONFIG_BQL error = sysfs_create_group(kobj, &dql_group); - if (error) { - kobject_put(kobj); - return error; - } + if (error) + goto err; #endif kobject_uevent(kobj, KOBJ_ADD); - return 0; + +err: + kobject_put(kobj); + return error; } #endif /* CONFIG_SYSFS */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a0e0d298c991..39402840025e 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -245,11 +245,12 @@ static int __peernet2id(struct net *net, struct net *peer) return __peernet2id_alloc(net, peer, &no); } -static void rtnl_net_notifyid(struct net *net, int cmd, int id); +static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, + struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ -int peernet2id_alloc(struct net *net, struct net *peer) +int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { bool alloc = false, alive = false; int id; @@ -268,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer) id = __peernet2id_alloc(net, peer, &alloc); spin_unlock_bh(&net->nsid_lock); if (alloc && id >= 0) - rtnl_net_notifyid(net, RTM_NEWNSID, id); + rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); if (alive) put_net(peer); return id; @@ -478,6 +479,7 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) { put_userns: + key_remove_domain(net->key_domain); put_user_ns(user_ns); net_drop_ns(net); dec_ucounts: @@ -532,7 +534,8 @@ static void unhash_nsid(struct net *net, struct net *last) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) - rtnl_net_notifyid(tmp, RTM_DELNSID, id); + rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, + GFP_KERNEL); if (tmp == last) break; } @@ -764,7 +767,8 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { - rtnl_net_notifyid(net, RTM_NEWNSID, err); + rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, + nlh, GFP_KERNEL); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; @@ -1051,16 +1055,19 @@ end: return err < 0 ? err : skb->len; } -static void rtnl_net_notifyid(struct net *net, int cmd, int id) +static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, + struct nlmsghdr *nlh, gfp_t gfp) { struct net_fill_args fillargs = { + .portid = portid, + .seq = nlh ? nlh->nlmsg_seq : 0, .cmd = cmd, .nsid = id, }; struct sk_buff *msg; int err = -ENOMEM; - msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); + msg = nlmsg_new(rtnl_net_get_size(), gfp); if (!msg) goto out; @@ -1068,7 +1075,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id) if (err < 0) goto err_out; - rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0); + rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp); return; err_out: diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 256b7954b720..8881dd943dd0 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -93,7 +93,7 @@ static int extend_netdev_table(struct net_device *dev, u32 target_idx) static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev) { struct netprio_map *map = rcu_dereference_rtnl(dev->priomap); - int id = css->cgroup->id; + int id = css->id; if (map && id < map->priomap_len) return map->priomap[id]; @@ -113,7 +113,7 @@ static int netprio_set_prio(struct cgroup_subsys_state *css, struct net_device *dev, u32 prio) { struct netprio_map *map; - int id = css->cgroup->id; + int id = css->id; int ret; /* avoid extending priomap for zero writes */ @@ -177,7 +177,7 @@ static void cgrp_css_free(struct cgroup_subsys_state *css) static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft) { - return css->cgroup->id; + return css->id; } static int read_priomap(struct seq_file *sf, void *v) @@ -237,7 +237,7 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; cgroup_taskset_for_each(p, css, tset) { - void *v = (void *)(unsigned long)css->cgroup->id; + void *v = (void *)(unsigned long)css->id; task_lock(p); iterate_fd(p->files, 0, update_netprio, v); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5bc65587f1c4..a6aefe989043 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -18,6 +18,9 @@ #include <trace/events/page_pool.h> +#define DEFER_TIME (msecs_to_jiffies(1000)) +#define DEFER_WARN_INTERVAL (60 * HZ) + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -44,6 +47,21 @@ static int page_pool_init(struct page_pool *pool, (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) { + /* In order to request DMA-sync-for-device the page + * needs to be mapped + */ + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + return -EINVAL; + + if (!pool->p.max_len) + return -EINVAL; + + /* pool->p.offset has to be set according to the address + * offset used by the DMA engine to start copying rx data + */ + } + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; @@ -112,6 +130,16 @@ static struct page *__page_pool_get_cached(struct page_pool *pool) return page; } +static void page_pool_dma_sync_for_device(struct page_pool *pool, + struct page *page, + unsigned int dma_sync_size) +{ + dma_sync_size = min(dma_sync_size, pool->p.max_len); + dma_sync_single_range_for_device(pool->p.dev, page->dma_addr, + pool->p.offset, dma_sync_size, + pool->p.dma_dir); +} + /* slow path */ noinline static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, @@ -156,6 +184,9 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, } page->dma_addr = dma; + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + page_pool_dma_sync_for_device(pool, page, pool->p.max_len); + skip_dma_map: /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -193,22 +224,14 @@ static s32 page_pool_inflight(struct page_pool *pool) { u32 release_cnt = atomic_read(&pool->pages_state_release_cnt); u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt); - s32 distance; + s32 inflight; - distance = _distance(hold_cnt, release_cnt); + inflight = _distance(hold_cnt, release_cnt); - trace_page_pool_inflight(pool, distance, hold_cnt, release_cnt); - return distance; -} - -static bool __page_pool_safe_to_destroy(struct page_pool *pool) -{ - s32 inflight = page_pool_inflight(pool); - - /* The distance should not be able to become negative */ + trace_page_pool_release(pool, inflight, hold_cnt, release_cnt); WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight); - return (inflight == 0); + return inflight; } /* Cleanup page_pool state from page */ @@ -216,6 +239,7 @@ static void __page_pool_clean_page(struct page_pool *pool, struct page *page) { dma_addr_t dma; + int count; if (!(pool->p.flags & PP_FLAG_DMA_MAP)) goto skip_dma_unmap; @@ -227,9 +251,11 @@ static void __page_pool_clean_page(struct page_pool *pool, DMA_ATTR_SKIP_CPU_SYNC); page->dma_addr = 0; skip_dma_unmap: - atomic_inc(&pool->pages_state_release_cnt); - trace_page_pool_state_release(pool, page, - atomic_read(&pool->pages_state_release_cnt)); + /* This may be the last page returned, releasing the pool, so + * it is not safe to reference pool afterwards. + */ + count = atomic_inc_return(&pool->pages_state_release_cnt); + trace_page_pool_state_release(pool, page, count); } /* unmap the page and clean our state */ @@ -283,8 +309,19 @@ static bool __page_pool_recycle_direct(struct page *page, return true; } -void __page_pool_put_page(struct page_pool *pool, - struct page *page, bool allow_direct) +/* page is NOT reusable when: + * 1) allocated when system is under some pressure. (page_is_pfmemalloc) + * 2) belongs to a different NUMA node than pool->p.nid. + * + * To update pool->p.nid users must call page_pool_update_nid. + */ +static bool pool_page_reusable(struct page_pool *pool, struct page *page) +{ + return !page_is_pfmemalloc(page) && page_to_nid(page) == pool->p.nid; +} + +void __page_pool_put_page(struct page_pool *pool, struct page *page, + unsigned int dma_sync_size, bool allow_direct) { /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the @@ -292,9 +329,14 @@ void __page_pool_put_page(struct page_pool *pool, * * refcnt == 1 means page_pool owns page, and can recycle it. */ - if (likely(page_ref_count(page) == 1)) { + if (likely(page_ref_count(page) == 1 && + pool_page_reusable(pool, page))) { /* Read barrier done in page_ref_count / READ_ONCE */ + if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) + page_pool_dma_sync_for_device(pool, page, + dma_sync_size); + if (allow_direct && in_serving_softirq()) if (__page_pool_recycle_direct(page, pool)) return; @@ -338,31 +380,10 @@ static void __page_pool_empty_ring(struct page_pool *pool) } } -static void __warn_in_flight(struct page_pool *pool) +static void page_pool_free(struct page_pool *pool) { - u32 release_cnt = atomic_read(&pool->pages_state_release_cnt); - u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt); - s32 distance; - - distance = _distance(hold_cnt, release_cnt); - - /* Drivers should fix this, but only problematic when DMA is used */ - WARN(1, "Still in-flight pages:%d hold:%u released:%u", - distance, hold_cnt, release_cnt); -} - -void __page_pool_free(struct page_pool *pool) -{ - /* Only last user actually free/release resources */ - if (!page_pool_put(pool)) - return; - - WARN(pool->alloc.count, "API usage violation"); - WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty"); - - /* Can happen due to forced shutdown */ - if (!__page_pool_safe_to_destroy(pool)) - __warn_in_flight(pool); + if (pool->disconnect) + pool->disconnect(pool); ptr_ring_cleanup(&pool->ring, NULL); @@ -371,15 +392,14 @@ void __page_pool_free(struct page_pool *pool) kfree(pool); } -EXPORT_SYMBOL(__page_pool_free); -/* Request to shutdown: release pages cached by page_pool, and check - * for in-flight pages - */ -bool __page_pool_request_shutdown(struct page_pool *pool) +static void page_pool_empty_alloc_cache_once(struct page_pool *pool) { struct page *page; + if (pool->destroy_cnt) + return; + /* Empty alloc cache, assume caller made sure this is * no-longer in use, and page_pool_alloc_pages() cannot be * call concurrently. @@ -388,12 +408,83 @@ bool __page_pool_request_shutdown(struct page_pool *pool) page = pool->alloc.cache[--pool->alloc.count]; __page_pool_return_page(pool, page); } +} + +static void page_pool_scrub(struct page_pool *pool) +{ + page_pool_empty_alloc_cache_once(pool); + pool->destroy_cnt++; /* No more consumers should exist, but producers could still * be in-flight. */ __page_pool_empty_ring(pool); +} + +static int page_pool_release(struct page_pool *pool) +{ + int inflight; + + page_pool_scrub(pool); + inflight = page_pool_inflight(pool); + if (!inflight) + page_pool_free(pool); + + return inflight; +} + +static void page_pool_release_retry(struct work_struct *wq) +{ + struct delayed_work *dwq = to_delayed_work(wq); + struct page_pool *pool = container_of(dwq, typeof(*pool), release_dw); + int inflight; + + inflight = page_pool_release(pool); + if (!inflight) + return; + + /* Periodic warning */ + if (time_after_eq(jiffies, pool->defer_warn)) { + int sec = (s32)((u32)jiffies - (u32)pool->defer_start) / HZ; + + pr_warn("%s() stalled pool shutdown %d inflight %d sec\n", + __func__, inflight, sec); + pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; + } + + /* Still not ready to be disconnected, retry later */ + schedule_delayed_work(&pool->release_dw, DEFER_TIME); +} - return __page_pool_safe_to_destroy(pool); +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)) +{ + refcount_inc(&pool->user_cnt); + pool->disconnect = disconnect; +} + +void page_pool_destroy(struct page_pool *pool) +{ + if (!pool) + return; + + if (!page_pool_put(pool)) + return; + + if (!page_pool_release(pool)) + return; + + pool->defer_start = jiffies; + pool->defer_warn = jiffies + DEFER_WARN_INTERVAL; + + INIT_DELAYED_WORK(&pool->release_dw, page_pool_release_retry); + schedule_delayed_work(&pool->release_dw, DEFER_TIME); +} +EXPORT_SYMBOL(page_pool_destroy); + +/* Caller must provide appropriate safe context, e.g. NAPI. */ +void page_pool_update_nid(struct page_pool *pool, int new_nid) +{ + trace_page_pool_update_nid(pool, new_nid); + pool->p.nid = new_nid; } -EXPORT_SYMBOL(__page_pool_request_shutdown); +EXPORT_SYMBOL(page_pool_update_nid); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 48b1e429857c..294bfcf0ce0e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3404,7 +3404,6 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) HARD_TX_LOCK(odev, txq, smp_processor_id()); if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) { - ret = NETDEV_TX_BUSY; pkt_dev->last_ok = 0; goto unlock; } diff --git a/net/core/request_sock.c b/net/core/request_sock.c index c9bb00008528..f35c2e998406 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq; - tcp_sk(sk)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL); spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; tcp_rsk(req)->tfo_listener = false; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1ee6460f8275..9f7aa448bd11 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -980,6 +980,19 @@ static size_t rtnl_xdp_size(void) return xdp_size; } +static size_t rtnl_prop_list_size(const struct net_device *dev) +{ + struct netdev_name_node *name_node; + size_t size; + + if (list_empty(&dev->name_node->list)) + return 0; + size = nla_total_size(0); + list_for_each_entry(name_node, &dev->name_node->list, list) + size += nla_total_size(ALTIFNAMSIZ); + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1027,6 +1040,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ + nla_total_size(4) /* IFLA_MIN_MTU */ + nla_total_size(4) /* IFLA_MAX_MTU */ + + rtnl_prop_list_size(dev) + 0; } @@ -1523,7 +1537,7 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, static int rtnl_fill_link_netnsid(struct sk_buff *skb, const struct net_device *dev, - struct net *src_net) + struct net *src_net, gfp_t gfp) { bool put_iflink = false; @@ -1531,7 +1545,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); if (!net_eq(dev_net(dev), link_net)) { - int id = peernet2id_alloc(src_net, link_net); + int id = peernet2id_alloc(src_net, link_net, gfp); if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) return -EMSGSIZE; @@ -1584,12 +1598,48 @@ static int rtnl_fill_link_af(struct sk_buff *skb, return 0; } +static int rtnl_fill_alt_ifnames(struct sk_buff *skb, + const struct net_device *dev) +{ + struct netdev_name_node *name_node; + int count = 0; + + list_for_each_entry(name_node, &dev->name_node->list, list) { + if (nla_put_string(skb, IFLA_ALT_IFNAME, name_node->name)) + return -EMSGSIZE; + count++; + } + return count; +} + +static int rtnl_fill_prop_list(struct sk_buff *skb, + const struct net_device *dev) +{ + struct nlattr *prop_list; + int ret; + + prop_list = nla_nest_start(skb, IFLA_PROP_LIST); + if (!prop_list) + return -EMSGSIZE; + + ret = rtnl_fill_alt_ifnames(skb, dev); + if (ret <= 0) + goto nest_cancel; + + nla_nest_end(skb, prop_list); + return 0; + +nest_cancel: + nla_nest_cancel(skb, prop_list); + return ret; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, u32 event, int *new_nsid, int new_ifindex, - int tgt_netnsid) + int tgt_netnsid, gfp_t gfp) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1681,7 +1731,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } - if (rtnl_fill_link_netnsid(skb, dev, src_net)) + if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp)) goto nla_put_failure; if (new_nsid && @@ -1697,6 +1747,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure_rcu; rcu_read_unlock(); + if (rtnl_fill_prop_list(skb, dev)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; @@ -1750,6 +1803,9 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, [IFLA_MIN_MTU] = { .type = NLA_U32 }, [IFLA_MAX_MTU] = { .type = NLA_U32 }, + [IFLA_PROP_LIST] = { .type = NLA_NESTED }, + [IFLA_ALT_IFNAME] = { .type = NLA_STRING, + .len = ALTIFNAMSIZ - 1 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2001,7 +2057,7 @@ walk_entries: NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, 0, flags, ext_filter_mask, 0, NULL, 0, - netnsid); + netnsid, GFP_KERNEL); if (err < 0) { if (likely(skb->len)) @@ -2195,6 +2251,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_MAC]) { struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); + if (ivm->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_mac) err = ops->ndo_set_vf_mac(dev, ivm->vf, @@ -2206,6 +2264,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_VLAN]) { struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + if (ivv->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, @@ -2238,6 +2298,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (len == 0) return -EINVAL; + if (ivvl[0]->vf >= INT_MAX) + return -EINVAL; err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) @@ -2248,6 +2310,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); struct ifla_vf_info ivf; + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_get_vf_config) err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf); @@ -2266,6 +2330,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_RATE]) { struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_rate) err = ops->ndo_set_vf_rate(dev, ivt->vf, @@ -2278,6 +2344,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_SPOOFCHK]) { struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + if (ivs->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_spoofchk) err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, @@ -2289,6 +2357,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_LINK_STATE]) { struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]); + if (ivl->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_link_state) err = ops->ndo_set_vf_link_state(dev, ivl->vf, @@ -2302,6 +2372,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]); + if (ivrssq_en->vf >= INT_MAX) + return -EINVAL; if (ops->ndo_set_vf_rss_query_en) err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf, ivrssq_en->setting); @@ -2312,6 +2384,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_TRUST]) { struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_trust) err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting); @@ -2322,15 +2396,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_IB_NODE_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; - return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID); } if (tb[IFLA_VF_IB_PORT_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; @@ -2355,6 +2432,7 @@ static int do_set_master(struct net_device *dev, int ifindex, err = ops->ndo_del_slave(upper_dev, dev); if (err) return err; + netdev_update_lockdep_key(dev); } else { return -EOPNOTSUPP; } @@ -2722,6 +2800,26 @@ errout: return err; } +static struct net_device *rtnl_dev_get(struct net *net, + struct nlattr *ifname_attr, + struct nlattr *altifname_attr, + char *ifname) +{ + char buffer[ALTIFNAMSIZ]; + + if (!ifname) { + ifname = buffer; + if (ifname_attr) + nla_strlcpy(ifname, ifname_attr, IFNAMSIZ); + else if (altifname_attr) + nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ); + else + return NULL; + } + + return __dev_get_by_name(net, ifname); +} + static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -2750,8 +2848,8 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); - else if (tb[IFLA_IFNAME]) - dev = __dev_get_by_name(net, ifname); + else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) + dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname); else goto errout; @@ -2824,7 +2922,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *tgt_net = net; struct net_device *dev = NULL; struct ifinfomsg *ifm; - char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; int err; int netnsid = -1; @@ -2838,9 +2935,6 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; - if (tb[IFLA_IFNAME]) - nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); - if (tb[IFLA_TARGET_NETNSID]) { netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid); @@ -2852,8 +2946,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); - else if (tb[IFLA_IFNAME]) - dev = __dev_get_by_name(tgt_net, ifname); + else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) + dev = rtnl_dev_get(net, tb[IFLA_IFNAME], + tb[IFLA_ALT_IFNAME], NULL); else if (tb[IFLA_GROUP]) err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP])); else @@ -3024,12 +3119,10 @@ replay: ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); - else { - if (ifname[0]) - dev = __dev_get_by_name(net, ifname); - else - dev = NULL; - } + else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) + dev = rtnl_dev_get(net, NULL, tb[IFLA_ALT_IFNAME], ifname); + else + dev = NULL; if (dev) { master_dev = netdev_master_upper_dev_get(dev); @@ -3291,6 +3384,7 @@ static int rtnl_valid_getlink_req(struct sk_buff *skb, switch (i) { case IFLA_IFNAME: + case IFLA_ALT_IFNAME: case IFLA_EXT_MASK: case IFLA_TARGET_NETNSID: break; @@ -3309,7 +3403,6 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct net *tgt_net = net; struct ifinfomsg *ifm; - char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; struct net_device *dev = NULL; struct sk_buff *nskb; @@ -3332,9 +3425,6 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, return PTR_ERR(tgt_net); } - if (tb[IFLA_IFNAME]) - nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); - if (tb[IFLA_EXT_MASK]) ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]); @@ -3342,8 +3432,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); - else if (tb[IFLA_IFNAME]) - dev = __dev_get_by_name(tgt_net, ifname); + else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) + dev = rtnl_dev_get(tgt_net, tb[IFLA_IFNAME], + tb[IFLA_ALT_IFNAME], NULL); else goto out; @@ -3359,7 +3450,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, err = rtnl_fill_ifinfo(nskb, dev, net, RTM_NEWLINK, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, ext_filter_mask, - 0, NULL, 0, netnsid); + 0, NULL, 0, netnsid, GFP_KERNEL); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -3373,6 +3464,100 @@ out: return err; } +static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, + bool *changed, struct netlink_ext_ack *extack) +{ + char *alt_ifname; + int err; + + err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack); + if (err) + return err; + + alt_ifname = nla_data(attr); + if (cmd == RTM_NEWLINKPROP) { + alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + err = netdev_name_node_alt_create(dev, alt_ifname); + if (err) { + kfree(alt_ifname); + return err; + } + } else if (cmd == RTM_DELLINKPROP) { + err = netdev_name_node_alt_destroy(dev, alt_ifname); + if (err) + return err; + } else { + WARN_ON(1); + return 0; + } + + *changed = true; + return 0; +} + +static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + struct ifinfomsg *ifm; + bool changed = false; + struct nlattr *attr; + int err, rem; + + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack); + if (err) + return err; + + err = rtnl_ensure_unique_netns(tb, extack, true); + if (err) + return err; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index > 0) + dev = __dev_get_by_index(net, ifm->ifi_index); + else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) + dev = rtnl_dev_get(net, tb[IFLA_IFNAME], + tb[IFLA_ALT_IFNAME], NULL); + else + return -EINVAL; + + if (!dev) + return -ENODEV; + + if (!tb[IFLA_PROP_LIST]) + return 0; + + nla_for_each_nested(attr, tb[IFLA_PROP_LIST], rem) { + switch (nla_type(attr)) { + case IFLA_ALT_IFNAME: + err = rtnl_alt_ifname(cmd, dev, attr, &changed, extack); + if (err) + return err; + break; + } + } + + if (changed) + netdev_state_change(dev); + return 0; +} + +static int rtnl_newlinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + return rtnl_linkprop(RTM_NEWLINKPROP, skb, nlh, extack); +} + +static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack); +} + static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); @@ -3471,7 +3656,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, 0, 0, change, 0, 0, event, - new_nsid, new_ifindex, -1); + new_nsid, new_ifindex, -1, flags); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -3916,7 +4101,7 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state || ndm->ndm_flags || ndm->ndm_type) { - NL_SET_ERR_MSG(extack, "Invalid values in header for fbd dump request"); + NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request"); return -EINVAL; } @@ -5331,6 +5516,9 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, 0); rtnl_register(PF_UNSPEC, RTM_GETNETCONF, NULL, rtnl_dump_all, 0); + rtnl_register(PF_UNSPEC, RTM_NEWLINKPROP, rtnl_newlinkprop, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_DELLINKPROP, rtnl_dellinkprop, NULL, 0); + rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, rtnl_fdb_add, NULL, 0); rtnl_register(PF_BRIDGE, RTM_DELNEIGH, rtnl_fdb_del, NULL, 0); rtnl_register(PF_BRIDGE, RTM_GETNEIGH, rtnl_fdb_get, rtnl_fdb_dump, 0); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 01d65206f4fb..867e61df00db 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4415,7 +4415,7 @@ static void skb_set_err_queue(struct sk_buff *skb) int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned int)sk->sk_rcvbuf) + (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); @@ -5120,7 +5120,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->ignore_df = 0; skb_dst_drop(skb); skb_ext_reset(skb); - nf_reset(skb); + nf_reset_ct(skb); nf_reset_trace(skb); #ifdef CONFIG_NET_SWITCHDEV @@ -5477,12 +5477,14 @@ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) + * @mac_len: length of the MAC header * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto) +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, + int mac_len) { struct mpls_shim_hdr *lse; int err; @@ -5499,15 +5501,15 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto) return err; if (!skb->inner_protocol) { - skb_set_inner_network_header(skb, skb->mac_len); + skb_set_inner_network_header(skb, mac_len); skb_set_inner_protocol(skb, skb->protocol); } skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), - skb->mac_len); + mac_len); skb_reset_mac_header(skb); - skb_set_network_header(skb, skb->mac_len); + skb_set_network_header(skb, mac_len); lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; @@ -5526,29 +5528,30 @@ EXPORT_SYMBOL_GPL(skb_mpls_push); * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header + * @mac_len: length of the MAC header * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto) +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) { int err; if (unlikely(!eth_p_mpls(skb->protocol))) - return -EINVAL; + return 0; - err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); + err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err; skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), - skb->mac_len); + mac_len); __skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); - skb_set_network_header(skb, skb->mac_len); + skb_set_network_header(skb, mac_len); if (skb->dev && skb->dev->type == ARPHRD_ETHER) { struct ethhdr *hdr; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index cf390e0aa73d..a469d2124f3f 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -270,18 +270,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len) msg->sg.data[i].length -= trim; sk_mem_uncharge(sk, trim); + /* Adjust copybreak if it falls into the trimmed part of last buf */ + if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length) + msg->sg.copybreak = msg->sg.data[i].length; out: - /* If we trim data before curr pointer update copybreak and current - * so that any future copy operations start at new copy location. + sk_msg_iter_var_next(i); + msg->sg.end = i; + + /* If we trim data a full sg elem before curr pointer update + * copybreak and current so that any future copy operations + * start at new copy location. * However trimed data that has not yet been used in a copy op * does not require an update. */ - if (msg->sg.curr >= i) { + if (!msg->sg.size) { + msg->sg.curr = msg->sg.start; + msg->sg.copybreak = 0; + } else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >= + sk_msg_iter_dist(msg->sg.start, msg->sg.end)) { + sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } - sk_msg_iter_var_next(i); - msg->sg.end = i; } EXPORT_SYMBOL_GPL(sk_msg_trim); @@ -783,15 +793,18 @@ static void sk_psock_strp_data_ready(struct sock *sk) static void sk_psock_write_space(struct sock *sk) { struct sk_psock *psock; - void (*write_space)(struct sock *sk); + void (*write_space)(struct sock *sk) = NULL; rcu_read_lock(); psock = sk_psock(sk); - if (likely(psock && sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))) - schedule_work(&psock->work); - write_space = psock->saved_write_space; + if (likely(psock)) { + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_work(&psock->work); + write_space = psock->saved_write_space; + } rcu_read_unlock(); - write_space(sk); + if (write_space) + write_space(sk); } int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) diff --git a/net/core/sock.c b/net/core/sock.c index 07863edbe6fc..71787f7c4f8c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -333,7 +333,6 @@ EXPORT_SYMBOL(__sk_backlog_rcv); static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; - int size; if (timeo == MAX_SCHEDULE_TIMEOUT) { tv.tv_sec = 0; @@ -354,13 +353,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) old_tv.tv_sec = tv.tv_sec; old_tv.tv_usec = tv.tv_usec; *(struct __kernel_old_timeval *)optval = old_tv; - size = sizeof(old_tv); - } else { - *(struct __kernel_sock_timeval *)optval = tv; - size = sizeof(tv); + return sizeof(old_tv); } - return size; + *(struct __kernel_sock_timeval *)optval = tv; + return sizeof(tv); } static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval) @@ -522,7 +519,7 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); - } else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { bh_unlock_sock(sk); atomic_inc(&sk->sk_drops); goto discard_and_relse; @@ -687,7 +684,8 @@ out: return ret; } -static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) +static inline void sock_valbool_flag(struct sock *sk, enum sock_flags bit, + int valbool) { if (valbool) sock_set_flag(sk, bit); @@ -785,7 +783,8 @@ set_sndbuf: */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -831,7 +830,8 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_RCVBUFFORCE: @@ -974,7 +974,7 @@ set_rcvbuf: if (sock->ops->set_rcvlowat) ret = sock->ops->set_rcvlowat(sk, val); else - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_RCVTIMEO_OLD: @@ -1125,7 +1125,7 @@ set_rcvbuf: break; } case SO_INCOMING_CPU: - sk->sk_incoming_cpu = val; + WRITE_ONCE(sk->sk_incoming_cpu, val); break; case SO_CNX_ADVICE: @@ -1474,7 +1474,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_INCOMING_CPU: - v.val = sk->sk_incoming_cpu; + v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: @@ -1700,8 +1700,6 @@ static void __sk_destruct(struct rcu_head *head) sk_filter_uncharge(sk, filter); RCU_INIT_POINTER(sk->sk_filter, NULL); } - if (rcu_access_pointer(sk->sk_reuseport_cb)) - reuseport_detach_sock(sk); sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); @@ -1728,7 +1726,14 @@ static void __sk_destruct(struct rcu_head *head) void sk_destruct(struct sock *sk) { - if (sock_flag(sk, SOCK_RCU_FREE)) + bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE); + + if (rcu_access_pointer(sk->sk_reuseport_cb)) { + reuseport_detach_sock(sk); + use_call_rcu = true; + } + + if (use_call_rcu) call_rcu(&sk->sk_rcu, __sk_destruct); else __sk_destruct(&sk->sk_rcu); @@ -2083,8 +2088,10 @@ EXPORT_SYMBOL(sock_i_ino); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { - if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { + if (force || + refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); + if (skb) { skb_set_owner_w(skb, sk); return skb; @@ -2185,7 +2192,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) + if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (sk->sk_shutdown & SEND_SHUTDOWN) break; @@ -2220,7 +2227,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (sk->sk_shutdown & SEND_SHUTDOWN) goto failure; - if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf) + if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -2329,8 +2336,8 @@ static void sk_leave_memory_pressure(struct sock *sk) } else { unsigned long *memory_pressure = sk->sk_prot->memory_pressure; - if (memory_pressure && *memory_pressure) - *memory_pressure = 0; + if (memory_pressure && READ_ONCE(*memory_pressure)) + WRITE_ONCE(*memory_pressure, 0); } } @@ -2801,7 +2808,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | @@ -3006,7 +3013,7 @@ int sock_gettstamp(struct socket *sock, void __user *userstamp, return -ENOENT; if (ts.tv_sec == 0) { ktime_t kt = ktime_get_real(); - sock_write_timestamp(sk, kt);; + sock_write_timestamp(sk, kt); ts = ktime_to_timespec64(kt); } @@ -3033,7 +3040,7 @@ int sock_gettstamp(struct socket *sock, void __user *userstamp, } EXPORT_SYMBOL(sock_gettstamp); -void sock_enable_timestamp(struct sock *sk, int flag) +void sock_enable_timestamp(struct sock *sk, enum sock_flags flag) { if (!sock_flag(sk, flag)) { unsigned long previous_flags = sk->sk_flags; @@ -3199,13 +3206,13 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); - mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; + mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); - mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; + mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; - mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; + mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } @@ -3492,7 +3499,7 @@ static long sock_prot_memory_allocated(struct proto *proto) return proto->memory_allocated != NULL ? proto_memory_allocated(proto) : -1L; } -static char *sock_prot_memory_pressure(struct proto *proto) +static const char *sock_prot_memory_pressure(struct proto *proto) { return proto->memory_pressure != NULL ? proto_memory_pressure(proto) ? "yes" : "no" : "NI"; @@ -3591,7 +3598,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; - return !skb_queue_empty(&sk->sk_receive_queue) || + return !skb_queue_empty_lockless(&sk->sk_receive_queue) || sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); diff --git a/net/core/xdp.c b/net/core/xdp.c index d7bf62ffbb5e..e334fad0a6b8 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -70,77 +70,63 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) xa = container_of(rcu, struct xdp_mem_allocator, rcu); - /* Allocator have indicated safe to remove before this is called */ - if (xa->mem.type == MEM_TYPE_PAGE_POOL) - page_pool_free(xa->page_pool); - /* Allow this ID to be reused */ ida_simple_remove(&mem_id_pool, xa->mem.id); - /* Poison memory */ - xa->mem.id = 0xFFFF; - xa->mem.type = 0xF0F0; - xa->allocator = (void *)0xDEAD9001; - kfree(xa); } -static bool __mem_id_disconnect(int id, bool force) +static void mem_xa_remove(struct xdp_mem_allocator *xa) { - struct xdp_mem_allocator *xa; - bool safe_to_remove = true; + trace_mem_disconnect(xa); mutex_lock(&mem_id_lock); - xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); - if (!xa) { - mutex_unlock(&mem_id_lock); - WARN(1, "Request remove non-existing id(%d), driver bug?", id); - return true; - } - xa->disconnect_cnt++; - - /* Detects in-flight packet-pages for page_pool */ - if (xa->mem.type == MEM_TYPE_PAGE_POOL) - safe_to_remove = page_pool_request_shutdown(xa->page_pool); - - trace_mem_disconnect(xa, safe_to_remove, force); - - if ((safe_to_remove || force) && - !rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) + if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); mutex_unlock(&mem_id_lock); - return (safe_to_remove|force); } -#define DEFER_TIME (msecs_to_jiffies(1000)) -#define DEFER_WARN_INTERVAL (30 * HZ) -#define DEFER_MAX_RETRIES 120 +static void mem_allocator_disconnect(void *allocator) +{ + struct xdp_mem_allocator *xa; + struct rhashtable_iter iter; + + rhashtable_walk_enter(mem_id_ht, &iter); + do { + rhashtable_walk_start(&iter); + + while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { + if (xa->allocator == allocator) + mem_xa_remove(xa); + } + + rhashtable_walk_stop(&iter); -static void mem_id_disconnect_defer_retry(struct work_struct *wq) + } while (xa == ERR_PTR(-EAGAIN)); + rhashtable_walk_exit(&iter); +} + +static void mem_id_disconnect(int id) { - struct delayed_work *dwq = to_delayed_work(wq); - struct xdp_mem_allocator *xa = container_of(dwq, typeof(*xa), defer_wq); - bool force = false; + struct xdp_mem_allocator *xa; - if (xa->disconnect_cnt > DEFER_MAX_RETRIES) - force = true; + mutex_lock(&mem_id_lock); - if (__mem_id_disconnect(xa->mem.id, force)) + xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); + if (!xa) { + mutex_unlock(&mem_id_lock); + WARN(1, "Request remove non-existing id(%d), driver bug?", id); return; + } - /* Periodic warning */ - if (time_after_eq(jiffies, xa->defer_warn)) { - int sec = (s32)((u32)jiffies - (u32)xa->defer_start) / HZ; + trace_mem_disconnect(xa); - pr_warn("%s() stalled mem.id=%u shutdown %d attempts %d sec\n", - __func__, xa->mem.id, xa->disconnect_cnt, sec); - xa->defer_warn = jiffies + DEFER_WARN_INTERVAL; - } + if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) + call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); - /* Still not ready to be disconnected, retry later */ - schedule_delayed_work(&xa->defer_wq, DEFER_TIME); + mutex_unlock(&mem_id_lock); } void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) @@ -153,38 +139,21 @@ void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) return; } - if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL && - xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) { - return; - } - if (id == 0) return; - if (__mem_id_disconnect(id, false)) - return; - - /* Could not disconnect, defer new disconnect attempt to later */ - mutex_lock(&mem_id_lock); + if (xdp_rxq->mem.type == MEM_TYPE_ZERO_COPY) + return mem_id_disconnect(id); - xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); - if (!xa) { - mutex_unlock(&mem_id_lock); - return; + if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) { + rcu_read_lock(); + xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + page_pool_destroy(xa->page_pool); + rcu_read_unlock(); } - xa->defer_start = jiffies; - xa->defer_warn = jiffies + DEFER_WARN_INTERVAL; - - INIT_DELAYED_WORK(&xa->defer_wq, mem_id_disconnect_defer_retry); - mutex_unlock(&mem_id_lock); - schedule_delayed_work(&xa->defer_wq, DEFER_TIME); } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); -/* This unregister operation will also cleanup and destroy the - * allocator. The page_pool_free() operation is first called when it's - * safe to remove, possibly deferred to a workqueue. - */ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ @@ -371,7 +340,7 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, } if (type == MEM_TYPE_PAGE_POOL) - page_pool_get(xdp_alloc->page_pool); + page_pool_use_xdp_mem(allocator, mem_allocator_disconnect); mutex_unlock(&mem_id_lock); @@ -386,7 +355,7 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame - * while still leveraging this protection. The @napi_direct boolian + * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ @@ -402,15 +371,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); - if (likely(xa)) { - napi_direct &= !xdp_return_frame_no_direct(); - page_pool_put_page(xa->page_pool, page, napi_direct); - } else { - /* Hopefully stack show who to blame for late return */ - WARN_ONCE(1, "page_pool gone mem.id=%d", mem->id); - trace_mem_return_failed(mem, page); - put_page(page); - } + napi_direct &= !xdp_return_frame_no_direct(); + page_pool_put_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: |