diff options
Diffstat (limited to 'net/core/dev.c')
-rw-r--r-- | net/core/dev.c | 185 |
1 files changed, 96 insertions, 89 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 3be256051e99..b76fb37b381e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1163,22 +1163,6 @@ int dev_change_name(struct net_device *dev, const char *newname) net = dev_net(dev); - /* Some auto-enslaved devices e.g. failover slaves are - * special, as userspace might rename the device after - * the interface had been brought up and running since - * the point kernel initiated auto-enslavement. Allow - * live name change even when these slave devices are - * up and running. - * - * Typically, users of these auto-enslaving devices - * don't actually care about slave name change, as - * they are supposed to operate on master interface - * directly. - */ - if (dev->flags & IFF_UP && - likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) - return -EBUSY; - down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { @@ -1195,7 +1179,8 @@ int dev_change_name(struct net_device *dev, const char *newname) } if (oldname[0] && !strchr(oldname, '%')) - netdev_info(dev, "renamed from %s\n", oldname); + netdev_info(dev, "renamed from %s%s\n", oldname, + dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; dev->name_assign_type = NET_NAME_RENAMED; @@ -1333,7 +1318,7 @@ void netdev_state_change(struct net_device *dev) call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); - rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL); } } EXPORT_SYMBOL(netdev_state_change); @@ -1469,7 +1454,7 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack) if (ret < 0) return ret; - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; @@ -1541,7 +1526,7 @@ void dev_close_many(struct list_head *head, bool unlink) __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); @@ -1621,10 +1606,10 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) - N(POST_INIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) - N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) - N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) - N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) + N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) + N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) + N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) + N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) @@ -1876,6 +1861,22 @@ int unregister_netdevice_notifier_net(struct net *net, } EXPORT_SYMBOL(unregister_netdevice_notifier_net); +static void __move_netdevice_notifier_net(struct net *src_net, + struct net *dst_net, + struct notifier_block *nb) +{ + __unregister_netdevice_notifier_net(src_net, nb); + __register_netdevice_notifier_net(dst_net, nb, true); +} + +void move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, + struct notifier_block *nb) +{ + rtnl_lock(); + __move_netdevice_notifier_net(src_net, dst_net, nb); + rtnl_unlock(); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -1912,10 +1913,8 @@ static void move_netdevice_notifiers_dev_net(struct net_device *dev, { struct netdev_net_notifier *nn; - list_for_each_entry(nn, &dev->net_notifier_list, list) { - __unregister_netdevice_notifier_net(dev_net(dev), nn->nb); - __register_netdevice_notifier_net(net, nn->nb, true); - } + list_for_each_entry(nn, &dev->net_notifier_list, list) + __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** @@ -2074,13 +2073,10 @@ static DECLARE_WORK(netstamp_work, netstamp_clear); void net_enable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL - int wanted; + int wanted = atomic_read(&netstamp_wanted); - while (1) { - wanted = atomic_read(&netstamp_wanted); - if (wanted <= 0) - break; - if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted + 1) == wanted) + while (wanted > 0) { + if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1)) return; } atomic_inc(&netstamp_needed_deferred); @@ -2094,13 +2090,10 @@ EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL - int wanted; + int wanted = atomic_read(&netstamp_wanted); - while (1) { - wanted = atomic_read(&netstamp_wanted); - if (wanted <= 1) - break; - if (atomic_cmpxchg(&netstamp_wanted, wanted, wanted - 1) == wanted) + while (wanted > 1) { + if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1)) return; } atomic_dec(&netstamp_needed_deferred); @@ -5986,10 +5979,9 @@ EXPORT_SYMBOL(__napi_schedule); */ bool napi_schedule_prep(struct napi_struct *n) { - unsigned long val, new; + unsigned long new, val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); if (unlikely(val & NAPIF_STATE_DISABLE)) return false; new = val | NAPIF_STATE_SCHED; @@ -6002,7 +5994,7 @@ bool napi_schedule_prep(struct napi_struct *n) */ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * NAPIF_STATE_MISSED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); return !(val & NAPIF_STATE_SCHED); } @@ -6070,9 +6062,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) local_irq_restore(flags); } + val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); - WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | @@ -6085,7 +6076,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) */ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * NAPIF_STATE_SCHED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); if (unlikely(val & NAPIF_STATE_MISSED)) { __napi_schedule(n); @@ -6406,19 +6397,16 @@ void napi_disable(struct napi_struct *n) might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); - for ( ; ; ) { - val = READ_ONCE(n->state); - if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { + val = READ_ONCE(n->state); + do { + while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); - continue; + val = READ_ONCE(n->state); } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); - - if (cmpxchg(&n->state, val, new) == val) - break; - } + } while (!try_cmpxchg(&n->state, &val, new)); hrtimer_cancel(&n->timer); @@ -6435,16 +6423,15 @@ EXPORT_SYMBOL(napi_disable); */ void napi_enable(struct napi_struct *n) { - unsigned long val, new; + unsigned long new, val = READ_ONCE(n->state); do { - val = READ_ONCE(n->state); BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); if (n->dev->threaded && n->thread) new |= NAPIF_STATE_THREADED; - } while (cmpxchg(&n->state, val, new) != val); + } while (!try_cmpxchg(&n->state, &val, new)); } EXPORT_SYMBOL(napi_enable); @@ -8351,7 +8338,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) - __dev_notify_flags(dev, old_flags, IFF_PROMISC); + __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); return 0; } @@ -8406,7 +8393,7 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify) dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, - dev->gflags ^ old_gflags); + dev->gflags ^ old_gflags, 0, NULL); } return 0; } @@ -8569,12 +8556,13 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags, } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, - unsigned int gchanges) + unsigned int gchanges, u32 portid, + const struct nlmsghdr *nlh) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) - rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC); + rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh); if (changes & IFF_UP) { if (dev->flags & IFF_UP) @@ -8616,7 +8604,7 @@ int dev_change_flags(struct net_device *dev, unsigned int flags, return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); - __dev_notify_flags(dev, old_flags, changes); + __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } EXPORT_SYMBOL(dev_change_flags); @@ -8822,7 +8810,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; @@ -10059,7 +10047,7 @@ int register_netdevice(struct net_device *dev) dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; write_unlock(&dev_base_lock); if (ret) - goto err_uninit; + goto err_uninit_notify; __netdev_update_features(dev); @@ -10101,11 +10089,13 @@ int register_netdevice(struct net_device *dev) */ if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); out: return ret; +err_uninit_notify: + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10379,24 +10369,16 @@ void netdev_run_todo(void) void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { -#if BITS_PER_LONG == 64 - BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats)); - memcpy(stats64, netdev_stats, sizeof(*netdev_stats)); - /* zero out counters that only exist in rtnl_link_stats64 */ - memset((char *)stats64 + sizeof(*netdev_stats), 0, - sizeof(*stats64) - sizeof(*netdev_stats)); -#else - size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long); - const unsigned long *src = (const unsigned long *)netdev_stats; + size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); + const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) - dst[i] = src[i]; + dst[i] = atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); -#endif } EXPORT_SYMBOL(netdev_stats_to_stats64); @@ -10477,12 +10459,12 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, stats = per_cpu_ptr(netstats, cpu); do { - start = u64_stats_fetch_begin_irq(&stats->syncp); + start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; @@ -10535,6 +10517,22 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, } EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); +/** + * netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default + * @dev: netdev to enable the IRQ coalescing on + * + * Sets a conservative default for SW IRQ coalescing. Users can use + * sysfs attributes to override the default values. + */ +void netdev_sw_irq_coalesce_default_on(struct net_device *dev) +{ + WARN_ON(dev->reg_state == NETREG_REGISTERED); + + dev->gro_flush_timeout = 20000; + dev->napi_defer_hard_irqs = 1; +} +EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); + void netdev_freemem(struct net_device *dev) { char *addr = (char *)dev - dev->padded; @@ -10780,14 +10778,8 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) } EXPORT_SYMBOL(unregister_netdevice_queue); -/** - * unregister_netdevice_many - unregister many devices - * @head: list of devices - * - * Note: As most callers use a stack allocated list_head, - * we force a list_del() to make sure stack wont be corrupted later. - */ -void unregister_netdevice_many(struct list_head *head) +void unregister_netdevice_many_notify(struct list_head *head, + u32 portid, const struct nlmsghdr *nlh) { struct net_device *dev, *tmp; LIST_HEAD(close_head); @@ -10849,7 +10841,8 @@ void unregister_netdevice_many(struct list_head *head) if (!dev->rtnl_link_ops || dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, - GFP_KERNEL, NULL, 0); + GFP_KERNEL, NULL, 0, + portid, nlmsg_seq(nlh)); /* * Flush the unicast and multicast chains @@ -10860,11 +10853,13 @@ void unregister_netdevice_many(struct list_head *head) netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); + call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); + if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (skb) - rtmsg_ifinfo_send(skb, dev, GFP_KERNEL); + rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); @@ -10887,6 +10882,18 @@ void unregister_netdevice_many(struct list_head *head) list_del(head); } + +/** + * unregister_netdevice_many - unregister many devices + * @head: list of devices + * + * Note: As most callers use a stack allocated list_head, + * we force a list_del() to make sure stack wont be corrupted later. + */ +void unregister_netdevice_many(struct list_head *head) +{ + unregister_netdevice_many_notify(head, 0, NULL); +} EXPORT_SYMBOL(unregister_netdevice_many); /** @@ -11042,7 +11049,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL); + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); synchronize_net(); err = 0; |