diff options
Diffstat (limited to 'net')
161 files changed, 1850 insertions, 1010 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 54728d2eda18..d4bcfd8f95bf 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -172,7 +172,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 93eadf179123..e5bff5cc6f97 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -489,36 +489,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev) dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev); } -/* - * vlan network devices have devices nesting below it, and are a special - * "super class" of normal network devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key vlan_netdev_xmit_lock_key; -static struct lock_class_key vlan_netdev_addr_lock_key; - -static void vlan_dev_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_subclass) -{ - lockdep_set_class_and_subclass(&txq->_xmit_lock, - &vlan_netdev_xmit_lock_key, - *(int *)_subclass); -} - -static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass) -{ - lockdep_set_class_and_subclass(&dev->addr_list_lock, - &vlan_netdev_addr_lock_key, - subclass); - netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass); -} - -static int vlan_dev_get_lock_subclass(struct net_device *dev) -{ - return vlan_dev_priv(dev)->nest_level; -} - static const struct header_ops vlan_header_ops = { .create = vlan_dev_hard_header, .parse = eth_header_parse, @@ -609,8 +579,6 @@ static int vlan_dev_init(struct net_device *dev) SET_NETDEV_DEVTYPE(dev, &vlan_type); - vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev)); - vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats); if (!vlan->vlan_pcpu_stats) return -ENOMEM; @@ -812,7 +780,6 @@ static const struct net_device_ops vlan_netdev_ops = { .ndo_netpoll_cleanup = vlan_dev_netpoll_cleanup, #endif .ndo_fix_features = vlan_dev_fix_features, - .ndo_get_lock_subclass = vlan_dev_get_lock_subclass, .ndo_get_iflink = vlan_dev_get_iflink, }; diff --git a/net/atm/common.c b/net/atm/common.c index b7528e77997c..0ce530af534d 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -668,7 +668,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* writable? */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index d78938e3e008..5b0b20e6da95 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -22,6 +22,8 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/pkt_sched.h> @@ -193,14 +195,18 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) unsigned char *ogm_buff; u32 random_seqno; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); atomic_set(&hard_iface->bat_iv.ogm_seqno, random_seqno); hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN; ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC); - if (!ogm_buff) + if (!ogm_buff) { + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); return -ENOMEM; + } hard_iface->bat_iv.ogm_buff = ogm_buff; @@ -212,35 +218,59 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->reserved = 0; batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE; + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); + return 0; } static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) { + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + kfree(hard_iface->bat_iv.ogm_buff); hard_iface->bat_iv.ogm_buff = NULL; + + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; ether_addr_copy(batadv_ogm_packet->orig, hard_iface->net_dev->dev_addr); ether_addr_copy(batadv_ogm_packet->prev_sender, hard_iface->net_dev->dev_addr); + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; batadv_ogm_packet->ttl = BATADV_TTL; + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } /* when do we schedule our own ogm to be sent */ @@ -742,7 +772,11 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) } } -static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +/** + * batadv_iv_ogm_schedule_buff() - schedule submission of hardif ogm buffer + * @hard_iface: interface whose ogm buffer should be transmitted + */ +static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff; @@ -753,9 +787,7 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) u16 tvlv_len = 0; unsigned long send_time; - if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || - hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) - return; + lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); /* the interface gets activated here to avoid race conditions between * the moment of activating the interface in @@ -823,6 +855,17 @@ out: batadv_hardif_put(primary_if); } +static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +{ + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) + return; + + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + batadv_iv_ogm_schedule_buff(hard_iface); + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); +} + /** * batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over iterface * @orig_node: originator which reproadcasted the OGMs directly diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index dc4f7430cb5a..8033f24f506c 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -18,6 +18,7 @@ #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/rculist.h> @@ -256,14 +257,12 @@ static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, } /** - * batadv_v_ogm_send() - periodic worker broadcasting the own OGM - * @work: work queue item + * batadv_v_ogm_send_softif() - periodic worker broadcasting the own OGM + * @bat_priv: the bat priv with all the soft interface information */ -static void batadv_v_ogm_send(struct work_struct *work) +static void batadv_v_ogm_send_softif(struct batadv_priv *bat_priv) { struct batadv_hard_iface *hard_iface; - struct batadv_priv_bat_v *bat_v; - struct batadv_priv *bat_priv; struct batadv_ogm2_packet *ogm_packet; struct sk_buff *skb, *skb_tmp; unsigned char *ogm_buff; @@ -271,8 +270,7 @@ static void batadv_v_ogm_send(struct work_struct *work) u16 tvlv_len = 0; int ret; - bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work); - bat_priv = container_of(bat_v, struct batadv_priv, bat_v); + lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex); if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; @@ -364,6 +362,23 @@ out: } /** + * batadv_v_ogm_send() - periodic worker broadcasting the own OGM + * @work: work queue item + */ +static void batadv_v_ogm_send(struct work_struct *work) +{ + struct batadv_priv_bat_v *bat_v; + struct batadv_priv *bat_priv; + + bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work); + bat_priv = container_of(bat_v, struct batadv_priv, bat_v); + + mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); + batadv_v_ogm_send_softif(bat_priv); + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); +} + +/** * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface * @work: work queue item * @@ -424,11 +439,15 @@ void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface) struct batadv_priv *bat_priv = netdev_priv(primary_iface->soft_iface); struct batadv_ogm2_packet *ogm_packet; + mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); if (!bat_priv->bat_v.ogm_buff) - return; + goto unlock; ogm_packet = (struct batadv_ogm2_packet *)bat_priv->bat_v.ogm_buff; ether_addr_copy(ogm_packet->orig, primary_iface->net_dev->dev_addr); + +unlock: + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } /** @@ -1050,6 +1069,8 @@ int batadv_v_ogm_init(struct batadv_priv *bat_priv) atomic_set(&bat_priv->bat_v.ogm_seqno, random_seqno); INIT_DELAYED_WORK(&bat_priv->bat_v.ogm_wq, batadv_v_ogm_send); + mutex_init(&bat_priv->bat_v.ogm_buff_mutex); + return 0; } @@ -1061,7 +1082,11 @@ void batadv_v_ogm_free(struct batadv_priv *bat_priv) { cancel_delayed_work_sync(&bat_priv->bat_v.ogm_wq); + mutex_lock(&bat_priv->bat_v.ogm_buff_mutex); + kfree(bat_priv->bat_v.ogm_buff); bat_priv->bat_v.ogm_buff = NULL; bat_priv->bat_v.ogm_buff_len = 0; + + mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex); } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index c90e47342bb0..afb52282d5bd 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -18,6 +18,7 @@ #include <linux/kref.h> #include <linux/limits.h> #include <linux/list.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> @@ -929,6 +930,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) INIT_LIST_HEAD(&hard_iface->list); INIT_HLIST_HEAD(&hard_iface->neigh_list); + mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); spin_lock_init(&hard_iface->neigh_list_lock); kref_init(&hard_iface->refcount); diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 9cbed6f5a85a..5ee8e9a100f9 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -740,36 +740,6 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto, return 0; } -/* batman-adv network devices have devices nesting below it and are a special - * "super class" of normal network devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key batadv_netdev_xmit_lock_key; -static struct lock_class_key batadv_netdev_addr_lock_key; - -/** - * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue - * @dev: device which owns the tx queue - * @txq: tx queue to modify - * @_unused: always NULL - */ -static void batadv_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &batadv_netdev_xmit_lock_key); -} - -/** - * batadv_set_lockdep_class() - Set txq and addr_list lockdep class - * @dev: network device to modify - */ -static void batadv_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL); -} - /** * batadv_softif_init_late() - late stage initialization of soft interface * @dev: registered network device to modify @@ -783,8 +753,6 @@ static int batadv_softif_init_late(struct net_device *dev) int ret; size_t cnt_len = sizeof(u64) * BATADV_CNT_NUM; - batadv_set_lockdep_class(dev); - bat_priv = netdev_priv(dev); bat_priv->soft_iface = dev; diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index be7c02aa91e2..4d7f1baee7b7 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -17,6 +17,7 @@ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/kref.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/sched.h> /* for linux/wait.h */ @@ -81,6 +82,9 @@ struct batadv_hard_iface_bat_iv { /** @ogm_seqno: OGM sequence number - used to identify each OGM */ atomic_t ogm_seqno; + + /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ + struct mutex ogm_buff_mutex; }; /** @@ -1539,6 +1543,9 @@ struct batadv_priv_bat_v { /** @ogm_seqno: OGM sequence number - used to identify each OGM */ atomic_t ogm_seqno; + /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ + struct mutex ogm_buff_mutex; + /** @ogm_wq: workqueue used to schedule OGM transmissions */ struct delayed_work ogm_wq; }; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index bb55d92691b0..4febc82a7c76 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -571,15 +571,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev) return err < 0 ? NET_XMIT_DROP : err; } -static int bt_dev_init(struct net_device *dev) -{ - netdev_lockdep_set_classes(dev); - - return 0; -} - static const struct net_device_ops netdev_ops = { - .ndo_init = bt_dev_init, .ndo_start_xmit = bt_xmit, }; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 94ddf19998c7..5f508c50649d 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -460,7 +460,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, if (sk->sk_state == BT_LISTEN) return bt_accept_poll(sk); - 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); @@ -470,7 +470,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == BT_CLOSED) diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 681b72862c16..e804a3016902 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -24,8 +24,6 @@ const struct nf_br_ops __rcu *nf_br_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_br_ops); -static struct lock_class_key bridge_netdev_addr_lock_key; - /* net device transmit always called with BH disabled */ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -108,11 +106,6 @@ out: return NETDEV_TX_OK; } -static void br_set_lockdep_class(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key); -} - static int br_dev_init(struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); @@ -150,7 +143,6 @@ static int br_dev_init(struct net_device *dev) br_mdb_hash_fini(br); br_fdb_hash_fini(br); } - br_set_lockdep_class(dev); return err; } diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index ed91ea31978a..12a4f4d93681 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -20,7 +20,6 @@ static unsigned int ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - struct net_device *dev; if (skb_ensure_writable(skb, ETH_ALEN)) return EBT_DROP; @@ -33,10 +32,22 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) else skb->pkt_type = PACKET_MULTICAST; } else { - if (xt_hooknum(par) != NF_BR_BROUTING) - dev = br_port_get_rcu(xt_in(par))->br->dev; - else + const struct net_device *dev; + + switch (xt_hooknum(par)) { + case NF_BR_BROUTING: dev = xt_in(par); + break; + case NF_BR_PRE_ROUTING: + dev = br_port_get_rcu(xt_in(par))->br->dev; + break; + default: + dev = NULL; + break; + } + + if (!dev) /* NF_BR_LOCAL_OUT */ + return info->target; if (ether_addr_equal(info->mac, dev->dev_addr)) skb->pkt_type = PACKET_HOST; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 8842798c29e6..809673222382 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -33,6 +33,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; unsigned int hlen, ll_rs, mtu; + ktime_t tstamp = skb->tstamp; struct ip_frag_state state; struct iphdr *iph; int err; @@ -80,6 +81,7 @@ static int nf_br_ip_fragment(struct net *net, struct sock *sk, if (iter.frag) ip_fraglist_prepare(skb, &iter); + skb->tstamp = tstamp; err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -93,7 +95,7 @@ slow_path: * This may also be a clone skbuff, we could preserve the geometry for * the copies but probably not worth the effort. */ - ip_frag_init(skb, hlen, ll_rs, frag_max_size, &state); + ip_frag_init(skb, hlen, ll_rs, frag_max_size, false, &state); while (state.left > 0) { struct sk_buff *skb2; @@ -104,6 +106,7 @@ slow_path: goto blackhole; } + skb2->tstamp = tstamp; err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 13ea920600ae..ef14da50a981 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -953,7 +953,7 @@ static __poll_t caif_poll(struct file *file, mask |= EPOLLRDHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/can/af_can.c b/net/can/af_can.c index 5518a7d9eed9..128d37a4c2e0 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -86,11 +86,12 @@ static atomic_t skbcounter = ATOMIC_INIT(0); /* af_can socket functions */ -static void can_sock_destruct(struct sock *sk) +void can_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_error_queue); } +EXPORT_SYMBOL(can_sock_destruct); static const struct can_proto *can_get_proto(int protocol) { diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index def2f813ffce..137054bff9ec 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -51,6 +51,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) if (!skb) return; + j1939_priv_get(priv); can_skb_set_owner(skb, iskb->sk); /* get a pointer to the header of the skb @@ -104,6 +105,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data) j1939_simple_recv(priv, skb); j1939_sk_recv(priv, skb); done: + j1939_priv_put(priv); kfree_skb(skb); } @@ -150,6 +152,10 @@ static void __j1939_priv_release(struct kref *kref) netdev_dbg(priv->ndev, "%s: 0x%p\n", __func__, priv); + WARN_ON_ONCE(!list_empty(&priv->active_session_list)); + WARN_ON_ONCE(!list_empty(&priv->ecus)); + WARN_ON_ONCE(!list_empty(&priv->j1939_socks)); + dev_put(ndev); kfree(priv); } @@ -207,6 +213,9 @@ static inline struct j1939_priv *j1939_ndev_to_priv(struct net_device *ndev) { struct can_ml_priv *can_ml_priv = ndev->ml_priv; + if (!can_ml_priv) + return NULL; + return can_ml_priv->j1939_priv; } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 37c1040bcb9c..de09b0a65791 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -78,7 +78,6 @@ static void j1939_jsk_add(struct j1939_priv *priv, struct j1939_sock *jsk) { jsk->state |= J1939_SOCK_BOUND; j1939_priv_get(priv); - jsk->priv = priv; spin_lock_bh(&priv->j1939_socks_lock); list_add_tail(&jsk->list, &priv->j1939_socks); @@ -91,7 +90,6 @@ static void j1939_jsk_del(struct j1939_priv *priv, struct j1939_sock *jsk) list_del_init(&jsk->list); spin_unlock_bh(&priv->j1939_socks_lock); - jsk->priv = NULL; j1939_priv_put(priv); jsk->state &= ~J1939_SOCK_BOUND; } @@ -349,6 +347,34 @@ void j1939_sk_recv(struct j1939_priv *priv, struct sk_buff *skb) spin_unlock_bh(&priv->j1939_socks_lock); } +static void j1939_sk_sock_destruct(struct sock *sk) +{ + struct j1939_sock *jsk = j1939_sk(sk); + + /* This function will be call by the generic networking code, when then + * the socket is ultimately closed (sk->sk_destruct). + * + * The race between + * - processing a received CAN frame + * (can_receive -> j1939_can_recv) + * and accessing j1939_priv + * ... and ... + * - closing a socket + * (j1939_can_rx_unregister -> can_rx_unregister) + * and calling the final j1939_priv_put() + * + * is avoided by calling the final j1939_priv_put() from this + * RCU deferred cleanup call. + */ + if (jsk->priv) { + j1939_priv_put(jsk->priv); + jsk->priv = NULL; + } + + /* call generic CAN sock destruct */ + can_sock_destruct(sk); +} + static int j1939_sk_init(struct sock *sk) { struct j1939_sock *jsk = j1939_sk(sk); @@ -371,6 +397,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + sk->sk_destruct = j1939_sk_sock_destruct; return 0; } @@ -443,6 +470,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) } jsk->ifindex = addr->can_ifindex; + + /* the corresponding j1939_priv_put() is called via + * sk->sk_destruct, which points to j1939_sk_sock_destruct() + */ + j1939_priv_get(priv); + jsk->priv = priv; } /* set default transmit pgn */ @@ -560,8 +593,8 @@ static int j1939_sk_release(struct socket *sock) if (!sk) return 0; - jsk = j1939_sk(sk); lock_sock(sk); + jsk = j1939_sk(sk); if (jsk->state & J1939_SOCK_BOUND) { struct j1939_priv *priv = jsk->priv; @@ -580,6 +613,7 @@ static int j1939_sk_release(struct socket *sock) j1939_netdev_stop(priv); } + kfree(jsk->filters); sock_orphan(sk); sock->sk = NULL; @@ -909,8 +943,10 @@ void j1939_sk_errqueue(struct j1939_session *session, memset(serr, 0, sizeof(*serr)); switch (type) { case J1939_ERRQUEUE_ACK: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) { + kfree_skb(skb); return; + } serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; @@ -918,8 +954,10 @@ void j1939_sk_errqueue(struct j1939_session *session, state = "ACK"; break; case J1939_ERRQUEUE_SCHED: - if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) + if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) { + kfree_skb(skb); return; + } serr->ee.ee_errno = ENOMSG; serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; @@ -1054,51 +1092,72 @@ static int j1939_sk_sendmsg(struct socket *sock, struct msghdr *msg, { struct sock *sk = sock->sk; struct j1939_sock *jsk = j1939_sk(sk); - struct j1939_priv *priv = jsk->priv; + struct j1939_priv *priv; int ifindex; int ret; + lock_sock(sock->sk); /* various socket state tests */ - if (!(jsk->state & J1939_SOCK_BOUND)) - return -EBADFD; + if (!(jsk->state & J1939_SOCK_BOUND)) { + ret = -EBADFD; + goto sendmsg_done; + } + priv = jsk->priv; ifindex = jsk->ifindex; - if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) + if (!jsk->addr.src_name && jsk->addr.sa == J1939_NO_ADDR) { /* no source address assigned yet */ - return -EBADFD; + ret = -EBADFD; + goto sendmsg_done; + } /* deal with provided destination address info */ if (msg->msg_name) { struct sockaddr_can *addr = msg->msg_name; - if (msg->msg_namelen < J1939_MIN_NAMELEN) - return -EINVAL; + if (msg->msg_namelen < J1939_MIN_NAMELEN) { + ret = -EINVAL; + goto sendmsg_done; + } - if (addr->can_family != AF_CAN) - return -EINVAL; + if (addr->can_family != AF_CAN) { + ret = -EINVAL; + goto sendmsg_done; + } - if (addr->can_ifindex && addr->can_ifindex != ifindex) - return -EBADFD; + if (addr->can_ifindex && addr->can_ifindex != ifindex) { + ret = -EBADFD; + goto sendmsg_done; + } if (j1939_pgn_is_valid(addr->can_addr.j1939.pgn) && - !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) - return -EINVAL; + !j1939_pgn_is_clean_pdu(addr->can_addr.j1939.pgn)) { + ret = -EINVAL; + goto sendmsg_done; + } if (!addr->can_addr.j1939.name && addr->can_addr.j1939.addr == J1939_NO_ADDR && - !sock_flag(sk, SOCK_BROADCAST)) + !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ - return -EACCES; + ret = -EACCES; + goto sendmsg_done; + } } else { if (!jsk->addr.dst_name && jsk->addr.da == J1939_NO_ADDR && - !sock_flag(sk, SOCK_BROADCAST)) + !sock_flag(sk, SOCK_BROADCAST)) { /* broadcast, but SO_BROADCAST not set */ - return -EACCES; + ret = -EACCES; + goto sendmsg_done; + } } ret = j1939_sk_send_loop(priv, sk, msg, size); +sendmsg_done: + release_sock(sock->sk); + return ret; } diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index fe000ea757ea..9f99af5b0b11 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -255,6 +255,7 @@ static void __j1939_session_drop(struct j1939_session *session) return; j1939_sock_pending_del(session->sk); + sock_put(session->sk); } static void j1939_session_destroy(struct j1939_session *session) @@ -266,6 +267,9 @@ static void j1939_session_destroy(struct j1939_session *session) netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); + WARN_ON_ONCE(!list_empty(&session->sk_session_queue_entry)); + WARN_ON_ONCE(!list_empty(&session->active_session_list_entry)); + skb_queue_purge(&session->skb_queue); __j1939_session_drop(session); j1939_priv_put(session->priv); @@ -1042,12 +1046,13 @@ j1939_session_deactivate_activate_next(struct j1939_session *session) j1939_sk_queue_activate_next(session); } -static void j1939_session_cancel(struct j1939_session *session, +static void __j1939_session_cancel(struct j1939_session *session, enum j1939_xtp_abort err) { struct j1939_priv *priv = session->priv; WARN_ON_ONCE(!err); + lockdep_assert_held(&session->priv->active_session_list_lock); session->err = j1939_xtp_abort_to_errno(priv, err); /* do not send aborts on incoming broadcasts */ @@ -1062,6 +1067,20 @@ static void j1939_session_cancel(struct j1939_session *session, j1939_sk_send_loop_abort(session->sk, session->err); } +static void j1939_session_cancel(struct j1939_session *session, + enum j1939_xtp_abort err) +{ + j1939_session_list_lock(session->priv); + + if (session->state >= J1939_SESSION_ACTIVE && + session->state < J1939_SESSION_WAITING_ABORT) { + j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); + __j1939_session_cancel(session, err); + } + + j1939_session_list_unlock(session->priv); +} + static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) { struct j1939_session *session = @@ -1108,8 +1127,6 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) netdev_alert(priv->ndev, "%s: 0x%p: tx aborted with unknown reason: %i\n", __func__, session, ret); if (session->skcb.addr.type != J1939_SIMPLE) { - j1939_tp_set_rxtimeout(session, - J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_OTHER); } else { session->err = ret; @@ -1169,7 +1186,7 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer) hrtimer_start(&session->rxtimer, ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS), HRTIMER_MODE_REL_SOFT); - j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); + __j1939_session_cancel(session, J1939_XTP_ABORT_TIMEOUT); } j1939_session_list_unlock(session->priv); } @@ -1273,9 +1290,27 @@ j1939_xtp_rx_abort(struct j1939_priv *priv, struct sk_buff *skb, static void j1939_xtp_rx_eoma_one(struct j1939_session *session, struct sk_buff *skb) { + struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); + const u8 *dat; + int len; + if (j1939_xtp_rx_cmd_bad_pgn(session, skb)) return; + dat = skb->data; + + if (skcb->addr.type == J1939_ETP) + len = j1939_etp_ctl_to_size(dat); + else + len = j1939_tp_ctl_to_size(dat); + + if (session->total_message_size != len) { + netdev_warn_once(session->priv->ndev, + "%s: 0x%p: Incorrect size. Expected: %i; got: %i.\n", + __func__, session, session->total_message_size, + len); + } + netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); session->pkt.tx_acked = session->pkt.total; @@ -1357,7 +1392,6 @@ j1939_xtp_rx_cts_one(struct j1939_session *session, struct sk_buff *skb) out_session_cancel: j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, err); } @@ -1432,7 +1466,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv, skcb = j1939_skb_to_cb(skb); memcpy(skcb, rel_skcb, sizeof(*skcb)); - session = j1939_session_new(priv, skb, skb->len); + session = j1939_session_new(priv, skb, size); if (!session) { kfree_skb(skb); return NULL; @@ -1554,7 +1588,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, /* RTS on active session */ j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); } @@ -1565,7 +1598,6 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session, session->last_cmd); j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_BUSY); return -EBUSY; @@ -1767,7 +1799,6 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, out_session_cancel: j1939_session_timers_cancel(session); - j1939_tp_set_rxtimeout(session, J1939_XTP_ABORT_TIMEOUT_MS); j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); j1939_session_put(session); } @@ -1848,6 +1879,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv, return ERR_PTR(-ENOMEM); /* skb is recounted in j1939_session_new() */ + sock_hold(skb->sk); session->sk = skb->sk; session->transmission = true; session->pkt.total = (size + 6) / 7; @@ -2010,7 +2042,11 @@ int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk) &priv->active_session_list, active_session_list_entry) { if (!sk || sk == session->sk) { - j1939_session_timers_cancel(session); + if (hrtimer_try_to_cancel(&session->txtimer) == 1) + j1939_session_put(session); + if (hrtimer_try_to_cancel(&session->rxtimer) == 1) + j1939_session_put(session); + session->err = ESHUTDOWN; j1939_session_deactivate_locked(session); } 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..99ac84ff398f 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) @@ -276,88 +277,6 @@ 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 @@ -6489,6 +6408,9 @@ 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 +6433,7 @@ 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 +6454,7 @@ 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 +6472,7 @@ 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 +6516,22 @@ 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 +6582,23 @@ 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 +6616,111 @@ 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 +6817,119 @@ 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 +6944,99 @@ 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 +7140,7 @@ 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 +7291,17 @@ 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 +7323,13 @@ 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 +7412,96 @@ 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 +7615,6 @@ 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 +8421,8 @@ 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; } @@ -8619,7 +8887,7 @@ 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 +8934,43 @@ 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 @@ -8700,7 +9005,7 @@ 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) @@ -9210,8 +9515,12 @@ 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 +9601,8 @@ 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 +9771,7 @@ 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); 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 f80151eeaf51..93905dc7c179 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2699,7 +2699,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) struct devlink *devlink = info->user_ptr[0]; int err; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink) || !devlink->reload_enabled) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -4618,6 +4618,7 @@ 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; @@ -4790,6 +4791,7 @@ 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; @@ -4952,6 +4954,10 @@ 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); @@ -6196,6 +6202,8 @@ 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 +6211,41 @@ 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 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/filter.c b/net/core/filter.c index ed6563622ce3..3fed5755494b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4252,12 +4252,14 @@ 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 +4276,7 @@ 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) { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 7c09d87d3269..68eda10d0680 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1350,30 +1350,21 @@ 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) +static const void *flow_keys_hash_start(const struct flow_keys *flow) { - return jhash2(words, length, keyval); -} - -static inline const u32 *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)); @@ -1388,7 +1379,7 @@ 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) @@ -1454,14 +1445,15 @@ 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 +1463,13 @@ 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 +1517,7 @@ 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 +1537,14 @@ 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/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/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/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..c81cd80114d9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1523,7 +1523,7 @@ 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 +1531,7 @@ 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; @@ -1589,7 +1589,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, 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 +1681,7 @@ 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 && @@ -2001,7 +2001,7 @@ 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)) @@ -2355,6 +2355,7 @@ 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; } @@ -3359,7 +3360,7 @@ 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); @@ -3471,7 +3472,7 @@ 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 +3917,7 @@ 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; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 529133611ea2..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); @@ -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..ad31e4e53d0a 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); diff --git a/net/core/sock.c b/net/core/sock.c index fac2b4d80de5..ac78a570e43a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -522,7 +522,7 @@ 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; @@ -785,7 +785,8 @@ 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 +832,8 @@ 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 +976,7 @@ 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 +1127,7 @@ 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 +1476,7 @@ 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: @@ -2088,8 +2090,10 @@ 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; @@ -2190,7 +2194,7 @@ 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; @@ -2225,7 +2229,7 @@ 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); @@ -2334,8 +2338,8 @@ 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); } } @@ -2806,7 +2810,7 @@ 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 | @@ -3204,13 +3208,13 @@ 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); } @@ -3596,7 +3600,7 @@ 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/dccp/ipv4.c b/net/dccp/ipv4.c index d9b4200ed12d..d19557c6d04b 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -117,7 +117,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = dp->dccps_iss ^ jiffies; + inet->inet_id = prandom_u32(); err = dccp_connect(sk); rt = NULL; @@ -416,7 +416,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = jiffies; + newinet->inet_id = prandom_u32(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 0ea75286abf4..3349ea81f901 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1205,7 +1205,7 @@ static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wai struct dn_scp *scp = DN_SK(sk); __poll_t mask = datagram_poll(file, sock, wait); - if (!skb_queue_empty(&scp->other_receive_queue)) + if (!skb_queue_empty_lockless(&scp->other_receive_queue)) mask |= EPOLLRDBAND; return mask; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 73002022c9d8..716d265ba8ca 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -46,7 +46,7 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index) dst->index = index; INIT_LIST_HEAD(&dst->list); - list_add_tail(&dsa_tree_list, &dst->list); + list_add_tail(&dst->list, &dsa_tree_list); kref_init(&dst->refcount); diff --git a/net/dsa/master.c b/net/dsa/master.c index a8e52c9967f4..3255dfc97f86 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -310,8 +310,6 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } -static struct lock_class_key dsa_master_addr_list_lock_key; - int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -325,9 +323,6 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; - lockdep_set_class(&dev->addr_list_lock, - &dsa_master_addr_list_lock_key); - ret = dsa_master_ethtool_setup(dev); if (ret) return ret; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 75d58229a4bd..028e65f4b5ba 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1341,15 +1341,6 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } -static struct lock_class_key dsa_slave_netdev_xmit_lock_key; -static void dsa_slave_set_lockdep_class_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, - &dsa_slave_netdev_xmit_lock_key); -} - int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); @@ -1433,9 +1424,6 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->max_mtu = ETH_MAX_MTU; SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); - netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, - NULL); - SET_NETDEV_DEV(slave_dev, port->ds->dev); slave_dev->dev.of_node = port->dn; slave_dev->vlan_features = master->vlan_features; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 9c1cc2482b68..9e5a883a9f0c 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -106,7 +106,7 @@ static int dsa_8021q_restore_pvid(struct dsa_switch *ds, int port) slave = ds->ports[port].slave; err = br_vlan_get_pvid(slave, &pvid); - if (err < 0) + if (!pvid || err < 0) /* There is no pvid on the bridge for this port, which is * perfectly valid. Nothing to restore, bye-bye! */ diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 3297e7fa9945..c0b107cdd715 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -58,13 +58,6 @@ static const struct header_ops lowpan_header_ops = { .create = lowpan_header_create, }; -static int lowpan_dev_init(struct net_device *ldev) -{ - netdev_lockdep_set_classes(ldev); - - return 0; -} - static int lowpan_open(struct net_device *dev) { if (!open_count) @@ -96,7 +89,6 @@ static int lowpan_get_iflink(const struct net_device *dev) } static const struct net_device_ops lowpan_netdev_ops = { - .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 9a0fe0c2fa02..4a8550c49202 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns(sk, true); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = jiffies; + inet->inet_id = prandom_u32(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index dde77f72e03e..71c78d223dfd 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1148,7 +1148,7 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || - prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32) + (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 0913a090b2bf..f1888c683426 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1814,8 +1814,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); - int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index a9183543ca30..eb30fc1770de 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -906,7 +906,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, percpu_counter_inc(sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { - BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if @@ -915,7 +915,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ - tcp_sk(child)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } @@ -934,7 +934,7 @@ struct sock *inet_csk_reqsk_queue_add(struct sock *sk, req->sk = child; req->dl_next = NULL; if (queue->rskq_accept_head == NULL) - queue->rskq_accept_head = req; + WRITE_ONCE(queue->rskq_accept_head, req); else queue->rskq_accept_tail->dl_next = req; queue->rskq_accept_tail = req; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index bbb005eb5218..7dc79b973e6e 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -193,7 +193,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), - .idiag_wmem = sk->sk_wmem_queued, + .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), .idiag_fmem = sk->sk_forward_alloc, .idiag_tmem = sk_wmem_alloc_get(sk), }; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 97824864e40d..83fb00153018 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -240,7 +240,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score = sk->sk_family == PF_INET ? 2 : 1; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 52690bb3e40f..10636fb6093e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -509,9 +509,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto err_free_skb; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto err_free_skb; + md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 28fca408812c..3d8baaaf7086 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -645,11 +645,12 @@ void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, - unsigned int ll_rs, unsigned int mtu, + unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); + state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; @@ -668,9 +669,6 @@ static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; - if (IPCB(from)->flags & IPSKB_FRAG_PMTU) - state->iph->frag_off |= htons(IP_DF); - /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE @@ -738,6 +736,8 @@ struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); + if (state->DF) + iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the @@ -771,6 +771,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; + ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; @@ -846,6 +847,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ip_fraglist_prepare(skb, &iter); } + skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) @@ -881,7 +883,8 @@ slow_path: * Fragment the datagram. */ - ip_frag_init(skb, hlen, ll_rs, mtu, &state); + ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, + &state); /* * Keep copying data until we run out. @@ -900,6 +903,7 @@ slow_path: /* * Put this fragment into the sending queue. */ + skb2->tstamp = tstamp; err = output(net, sk, skb2); if (err) goto fail; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 716d5472c022..58007439cffd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2289,7 +2289,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_unlock(); return -ENODEV; } - skb2 = skb_clone(skb, GFP_ATOMIC); + + skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { read_unlock(&mrt_lock); rcu_read_unlock(); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 14654876127e..621f83434b24 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1482,7 +1482,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { - dst_dev_put(&orig->dst); + rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { @@ -2470,14 +2470,17 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; - int err = -ENETUNREACH; + int err; if (fl4->saddr) { - rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || - ipv4_is_zeronet(fl4->saddr)) + ipv4_is_zeronet(fl4->saddr)) { + rth = ERR_PTR(-EINVAL); goto out; + } + + rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. It was wrong for two reasons: diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f98a1882e537..d8876f0e9672 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -326,7 +326,7 @@ void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; - if (tcp_memory_pressure) + if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; @@ -341,7 +341,7 @@ void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; - if (!tcp_memory_pressure) + if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) @@ -450,8 +450,8 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; + WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); sk_sockets_allocated_inc(sk); sk->sk_route_forced_caps = NETIF_F_GSO; @@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (tp->rcv_nxt - tp->copied_seq >= target) || + return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || (sk->sk_prot->stream_memory_read ? sk->sk_prot->stream_memory_read(sk) : false); } @@ -543,10 +543,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && - (state != TCP_SYN_RECV || tp->fastopen_rsk)) { + (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); - if (tp->urg_seq == tp->copied_seq && + if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) target++; @@ -584,7 +584,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); - 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; return mask; @@ -607,7 +607,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && tp->urg_seq == tp->copied_seq; + answ = tp->urg_data && + READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) @@ -616,7 +617,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_una; + answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) @@ -625,7 +626,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_nxt; + answ = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; @@ -657,7 +659,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) tcb->sacked = 0; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; @@ -1032,10 +1034,10 @@ new_segment: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); skb->ip_summed = CHECKSUM_PARTIAL; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1362,7 +1364,7 @@ new_segment: if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1668,9 +1670,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb); if (!desc->count) break; - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); } - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -1699,7 +1701,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) else cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1; val = min(val, cap); - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); @@ -1709,7 +1711,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) val <<= 1; if (val > sk->sk_rcvbuf) { - sk->sk_rcvbuf = val; + WRITE_ONCE(sk->sk_rcvbuf, val); tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); } return 0; @@ -1819,7 +1821,7 @@ static int tcp_zerocopy_receive(struct sock *sk, out: up_read(¤t->mm->mmap_sem); if (length) { - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ @@ -1962,7 +1964,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); - if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && + if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && (sk->sk_state == TCP_ESTABLISHED)) sk_busy_loop(sk, nonblock); @@ -2117,7 +2119,7 @@ found_ok_skb: if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { - ++*seq; + WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; @@ -2139,7 +2141,7 @@ found_ok_skb: } } - *seq += used; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; @@ -2166,7 +2168,7 @@ skip_copy: found_fin_ok: /* Process the FIN. */ - ++*seq; + WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; @@ -2487,7 +2489,10 @@ adjudge_to_death: } if (sk->sk_state == TCP_CLOSE) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. @@ -2559,6 +2564,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -2585,7 +2591,7 @@ int tcp_disconnect(struct sock *sk, int flags) __kfree_skb(sk->sk_rx_skb_cache); sk->sk_rx_skb_cache = NULL; } - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); @@ -2601,9 +2607,12 @@ int tcp_disconnect(struct sock *sk, int flags) tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; - tp->write_seq += tp->max_window + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + + seq = tp->write_seq + tp->max_window + 2; + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; @@ -2930,9 +2939,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sk->sk_state != TCP_CLOSE) err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) - tp->write_seq = val; + WRITE_ONCE(tp->write_seq, val); else if (tp->repair_queue == TCP_RECV_QUEUE) - tp->rcv_nxt = val; + WRITE_ONCE(tp->rcv_nxt, val); else err = -EINVAL; break; @@ -3831,7 +3840,13 @@ EXPORT_SYMBOL(tcp_md5_hash_key); void tcp_done(struct sock *sk) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + /* We might be called with a new socket, after + * inet_csk_prepare_forced_close() has been called + * so we can not use lockdep_sock_is_held(sk) + */ + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 81a8221d650a..549506162dde 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -26,8 +26,9 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); - r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); - r->idiag_wqueue = tp->write_seq - tp->snd_una; + r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); + r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3fd451271a70..a915ade0c818 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -253,7 +253,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, */ tp = tcp_sk(child); - tp->fastopen_rsk = req; + rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3578357abe30..a2e52ad7cdab 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -359,7 +359,8 @@ static void tcp_sndbuf_expand(struct sock *sk) sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) - sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]); + WRITE_ONCE(sk->sk_sndbuf, + min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2])); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -483,8 +484,9 @@ static void tcp_clamp_window(struct sock *sk) !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { - sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), - net->ipv4.sysctl_tcp_rmem[2]); + WRITE_ONCE(sk->sk_rcvbuf, + min(atomic_read(&sk->sk_rmem_alloc), + net->ipv4.sysctl_tcp_rmem[2])); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); @@ -648,7 +650,7 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, rcvwin * rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { - sk->sk_rcvbuf = rcvbuf; + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */ tp->window_clamp = tcp_win_from_space(sk, rcvbuf); @@ -2666,7 +2668,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); - if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) && + if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) && tcp_try_undo_loss(sk, false)) return; @@ -2990,7 +2992,7 @@ void tcp_rearm_rto(struct sock *sk) /* If the retrans timer is currently being used by Fast Open * for SYN-ACK retrans purpose, stay put. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return; if (!tp->packets_out) { @@ -3362,7 +3364,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) sock_owned_by_me((struct sock *)tp); tp->bytes_received += delta; - tp->rcv_nxt = seq; + WRITE_ONCE(tp->rcv_nxt, seq); } /* Update our send window. @@ -5356,7 +5358,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) } tp->urg_data = TCP_URG_NOTYET; - tp->urg_seq = ptr; + WRITE_ONCE(tp->urg_seq, ptr); /* Disable header prediction. */ tp->pred_flags = 0; @@ -5932,7 +5934,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Ok.. it's good. Set up sequence numbers and * move to established. */ - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -5961,7 +5963,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); smc_check_reset_syn(tp); @@ -6035,8 +6037,8 @@ discard: tp->tcp_header_len = sizeof(struct tcphdr); } - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -6087,6 +6089,8 @@ reset_and_undo: static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { + struct request_sock *req; + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ @@ -6096,7 +6100,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) /* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1, * we no longer need req so release it. */ - reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false); + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); + reqsk_fastopen_remove(sk, req, false); /* Re-arm the timer because data may have been sent out. * This is similar to the regular data transmission case @@ -6171,7 +6177,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; - req = tp->fastopen_rsk; + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); if (req) { bool req_stolen; @@ -6211,7 +6218,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bf124b1742df..67b2dc7a1727 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) * without appearing to create any others. */ if (likely(!tp->repair)) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + u32 seq = tcptw->tw_snd_nxt + 65535 + 2; + + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } @@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; @@ -291,16 +293,17 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port); + WRITE_ONCE(tp->write_seq, + secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); } - inet->inet_id = tp->write_seq ^ jiffies; + inet->inet_id = prandom_u32(); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -478,7 +481,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -1447,7 +1450,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = newtp->write_seq ^ jiffies; + newinet->inet_id = prandom_u32(); if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); @@ -1644,7 +1647,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { - u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; + u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf); struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -2121,7 +2124,7 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - BUG_ON(tp->fastopen_rsk); + BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -2455,12 +2458,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), @@ -2677,7 +2681,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; - net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); + net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index bb140a5db8c0..c802bc80c400 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -462,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk; struct tcp_sock *oldtp, *newtp; + u32 seq; if (!newsk) return NULL; @@ -475,12 +476,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, /* Now setup tcp_sock */ newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = - newtp->rcv_nxt = treq->rcv_isn + 1; + seq = treq->rcv_isn + 1; + newtp->rcv_wup = seq; + WRITE_ONCE(newtp->copied_seq, seq); + WRITE_ONCE(newtp->rcv_nxt, seq); newtp->segs_in = 1; - newtp->snd_sml = newtp->snd_una = - newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; + seq = treq->snt_isn + 1; + newtp->snd_sml = newtp->snd_una = seq; + WRITE_ONCE(newtp->snd_nxt, seq); + newtp->snd_up = seq; INIT_LIST_HEAD(&newtp->tsq_node); INIT_LIST_HEAD(&newtp->tsorted_sent_queue); @@ -495,7 +500,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1); if (sock_flag(newsk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(newsk, @@ -541,7 +546,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); newtp->fastopen_req = NULL; - newtp->fastopen_rsk = NULL; + RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fec6d67bfd14..0488607c5cd3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -67,7 +67,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); @@ -1196,10 +1196,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ - tp->write_seq = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } @@ -1333,7 +1333,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; @@ -1443,7 +1443,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; - sk->sk_wmem_queued -= delta_truesize; + sk_wmem_queued_add(sk, -delta_truesize); sk_mem_uncharge(sk, delta_truesize); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); } @@ -1888,7 +1888,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, return -ENOMEM; skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; @@ -2152,7 +2152,7 @@ static int tcp_mtu_probe(struct sock *sk) nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); @@ -2482,7 +2482,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; @@ -3142,7 +3142,7 @@ void tcp_send_fin(struct sock *sk) * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ - tp->snd_nxt++; + WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { @@ -3222,7 +3222,7 @@ int tcp_send_synack(struct sock *sk) tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } @@ -3426,14 +3426,14 @@ static void tcp_connect_init(struct sock *sk) tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; @@ -3447,9 +3447,9 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); - tp->write_seq = tcb->end_seq; + WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } @@ -3586,11 +3586,11 @@ int tcp_connect(struct sock *sk) /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { - tp->snd_nxt = TCP_SKB_CB(buff)->seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 05be564414e9..dd5a6317a801 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -386,15 +386,13 @@ abort: tcp_write_err(sk); * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ -static void tcp_fastopen_synack_timer(struct sock *sk) +static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); int max_retries = icsk->icsk_syn_retries ? : sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req; - req = tcp_sk(sk)->fastopen_rsk; req->rsk_ops->syn_ack_timeout(req); if (req->num_timeout >= max_retries) { @@ -435,11 +433,14 @@ void tcp_retransmit_timer(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; - if (tp->fastopen_rsk) { + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - tcp_fastopen_synack_timer(sk); + tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 14bc654b6842..1d58ce829dca 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -388,7 +388,7 @@ static int compute_score(struct sock *sk, struct net *net, return -1; score += 4; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } @@ -1316,6 +1316,20 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } +static void udp_skb_csum_unnecessary_set(struct sk_buff *skb) +{ + /* We come here after udp_lib_checksum_complete() returned 0. + * This means that __skb_checksum_complete() might have + * set skb->csum_valid to 1. + * On 64bit platforms, we can set csum_unnecessary + * to true, but only if the skb is not shared. + */ +#if BITS_PER_LONG == 64 + if (!skb_shared(skb)) + udp_skb_scratch(skb)->csum_unnecessary = true; +#endif +} + static int udp_skb_truesize(struct sk_buff *skb) { return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; @@ -1550,10 +1564,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk, *total += skb->truesize; kfree_skb(skb); } else { - /* the csum related bits could be changed, refresh - * the scratch area - */ - udp_set_dev_scratch(skb); + udp_skb_csum_unnecessary_set(skb); break; } } @@ -1577,7 +1588,7 @@ static int first_packet_length(struct sock *sk) spin_lock_bh(&rcvq->lock); skb = __first_packet_length(sk, rcvq, &total); - if (!skb && !skb_queue_empty(sk_queue)) { + if (!skb && !skb_queue_empty_lockless(sk_queue)) { spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, rcvq); spin_unlock(&sk_queue->lock); @@ -1650,7 +1661,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, return skb; } - if (skb_queue_empty(sk_queue)) { + if (skb_queue_empty_lockless(sk_queue)) { spin_unlock_bh(&queue->lock); goto busy_check; } @@ -1676,7 +1687,7 @@ busy_check: break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (!skb_queue_empty(sk_queue)); + } while (!skb_queue_empty_lockless(sk_queue)); /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && @@ -2712,7 +2723,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; - if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) + if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 783f3c1466da..2fc079284ca4 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -7,6 +7,7 @@ #include <linux/export.h> #include <net/ipv6.h> #include <net/ipv6_stubs.h> +#include <net/addrconf.h> #include <net/ip.h> /* if ipv6 module registers this function is used by xfrm to force all diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index cf60fae9533b..fbe9d4295eac 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -105,7 +105,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score = 1; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d5779d6a6065..923034c52ce4 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -980,9 +980,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, dsfield = key->tos; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto tx_err; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto tx_err; + md = ip_tunnel_info_opts(tun_info); tun_id = tunnel_id_to_key32(key->tun_id); if (md->version == 1) { @@ -2192,6 +2192,7 @@ static void ip6erspan_tap_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &ip6erspan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index edadee4a7e76..71827b56c006 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -768,6 +768,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, inet6_sk(skb->sk) : NULL; struct ip6_frag_state state; unsigned int mtu, hlen, nexthdr_offset; + ktime_t tstamp = skb->tstamp; int hroom, err = 0; __be32 frag_id; u8 *prevhdr, nexthdr = 0; @@ -855,6 +856,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); + skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), @@ -913,6 +915,7 @@ slow_path: /* * Put this fragment into the sending queue. */ + frag->tstamp = tstamp; err = output(net, sk, frag); if (err) goto fail; diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index a9bff556d3b2..409e79b84a83 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -119,6 +119,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct sk_buff *)) { int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size; + ktime_t tstamp = skb->tstamp; struct ip6_frag_state state; u8 *prevhdr, nexthdr = 0; unsigned int mtu, hlen; @@ -183,6 +184,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (iter.frag) ip6_fraglist_prepare(skb, &iter); + skb->tstamp = tstamp; err = output(net, sk, data, skb); if (err || !iter.frag) break; @@ -215,6 +217,7 @@ slow_path: goto blackhole; } + skb2->tstamp = tstamp; err = output(net, sk, data, skb2); if (err) goto blackhole; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a63ff85fe141..e60bf8e7dd1a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -621,6 +621,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; + unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; @@ -639,6 +640,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock_bh(); + last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { @@ -654,13 +656,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh) __neigh_set_probe_once(neigh); } write_unlock(&neigh->lock); - } else if (time_after(jiffies, fib6_nh->last_probe + + } else if (time_after(jiffies, last_probe + idev->cnf.rtr_probe_interval)) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } - if (work) { - fib6_nh->last_probe = jiffies; + if (!work || cmpxchg(&fib6_nh->last_probe, + last_probe, jiffies) != last_probe) { + kfree(work); + } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; dev_hold(dev); @@ -3383,6 +3387,9 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, int err; fib6_nh->fib_nh_family = AF_INET6; +#ifdef CONFIG_IPV6_ROUTER_PREF + fib6_nh->last_probe = jiffies; +#endif err = -ENODEV; if (cfg->fc_ifindex) { diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 9d4f75e0d33a..e70567446f28 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -81,6 +81,11 @@ static struct ipv6_sr_hdr *get_srh(struct sk_buff *skb) if (!pskb_may_pull(skb, srhoff + len)) return NULL; + /* note that pskb_may_pull may change pointers in header; + * for this reason it is necessary to reload them when needed. + */ + srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); + if (!seg6_validate_srh(srh, len)) return NULL; @@ -336,6 +341,8 @@ static int input_action_end_dx6(struct sk_buff *skb, if (!ipv6_addr_any(&slwt->nh6)) nhaddr = &slwt->nh6; + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + seg6_lookup_nexthop(skb, nhaddr, 0); return dst_input(skb); @@ -365,6 +372,8 @@ static int input_action_end_dx4(struct sk_buff *skb, skb_dst_drop(skb); + skb_set_transport_header(skb, sizeof(struct iphdr)); + err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev); if (err) goto drop; @@ -385,6 +394,8 @@ static int input_action_end_dt6(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; + skb_set_transport_header(skb, sizeof(struct ipv6hdr)); + seg6_lookup_nexthop(skb, NULL, slwt->table); return dst_input(skb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e3d9f4559c99..4804b6dc5e65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; @@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport); + WRITE_ONCE(tp->write_seq, + secure_tcpv6_seq(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); @@ -406,7 +407,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -1895,7 +1896,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " @@ -1906,7 +1908,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6324d3a8cb53..9fec580c968e 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -135,7 +135,7 @@ static int compute_score(struct sock *sk, struct net *net, return -1; score++; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index fd5ac2788e45..d3b520b9b2c9 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -56,7 +56,6 @@ static int l2tp_eth_dev_init(struct net_device *dev) { eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); - netdev_lockdep_set_classes(dev); return 0; } diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2017b7d780f5..c74f44dfaa22 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -113,22 +113,26 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr) * * Send data via reliable llc2 connection. * Returns 0 upon success, non-zero if action did not succeed. + * + * This function always consumes a reference to the skb. */ static int llc_ui_send_data(struct sock* sk, struct sk_buff *skb, int noblock) { struct llc_sock* llc = llc_sk(sk); - int rc = 0; if (unlikely(llc_data_accept_state(llc->state) || llc->remote_busy_flag || llc->p_flag)) { long timeout = sock_sndtimeo(sk, noblock); + int rc; rc = llc_ui_wait_for_busy_core(sk, timeout); + if (rc) { + kfree_skb(skb); + return rc; + } } - if (unlikely(!rc)) - rc = llc_build_and_send_pkt(sk, skb); - return rc; + return llc_build_and_send_pkt(sk, skb); } static void llc_ui_sk_init(struct socket *sock, struct sock *sk) @@ -899,7 +903,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; - struct sk_buff *skb; + struct sk_buff *skb = NULL; size_t size = 0; int rc = -EINVAL, copied = 0, hdrlen; @@ -908,10 +912,10 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) lock_sock(sk); if (addr) { if (msg->msg_namelen < sizeof(*addr)) - goto release; + goto out; } else { if (llc_ui_addr_null(&llc->addr)) - goto release; + goto out; addr = &llc->addr; } /* must bind connection to sap if user hasn't done it. */ @@ -919,7 +923,7 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) /* bind to sap with null dev, exclusive. */ rc = llc_ui_autobind(sock, addr); if (rc) - goto release; + goto out; } hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); size = hdrlen + len; @@ -928,12 +932,12 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) copied = size - hdrlen; rc = -EINVAL; if (copied < 0) - goto release; + goto out; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); if (!skb) - goto release; + goto out; skb->dev = llc->dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); skb_reserve(skb, hdrlen); @@ -943,29 +947,31 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (sk->sk_type == SOCK_DGRAM || addr->sllc_ua) { llc_build_and_send_ui_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } if (addr->sllc_test) { llc_build_and_send_test_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } if (addr->sllc_xid) { llc_build_and_send_xid_pkt(llc->sap, skb, addr->sllc_mac, addr->sllc_sap); + skb = NULL; goto out; } rc = -ENOPROTOOPT; if (!(sk->sk_type == SOCK_STREAM && !addr->sllc_ua)) goto out; rc = llc_ui_send_data(sk, skb, noblock); + skb = NULL; out: - if (rc) { - kfree_skb(skb); -release: + kfree_skb(skb); + if (rc) dprintk("%s: failed sending from %02X to %02X: %d\n", __func__, llc->laddr.lsap, llc->daddr.lsap, rc); - } release_sock(sk); return rc ? : copied; } diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 4d78375f9872..647c0554d04c 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -372,6 +372,7 @@ int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -389,7 +390,8 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; @@ -406,6 +408,7 @@ int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -916,7 +919,8 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk, llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 4ff89cb7c86f..7b620acaca9e 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -30,7 +30,7 @@ #endif static int llc_find_offset(int state, int ev_type); -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb); +static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, struct llc_conn_state_trans *trans, @@ -55,6 +55,8 @@ int sysctl_llc2_busy_timeout = LLC2_BUSY_TIME * HZ; * (executing it's actions and changing state), upper layer will be * indicated or confirmed, if needed. Returns 0 for success, 1 for * failure. The socket lock has to be held before calling this function. + * + * This function always consumes a reference to the skb. */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) { @@ -62,12 +64,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) struct llc_sock *llc = llc_sk(skb->sk); struct llc_conn_state_ev *ev = llc_conn_ev(skb); - /* - * We have to hold the skb, because llc_conn_service will kfree it in - * the sending path and we need to look at the skb->cb, where we encode - * llc_conn_state_ev. - */ - skb_get(skb); ev->ind_prim = ev->cfm_prim = 0; /* * Send event to state machine @@ -75,21 +71,12 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) rc = llc_conn_service(skb->sk, skb); if (unlikely(rc != 0)) { printk(KERN_ERR "%s: llc_conn_service failed\n", __func__); - goto out_kfree_skb; - } - - if (unlikely(!ev->ind_prim && !ev->cfm_prim)) { - /* indicate or confirm not required */ - if (!skb->next) - goto out_kfree_skb; goto out_skb_put; } - if (unlikely(ev->ind_prim && ev->cfm_prim)) /* Paranoia */ - skb_get(skb); - switch (ev->ind_prim) { case LLC_DATA_PRIM: + skb_get(skb); llc_save_primitive(sk, skb, LLC_DATA_PRIM); if (unlikely(sock_queue_rcv_skb(sk, skb))) { /* @@ -106,6 +93,7 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) * skb->sk pointing to the newly created struct sock in * llc_conn_handler. -acme */ + skb_get(skb); skb_queue_tail(&sk->sk_receive_queue, skb); sk->sk_state_change(sk); break; @@ -121,7 +109,6 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) sk->sk_state_change(sk); } } - kfree_skb(skb); sock_put(sk); break; case LLC_RESET_PRIM: @@ -130,14 +117,11 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) * RESET is not being notified to upper layers for now */ printk(KERN_INFO "%s: received a reset ind!\n", __func__); - kfree_skb(skb); break; default: - if (ev->ind_prim) { + if (ev->ind_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->ind_prim); - kfree_skb(skb); - } /* No indication */ break; } @@ -179,25 +163,22 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) printk(KERN_INFO "%s: received a reset conf!\n", __func__); break; default: - if (ev->cfm_prim) { + if (ev->cfm_prim) printk(KERN_INFO "%s: received unknown %d prim!\n", __func__, ev->cfm_prim); - break; - } - goto out_skb_put; /* No confirmation */ + /* No confirmation */ + break; } -out_kfree_skb: - kfree_skb(skb); out_skb_put: kfree_skb(skb); return rc; } -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) { /* queue PDU to send to MAC layer */ skb_queue_tail(&sk->sk_write_queue, skb); - return llc_conn_send_pdus(sk, skb); + llc_conn_send_pdus(sk); } /** @@ -255,7 +236,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -296,7 +277,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -340,16 +321,12 @@ out: /** * llc_conn_send_pdus - Sends queued PDUs * @sk: active connection - * @hold_skb: the skb held by caller, or NULL if does not care * - * Sends queued pdus to MAC layer for transmission. When @hold_skb is - * NULL, always return 0. Otherwise, return 0 if @hold_skb is sent - * successfully, or 1 for failure. + * Sends queued pdus to MAC layer for transmission. */ -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) +static void llc_conn_send_pdus(struct sock *sk) { struct sk_buff *skb; - int ret = 0; while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); @@ -361,20 +338,10 @@ static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb); if (!skb2) break; - dev_queue_xmit(skb2); - } else { - bool is_target = skb == hold_skb; - int rc; - - if (is_target) - skb_get(skb); - rc = dev_queue_xmit(skb); - if (is_target) - ret = rc; + skb = skb2; } + dev_queue_xmit(skb); } - - return ret; } /** @@ -846,7 +813,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) else { dprintk("%s: adding to backlog...\n", __func__); llc_set_backlog_type(skb, LLC_PACKET); - if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) + if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) goto drop_unlock; } out: diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index 8db03c2d5440..ad6547736c21 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -38,6 +38,8 @@ * closed and -EBUSY when sending data is not permitted in this state or * LLC has send an I pdu with p bit set to 1 and is waiting for it's * response. + * + * This function always consumes a reference to the skb. */ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb) { @@ -46,20 +48,22 @@ int llc_build_and_send_pkt(struct sock *sk, struct sk_buff *skb) struct llc_sock *llc = llc_sk(sk); if (unlikely(llc->state == LLC_CONN_STATE_ADM)) - goto out; + goto out_free; rc = -EBUSY; if (unlikely(llc_data_accept_state(llc->state) || /* data_conn_refuse */ llc->p_flag)) { llc->failed_data_req = 1; - goto out; + goto out_free; } ev = llc_conn_ev(skb); ev->type = LLC_CONN_EV_TYPE_PRIM; ev->prim = LLC_DATA_PRIM; ev->prim_type = LLC_PRIM_TYPE_REQ; skb->dev = llc->dev; - rc = llc_conn_state_process(sk, skb); -out: + return llc_conn_state_process(sk, skb); + +out_free: + kfree_skb(skb); return rc; } diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index a94bd56bcac6..7ae4cc684d3a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -58,8 +58,10 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -81,8 +83,10 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -135,8 +139,10 @@ int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_test_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index a7f7b8ff4729..be419062e19a 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -197,29 +197,22 @@ out: * After executing actions of the event, upper layer will be indicated * if needed(on receiving an UI frame). sk can be null for the * datalink_proto case. + * + * This function always consumes a reference to the skb. */ static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); - /* - * We have to hold the skb, because llc_sap_next_state - * will kfree it in the sending path and we need to - * look at the skb->cb, where we encode llc_sap_state_ev. - */ - skb_get(skb); ev->ind_cfm_flag = 0; llc_sap_next_state(sap, skb); - if (ev->ind_cfm_flag == LLC_IND) { - if (skb->sk->sk_state == TCP_LISTEN) - kfree_skb(skb); - else { - llc_save_primitive(skb->sk, skb, ev->prim); - /* queue skb to the user. */ - if (sock_queue_rcv_skb(skb->sk, skb)) - kfree_skb(skb); - } + if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) { + llc_save_primitive(skb->sk, skb, ev->prim); + + /* queue skb to the user. */ + if (sock_queue_rcv_skb(skb->sk, skb) == 0) + return; } kfree_skb(skb); } diff --git a/net/mac80211/main.c b/net/mac80211/main.c index aba094b4ccfc..2d05c4cfaf6d 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1292,8 +1292,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) ieee80211_remove_interfaces(local); fail_rate: rtnl_unlock(); - ieee80211_led_exit(local); fail_flows: + ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: wiphy_unregister(local->hw.wiphy); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 26a2f49208b6..54dd8849d1cc 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2633,7 +2633,8 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, rcu_read_lock(); ssid = ieee80211_bss_get_ie(cbss, WLAN_EID_SSID); - if (WARN_ON_ONCE(ssid == NULL)) + if (WARN_ONCE(!ssid || ssid[1] > IEEE80211_MAX_SSID_LEN, + "invalid SSID element (len=%d)", ssid ? ssid[1] : -1)) ssid_len = 0; else ssid_len = ssid[1]; @@ -5233,7 +5234,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, rcu_read_lock(); ssidie = ieee80211_bss_get_ie(req->bss, WLAN_EID_SSID); - if (!ssidie) { + if (!ssidie || ssidie[1] > sizeof(assoc_data->ssid)) { rcu_read_unlock(); kfree(assoc_data); return -EINVAL; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 768d14c9a716..0e05ff037672 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3467,9 +3467,18 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx) case cpu_to_le16(IEEE80211_STYPE_PROBE_RESP): /* process for all: mesh, mlme, ibss */ break; + case cpu_to_le16(IEEE80211_STYPE_DEAUTH): + if (is_multicast_ether_addr(mgmt->da) && + !is_broadcast_ether_addr(mgmt->da)) + return RX_DROP_MONITOR; + + /* process only for station/IBSS */ + if (sdata->vif.type != NL80211_IFTYPE_STATION && + sdata->vif.type != NL80211_IFTYPE_ADHOC) + return RX_DROP_MONITOR; + break; case cpu_to_le16(IEEE80211_STYPE_ASSOC_RESP): case cpu_to_le16(IEEE80211_STYPE_REASSOC_RESP): - case cpu_to_le16(IEEE80211_STYPE_DEAUTH): case cpu_to_le16(IEEE80211_STYPE_DISASSOC): if (is_multicast_ether_addr(mgmt->da) && !is_broadcast_ether_addr(mgmt->da)) diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index adf94ba1ed77..4d31d9688dc2 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -520,10 +520,33 @@ static int ieee80211_start_sw_scan(struct ieee80211_local *local, return 0; } +static bool __ieee80211_can_leave_ch(struct ieee80211_sub_if_data *sdata) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_sub_if_data *sdata_iter; + + if (!ieee80211_is_radar_required(local)) + return true; + + if (!regulatory_pre_cac_allowed(local->hw.wiphy)) + return false; + + mutex_lock(&local->iflist_mtx); + list_for_each_entry(sdata_iter, &local->interfaces, list) { + if (sdata_iter->wdev.cac_started) { + mutex_unlock(&local->iflist_mtx); + return false; + } + } + mutex_unlock(&local->iflist_mtx); + + return true; +} + static bool ieee80211_can_scan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata) { - if (ieee80211_is_radar_required(local)) + if (!__ieee80211_can_leave_ch(sdata)) return false; if (!list_empty(&local->roc_list)) @@ -630,7 +653,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata, lockdep_assert_held(&local->mtx); - if (local->scan_req || ieee80211_is_radar_required(local)) + if (local->scan_req) + return -EBUSY; + + if (!__ieee80211_can_leave_ch(sdata)) return -EBUSY; if (!ieee80211_can_scan(local, sdata)) { diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index bd11fef2139f..8d3a2389b055 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2457,7 +2457,8 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta) { struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta); - if (time_after(stats->last_rx, sta->status_stats.last_ack)) + if (!sta->status_stats.last_ack || + time_after(stats->last_rx, sta->status_stats.last_ack)) return stats->last_rx; return sta->status_stats.last_ack; } diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e64d5f9a89dd..d73d1828216a 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -296,7 +296,8 @@ ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4))) return -IPSET_ERR_PROTOCOL; @@ -314,7 +315,8 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6))) return -IPSET_ERR_PROTOCOL; @@ -934,7 +936,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Without holding any locks, create private part. */ if (attr[IPSET_ATTR_DATA] && - nla_parse_nested_deprecated(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy, NULL)) { + nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], + set->type->create_policy, NULL)) { ret = -IPSET_ERR_PROTOCOL; goto put_out; } @@ -1281,6 +1284,14 @@ dump_attrs(struct nlmsghdr *nlh) } } +static const struct nla_policy +ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_FLAGS] = { .type = NLA_U32 }, +}; + static int dump_init(struct netlink_callback *cb, struct ip_set_net *inst) { @@ -1292,9 +1303,9 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst) ip_set_id_t index; int ret; - ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, attr, - nlh->nlmsg_len - min_len, - ip_set_setname_policy, NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, + nlh->nlmsg_len - min_len, + ip_set_dump_policy, NULL); if (ret) return ret; @@ -1543,9 +1554,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, memcpy(&errmsg->msg, nlh, nlh->nlmsg_len); cmdattr = (void *)&errmsg->msg + min_len; - ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, cmdattr, - nlh->nlmsg_len - min_len, - ip_set_adt_policy, NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr, + nlh->nlmsg_len - min_len, ip_set_adt_policy, + NULL); if (ret) { nlmsg_free(skb2); @@ -1596,7 +1607,9 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, use_lineno = !!attr[IPSET_ATTR_LINENO]; if (attr[IPSET_ATTR_DATA]) { - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, + attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, adt, flags, use_lineno); @@ -1606,7 +1619,8 @@ static int ip_set_ad(struct net *net, struct sock *ctnl, nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) { if (nla_type(nla) != IPSET_ATTR_DATA || !flag_nested(nla) || - nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL)) + nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, adt, flags, use_lineno); @@ -1655,7 +1669,8 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, if (!set) return -ENOENT; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; rcu_read_lock_bh(); @@ -1961,7 +1976,7 @@ static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { [IPSET_CMD_LIST] = { .call = ip_set_dump, .attr_count = IPSET_ATTR_CMD_MAX, - .policy = ip_set_setname_policy, + .policy = ip_set_dump_policy, }, [IPSET_CMD_SAVE] = { .call = ip_set_dump, @@ -2069,8 +2084,9 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } req_version->version = IPSET_PROTOCOL; - ret = copy_to_user(user, req_version, - sizeof(struct ip_set_req_version)); + if (copy_to_user(user, req_version, + sizeof(struct ip_set_req_version))) + ret = -EFAULT; goto done; } case IP_SET_OP_GET_BYNAME: { @@ -2129,7 +2145,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } /* end of switch(op) */ copy: - ret = copy_to_user(user, data, copylen); + if (copy_to_user(user, data, copylen)) + ret = -EFAULT; done: vfree(data); diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index 24d8f4df4230..4ce563eb927d 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -209,7 +209,7 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb, (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c259cbc3ef45..3d932de0ad29 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -368,6 +368,7 @@ static struct ip_set_type hash_net_type __read_mostly = { [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index a3ae69bfee66..4398322fad59 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -476,6 +476,7 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 4515056ef1c2..f9b16f2b2219 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -193,21 +193,29 @@ struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app * mutex_lock(&__ip_vs_app_mutex); + /* increase the module use count */ + if (!ip_vs_use_count_inc()) { + err = -ENOENT; + goto out_unlock; + } + list_for_each_entry(a, &ipvs->app_list, a_list) { if (!strcmp(app->name, a->name)) { err = -EEXIST; + /* decrease the module use count */ + ip_vs_use_count_dec(); goto out_unlock; } } a = kmemdup(app, sizeof(*app), GFP_KERNEL); if (!a) { err = -ENOMEM; + /* decrease the module use count */ + ip_vs_use_count_dec(); goto out_unlock; } INIT_LIST_HEAD(&a->incs_list); list_add(&a->a_list, &ipvs->app_list); - /* increase the module use count */ - ip_vs_use_count_inc(); out_unlock: mutex_unlock(&__ip_vs_app_mutex); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 8b48e7ce1c2c..3cccc88ef817 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -93,7 +93,6 @@ static bool __ip_vs_addr_is_local_v6(struct net *net, static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; - static int old_secure_tcp = 0; int availmem; int nomem; int to_change = -1; @@ -174,35 +173,35 @@ static void update_defense_level(struct netns_ipvs *ipvs) spin_lock(&ipvs->securetcp_lock); switch (ipvs->sysctl_secure_tcp) { case 0: - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; break; case 1: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; ipvs->sysctl_secure_tcp = 2; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; } break; case 2: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; ipvs->sysctl_secure_tcp = 1; } break; case 3: - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; break; } - old_secure_tcp = ipvs->sysctl_secure_tcp; + ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp; if (to_change >= 0) ip_vs_protocol_timeout_change(ipvs, ipvs->sysctl_secure_tcp > 1); @@ -1275,7 +1274,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_service *svc = NULL; /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOPROTOOPT; /* Lookup the scheduler by 'u->sched_name' */ if (strcmp(u->sched_name, "none")) { @@ -2435,9 +2435,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (copy_from_user(arg, user, len) != 0) return -EFAULT; - /* increase the module use count */ - ip_vs_use_count_inc(); - /* Handle daemons since they have another lock */ if (cmd == IP_VS_SO_SET_STARTDAEMON || cmd == IP_VS_SO_SET_STOPDAEMON) { @@ -2450,13 +2447,13 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) ret = -EINVAL; if (strscpy(cfg.mcast_ifn, dm->mcast_ifn, sizeof(cfg.mcast_ifn)) <= 0) - goto out_dec; + return ret; cfg.syncid = dm->syncid; ret = start_sync_thread(ipvs, &cfg, dm->state); } else { ret = stop_sync_thread(ipvs, dm->state); } - goto out_dec; + return ret; } mutex_lock(&__ip_vs_mutex); @@ -2551,10 +2548,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) out_unlock: mutex_unlock(&__ip_vs_mutex); - out_dec: - /* decrease the module use count */ - ip_vs_use_count_dec(); - return ret; } diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c index 8e104dff7abc..166c669f0763 100644 --- a/net/netfilter/ipvs/ip_vs_pe.c +++ b/net/netfilter/ipvs/ip_vs_pe.c @@ -68,7 +68,8 @@ int register_ip_vs_pe(struct ip_vs_pe *pe) struct ip_vs_pe *tmp; /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOENT; mutex_lock(&ip_vs_pe_mutex); /* Make sure that the pe with this name doesn't exist diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 2f9d5cd5daee..d4903723be7e 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -179,7 +179,8 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) } /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOENT; mutex_lock(&ip_vs_sched_mutex); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index a4a78c4b06de..8dc892a9dc91 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1762,6 +1762,10 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + /* increase the module use count */ + if (!ip_vs_use_count_inc()) + return -ENOPROTOOPT; + /* Do not hold one mutex and then to block on another */ for (;;) { rtnl_lock(); @@ -1892,9 +1896,6 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); - /* increase the module use count */ - ip_vs_use_count_inc(); - return 0; out: @@ -1924,11 +1925,17 @@ out: } kfree(ti); } + + /* decrease the module use count */ + ip_vs_use_count_dec(); return result; out_early: mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); + + /* decrease the module use count */ + ip_vs_use_count_dec(); return result; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0c63120b2db2..5cd610b547e0 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1792,8 +1792,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) extra_jiffies += nfct_time_stamp; - if (ct->timeout != extra_jiffies) - ct->timeout = extra_jiffies; + if (READ_ONCE(ct->timeout) != extra_jiffies) + WRITE_ONCE(ct->timeout, extra_jiffies); acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 132f5228b431..128245efe84a 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -202,6 +202,8 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; + flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, nf_flow_offload_rhash_params); @@ -218,7 +220,6 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d481f9baca2f..712a428509ad 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1922,6 +1922,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + flags |= chain->flags & NFT_BASE_CHAIN; return nf_tables_updchain(&ctx, genmask, policy, flags); } @@ -5143,9 +5144,6 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, struct nft_trans *trans; int err; - if (!obj->ops->update) - return -EOPNOTSUPP; - trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) @@ -6499,7 +6497,8 @@ static void nft_obj_commit_update(struct nft_trans *trans) obj = nft_trans_obj(trans); newobj = nft_trans_obj_newobj(trans); - obj->ops->update(obj, newobj); + if (obj->ops->update) + obj->ops->update(obj, newobj); kfree(newobj); } diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index e546f759b7a7..e25dab8128db 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -334,7 +334,8 @@ int nft_flow_rule_offload_commit(struct net *net) switch (trans->msg_type) { case NFT_MSG_NEWCHAIN: - if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) + if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) || + nft_trans_chain_update(trans)) continue; policy = nft_trans_chain_policy(trans); @@ -347,7 +348,7 @@ int nft_flow_rule_offload_commit(struct net *net) policy = nft_trans_chain_policy(trans); err = nft_flow_offload_chain(trans->ctx.chain, &policy, - FLOW_BLOCK_BIND); + FLOW_BLOCK_UNBIND); break; case NFT_MSG_NEWRULE: if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)) diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 974300178fa9..02afa752dd2e 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -134,12 +134,13 @@ static int nft_bitwise_offload(struct nft_offload_ctx *ctx, const struct nft_expr *expr) { const struct nft_bitwise *priv = nft_expr_priv(expr); + struct nft_offload_reg *reg = &ctx->regs[priv->dreg]; if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) || - priv->sreg != priv->dreg) + priv->sreg != priv->dreg || priv->len != reg->len) return -EOPNOTSUPP; - memcpy(&ctx->regs[priv->dreg].mask, &priv->mask, sizeof(priv->mask)); + memcpy(®->mask, &priv->mask, sizeof(priv->mask)); return 0; } diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index bd173b1824c6..0744b2bb46da 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -116,7 +116,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx, u8 *mask = (u8 *)&flow->match.mask; u8 *key = (u8 *)&flow->match.key; - if (priv->op != NFT_CMP_EQ) + if (priv->op != NFT_CMP_EQ || reg->len != priv->len) return -EOPNOTSUPP; memcpy(key + reg->offset, &priv->data, priv->len); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 22a80eb60222..5cb2d8908d2a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -161,13 +161,21 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ethhdr, h_source): + if (priv->len != ETH_ALEN) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, src, ETH_ALEN, reg); break; case offsetof(struct ethhdr, h_dest): + if (priv->len != ETH_ALEN) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs, dst, ETH_ALEN, reg); break; + default: + return -EOPNOTSUPP; } return 0; @@ -181,14 +189,23 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct iphdr, saddr): + if (priv->len != sizeof(struct in_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src, sizeof(struct in_addr), reg); break; case offsetof(struct iphdr, daddr): + if (priv->len != sizeof(struct in_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst, sizeof(struct in_addr), reg); break; case offsetof(struct iphdr, protocol): + if (priv->len != sizeof(__u8)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, sizeof(__u8), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT); @@ -208,14 +225,23 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct ipv6hdr, saddr): + if (priv->len != sizeof(struct in6_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src, sizeof(struct in6_addr), reg); break; case offsetof(struct ipv6hdr, daddr): + if (priv->len != sizeof(struct in6_addr)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst, sizeof(struct in6_addr), reg); break; case offsetof(struct ipv6hdr, nexthdr): + if (priv->len != sizeof(__u8)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto, sizeof(__u8), reg); nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT); @@ -255,10 +281,16 @@ static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct tcphdr, source): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct tcphdr, dest): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, sizeof(__be16), reg); break; @@ -277,10 +309,16 @@ static int nft_payload_offload_udp(struct nft_offload_ctx *ctx, switch (priv->offset) { case offsetof(struct udphdr, source): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src, sizeof(__be16), reg); break; case offsetof(struct udphdr, dest): + if (priv->len != sizeof(__be16)) + return -EOPNOTSUPP; + NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst, sizeof(__be16), reg); break; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index c4f54ad2b98a..58d5373c513c 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -64,28 +64,6 @@ static DEFINE_SPINLOCK(nr_list_lock); static const struct proto_ops nr_proto_ops; /* - * NETROM network devices are virtual network devices encapsulating NETROM - * frames into AX.25 which will be sent through an AX.25 device, so form a - * special "super class" of normal net devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key nr_netdev_xmit_lock_key; -static struct lock_class_key nr_netdev_addr_lock_key; - -static void nr_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &nr_netdev_xmit_lock_key); -} - -static void nr_set_lockdep_key(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL); -} - -/* * Socket removal during an interrupt is now safe. */ static void nr_remove_socket(struct sock *sk) @@ -1414,7 +1392,6 @@ static int __init nr_proto_init(void) free_netdev(dev); goto fail; } - nr_set_lockdep_key(dev); dev_nr[i] = dev; } diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index ccdd790e163a..28604414dec1 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -554,11 +554,11 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock, if (sk->sk_state == LLCP_LISTEN) return llcp_accept_poll(sk); - 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); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == LLCP_CLOSED) diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 17e6ca62f1be..afde0d763039 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1099,7 +1099,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } @@ -1159,7 +1158,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 3572e11b6f21..1c77f520f474 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -165,7 +165,8 @@ static int push_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype); + err = skb_mpls_push(skb, mpls->mpls_lse, mpls->mpls_ethertype, + skb->mac_len); if (err) return err; @@ -178,7 +179,7 @@ static int pop_mpls(struct sk_buff *skb, struct sw_flow_key *key, { int err; - err = skb_mpls_pop(skb, ethertype); + err = skb_mpls_pop(skb, ethertype, skb->mac_len); if (err) return err; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index f30e406fbec5..d8c364d637b1 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1881,7 +1881,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, struct net *net, u32 portid, u32 seq, - u32 flags, u8 cmd) + u32 flags, u8 cmd, gfp_t gfp) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; @@ -1902,7 +1902,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, goto nla_put_failure; if (!net_eq(net, dev_net(vport->dev))) { - int id = peernet2id_alloc(net, dev_net(vport->dev)); + int id = peernet2id_alloc(net, dev_net(vport->dev), gfp); if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) goto nla_put_failure; @@ -1943,11 +1943,12 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, struct sk_buff *skb; int retval; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd, + GFP_KERNEL); BUG_ON(retval < 0); return skb; @@ -2089,7 +2090,7 @@ restart: err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_NEW); + OVS_VPORT_CMD_NEW, GFP_KERNEL); new_headroom = netdev_get_fwd_headroom(vport->dev); @@ -2150,7 +2151,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_SET); + OVS_VPORT_CMD_SET, GFP_KERNEL); BUG_ON(err < 0); ovs_unlock(); @@ -2190,7 +2191,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_DEL); + OVS_VPORT_CMD_DEL, GFP_KERNEL); BUG_ON(err < 0); /* the vport deletion may trigger dp headroom update */ @@ -2237,7 +2238,7 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_GET); + OVS_VPORT_CMD_GET, GFP_ATOMIC); BUG_ON(err < 0); rcu_read_unlock(); @@ -2273,7 +2274,8 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - OVS_VPORT_CMD_GET) < 0) + OVS_VPORT_CMD_GET, + GFP_ATOMIC) < 0) goto out; j++; diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 21c90d3a7ebf..58a7b8312c28 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -137,7 +137,7 @@ static void do_setup(struct net_device *netdev) netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH | IFF_NO_QUEUE; netdev->needs_free_netdev = true; - netdev->priv_destructor = internal_dev_destructor; + netdev->priv_destructor = NULL; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; @@ -159,7 +159,6 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) struct internal_dev *internal_dev; struct net_device *dev; int err; - bool free_vport = true; vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms); if (IS_ERR(vport)) { @@ -190,10 +189,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) rtnl_lock(); err = register_netdevice(vport->dev); - if (err) { - free_vport = false; + if (err) goto error_unlock; - } + vport->dev->priv_destructor = internal_dev_destructor; dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); @@ -207,8 +205,7 @@ error_unlock: error_free_netdev: free_netdev(dev); error_free_vport: - if (free_vport) - ovs_vport_free(vport); + ovs_vport_free(vport); error: return ERR_PTR(err); } diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 96ea9f254ae9..76d499f6af9a 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -338,9 +338,9 @@ static __poll_t pn_socket_poll(struct file *file, struct socket *sock, if (sk->sk_state == TCP_CLOSE) return EPOLLERR; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; - if (!skb_queue_empty(&pn->ctrlreq_queue)) + if (!skb_queue_empty_lockless(&pn->ctrlreq_queue)) mask |= EPOLLPRI; if (!mask && sk->sk_state == TCP_CLOSE_WAIT) return EPOLLHUP; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index 233f1368162b..18c6fac6ead9 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -450,6 +450,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn) struct ib_qp_init_attr attr; struct ib_cq_init_attr cq_attr = {}; struct rds_ib_device *rds_ibdev; + unsigned long max_wrs; int ret, fr_queue_space; /* @@ -469,10 +470,15 @@ static int rds_ib_setup_qp(struct rds_connection *conn) /* add the conn now so that connection establishment has the dev */ rds_ib_add_conn(rds_ibdev, conn); - if (rds_ibdev->max_wrs < ic->i_send_ring.w_nr + 1) - rds_ib_ring_resize(&ic->i_send_ring, rds_ibdev->max_wrs - 1); - if (rds_ibdev->max_wrs < ic->i_recv_ring.w_nr + 1) - rds_ib_ring_resize(&ic->i_recv_ring, rds_ibdev->max_wrs - 1); + max_wrs = rds_ibdev->max_wrs < rds_ib_sysctl_max_send_wr + 1 ? + rds_ibdev->max_wrs - 1 : rds_ib_sysctl_max_send_wr; + if (ic->i_send_ring.w_nr != max_wrs) + rds_ib_ring_resize(&ic->i_send_ring, max_wrs); + + max_wrs = rds_ibdev->max_wrs < rds_ib_sysctl_max_recv_wr + 1 ? + rds_ibdev->max_wrs - 1 : rds_ib_sysctl_max_recv_wr; + if (ic->i_recv_ring.w_nr != max_wrs) + rds_ib_ring_resize(&ic->i_recv_ring, max_wrs); /* Protection domain and memory range */ ic->i_pd = rds_ibdev->pd; @@ -1099,8 +1105,9 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp) ic->i_flowctl = 0; atomic_set(&ic->i_credits, 0); - rds_ib_ring_init(&ic->i_send_ring, rds_ib_sysctl_max_send_wr); - rds_ib_ring_init(&ic->i_recv_ring, rds_ib_sysctl_max_recv_wr); + /* Re-init rings, but retain sizes. */ + rds_ib_ring_init(&ic->i_send_ring, ic->i_send_ring.w_nr); + rds_ib_ring_init(&ic->i_recv_ring, ic->i_recv_ring.w_nr); if (ic->i_ibinc) { rds_inc_put(&ic->i_ibinc->ii_inc); @@ -1147,8 +1154,8 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp) * rds_ib_conn_shutdown() waits for these to be emptied so they * must be initialized before it can be called. */ - rds_ib_ring_init(&ic->i_send_ring, rds_ib_sysctl_max_send_wr); - rds_ib_ring_init(&ic->i_recv_ring, rds_ib_sysctl_max_recv_wr); + rds_ib_ring_init(&ic->i_send_ring, 0); + rds_ib_ring_init(&ic->i_recv_ring, 0); ic->conn = conn; conn->c_transport_data = ic; diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index f0e9ccf472a9..6a0df7c8a939 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -65,28 +65,6 @@ static const struct proto_ops rose_proto_ops; ax25_address rose_callsign; /* - * ROSE network devices are virtual network devices encapsulating ROSE - * frames into AX.25 which will be sent through an AX.25 device, so form a - * special "super class" of normal net devices; split their locks off into a - * separate class since they always nest. - */ -static struct lock_class_key rose_netdev_xmit_lock_key; -static struct lock_class_key rose_netdev_addr_lock_key; - -static void rose_set_lockdep_one(struct net_device *dev, - struct netdev_queue *txq, - void *_unused) -{ - lockdep_set_class(&txq->_xmit_lock, &rose_netdev_xmit_lock_key); -} - -static void rose_set_lockdep_key(struct net_device *dev) -{ - lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key); - netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL); -} - -/* * Convert a ROSE address into text. */ char *rose2asc(char *buf, const rose_address *addr) @@ -1533,7 +1511,6 @@ static int __init rose_proto_init(void) free_netdev(dev); goto fail; } - rose_set_lockdep_key(dev); dev_rose[i] = dev; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1091bf35a199..7c7d10f2e0c1 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -556,6 +556,7 @@ struct rxrpc_call { struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ + const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ unsigned long ack_at; /* When deferred ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ @@ -600,6 +601,7 @@ struct rxrpc_call { int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ + bool rx_pkt_last; /* Current recvmsg packet is last */ /* Rx/Tx circular buffer, depending on phase. * diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 00c095d74145..135bf5cd8dd5 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -84,7 +84,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, smp_store_release(&b->conn_backlog_head, (head + 1) & (size - 1)); - trace_rxrpc_conn(conn, rxrpc_conn_new_service, + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, atomic_read(&conn->usage), here); } @@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; - trace_rxrpc_call(call, rxrpc_call_new_service, + trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, atomic_read(&call->usage), here, (const void *)user_call_ID); @@ -307,6 +307,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_see_call(call); call->conn = conn; + call->security = conn->security; call->peer = rxrpc_get_peer(conn->params.peer); call->cong_cwnd = call->peer->cong_cwnd; return call; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 32d8dc677142..a31c18c09894 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -240,7 +240,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (p->intr) __set_bit(RXRPC_CALL_IS_INTR, &call->flags); call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, + atomic_read(&call->usage), here, (const void *)p->user_call_ID); /* We need to protect a partially set up call against the user as we @@ -290,8 +291,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (ret < 0) goto error; - trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), - here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_connected, + atomic_read(&call->usage), here, NULL); rxrpc_start_call_timer(call); @@ -313,8 +314,8 @@ error_dup_user_ID: error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, ret); - trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), - here, ERR_PTR(ret)); + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); @@ -376,7 +377,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call) if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -391,7 +393,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call) int n = atomic_read(&call->usage); ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -406,7 +409,8 @@ void rxrpc_see_call(struct rxrpc_call *call) if (call) { int n = atomic_read(&call->usage); - trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, + here, NULL); } } @@ -418,7 +422,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(call->debug_id, op, n, here, NULL); } /* @@ -445,7 +449,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_release, + atomic_read(&call->usage), here, (const void *)call->flags); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -488,10 +493,10 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn) { + if (conn) rxrpc_disconnect_call(call); - conn->security->free_call_crypto(call); - } + if (call->security) + call->security->free_call_crypto(call); rxrpc_cleanup_ring(call); _leave(""); @@ -534,12 +539,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { struct rxrpc_net *rxnet = call->rxnet; const void *here = __builtin_return_address(0); + unsigned int debug_id = call->debug_id; int n; ASSERT(call != NULL); n = atomic_dec_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(debug_id, op, n, here, NULL); ASSERTCMP(n, >=, 0); if (n == 0) { _debug("call %d dead", call->debug_id); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3f1da1b49f69..376370cd9285 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -212,7 +212,8 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp) rxrpc_get_local(conn->params.local); key_get(conn->params.key); - trace_rxrpc_conn(conn, rxrpc_conn_new_client, atomic_read(&conn->usage), + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, + atomic_read(&conn->usage), __builtin_return_address(0)); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); _leave(" = %p", conn); @@ -352,6 +353,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, if (cp->exclusive) { call->conn = candidate; + call->security = candidate->security; call->security_ix = candidate->security_ix; call->service_id = candidate->service_id; _leave(" = 0 [exclusive %d]", candidate->debug_id); @@ -403,6 +405,7 @@ static int rxrpc_get_client_conn(struct rxrpc_sock *rx, candidate_published: set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags); call->conn = candidate; + call->security = candidate->security; call->security_ix = candidate->security_ix; call->service_id = candidate->service_id; spin_unlock(&local->client_conns_lock); @@ -425,6 +428,7 @@ found_extant_conn: spin_lock(&conn->channel_lock); call->conn = conn; + call->security = conn->security; call->security_ix = conn->security_ix; call->service_id = conn->service_id; list_add_tail(&call->chan_wait_link, &conn->waiting_calls); @@ -985,11 +989,12 @@ rxrpc_put_one_client_conn(struct rxrpc_connection *conn) void rxrpc_put_client_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); + unsigned int debug_id = conn->debug_id; int n; do { n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_put_client, n, here); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here); if (n > 0) return; ASSERTCMP(n, >=, 0); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index ed05b6922132..38d718e90dc6 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -269,7 +269,7 @@ bool rxrpc_queue_conn(struct rxrpc_connection *conn) if (n == 0) return false; if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn, rxrpc_conn_queued, n + 1, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, n + 1, here); else rxrpc_put_connection(conn); return true; @@ -284,7 +284,7 @@ void rxrpc_see_connection(struct rxrpc_connection *conn) if (conn) { int n = atomic_read(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_seen, n, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here); } } @@ -296,7 +296,7 @@ void rxrpc_get_connection(struct rxrpc_connection *conn) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_got, n, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here); } /* @@ -310,7 +310,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn) if (conn) { int n = atomic_fetch_add_unless(&conn->usage, 1, 0); if (n > 0) - trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n + 1, here); else conn = NULL; } @@ -333,10 +333,11 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, void rxrpc_put_service_conn(struct rxrpc_connection *conn) { const void *here = __builtin_return_address(0); + unsigned int debug_id = conn->debug_id; int n; n = atomic_dec_return(&conn->usage); - trace_rxrpc_conn(conn, rxrpc_conn_put_service, n, here); + trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, n, here); ASSERTCMP(n, >=, 0); if (n == 1) rxrpc_set_service_reap_timer(conn->params.local->rxnet, @@ -420,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) */ if (atomic_cmpxchg(&conn->usage, 1, 0) != 1) continue; - trace_rxrpc_conn(conn, rxrpc_conn_reap_service, 0, NULL); + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL); if (rxrpc_conn_is_client(conn)) BUG(); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index b30e13f6d95f..123d6ceab15c 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -134,7 +134,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - trace_rxrpc_conn(conn, rxrpc_conn_new_service, + trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, atomic_read(&conn->usage), __builtin_return_address(0)); } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index c97ebdc043e4..48f67a9b1037 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -147,10 +147,16 @@ void rxrpc_error_report(struct sock *sk) { struct sock_exterr_skb *serr; struct sockaddr_rxrpc srx; - struct rxrpc_local *local = sk->sk_user_data; + struct rxrpc_local *local; struct rxrpc_peer *peer; struct sk_buff *skb; + rcu_read_lock(); + local = rcu_dereference_sk_user_data(sk); + if (unlikely(!local)) { + rcu_read_unlock(); + return; + } _enter("%p{%d}", sk, local->debug_id); /* Clear the outstanding error value on the socket so that it doesn't @@ -160,6 +166,7 @@ void rxrpc_error_report(struct sock *sk) skb = sock_dequeue_err_skb(sk); if (!skb) { + rcu_read_unlock(); _leave("UDP socket errqueue empty"); return; } @@ -167,11 +174,11 @@ void rxrpc_error_report(struct sock *sk) serr = SKB_EXT_ERR(skb); if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); + rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_freed); return; } - rcu_read_lock(); peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9c3ac96f71cb..64830d8c1fdb 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { atomic_set(&peer->usage, 1); - peer->local = local; + peer->local = rxrpc_get_local(local); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); @@ -307,7 +307,6 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); - peer->local = local; rxrpc_init_peer(rx, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); @@ -382,7 +381,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) int n; n = atomic_inc_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_got, n, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here); return peer; } @@ -396,7 +395,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) if (peer) { int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) - trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here); else peer = NULL; } @@ -417,6 +416,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } @@ -426,11 +426,13 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id; int n; if (peer) { + debug_id = peer->debug_id; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) __rxrpc_put_peer(peer); } @@ -443,13 +445,15 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer_locked(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id = peer->debug_id; int n; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 3b0becb12041..8578c39ec839 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -251,8 +251,8 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, seq += subpacket; } - return call->conn->security->verify_packet(call, skb, offset, len, - seq, cksum); + return call->security->verify_packet(call, skb, offset, len, + seq, cksum); } /* @@ -267,11 +267,13 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, */ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, u8 *_annotation, - unsigned int *_offset, unsigned int *_len) + unsigned int *_offset, unsigned int *_len, + bool *_last) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len; + bool last = false; int ret; u8 annotation = *_annotation; u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; @@ -281,6 +283,8 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, len = skb->len - offset; if (subpacket < sp->nr_subpackets - 1) len = RXRPC_JUMBO_DATALEN; + else if (sp->rx_flags & RXRPC_SKB_INCL_LAST) + last = true; if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { ret = rxrpc_verify_packet(call, skb, annotation, offset, len); @@ -291,7 +295,8 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, *_offset = offset; *_len = len; - call->conn->security->locate_data(call, skb, _offset, _len); + *_last = last; + call->security->locate_data(call, skb, _offset, _len); return 0; } @@ -309,7 +314,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; size_t remain; - bool last; + bool rx_pkt_last; unsigned int rx_pkt_offset, rx_pkt_len; int ix, copy, ret = -EAGAIN, ret2; @@ -319,6 +324,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; + rx_pkt_last = call->rx_pkt_last; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { seq = call->rx_hard_ack; @@ -329,6 +335,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, /* Barriers against rxrpc_input_data(). */ hard_ack = call->rx_hard_ack; seq = hard_ack + 1; + while (top = smp_load_acquire(&call->rx_top), before_eq(seq, top) ) { @@ -356,7 +363,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (rx_pkt_offset == 0) { ret2 = rxrpc_locate_data(call, skb, &call->rxtx_annotations[ix], - &rx_pkt_offset, &rx_pkt_len); + &rx_pkt_offset, &rx_pkt_len, + &rx_pkt_last); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq, rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { @@ -396,13 +404,12 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } /* The whole packet has been transferred. */ - last = sp->hdr.flags & RXRPC_LAST_PACKET; if (!(flags & MSG_PEEK)) rxrpc_rotate_rx_window(call); rx_pkt_offset = 0; rx_pkt_len = 0; - if (last) { + if (rx_pkt_last) { ASSERTCMP(seq, ==, READ_ONCE(call->rx_top)); ret = 1; goto out; @@ -415,6 +422,7 @@ out: if (!(flags & MSG_PEEK)) { call->rx_pkt_offset = rx_pkt_offset; call->rx_pkt_len = rx_pkt_len; + call->rx_pkt_last = rx_pkt_last; } done: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6a1547b270fe..813fd6888142 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -419,7 +419,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, call->tx_winsize) sp->hdr.flags |= RXRPC_MORE_PACKETS; - ret = conn->security->secure_packet( + ret = call->security->secure_packet( call, skb, skb->mark, skb->head); if (ret < 0) goto out; @@ -661,6 +661,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: case RXRPC_CALL_SERVER_ACCEPTING: + rxrpc_put_call(call, rxrpc_call_put); ret = -EBUSY; goto error_release_sock; default: diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2558f00f6b3e..69d4676a402f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -832,8 +832,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb) } static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { - [TCA_ACT_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_ACT_KIND] = { .type = NLA_STRING }, [TCA_ACT_INDEX] = { .type = NLA_U32 }, [TCA_ACT_COOKIE] = { .type = NLA_BINARY, .len = TC_COOKIE_MAX_SIZE }, @@ -865,8 +864,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, NL_SET_ERR_MSG(extack, "TC action kind must be specified"); goto err_out; } - nla_strlcpy(act_name, kind, IFNAMSIZ); - + if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) { + NL_SET_ERR_MSG(extack, "TC action name too long"); + goto err_out; + } if (tb[TCA_ACT_COOKIE]) { cookie = nla_memdup_cookie(tb); if (!cookie) { @@ -1352,11 +1353,16 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { size_t attr_size = 0; - int ret = 0; + int loop, ret; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; - ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions, - &attr_size, true, extack); + for (loop = 0; loop < 10; loop++) { + ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, + actions, &attr_size, true, extack); + if (ret != -EAGAIN) + break; + } + if (ret < 0) return ret; ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); @@ -1406,11 +1412,8 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, */ if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; -replay: ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr, extack); - if (ret == -EAGAIN) - goto replay; break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 9ce073a05414..08923b21e566 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -484,7 +484,11 @@ static int __init mirred_init_module(void) return err; pr_info("Mirror/redirect action on\n"); - return tcf_register_action(&act_mirred_ops, &mirred_net_ops); + err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); + if (err) + unregister_netdevice_notifier(&mirred_device_notifier); + + return err; } static void __exit mirred_cleanup_module(void) diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index e168df0e008a..4cf6c553bb0b 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -55,7 +55,7 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_mpls *m = to_mpls(a); struct tcf_mpls_params *p; __be32 new_lse; - int ret; + int ret, mac_len; tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); @@ -63,8 +63,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, /* Ensure 'data' points at mac_header prior calling mpls manipulating * functions. */ - if (skb_at_tc_ingress(skb)) + if (skb_at_tc_ingress(skb)) { skb_push_rcsum(skb, skb->mac_len); + mac_len = skb->mac_len; + } else { + mac_len = skb_network_header(skb) - skb_mac_header(skb); + } ret = READ_ONCE(m->tcf_action); @@ -72,12 +76,12 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a, switch (p->tcfm_action) { case TCA_MPLS_ACT_POP: - if (skb_mpls_pop(skb, p->tcfm_proto)) + if (skb_mpls_pop(skb, p->tcfm_proto, mac_len)) goto drop; break; case TCA_MPLS_ACT_PUSH: new_lse = tcf_mpls_get_lse(NULL, p, !eth_p_mpls(skb->protocol)); - if (skb_mpls_push(skb, new_lse, p->tcfm_proto)) + if (skb_mpls_push(skb, new_lse, p->tcfm_proto, mac_len)) goto drop; break; case TCA_MPLS_ACT_MODIFY: diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 64584a1df425..20d60b8fcb70 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -47,6 +48,62 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +static u32 destroy_obj_hashfn(const struct tcf_proto *tp) +{ + return jhash_3words(tp->chain->index, tp->prio, + (__force __u32)tp->protocol, 0); +} + +static void tcf_proto_signal_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node, + destroy_obj_hashfn(tp)); + mutex_unlock(&block->proto_destroy_lock); +} + +static bool tcf_proto_cmp(const struct tcf_proto *tp1, + const struct tcf_proto *tp2) +{ + return tp1->chain->index == tp2->chain->index && + tp1->prio == tp2->prio && + tp1->protocol == tp2->protocol; +} + +static bool tcf_proto_exists_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + u32 hash = destroy_obj_hashfn(tp); + struct tcf_proto *iter; + bool found = false; + + rcu_read_lock(); + hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter, + destroy_ht_node, hash) { + if (tcf_proto_cmp(tp, iter)) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; +} + +static void +tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + if (hash_hashed(&tp->destroy_ht_node)) + hash_del_rcu(&tp->destroy_ht_node); + mutex_unlock(&block->proto_destroy_lock); +} + /* Find classifier type by string name */ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) @@ -162,11 +219,22 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_check_kind(struct nlattr *kind, char *name) +{ + if (kind) + return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ; + memset(name, 0, IFNAMSIZ); + return false; +} + static bool tcf_proto_is_unlocked(const char *kind) { const struct tcf_proto_ops *ops; bool ret; + if (strlen(kind) == 0) + return false; + ops = tcf_proto_lookup_ops(kind, false, NULL); /* On error return false to take rtnl lock. Proto lookup/create * functions will perform lookup again and properly handle errors. @@ -223,9 +291,11 @@ static void tcf_proto_get(struct tcf_proto *tp) static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) + bool sig_destroy, struct netlink_ext_ack *extack) { tp->ops->destroy(tp, rtnl_held, extack); + if (sig_destroy) + tcf_proto_signal_destroyed(tp->chain, tp); tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); @@ -235,7 +305,7 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { if (refcount_dec_and_test(&tp->refcnt)) - tcf_proto_destroy(tp, rtnl_held, extack); + tcf_proto_destroy(tp, rtnl_held, true, extack); } static int walker_check_empty(struct tcf_proto *tp, void *fh, @@ -359,6 +429,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain) static void tcf_block_destroy(struct tcf_block *block) { mutex_destroy(&block->lock); + mutex_destroy(&block->proto_destroy_lock); kfree_rcu(block, rcu); } @@ -534,6 +605,12 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_dereference(chain->filter_chain, chain); + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_signal_destroying(chain, tp); + tp = tp_next; + } + tp = tcf_chain_dereference(chain->filter_chain, chain); RCU_INIT_POINTER(chain->filter_chain, NULL); tcf_chain0_head_change(chain, NULL); chain->flushing = true; @@ -833,6 +910,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + mutex_init(&block->proto_destroy_lock); init_rwsem(&block->cb_lock); flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); @@ -1610,6 +1688,12 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_lock(&chain->filter_chain_lock); + if (tcf_proto_exists_destroying(chain, tp_new)) { + mutex_unlock(&chain->filter_chain_lock); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + return ERR_PTR(-EAGAIN); + } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); if (!tp) @@ -1617,10 +1701,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_unlock(&chain->filter_chain_lock); if (tp) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = tp; } else if (err) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = ERR_PTR(err); } @@ -1658,6 +1742,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, return; } + tcf_proto_signal_destroying(chain, tp); next = tcf_chain_dereference(chain_info.next, chain); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); @@ -1843,6 +1928,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -1899,13 +1985,19 @@ replay: if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, * block is shared (no qdisc found), qdisc is not unlocked, classifier * type is not specified, classifier is not unlocked. */ if (rtnl_held || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2063,6 +2155,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2102,13 +2195,18 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc * found), qdisc is not unlocked, classifier type is not specified, * classifier is not unlocked. */ if (!prio || (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } @@ -2164,6 +2262,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -EINVAL; goto errout_locked; } else if (t->tcm_handle == 0) { + tcf_proto_signal_destroying(chain, tp); tcf_chain_tp_remove(chain, &chain_info, tp); mutex_unlock(&chain->filter_chain_lock); @@ -2216,6 +2315,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; + char name[IFNAMSIZ]; struct tcmsg *t; u32 protocol; u32 prio; @@ -2252,12 +2352,17 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (err) return err; + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC filter name too long"); + err = -EINVAL; + goto errout; + } /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not * unlocked, classifier type is not specified, classifier is not * unlocked. */ if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || - !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + !tcf_proto_is_unlocked(name)) { rtnl_held = true; rtnl_lock(); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index bf10bdaf5012..8229ed4a67be 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -162,16 +162,20 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, cls_bpf.name = obj->bpf_name; cls_bpf.exts_integrated = obj->exts_integrated; - if (oldprog) + if (oldprog && prog) err = tc_setup_cb_replace(block, tp, TC_SETUP_CLSBPF, &cls_bpf, skip_sw, &oldprog->gen_flags, &oldprog->in_hw_count, &prog->gen_flags, &prog->in_hw_count, true); - else + else if (prog) err = tc_setup_cb_add(block, tp, TC_SETUP_CLSBPF, &cls_bpf, skip_sw, &prog->gen_flags, &prog->in_hw_count, true); + else + err = tc_setup_cb_destroy(block, tp, TC_SETUP_CLSBPF, &cls_bpf, + skip_sw, &oldprog->gen_flags, + &oldprog->in_hw_count, true); if (prog && err) { cls_bpf_offload_cmd(tp, oldprog, prog, extack); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 82bd14e7ac93..3177dcb17316 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued) *err = -1; return; } - dst->value = sk->sk_wmem_queued; + dst->value = READ_ONCE(sk->sk_wmem_queued); } META_COLLECTOR(int_sk_fwd_alloc) @@ -554,7 +554,7 @@ META_COLLECTOR(int_sk_rcvlowat) *err = -1; return; } - dst->value = sk->sk_rcvlowat; + dst->value = READ_ONCE(sk->sk_rcvlowat); } META_COLLECTOR(int_sk_rcvtimeo) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 81d58b280612..1047825d9f48 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1390,8 +1390,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { - [TCA_KIND] = { .type = NLA_NUL_STRING, - .len = IFNAMSIZ - 1 }, + [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index cebfb65d8556..b1da5589a0c6 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -177,7 +177,7 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, parent = *p; skb = rb_to_skb(parent); - if (ktime_after(txtime, skb->tstamp)) { + if (ktime_compare(txtime, skb->tstamp) >= 0) { p = &parent->rb_right; leftmost = false; } else { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 17bd8f539bc7..8769b4b8807d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -799,9 +799,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { }; EXPORT_SYMBOL(pfifo_fast_ops); -static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; - struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) @@ -854,17 +851,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, } spin_lock_init(&sch->busylock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); sch->ops = ops; sch->flags = ops->static_flags; @@ -875,6 +864,12 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, dev_hold(dev); refcount_set(&sch->refcnt, 1); + if (sch != &noop_qdisc) { + lockdep_set_class(&sch->busylock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->seqlock, &dev->qdisc_tx_busylock_key); + lockdep_set_class(&sch->running, &dev->qdisc_running_key); + } + return sch; errout1: kfree(p); @@ -1043,6 +1038,8 @@ static void attach_one_default_qdisc(struct net_device *dev, if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; + else if(dev->type == ARPHRD_CAN) + ops = &pfifo_fast_ops; qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); if (!qdisc) { diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 23cd1c873a2c..be35f03b657b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -5,11 +5,11 @@ * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com> */ -#include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> +#include <linux/siphash.h> #include <net/pkt_sched.h> #include <net/sock.h> @@ -126,7 +126,7 @@ struct wdrr_bucket { struct hhf_sched_data { struct wdrr_bucket buckets[WDRR_BUCKET_CNT]; - u32 perturbation; /* hash perturbation */ + siphash_key_t perturbation; /* hash perturbation */ u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ u32 drop_overlimit; /* number of times max qdisc packet * limit was hit @@ -264,7 +264,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) } /* Get hashed flow-id of the skb. */ - hash = skb_get_hash_perturb(skb, q->perturbation); + hash = skb_get_hash_perturb(skb, &q->perturbation); /* Check if this packet belongs to an already established HH flow. */ flow_pos = hash & HHF_BIT_MASK; @@ -582,7 +582,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, sch->limit = 1000; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 0e44039e729c..42e557d48e4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -509,6 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) { qdisc_drop(skb, sch, to_free); + skb = NULL; goto finish_segs; } @@ -593,9 +594,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, finish_segs: if (segs) { unsigned int len, last_len; - int nb = 0; + int nb; - len = skb->len; + len = skb ? skb->len : 0; + nb = skb ? 1 : 0; while (segs) { skb2 = segs->next; @@ -612,7 +614,10 @@ finish_segs: } segs = skb2; } - qdisc_tree_reduce_backlog(sch, -nb, prev_len - len); + /* Parent qdiscs accounted for 1 skb of size @prev_len */ + qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); + } else if (!skb) { + return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index d448fe3068e5..4074c50ac3d7 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -18,7 +18,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/random.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <net/ip.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -45,7 +45,7 @@ struct sfb_bucket { * (Section 4.4 of SFB reference : moving hash functions) */ struct sfb_bins { - u32 perturbation; /* jhash perturbation */ + siphash_key_t perturbation; /* siphash key */ struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; }; @@ -217,7 +217,8 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = prandom_u32(); + get_random_bytes(&q->bins[slot].perturbation, + sizeof(q->bins[slot].perturbation)); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -314,9 +315,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If using external classifiers, get result and record it. */ if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; - sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation); } else { - sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation); + sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation); } @@ -352,7 +353,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Inelastic flow */ if (q->double_buffering) { sfbhash = skb_get_hash_perturb(skb, - q->bins[slot].perturbation); + &q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 68404a9d2ce4..c787d4d46017 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/netlink.h> @@ -117,7 +117,7 @@ struct sfq_sched_data { u8 headdrop; u8 maxdepth; /* limit of packets per flow */ - u32 perturbation; + siphash_key_t perturbation; u8 cur_depth; /* depth of longest slot */ u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ @@ -157,7 +157,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index static unsigned int sfq_hash(const struct sfq_sched_data *q, const struct sk_buff *skb) { - return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1); + return skb_get_hash_perturb(skb, &q->perturbation) & (q->divisor - 1); } static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, @@ -607,9 +607,11 @@ static void sfq_perturbation(struct timer_list *t) struct sfq_sched_data *q = from_timer(q, t, perturb_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + siphash_key_t nkey; + get_random_bytes(&nkey, sizeof(nkey)); spin_lock(root_lock); - q->perturbation = prandom_u32(); + q->perturbation = nkey; if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); @@ -688,7 +690,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) del_timer(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); } sch_tree_unlock(sch); kfree(p); @@ -745,7 +747,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt, q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); if (opt) { int err = sfq_change(sch, opt); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 68b543f85a96..7cd68628c637 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1152,7 +1152,7 @@ EXPORT_SYMBOL_GPL(taprio_offload_free); * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump(). * This is left as TODO. */ -void taprio_offload_config_changed(struct taprio_sched *q) +static void taprio_offload_config_changed(struct taprio_sched *q) { struct sched_gate_list *oper, *admin; @@ -1224,8 +1224,6 @@ static int taprio_enable_offload(struct net_device *dev, goto done; } - taprio_offload_config_changed(q); - done: taprio_offload_free(offload); @@ -1341,6 +1339,10 @@ static int taprio_parse_clockid(struct Qdisc *sch, struct nlattr **tb, NL_SET_ERR_MSG(extack, "Specifying a 'clockid' is mandatory"); goto out; } + + /* Everything went ok, return success. */ + err = 0; + out: return err; } @@ -1501,6 +1503,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, call_rcu(&admin->rcu, taprio_free_sched_cb); spin_unlock_irqrestore(&q->current_entry_lock, flags); + + if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) + taprio_offload_config_changed(q); } new_admin = NULL; diff --git a/net/sctp/diag.c b/net/sctp/diag.c index fc9a4c6629ce..0851166b9175 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -175,7 +175,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = 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); if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0) diff --git a/net/sctp/input.c b/net/sctp/input.c index 5a070fb5b278..2277981559d0 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -243,7 +243,7 @@ int sctp_rcv(struct sk_buff *skb) bh_lock_sock(sk); } - if (sock_owned_by_user(sk)) { + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sctp_add_backlog(sk, skb)) { bh_unlock_sock(sk); sctp_chunk_free(chunk); @@ -321,8 +321,8 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) local_bh_disable(); bh_lock_sock(sk); - if (sock_owned_by_user(sk)) { - if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { + if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) sctp_chunk_free(chunk); else backloged = 1; @@ -336,7 +336,13 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) if (backloged) return 0; } else { - sctp_inq_push(inqueue, chunk); + if (!sctp_newsk_ready(sk)) { + if (!sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) + return 0; + sctp_chunk_free(chunk); + } else { + sctp_inq_push(inqueue, chunk); + } } done: @@ -358,7 +364,7 @@ static int sctp_add_backlog(struct sock *sk, struct sk_buff *skb) struct sctp_ep_common *rcvr = chunk->rcvr; int ret; - ret = sk_add_backlog(sk, skb, sk->sk_rcvbuf); + ret = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); if (!ret) { /* Hold the assoc/ep while hanging on the backlog queue. * This way, we know structures we need will not disappear diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e41ed2e0ae7d..48d63956a68c 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2155,7 +2155,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_SET_PRIMARY: if (ep->asconf_enable) break; - goto fallthrough; + goto unhandled; case SCTP_PARAM_HOST_NAME_ADDRESS: /* Tell the peer, we won't support this param. */ @@ -2166,11 +2166,11 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_FWD_TSN_SUPPORT: if (ep->prsctp_enable) break; - goto fallthrough; + goto unhandled; case SCTP_PARAM_RANDOM: if (!ep->auth_enable) - goto fallthrough; + goto unhandled; /* SCTP-AUTH: Secion 6.1 * If the random number is not 32 byte long the association @@ -2187,7 +2187,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_CHUNKS: if (!ep->auth_enable) - goto fallthrough; + goto unhandled; /* SCTP-AUTH: Section 3.2 * The CHUNKS parameter MUST be included once in the INIT or @@ -2203,7 +2203,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, case SCTP_PARAM_HMAC_ALGO: if (!ep->auth_enable) - goto fallthrough; + goto unhandled; hmacs = (struct sctp_hmac_algo_param *)param.p; n_elt = (ntohs(param.p->length) - @@ -2226,7 +2226,7 @@ static enum sctp_ierror sctp_verify_param(struct net *net, retval = SCTP_IERROR_ABORT; } break; -fallthrough: +unhandled: default: pr_debug("%s: unrecognized param:%d for chunk:%d\n", __func__, ntohs(param.p->type), cid); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 939b8d2595bc..ffd3262b7a41 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8476,7 +8476,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) mask = 0; /* Is there any 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); if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -8485,7 +8485,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= EPOLLHUP; /* Is it readable? Reconsider this code with TCP-style support. */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* The association is either gone or not ready. */ @@ -8871,7 +8871,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, if (sk_can_busy_loop(sk)) { sk_busy_loop(sk, noblock); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) continue; } @@ -9306,7 +9306,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = asoc->next_tsn ^ jiffies; + newinet->inet_id = prandom_u32(); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; @@ -9500,7 +9500,7 @@ struct proto sctp_prot = { .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, - .get_port = sctp_get_port, + .no_autobind = true, .obj_size = sizeof(struct sctp_sock), .useroffset = offsetof(struct sctp_sock, subscribe), .usersize = offsetof(struct sctp_sock, initmsg) - @@ -9542,7 +9542,7 @@ struct proto sctpv6_prot = { .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, - .get_port = sctp_get_port, + .no_autobind = true, .obj_size = sizeof(struct sctp6_sock), .useroffset = offsetof(struct sctp6_sock, sctp.subscribe), .usersize = offsetof(struct sctp6_sock, sctp.initmsg) - diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5b932583e407..737b49909a7a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -123,6 +123,12 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_restore_fallback_changes(struct smc_sock *smc) +{ + smc->clcsock->file->private_data = smc->sk.sk_socket; + smc->clcsock->file = NULL; +} + static int __smc_release(struct smc_sock *smc) { struct sock *sk = &smc->sk; @@ -141,6 +147,7 @@ static int __smc_release(struct smc_sock *smc) } sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); + smc_restore_fallback_changes(smc); } sk->sk_prot->unhash(sk); @@ -700,8 +707,6 @@ static int __smc_connect(struct smc_sock *smc) int smc_type; int rc = 0; - sock_hold(&smc->sk); /* sock put in passive closing */ - if (smc->use_fallback) return smc_connect_fallback(smc, smc->fallback_rsn); @@ -791,6 +796,7 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = EPIPE; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); + sock_put(&smc->sk); /* passive closing */ goto out; } @@ -846,6 +852,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, rc = kernel_connect(smc->clcsock, addr, alen, flags); if (rc && rc != -EINPROGRESS) goto out; + + sock_hold(&smc->sk); /* sock put in passive closing */ if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1291,8 +1299,8 @@ static void smc_listen_work(struct work_struct *work) /* check if RDMA is available */ if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */ /* prepare RDMA check */ - memset(&ini, 0, sizeof(ini)); ini.is_smcd = false; + ini.ism_dev = NULL; ini.ib_lcl = &pclc->lcl; rc = smc_find_rdma_device(new_smc, &ini); if (rc) { @@ -1724,7 +1732,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 4ca50ddf8d16..2ba97ff325a5 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -213,7 +213,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr = kzalloc(sizeof(*lgr), GFP_KERNEL); if (!lgr) { rc = SMC_CLC_DECL_MEM; - goto out; + goto ism_put_vlan; } lgr->is_smcd = ini->is_smcd; lgr->sync_err = 0; @@ -289,6 +289,9 @@ clear_llc_lnk: smc_llc_link_clear(lnk); free_lgr: kfree(lgr); +ism_put_vlan: + if (ini->is_smcd && ini->vlan_id) + smc_ism_put_vlan(ini->ism_dev, ini->vlan_id); out: if (rc < 0) { if (rc == -ENOMEM) @@ -558,7 +561,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) } rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index bab2da8cf17a..571e6d84da3b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -376,8 +376,6 @@ static int smc_pnet_fill_entry(struct net *net, return 0; error: - if (pnetelem->ndev) - dev_put(pnetelem->ndev); return rc; } @@ -718,7 +716,7 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) int i, nest_lvl; rtnl_lock(); - nest_lvl = dev_get_nest_level(ndev); + nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index 413a6abf227e..97e8369002d7 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -211,8 +211,7 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo, rc = sk_wait_event(sk, timeo, sk->sk_err || sk->sk_shutdown & RCV_SHUTDOWN || - fcrit(conn) || - smc_cdc_rxed_any_close_or_senddone(conn), + fcrit(conn), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); @@ -262,6 +261,18 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len, return -EAGAIN; } +static bool smc_rx_recvmsg_data_available(struct smc_sock *smc) +{ + struct smc_connection *conn = &smc->conn; + + if (smc_rx_data_available(conn)) + return true; + else if (conn->urg_state == SMC_URG_VALID) + /* we received a single urgent Byte - skip */ + smc_rx_update_cons(smc, 0); + return false; +} + /* smc_rx_recvmsg - receive data from RMBE * @msg: copy data to receive buffer * @pipe: copy data to pipe if set - indicates splice() call @@ -303,16 +314,18 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, if (read_done >= target || (pipe && read_done)) break; - if (atomic_read(&conn->bytes_to_rcv)) + if (smc_rx_recvmsg_data_available(smc)) goto copy; - else if (conn->urg_state == SMC_URG_VALID) - /* we received a single urgent Byte - skip */ - smc_rx_update_cons(smc, 0); if (sk->sk_shutdown & RCV_SHUTDOWN || - smc_cdc_rxed_any_close_or_senddone(conn) || - conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) + conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) { + /* smc_cdc_msg_recv_action() could have run after + * above smc_rx_recvmsg_data_available() + */ + if (smc_rx_recvmsg_data_available(smc)) + goto copy; break; + } if (read_done) { if (sk->sk_err || diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index 339e8c077c2d..195b40c5dae4 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -220,7 +220,7 @@ void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs) goto out; spin_lock_bh(&xprt->bc_pa_lock); - xprt->bc_alloc_max -= max_reqs; + xprt->bc_alloc_max -= min(max_reqs, xprt->bc_alloc_max); list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) { dprintk("RPC: req=%p\n", req); list_del(&req->rq_bc_pa_list); @@ -307,8 +307,8 @@ void xprt_free_bc_rqst(struct rpc_rqst *req) */ dprintk("RPC: Last session removed req=%p\n", req); xprt_free_allocation(req); - return; } + xprt_put(xprt); } /* @@ -339,7 +339,7 @@ found: spin_unlock(&xprt->bc_pa_lock); if (new) { if (req != new) - xprt_free_bc_rqst(new); + xprt_free_allocation(new); break; } else if (req) break; @@ -368,6 +368,7 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); dprintk("RPC: add callback request to list\n"); + xprt_get(xprt); spin_lock(&bc_serv->sv_cb_lock); list_add(&req->rq_bc_list, &bc_serv->sv_cb_list); wake_up(&bc_serv->sv_cb_waitq); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8a45b3ccc313..41df4c507193 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1943,6 +1943,11 @@ static void xprt_destroy_cb(struct work_struct *work) rpc_destroy_wait_queue(&xprt->backlog); kfree(xprt->servername); /* + * Destroy any existing back channel + */ + xprt_destroy_backchannel(xprt, UINT_MAX); + + /* * Tear down transport state and free the rpc_xprt */ xprt->ops->destroy(xprt); diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 50e075fcdd8f..b458bf53ca69 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -163,6 +163,7 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst) spin_lock(&xprt->bc_pa_lock); list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list); spin_unlock(&xprt->bc_pa_lock); + xprt_put(xprt); } static struct rpc_rqst *rpcrdma_bc_rqst_get(struct rpcrdma_xprt *r_xprt) @@ -259,6 +260,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, /* Queue rqst for ULP's callback service */ bc_serv = xprt->bc_serv; + xprt_get(xprt); spin_lock(&bc_serv->sv_cb_lock); list_add(&rqst->rq_bc_list, &bc_serv->sv_cb_list); spin_unlock(&bc_serv->sv_cb_lock); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 9ac88722fa83..70e52f567b2a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1249,19 +1249,21 @@ static void xs_error_report(struct sock *sk) { struct sock_xprt *transport; struct rpc_xprt *xprt; - int err; read_lock_bh(&sk->sk_callback_lock); if (!(xprt = xprt_from_sock(sk))) goto out; transport = container_of(xprt, struct sock_xprt, xprt); - err = -sk->sk_err; - if (err == 0) + transport->xprt_err = -sk->sk_err; + if (transport->xprt_err == 0) goto out; dprintk("RPC: xs_error_report client %p, error=%d...\n", - xprt, -err); - trace_rpc_socket_error(xprt, sk->sk_socket, err); + xprt, -transport->xprt_err); + trace_rpc_socket_error(xprt, sk->sk_socket, transport->xprt_err); + + /* barrier ensures xprt_err is set before XPRT_SOCK_WAKE_ERROR */ + smp_mb__before_atomic(); xs_run_error_worker(transport, XPRT_SOCK_WAKE_ERROR); out: read_unlock_bh(&sk->sk_callback_lock); @@ -2476,7 +2478,6 @@ static void xs_wake_write(struct sock_xprt *transport) static void xs_wake_error(struct sock_xprt *transport) { int sockerr; - int sockerr_len = sizeof(sockerr); if (!test_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state)) return; @@ -2485,9 +2486,7 @@ static void xs_wake_error(struct sock_xprt *transport) goto out; if (!test_and_clear_bit(XPRT_SOCK_WAKE_ERROR, &transport->sock_state)) goto out; - if (kernel_getsockopt(transport->sock, SOL_SOCKET, SO_ERROR, - (char *)&sockerr, &sockerr_len) != 0) - goto out; + sockerr = xchg(&transport->xprt_err, 0); if (sockerr < 0) xprt_wake_pending_tasks(&transport->xprt, sockerr); out: diff --git a/net/tipc/core.c b/net/tipc/core.c index 23cb379a93d6..8f35060a24e1 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -34,8 +34,6 @@ * POSSIBILITY OF SUCH DAMAGE. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - #include "core.h" #include "name_table.h" #include "subscr.h" diff --git a/net/tipc/core.h b/net/tipc/core.h index 60d829581068..3042f654e0af 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -60,6 +60,12 @@ #include <linux/rhashtable.h> #include <net/genetlink.h> +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + struct tipc_node; struct tipc_bearer; struct tipc_bc_base; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3b9f8cc328f5..4b92b196cfa6 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -740,7 +740,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, /* fall through */ case TIPC_LISTEN: case TIPC_CONNECTING: - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) revents |= EPOLLIN | EPOLLRDNORM; break; case TIPC_OPEN: @@ -748,7 +748,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, revents |= EPOLLOUT; if (!tipc_sk_type_connectionless(sk)) break; - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) break; revents |= EPOLLIN | EPOLLRDNORM; break; @@ -2119,13 +2119,13 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb) struct tipc_msg *hdr = buf_msg(skb); if (unlikely(msg_in_group(hdr))) - return sk->sk_rcvbuf; + return READ_ONCE(sk->sk_rcvbuf); if (unlikely(!msg_connected(hdr))) - return sk->sk_rcvbuf << msg_importance(hdr); + return READ_ONCE(sk->sk_rcvbuf) << msg_importance(hdr); if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL)) - return sk->sk_rcvbuf; + return READ_ONCE(sk->sk_rcvbuf); return FLOWCTL_MSG_LIM; } @@ -3790,7 +3790,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf); i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk)); i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf); - i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len); + i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len)); if (dqueues & TIPC_DUMP_SK_SNDQ) { i += scnprintf(buf + i, sz - i, "sk_write_queue: "); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index f959487c5cd1..683d00837693 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -523,8 +523,10 @@ last_record: int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; + struct tls_context *tls_ctx = tls_get_ctx(sk); int rc; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (unlikely(msg->msg_controllen)) { @@ -538,12 +540,14 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; char *kaddr = kmap(page); struct kvec iov; @@ -552,6 +556,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, if (flags & MSG_SENDPAGE_NOTLAST) flags |= MSG_MORE; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (flags & MSG_OOB) { @@ -568,6 +573,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } @@ -623,9 +629,11 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) void tls_device_write_space(struct sock *sk, struct tls_context *ctx) { - if (!sk->sk_write_pending && tls_is_partially_sent_record(ctx)) { + if (tls_is_partially_sent_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; + WARN_ON_ONCE(sk->sk_write_pending); + sk->sk_allocation = GFP_ATOMIC; tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL | diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index ac88877dcade..0775ae40fcfb 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -267,6 +267,7 @@ void tls_ctx_free(struct sock *sk, struct tls_context *ctx) memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + mutex_destroy(&ctx->tx_lock); if (sk) kfree_rcu(ctx, rcu); @@ -612,6 +613,7 @@ static struct tls_context *create_ctx(struct sock *sk) if (!ctx) return NULL; + mutex_init(&ctx->tx_lock); rcu_assign_pointer(icsk->icsk_ulp_data, ctx); ctx->sk_proto = sk->sk_prot; return ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index c2b5e0d2ba1a..446f23c1f3ce 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -897,15 +897,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) return -ENOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto send_end; - } - if (unlikely(msg->msg_controllen)) { ret = tls_proccess_cmsg(sk, msg, &record_type); if (ret) { @@ -1091,6 +1085,7 @@ send_end: ret = sk_stream_error(sk, msg->msg_flags, ret); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return copied ? copied : ret; } @@ -1114,13 +1109,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto sendpage_end; - } - /* Call the sk_stream functions to manage the sndbuf mem. */ while (size > 0) { size_t copy, required_size; @@ -1219,15 +1207,18 @@ sendpage_end: int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); int ret; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) return -ENOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); ret = tls_sw_do_sendpage(sk, page, offset, size, flags); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return ret; } @@ -2170,9 +2161,11 @@ static void tx_work_handler(struct work_struct *work) if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) return; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); } void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) @@ -2180,12 +2173,9 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx); /* Schedule the transmission if tx list is ready */ - if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) { - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, - &tx_ctx->tx_bitmask)) - schedule_delayed_work(&tx_ctx->tx_work.work, 0); - } + if (is_tx_ready(tx_ctx) && + !test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) + schedule_delayed_work(&tx_ctx->tx_work.work, 0); } void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 67e87db5877f..0d8da809bea2 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2599,7 +2599,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* 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 */ @@ -2628,7 +2628,7 @@ static __poll_t unix_dgram_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); @@ -2638,7 +2638,7 @@ static __poll_t unix_dgram_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/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 2ab43b2bba31..582a3e4dfce2 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -870,7 +870,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, * the queue and write as long as the socket isn't shutdown for * sending. */ - if (!skb_queue_empty(&sk->sk_receive_queue) || + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) { mask |= EPOLLIN | EPOLLRDNORM; } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a666ef8fc54e..fb2060dffb0a 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -204,10 +204,14 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, return virtio_transport_get_ops()->send_pkt(pkt); } -static void virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, +static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt) { + if (vvs->rx_bytes + pkt->len > vvs->buf_alloc) + return false; + vvs->rx_bytes += pkt->len; + return true; } static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs, @@ -458,6 +462,9 @@ void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val) vvs->buf_size_max = val; vvs->buf_size = val; vvs->buf_alloc = val; + + virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, + NULL); } EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size); @@ -876,14 +883,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt) { struct virtio_vsock_sock *vvs = vsk->trans; - bool free_pkt = false; + bool can_enqueue, free_pkt = false; pkt->len = le32_to_cpu(pkt->hdr.len); pkt->off = 0; spin_lock_bh(&vvs->rx_lock); - virtio_transport_inc_rx_pkt(vvs, pkt); + can_enqueue = virtio_transport_inc_rx_pkt(vvs, pkt); + if (!can_enqueue) { + free_pkt = true; + goto out; + } /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small @@ -936,9 +947,11 @@ virtio_transport_recv_connected(struct sock *sk, if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) vsk->peer_shutdown |= SEND_SHUTDOWN; if (vsk->peer_shutdown == SHUTDOWN_MASK && - vsock_stream_has_data(vsk) <= 0) { - sock_set_flag(sk, SOCK_DONE); - sk->sk_state = TCP_CLOSING; + vsock_stream_has_data(vsk) <= 0 && + !sock_flag(sk, SOCK_DONE)) { + (void)virtio_transport_reset(vsk, NULL); + + virtio_transport_do_close(vsk, true); } if (le32_to_cpu(pkt->hdr.flags)) sk->sk_state_change(sk); diff --git a/net/wireless/chan.c b/net/wireless/chan.c index e851cafd8e2f..fcac5c6366e1 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -204,6 +204,11 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef) return false; } + /* channel 14 is only for IEEE 802.11b */ + if (chandef->center_freq1 == 2484 && + chandef->width != NL80211_CHAN_WIDTH_20_NOHT) + return false; + if (cfg80211_chandef_is_edmg(chandef) && !cfg80211_edmg_chandef_valid(chandef)) return false; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 141cdb171665..7b72286922f7 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -393,7 +393,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MNTR_FLAGS] = { /* NLA_NESTED can't be empty */ }, [NL80211_ATTR_MESH_ID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_MESH_ID_LEN }, - [NL80211_ATTR_MPATH_NEXT_HOP] = { .type = NLA_U32 }, + [NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT, [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, [NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED }, @@ -13682,7 +13682,7 @@ static int nl80211_get_ftm_responder_stats(struct sk_buff *skb, hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_GET_FTM_RESPONDER_STATS); if (!hdr) - return -ENOBUFS; + goto nla_put_failure; if (nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 420c4207ab59..446c76d44e65 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -3883,6 +3883,7 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy) return pre_cac_allowed; } +EXPORT_SYMBOL(regulatory_pre_cac_allowed); void regulatory_propagate_dfs_state(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 504133d76de4..dc8f689bd469 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -156,14 +156,6 @@ bool regulatory_indoor_allowed(void); #define REG_PRE_CAC_EXPIRY_GRACE_MS 2000 /** - * regulatory_pre_cac_allowed - if pre-CAC allowed in the current dfs domain - * @wiphy: wiphy for which pre-CAC capability is checked. - - * Pre-CAC is allowed only in ETSI domain. - */ -bool regulatory_pre_cac_allowed(struct wiphy *wiphy); - -/** * regulatory_propagate_dfs_state - Propagate DFS channel state to other wiphys * @wiphy - wiphy on which radar is detected and the event will be propagated * to other available wiphys having the same DFS domain diff --git a/net/wireless/scan.c b/net/wireless/scan.c index ff1016607f0b..aef240fdf8df 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1703,8 +1703,7 @@ cfg80211_parse_mbssid_frame_data(struct wiphy *wiphy, static void cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, struct cfg80211_bss *nontrans_bss, - struct ieee80211_mgmt *mgmt, size_t len, - gfp_t gfp) + struct ieee80211_mgmt *mgmt, size_t len) { u8 *ie, *new_ie, *pos; const u8 *nontrans_ssid, *trans_ssid, *mbssid; @@ -1715,6 +1714,8 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, const struct cfg80211_bss_ies *old; u8 cpy_len; + lockdep_assert_held(&wiphy_to_rdev(wiphy)->bss_lock); + ie = mgmt->u.probe_resp.variable; new_ie_len = ielen; @@ -1731,23 +1732,22 @@ cfg80211_update_notlisted_nontrans(struct wiphy *wiphy, if (!mbssid || mbssid < trans_ssid) return; new_ie_len -= mbssid[1]; - rcu_read_lock(); + nontrans_ssid = ieee80211_bss_get_ie(nontrans_bss, WLAN_EID_SSID); - if (!nontrans_ssid) { - rcu_read_unlock(); + if (!nontrans_ssid) return; - } + new_ie_len += nontrans_ssid[1]; - rcu_read_unlock(); /* generate new ie for nontrans BSS * 1. replace SSID with nontrans BSS' SSID * 2. skip MBSSID IE */ - new_ie = kzalloc(new_ie_len, gfp); + new_ie = kzalloc(new_ie_len, GFP_ATOMIC); if (!new_ie) return; - new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, gfp); + + new_ies = kzalloc(sizeof(*new_ies) + new_ie_len, GFP_ATOMIC); if (!new_ies) goto out_free; @@ -1901,6 +1901,8 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, cfg80211_parse_mbssid_frame_data(wiphy, data, mgmt, len, &non_tx_data, gfp); + spin_lock_bh(&wiphy_to_rdev(wiphy)->bss_lock); + /* check if the res has other nontransmitting bss which is not * in MBSSID IE */ @@ -1915,8 +1917,9 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy, ies2 = rcu_access_pointer(tmp_bss->ies); if (ies2->tsf < ies1->tsf) cfg80211_update_notlisted_nontrans(wiphy, tmp_bss, - mgmt, len, gfp); + mgmt, len); } + spin_unlock_bh(&wiphy_to_rdev(wiphy)->bss_lock); return res; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 419eb12c1e93..5b4ed5bbc542 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1559,7 +1559,8 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, } if (freq == 2484) { - if (chandef->width > NL80211_CHAN_WIDTH_40) + /* channel 14 is only for IEEE 802.11b */ + if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT) return false; *op_class = 82; /* channel 14 */ diff --git a/net/wireless/wext-sme.c b/net/wireless/wext-sme.c index c67d7a82ab13..73fd0eae08ca 100644 --- a/net/wireless/wext-sme.c +++ b/net/wireless/wext-sme.c @@ -202,6 +202,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; + int ret = 0; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) @@ -219,7 +220,10 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, if (ie) { data->flags = 1; data->length = ie[1]; - memcpy(ssid, ie + 2, data->length); + if (data->length > IW_ESSID_MAX_SIZE) + ret = -EINVAL; + else + memcpy(ssid, ie + 2, data->length); } rcu_read_unlock(); } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { @@ -229,7 +233,7 @@ int cfg80211_mgd_wext_giwessid(struct net_device *dev, } wdev_unlock(wdev); - return 0; + return ret; } int cfg80211_mgd_wext_siwap(struct net_device *dev, diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 5c111bc3c8ea..00e782335cb0 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -55,7 +55,7 @@ static int x25_receive_data(struct sk_buff *skb, struct x25_neigh *nb) if (!sock_owned_by_user(sk)) { queued = x25_process_rx_frame(sk, skb); } else { - queued = !sk_add_backlog(sk, skb, sk->sk_rcvbuf); + queued = !sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)); } bh_unlock_sock(sk); sock_put(sk); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 16d5f353163a..3049af269fbf 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -27,6 +27,9 @@ void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; + if (!xs->tx) + return; + spin_lock_irqsave(&umem->xsk_list_lock, flags); list_add_rcu(&xs->list, &umem->xsk_list); spin_unlock_irqrestore(&umem->xsk_list_lock, flags); @@ -36,6 +39,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; + if (!xs->tx) + return; + spin_lock_irqsave(&umem->xsk_list_lock, flags); list_del_rcu(&xs->list); spin_unlock_irqrestore(&umem->xsk_list_lock, flags); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index fa8fbb8fa3c8..9044073fbf22 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -305,9 +305,8 @@ out: } EXPORT_SYMBOL(xsk_umem_consume_tx); -static int xsk_zc_xmit(struct sock *sk) +static int xsk_zc_xmit(struct xdp_sock *xs) { - struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev = xs->dev; return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, @@ -327,11 +326,10 @@ static void xsk_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, - size_t total_len) +static int xsk_generic_xmit(struct sock *sk) { - u32 max_batch = TX_BATCH_SIZE; struct xdp_sock *xs = xdp_sk(sk); + u32 max_batch = TX_BATCH_SIZE; bool sent_frame = false; struct xdp_desc desc; struct sk_buff *skb; @@ -394,6 +392,18 @@ out: return err; } +static int __xsk_sendmsg(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (unlikely(!(xs->dev->flags & IFF_UP))) + return -ENETDOWN; + if (unlikely(!xs->tx)) + return -ENOBUFS; + + return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk); +} + static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { bool need_wait = !(m->msg_flags & MSG_DONTWAIT); @@ -402,21 +412,18 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) if (unlikely(!xsk_is_bound(xs))) return -ENXIO; - if (unlikely(!(xs->dev->flags & IFF_UP))) - return -ENETDOWN; - if (unlikely(!xs->tx)) - return -ENOBUFS; - if (need_wait) + if (unlikely(need_wait)) return -EOPNOTSUPP; - return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len); + return __xsk_sendmsg(sk); } static unsigned int xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { unsigned int mask = datagram_poll(file, sock, wait); - struct xdp_sock *xs = xdp_sk(sock->sk); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; struct xdp_umem *umem; @@ -426,9 +433,14 @@ static unsigned int xsk_poll(struct file *file, struct socket *sock, dev = xs->dev; umem = xs->umem; - if (umem->need_wakeup) - dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, - umem->need_wakeup); + if (umem->need_wakeup) { + if (dev->netdev_ops->ndo_xsk_wakeup) + dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, + umem->need_wakeup); + else + /* Poll needs to drive Tx also in copy mode */ + __xsk_sendmsg(sk); + } if (xs->rx && !xskq_empty_desc(xs->rx)) mask |= POLLIN | POLLRDNORM; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 9b599ed66d97..2c86a2fc3915 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -480,6 +480,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); + + if (encap_type == -1) + dev_put(skb->dev); goto drop; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index c6f3c4a1bd99..f3423562d933 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -495,6 +495,8 @@ static void ___xfrm_state_destroy(struct xfrm_state *x) x->type->destructor(x); xfrm_put_type(x->type); } + if (x->xfrag.page) + put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); |