diff options
author | Otavio Salvador <otavio@ossystems.com.br> | 2016-10-05 16:23:28 -0300 |
---|---|---|
committer | Otavio Salvador <otavio@ossystems.com.br> | 2016-10-05 16:23:28 -0300 |
commit | a7f858238e7c8e8c4b9040aac0eb28bb0b6ab9dc (patch) | |
tree | f87a76eb101d6b9ea2016c404982991345d95dc8 /net | |
parent | 5bc73053cc0a6a0e5c5f953f8b774854316b87a9 (diff) | |
parent | 04cb720142764ebf3786eba1feb8fc4b6ef87fcf (diff) |
Merge tag 'v4.1.33' into 4.1-2.0.x-imx
Linux 4.1.33
* tag 'v4.1.33': (1760 commits)
Linux 4.1.33
Revert "ARC: mm: don't loose PTE_SPECIAL in pte_modify()"
x86/AMD: Apply erratum 665 on machines without a BIOS fix
x86/paravirt: Do not trace _paravirt_ident_*() functions
ovl: listxattr: use strnlen()
ovl: remove posix_acl_default from workdir
serial: 8250: added acces i/o products quad and octal serial cards
sysfs: correctly handle read offset on PREALLOC attrs
sysfs: correctly handle short reads on PREALLOC attrs.
kernfs: don't depend on d_find_any_alias() when generating notifications
dm crypt: fix free of bad values after tfm allocation failure
dm crypt: fix error with too large bios
dm log writes: fix check of kthread_run() return value
dm log writes: fix bug with too large bios
dm log writes: move IO accounting earlier to fix error path
NFSv4.x: Fix a refcount leak in nfs_callback_up_net
xfs: prevent dropping ioend completions during buftarg wait
xfs: fix superblock inprogress check
USB: serial: option: add WeTelecom 0x6802 and 0x6803 products
USB: avoid left shift by -1
...
Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>
Diffstat (limited to 'net')
152 files changed, 2095 insertions, 1594 deletions
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 330c1f4a5a0b..a64884bbf0ce 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -806,6 +806,9 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; ax25_cb *ax25; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c index 7c646bb2c6f7..98d206b22653 100644 --- a/net/ax25/ax25_ip.c +++ b/net/ax25/ax25_ip.c @@ -229,8 +229,23 @@ netdev_tx_t ax25_ip_xmit(struct sk_buff *skb) } #endif +static bool ax25_validate_header(const char *header, unsigned int len) +{ + ax25_digi digi; + + if (!len) + return false; + + if (header[0]) + return true; + + return ax25_addr_parse(header + 1, len - 1, NULL, NULL, &digi, NULL, + NULL); +} + const struct header_ops ax25_header_ops = { .create = ax25_hard_header, + .validate = ax25_validate_header, }; EXPORT_SYMBOL(ax25_header_ops); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index ac4b96eccade..bd3357e69c5c 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -112,21 +112,17 @@ batadv_backbone_gw_free_ref(struct batadv_bla_backbone_gw *backbone_gw) } /* finally deinitialize the claim */ -static void batadv_claim_free_rcu(struct rcu_head *rcu) +static void batadv_claim_release(struct batadv_bla_claim *claim) { - struct batadv_bla_claim *claim; - - claim = container_of(rcu, struct batadv_bla_claim, rcu); - batadv_backbone_gw_free_ref(claim->backbone_gw); - kfree(claim); + kfree_rcu(claim, rcu); } /* free a claim, call claim_free_rcu if its the last reference */ static void batadv_claim_free_ref(struct batadv_bla_claim *claim) { if (atomic_dec_and_test(&claim->refcount)) - call_rcu(&claim->rcu, batadv_claim_free_rcu); + batadv_claim_release(claim); } /** diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 1918cd50b62e..b6bff9c1877a 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -64,18 +64,6 @@ batadv_hardif_free_ref(struct batadv_hard_iface *hard_iface) call_rcu(&hard_iface->rcu, batadv_hardif_free_rcu); } -/** - * batadv_hardif_free_ref_now - decrement the hard interface refcounter and - * possibly free it (without rcu callback) - * @hard_iface: the hard interface to free - */ -static inline void -batadv_hardif_free_ref_now(struct batadv_hard_iface *hard_iface) -{ - if (atomic_dec_and_test(&hard_iface->refcount)) - batadv_hardif_free_rcu(&hard_iface->rcu); -} - static inline struct batadv_hard_iface * batadv_primary_if_get_selected(struct batadv_priv *bat_priv) { diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index a449195c5b2b..2fbd3a6bde9a 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -175,28 +175,25 @@ void batadv_nc_init_orig(struct batadv_orig_node *orig_node) } /** - * batadv_nc_node_free_rcu - rcu callback to free an nc node and remove - * its refcount on the orig_node - * @rcu: rcu pointer of the nc node + * batadv_nc_node_release - release nc_node from lists and queue for free after + * rcu grace period + * @nc_node: the nc node to free */ -static void batadv_nc_node_free_rcu(struct rcu_head *rcu) +static void batadv_nc_node_release(struct batadv_nc_node *nc_node) { - struct batadv_nc_node *nc_node; - - nc_node = container_of(rcu, struct batadv_nc_node, rcu); batadv_orig_node_free_ref(nc_node->orig_node); - kfree(nc_node); + kfree_rcu(nc_node, rcu); } /** - * batadv_nc_node_free_ref - decrements the nc node refcounter and possibly - * frees it + * batadv_nc_node_free_ref - decrement the nc node refcounter and possibly + * release it * @nc_node: the nc node to free */ static void batadv_nc_node_free_ref(struct batadv_nc_node *nc_node) { if (atomic_dec_and_test(&nc_node->refcount)) - call_rcu(&nc_node->rcu, batadv_nc_node_free_rcu); + batadv_nc_node_release(nc_node); } /** diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index dfae97408628..77ea1d4de2ba 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -150,86 +150,58 @@ err: } /** - * batadv_neigh_ifinfo_free_rcu - free the neigh_ifinfo object - * @rcu: rcu pointer of the neigh_ifinfo object - */ -static void batadv_neigh_ifinfo_free_rcu(struct rcu_head *rcu) -{ - struct batadv_neigh_ifinfo *neigh_ifinfo; - - neigh_ifinfo = container_of(rcu, struct batadv_neigh_ifinfo, rcu); - - if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(neigh_ifinfo->if_outgoing); - - kfree(neigh_ifinfo); -} - -/** - * batadv_neigh_ifinfo_free_now - decrement the refcounter and possibly free - * the neigh_ifinfo (without rcu callback) + * batadv_neigh_ifinfo_release - release neigh_ifinfo from lists and queue for + * free after rcu grace period * @neigh_ifinfo: the neigh_ifinfo object to release */ static void -batadv_neigh_ifinfo_free_ref_now(struct batadv_neigh_ifinfo *neigh_ifinfo) +batadv_neigh_ifinfo_release(struct batadv_neigh_ifinfo *neigh_ifinfo) { - if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - batadv_neigh_ifinfo_free_rcu(&neigh_ifinfo->rcu); + if (neigh_ifinfo->if_outgoing != BATADV_IF_DEFAULT) + batadv_hardif_free_ref(neigh_ifinfo->if_outgoing); + + kfree_rcu(neigh_ifinfo, rcu); } /** - * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly free + * batadv_neigh_ifinfo_free_ref - decrement the refcounter and possibly release * the neigh_ifinfo * @neigh_ifinfo: the neigh_ifinfo object to release */ void batadv_neigh_ifinfo_free_ref(struct batadv_neigh_ifinfo *neigh_ifinfo) { if (atomic_dec_and_test(&neigh_ifinfo->refcount)) - call_rcu(&neigh_ifinfo->rcu, batadv_neigh_ifinfo_free_rcu); + batadv_neigh_ifinfo_release(neigh_ifinfo); } /** - * batadv_neigh_node_free_rcu - free the neigh_node - * @rcu: rcu pointer of the neigh_node + * batadv_neigh_node_release - release neigh_node from lists and queue for + * free after rcu grace period + * @neigh_node: neigh neighbor to free */ -static void batadv_neigh_node_free_rcu(struct rcu_head *rcu) +static void batadv_neigh_node_release(struct batadv_neigh_node *neigh_node) { struct hlist_node *node_tmp; - struct batadv_neigh_node *neigh_node; struct batadv_neigh_ifinfo *neigh_ifinfo; - neigh_node = container_of(rcu, struct batadv_neigh_node, rcu); - hlist_for_each_entry_safe(neigh_ifinfo, node_tmp, &neigh_node->ifinfo_list, list) { - batadv_neigh_ifinfo_free_ref_now(neigh_ifinfo); + batadv_neigh_ifinfo_free_ref(neigh_ifinfo); } - batadv_hardif_free_ref_now(neigh_node->if_incoming); + batadv_hardif_free_ref(neigh_node->if_incoming); - kfree(neigh_node); -} - -/** - * batadv_neigh_node_free_ref_now - decrement the neighbors refcounter - * and possibly free it (without rcu callback) - * @neigh_node: neigh neighbor to free - */ -static void -batadv_neigh_node_free_ref_now(struct batadv_neigh_node *neigh_node) -{ - if (atomic_dec_and_test(&neigh_node->refcount)) - batadv_neigh_node_free_rcu(&neigh_node->rcu); + kfree_rcu(neigh_node, rcu); } /** * batadv_neigh_node_free_ref - decrement the neighbors refcounter - * and possibly free it + * and possibly release it * @neigh_node: neigh neighbor to free */ void batadv_neigh_node_free_ref(struct batadv_neigh_node *neigh_node) { if (atomic_dec_and_test(&neigh_node->refcount)) - call_rcu(&neigh_node->rcu, batadv_neigh_node_free_rcu); + batadv_neigh_node_release(neigh_node); } /** @@ -495,108 +467,99 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node, } /** - * batadv_orig_ifinfo_free_rcu - free the orig_ifinfo object - * @rcu: rcu pointer of the orig_ifinfo object + * batadv_orig_ifinfo_release - release orig_ifinfo from lists and queue for + * free after rcu grace period + * @orig_ifinfo: the orig_ifinfo object to release */ -static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu) +static void batadv_orig_ifinfo_release(struct batadv_orig_ifinfo *orig_ifinfo) { - struct batadv_orig_ifinfo *orig_ifinfo; struct batadv_neigh_node *router; - orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu); - if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT) - batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing); + batadv_hardif_free_ref(orig_ifinfo->if_outgoing); /* this is the last reference to this object */ router = rcu_dereference_protected(orig_ifinfo->router, true); if (router) - batadv_neigh_node_free_ref_now(router); - kfree(orig_ifinfo); + batadv_neigh_node_free_ref(router); + + kfree_rcu(orig_ifinfo, rcu); } /** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free - * the orig_ifinfo (without rcu callback) + * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly release + * the orig_ifinfo * @orig_ifinfo: the orig_ifinfo object to release */ -static void -batadv_orig_ifinfo_free_ref_now(struct batadv_orig_ifinfo *orig_ifinfo) +void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) { if (atomic_dec_and_test(&orig_ifinfo->refcount)) - batadv_orig_ifinfo_free_rcu(&orig_ifinfo->rcu); + batadv_orig_ifinfo_release(orig_ifinfo); } /** - * batadv_orig_ifinfo_free_ref - decrement the refcounter and possibly free - * the orig_ifinfo - * @orig_ifinfo: the orig_ifinfo object to release + * batadv_orig_node_free_rcu - free the orig_node + * @rcu: rcu pointer of the orig_node */ -void batadv_orig_ifinfo_free_ref(struct batadv_orig_ifinfo *orig_ifinfo) +static void batadv_orig_node_free_rcu(struct rcu_head *rcu) { - if (atomic_dec_and_test(&orig_ifinfo->refcount)) - call_rcu(&orig_ifinfo->rcu, batadv_orig_ifinfo_free_rcu); + struct batadv_orig_node *orig_node; + + orig_node = container_of(rcu, struct batadv_orig_node, rcu); + + batadv_mcast_purge_orig(orig_node); + + batadv_frag_purge_orig(orig_node, NULL); + + if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) + orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node); + + kfree(orig_node->tt_buff); + kfree(orig_node); } -static void batadv_orig_node_free_rcu(struct rcu_head *rcu) +/** + * batadv_orig_node_release - release orig_node from lists and queue for + * free after rcu grace period + * @orig_node: the orig node to free + */ +static void batadv_orig_node_release(struct batadv_orig_node *orig_node) { struct hlist_node *node_tmp; struct batadv_neigh_node *neigh_node; - struct batadv_orig_node *orig_node; struct batadv_orig_ifinfo *orig_ifinfo; - orig_node = container_of(rcu, struct batadv_orig_node, rcu); - spin_lock_bh(&orig_node->neigh_list_lock); /* for all neighbors towards this originator ... */ hlist_for_each_entry_safe(neigh_node, node_tmp, &orig_node->neigh_list, list) { hlist_del_rcu(&neigh_node->list); - batadv_neigh_node_free_ref_now(neigh_node); + batadv_neigh_node_free_ref(neigh_node); } hlist_for_each_entry_safe(orig_ifinfo, node_tmp, &orig_node->ifinfo_list, list) { hlist_del_rcu(&orig_ifinfo->list); - batadv_orig_ifinfo_free_ref_now(orig_ifinfo); + batadv_orig_ifinfo_free_ref(orig_ifinfo); } spin_unlock_bh(&orig_node->neigh_list_lock); - batadv_mcast_purge_orig(orig_node); - /* Free nc_nodes */ batadv_nc_purge_orig(orig_node->bat_priv, orig_node, NULL); - batadv_frag_purge_orig(orig_node, NULL); - - if (orig_node->bat_priv->bat_algo_ops->bat_orig_free) - orig_node->bat_priv->bat_algo_ops->bat_orig_free(orig_node); - - kfree(orig_node->tt_buff); - kfree(orig_node); + call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } /** * batadv_orig_node_free_ref - decrement the orig node refcounter and possibly - * schedule an rcu callback for freeing it + * release it * @orig_node: the orig node to free */ void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node) { if (atomic_dec_and_test(&orig_node->refcount)) - call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); -} - -/** - * batadv_orig_node_free_ref_now - decrement the orig node refcounter and - * possibly free it (without rcu callback) - * @orig_node: the orig node to free - */ -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node) -{ - if (atomic_dec_and_test(&orig_node->refcount)) - batadv_orig_node_free_rcu(&orig_node->rcu); + batadv_orig_node_release(orig_node); } void batadv_originator_free(struct batadv_priv *bat_priv) diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index aa4a43696295..28b751ad549c 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -25,7 +25,6 @@ int batadv_originator_init(struct batadv_priv *bat_priv); void batadv_originator_free(struct batadv_priv *bat_priv); void batadv_purge_orig_ref(struct batadv_priv *bat_priv); void batadv_orig_node_free_ref(struct batadv_orig_node *orig_node); -void batadv_orig_node_free_ref_now(struct batadv_orig_node *orig_node); struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv, const uint8_t *addr); struct batadv_neigh_node * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index da83982bf974..f77dafc114a6 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -88,6 +88,15 @@ static void _batadv_update_route(struct batadv_priv *bat_priv, neigh_node = NULL; spin_lock_bh(&orig_node->neigh_list_lock); + /* curr_router used earlier may not be the current orig_ifinfo->router + * anymore because it was dereferenced outside of the neigh_list_lock + * protected region. After the new best neighbor has replace the current + * best neighbor the reference counter needs to decrease. Consequently, + * the code needs to ensure the curr_router variable contains a pointer + * to the replaced best neighbor. + */ + curr_router = rcu_dereference_protected(orig_ifinfo->router, true); + rcu_assign_pointer(orig_ifinfo->router, neigh_node); spin_unlock_bh(&orig_node->neigh_list_lock); batadv_orig_ifinfo_free_ref(orig_ifinfo); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3d64ed20c393..6004c2de7b2a 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -611,6 +611,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->bcast_queue_left); + batadv_forw_packet_free(forw_packet); } } @@ -638,6 +641,9 @@ batadv_purge_outstanding_packets(struct batadv_priv *bat_priv, if (pending) { hlist_del(&forw_packet->list); + if (!forw_packet->own) + atomic_inc(&bat_priv->batman_queue_left); + batadv_forw_packet_free(forw_packet); } } diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index a0b1b861b968..b38a8aa3cce8 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -377,11 +377,17 @@ void batadv_interface_rx(struct net_device *soft_iface, */ nf_reset(skb); + if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) + goto dropped; + vid = batadv_get_vid(skb, 0); ethhdr = eth_hdr(skb); switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, VLAN_ETH_HLEN)) + goto dropped; + vhdr = (struct vlan_ethhdr *)skb->data; if (vhdr->h_vlan_encapsulated_proto != ethertype) @@ -393,8 +399,6 @@ void batadv_interface_rx(struct net_device *soft_iface, } /* skb->dev & skb->pkt_type are set here */ - if (unlikely(!pskb_may_pull(skb, ETH_HLEN))) - goto dropped; skb->protocol = eth_type_trans(skb, soft_iface); /* should not be necessary anymore as we use skb_pull_rcsum() diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 4f2a9d2c56db..ddd62c9af5b4 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -219,20 +219,6 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv, return count; } -static void batadv_tt_orig_list_entry_free_rcu(struct rcu_head *rcu) -{ - struct batadv_tt_orig_list_entry *orig_entry; - - orig_entry = container_of(rcu, struct batadv_tt_orig_list_entry, rcu); - - /* We are in an rcu callback here, therefore we cannot use - * batadv_orig_node_free_ref() and its call_rcu(): - * An rcu_barrier() wouldn't wait for that to finish - */ - batadv_orig_node_free_ref_now(orig_entry->orig_node); - kfree(orig_entry); -} - /** * batadv_tt_local_size_mod - change the size by v of the local table identified * by vid @@ -328,13 +314,25 @@ static void batadv_tt_global_size_dec(struct batadv_orig_node *orig_node, batadv_tt_global_size_mod(orig_node, vid, -1); } +/** + * batadv_tt_orig_list_entry_release - release tt orig entry from lists and + * queue for free after rcu grace period + * @orig_entry: tt orig entry to be free'd + */ +static void +batadv_tt_orig_list_entry_release(struct batadv_tt_orig_list_entry *orig_entry) +{ + batadv_orig_node_free_ref(orig_entry->orig_node); + kfree_rcu(orig_entry, rcu); +} + static void batadv_tt_orig_list_entry_free_ref(struct batadv_tt_orig_list_entry *orig_entry) { if (!atomic_dec_and_test(&orig_entry->refcount)) return; - call_rcu(&orig_entry->rcu, batadv_tt_orig_list_entry_free_rcu); + batadv_tt_orig_list_entry_release(orig_entry); } /** diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index a7278f05eafb..289c96d3e47d 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -927,7 +927,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (get_user(opt, (u32 __user *) optval)) { + if (get_user(opt, (u16 __user *) optval)) { err = -EFAULT; break; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 4322c833e748..8611bc7bdd32 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -520,6 +520,9 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_le if (!addr || addr->sa_family != AF_BLUETOOTH) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_sco)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != BT_OPEN) { diff --git a/net/bridge/br.c b/net/bridge/br.c index 02c24cf63c34..c72e01cf09d0 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -121,6 +121,7 @@ static struct notifier_block br_device_notifier = { .notifier_call = br_device_event }; +/* called with RTNL */ static int br_netdev_switch_event(struct notifier_block *unused, unsigned long event, void *ptr) { @@ -130,7 +131,6 @@ static int br_netdev_switch_event(struct notifier_block *unused, struct netdev_switch_notifier_fdb_info *fdb_info; int err = NOTIFY_DONE; - rtnl_lock(); p = br_port_get_rtnl(dev); if (!p) goto out; @@ -155,7 +155,6 @@ static int br_netdev_switch_event(struct notifier_block *unused, } out: - rtnl_unlock(); return err; } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 4ff77a16956c..3d6c8e222391 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -28,6 +28,8 @@ 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) { @@ -87,6 +89,11 @@ 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); @@ -99,6 +106,7 @@ static int br_dev_init(struct net_device *dev) err = br_vlan_init(br); if (err) free_percpu(br->stats); + br_set_lockdep_class(dev); return err; } diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 8d423bc649b9..f876f707fd9e 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -21,18 +21,19 @@ #include <asm/uaccess.h> #include "br_private.h" -/* called with RTNL */ static int get_bridge_ifindices(struct net *net, int *indices, int num) { struct net_device *dev; int i = 0; - for_each_netdev(net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { if (i >= num) break; if (dev->priv_flags & IFF_EBRIDGE) indices[i++] = dev->ifindex; } + rcu_read_unlock(); return i; } diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 7832d07f48f6..ce658abdc2c8 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -128,7 +128,10 @@ static void br_stp_start(struct net_bridge *br) char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL }; char *envp[] = { NULL }; - r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + if (net_eq(dev_net(br->dev), &init_net)) + r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC); + else + r = -ENOENT; spin_lock_bh(&br->lock); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 967080a9f043..84201c21705e 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -675,6 +675,8 @@ static void reset_connection(struct ceph_connection *con) } con->in_seq = 0; con->in_seq_acked = 0; + + con->out_skip = 0; } /* @@ -774,6 +776,8 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt) static void con_out_kvec_reset(struct ceph_connection *con) { + BUG_ON(con->out_skip); + con->out_kvec_left = 0; con->out_kvec_bytes = 0; con->out_kvec_cur = &con->out_kvec[0]; @@ -782,9 +786,9 @@ static void con_out_kvec_reset(struct ceph_connection *con) static void con_out_kvec_add(struct ceph_connection *con, size_t size, void *data) { - int index; + int index = con->out_kvec_left; - index = con->out_kvec_left; + BUG_ON(con->out_skip); BUG_ON(index >= ARRAY_SIZE(con->out_kvec)); con->out_kvec[index].iov_len = size; @@ -793,6 +797,27 @@ static void con_out_kvec_add(struct ceph_connection *con, con->out_kvec_bytes += size; } +/* + * Chop off a kvec from the end. Return residual number of bytes for + * that kvec, i.e. how many bytes would have been written if the kvec + * hadn't been nuked. + */ +static int con_out_kvec_skip(struct ceph_connection *con) +{ + int off = con->out_kvec_cur - con->out_kvec; + int skip = 0; + + if (con->out_kvec_bytes > 0) { + skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len; + BUG_ON(con->out_kvec_bytes < skip); + BUG_ON(!con->out_kvec_left); + con->out_kvec_bytes -= skip; + con->out_kvec_left--; + } + + return skip; +} + #ifdef CONFIG_BLOCK /* @@ -1178,6 +1203,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, return new_piece; } +static size_t sizeof_footer(struct ceph_connection *con) +{ + return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ? + sizeof(struct ceph_msg_footer) : + sizeof(struct ceph_msg_footer_old); +} + static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { BUG_ON(!msg); @@ -1200,7 +1232,6 @@ static void prepare_write_message_footer(struct ceph_connection *con) m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE; dout("prepare_write_message_footer %p\n", con); - con->out_kvec_is_msg = true; con->out_kvec[v].iov_base = &m->footer; if (con->peer_features & CEPH_FEATURE_MSG_AUTH) { if (con->ops->sign_message) @@ -1228,7 +1259,6 @@ static void prepare_write_message(struct ceph_connection *con) u32 crc; con_out_kvec_reset(con); - con->out_kvec_is_msg = true; con->out_msg_done = false; /* Sneak an ack in there first? If we can get it into the same @@ -1268,18 +1298,19 @@ static void prepare_write_message(struct ceph_connection *con) /* tag + hdr + front + middle */ con_out_kvec_add(con, sizeof (tag_msg), &tag_msg); - con_out_kvec_add(con, sizeof (m->hdr), &m->hdr); + con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr); con_out_kvec_add(con, m->front.iov_len, m->front.iov_base); if (m->middle) con_out_kvec_add(con, m->middle->vec.iov_len, m->middle->vec.iov_base); - /* fill in crc (except data pages), footer */ + /* fill in hdr crc and finalize hdr */ crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc)); con->out_msg->hdr.crc = cpu_to_le32(crc); - con->out_msg->footer.flags = 0; + memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr)); + /* fill in front and middle crc, footer */ crc = crc32c(0, m->front.iov_base, m->front.iov_len); con->out_msg->footer.front_crc = cpu_to_le32(crc); if (m->middle) { @@ -1291,6 +1322,7 @@ static void prepare_write_message(struct ceph_connection *con) dout("%s front_crc %u middle_crc %u\n", __func__, le32_to_cpu(con->out_msg->footer.front_crc), le32_to_cpu(con->out_msg->footer.middle_crc)); + con->out_msg->footer.flags = 0; /* is there a data payload? */ con->out_msg->footer.data_crc = 0; @@ -1485,7 +1517,6 @@ static int write_partial_kvec(struct ceph_connection *con) } } con->out_kvec_left = 0; - con->out_kvec_is_msg = false; ret = 1; out: dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con, @@ -1577,6 +1608,7 @@ static int write_partial_skip(struct ceph_connection *con) { int ret; + dout("%s %p %d left\n", __func__, con, con->out_skip); while (con->out_skip > 0) { size_t size = min(con->out_skip, (int) PAGE_CACHE_SIZE); @@ -2301,9 +2333,9 @@ static int read_partial_message(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; - return 0; + return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); @@ -2333,10 +2365,10 @@ static int read_partial_message(struct ceph_connection *con) /* skip this message */ dout("alloc_msg said skip message\n"); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; - return 0; + return 1; } BUG_ON(!con->in_msg); @@ -2493,13 +2525,13 @@ more: more_kvec: /* kvec data queued? */ - if (con->out_skip) { - ret = write_partial_skip(con); + if (con->out_kvec_left) { + ret = write_partial_kvec(con); if (ret <= 0) goto out; } - if (con->out_kvec_left) { - ret = write_partial_kvec(con); + if (con->out_skip) { + ret = write_partial_skip(con); if (ret <= 0) goto out; } @@ -3026,16 +3058,31 @@ void ceph_msg_revoke(struct ceph_msg *msg) ceph_msg_put(msg); } if (con->out_msg == msg) { - dout("%s %p msg %p - was sending\n", __func__, con, msg); - con->out_msg = NULL; - if (con->out_kvec_is_msg) { - con->out_skip = con->out_kvec_bytes; - con->out_kvec_is_msg = false; + BUG_ON(con->out_skip); + /* footer */ + if (con->out_msg_done) { + con->out_skip += con_out_kvec_skip(con); + } else { + BUG_ON(!msg->data_length); + if (con->peer_features & CEPH_FEATURE_MSG_AUTH) + con->out_skip += sizeof(msg->footer); + else + con->out_skip += sizeof(msg->old_footer); } + /* data, middle, front */ + if (msg->data_length) + con->out_skip += msg->cursor.total_resid; + if (msg->middle) + con->out_skip += con_out_kvec_skip(con); + con->out_skip += con_out_kvec_skip(con); + + dout("%s %p msg %p - was sending, will write %d skip %d\n", + __func__, con, msg, con->out_kvec_bytes, con->out_skip); msg->hdr.seq = 0; - + con->out_msg = NULL; ceph_msg_put(msg); } + mutex_unlock(&con->mutex); } diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 4a3125836b64..ddc3573894b0 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -1192,6 +1192,115 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end) } /* + * Encoding order is (new_up_client, new_state, new_weight). Need to + * apply in the (new_weight, new_state, new_up_client) order, because + * an incremental map may look like e.g. + * + * new_up_client: { osd=6, addr=... } # set osd_state and addr + * new_state: { osd=6, xorstate=EXISTS } # clear osd_state + */ +static int decode_new_up_state_weight(void **p, void *end, + struct ceph_osdmap *map) +{ + void *new_up_client; + void *new_state; + void *new_weight_end; + u32 len; + + new_up_client = *p; + ceph_decode_32_safe(p, end, len, e_inval); + len *= sizeof(u32) + sizeof(struct ceph_entity_addr); + ceph_decode_need(p, end, len, e_inval); + *p += len; + + new_state = *p; + ceph_decode_32_safe(p, end, len, e_inval); + len *= sizeof(u32) + sizeof(u8); + ceph_decode_need(p, end, len, e_inval); + *p += len; + + /* new_weight */ + ceph_decode_32_safe(p, end, len, e_inval); + while (len--) { + s32 osd; + u32 w; + + ceph_decode_need(p, end, 2*sizeof(u32), e_inval); + osd = ceph_decode_32(p); + w = ceph_decode_32(p); + BUG_ON(osd >= map->max_osd); + pr_info("osd%d weight 0x%x %s\n", osd, w, + w == CEPH_OSD_IN ? "(in)" : + (w == CEPH_OSD_OUT ? "(out)" : "")); + map->osd_weight[osd] = w; + + /* + * If we are marking in, set the EXISTS, and clear the + * AUTOOUT and NEW bits. + */ + if (w) { + map->osd_state[osd] |= CEPH_OSD_EXISTS; + map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT | + CEPH_OSD_NEW); + } + } + new_weight_end = *p; + + /* new_state (up/down) */ + *p = new_state; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + u8 xorstate; + int ret; + + osd = ceph_decode_32(p); + xorstate = ceph_decode_8(p); + if (xorstate == 0) + xorstate = CEPH_OSD_UP; + BUG_ON(osd >= map->max_osd); + if ((map->osd_state[osd] & CEPH_OSD_UP) && + (xorstate & CEPH_OSD_UP)) + pr_info("osd%d down\n", osd); + if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && + (xorstate & CEPH_OSD_EXISTS)) { + pr_info("osd%d does not exist\n", osd); + map->osd_weight[osd] = CEPH_OSD_IN; + ret = set_primary_affinity(map, osd, + CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); + if (ret) + return ret; + memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr)); + map->osd_state[osd] = 0; + } else { + map->osd_state[osd] ^= xorstate; + } + } + + /* new_up_client */ + *p = new_up_client; + len = ceph_decode_32(p); + while (len--) { + s32 osd; + struct ceph_entity_addr addr; + + osd = ceph_decode_32(p); + ceph_decode_copy(p, &addr, sizeof(addr)); + ceph_decode_addr(&addr); + BUG_ON(osd >= map->max_osd); + pr_info("osd%d up\n", osd); + map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP; + map->osd_addr[osd] = addr; + } + + *p = new_weight_end; + return 0; + +e_inval: + return -EINVAL; +} + +/* * decode and apply an incremental map update. */ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, @@ -1290,49 +1399,10 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, __remove_pg_pool(&map->pg_pools, pi); } - /* new_up */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd; - struct ceph_entity_addr addr; - ceph_decode_32_safe(p, end, osd, e_inval); - ceph_decode_copy_safe(p, end, &addr, sizeof(addr), e_inval); - ceph_decode_addr(&addr); - pr_info("osd%d up\n", osd); - BUG_ON(osd >= map->max_osd); - map->osd_state[osd] |= CEPH_OSD_UP; - map->osd_addr[osd] = addr; - } - - /* new_state */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd; - u8 xorstate; - ceph_decode_32_safe(p, end, osd, e_inval); - xorstate = **(u8 **)p; - (*p)++; /* clean flag */ - if (xorstate == 0) - xorstate = CEPH_OSD_UP; - if (xorstate & CEPH_OSD_UP) - pr_info("osd%d down\n", osd); - if (osd < map->max_osd) - map->osd_state[osd] ^= xorstate; - } - - /* new_weight */ - ceph_decode_32_safe(p, end, len, e_inval); - while (len--) { - u32 osd, off; - ceph_decode_need(p, end, sizeof(u32)*2, e_inval); - osd = ceph_decode_32(p); - off = ceph_decode_32(p); - pr_info("osd%d weight 0x%x %s\n", osd, off, - off == CEPH_OSD_IN ? "(in)" : - (off == CEPH_OSD_OUT ? "(out)" : "")); - if (osd < map->max_osd) - map->osd_weight[osd] = off; - } + /* new_up_client, new_state, new_weight */ + err = decode_new_up_state_weight(p, end, map); + if (err) + goto bad; /* new_pg_temp */ err = decode_new_pg_temp(p, end, map); diff --git a/net/core/dev.c b/net/core/dev.c index a42b232805a5..185a3398c651 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2479,6 +2479,8 @@ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) * * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. + * + * Segmentation preserves SKB_SGO_CB_OFFSET bytes of previous skb cb. */ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path) @@ -2493,6 +2495,9 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return ERR_PTR(err); } + BUILD_BUG_ON(SKB_SGO_CB_OFFSET + + sizeof(*SKB_GSO_CB(skb)) > sizeof(skb->cb)); + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); SKB_GSO_CB(skb)->encap_level = 0; diff --git a/net/core/dst.c b/net/core/dst.c index f8db4032d45a..540066cb33ef 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -282,10 +282,11 @@ void dst_release(struct dst_entry *dst) { if (dst) { int newrefcnt; + unsigned short nocache = dst->flags & DST_NOCACHE; newrefcnt = atomic_dec_return(&dst->__refcnt); WARN_ON(newrefcnt < 0); - if (!newrefcnt && unlikely(dst->flags & DST_NOCACHE)) + if (!newrefcnt && unlikely(nocache)) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } diff --git a/net/core/filter.c b/net/core/filter.c index 0fa2613b5e35..238bb3f9c51d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -775,6 +775,11 @@ int bpf_check_classic(const struct sock_filter *filter, unsigned int flen) if (ftest->k == 0) return -EINVAL; break; + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + if (ftest->k >= 32) + return -EINVAL; + break; case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2c35c02a931e..3556791fdc6e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -113,7 +113,6 @@ ip: case htons(ETH_P_IPV6): { const struct ipv6hdr *iph; struct ipv6hdr _iph; - __be32 flow_label; ipv6: iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph); @@ -130,8 +129,9 @@ ipv6: flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr); flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr); - flow_label = ip6_flowlabel(iph); - if (flow_label) { + if (skb && ip6_flowlabel(iph)) { + __be32 flow_label = ip6_flowlabel(iph); + /* Awesome, IPv6 packet has a flow label so we can * use that to represent the ports without any * further dissection. @@ -233,6 +233,13 @@ ipv6: return false; proto = eth->h_proto; nhoff += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + hlen = nhoff; } goto again; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index fe95cb704aaa..e9c4b51525de 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -884,7 +884,9 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_PORT_ID */ - + nla_total_size(MAX_PHYS_ITEM_ID_LEN); /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(MAX_PHYS_ITEM_ID_LEN) /* IFLA_PHYS_SWITCH_ID */ + + nla_total_size(IFNAMSIZ); /* IFLA_PHYS_PORT_NAME */ + } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -1070,14 +1072,16 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; if (1) { - struct rtnl_link_ifmap map = { - .mem_start = dev->mem_start, - .mem_end = dev->mem_end, - .base_addr = dev->base_addr, - .irq = dev->irq, - .dma = dev->dma, - .port = dev->if_port, - }; + struct rtnl_link_ifmap map; + + memset(&map, 0, sizeof(map)); + map.mem_start = dev->mem_start; + map.mem_end = dev->mem_end; + map.base_addr = dev->base_addr; + map.irq = dev->irq; + map.dma = dev->dma; + map.port = dev->if_port; + if (nla_put(skb, IFLA_MAP, sizeof(map), &map)) goto nla_put_failure; } diff --git a/net/core/scm.c b/net/core/scm.c index 8a1741b14302..dce0acb929f1 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -87,6 +87,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fplp = fpl; fpl->count = 0; fpl->max = SCM_MAX_FD; + fpl->user = NULL; } fpp = &fpl->fp[fpl->count]; @@ -107,6 +108,10 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) *fpp++ = file; fpl->count++; } + + if (!fpl->user) + fpl->user = get_uid(current_user()); + return num; } @@ -119,6 +124,7 @@ void __scm_destroy(struct scm_cookie *scm) scm->fp = NULL; for (i=fpl->count-1; i>=0; i--) fput(fpl->fp[i]); + free_uid(fpl->user); kfree(fpl); } } @@ -336,6 +342,7 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); new_fpl->max = new_fpl->count; + new_fpl->user = get_uid(fpl->user); } return new_fpl; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 075d2e78c87e..c9793c6c5005 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -79,6 +79,8 @@ struct kmem_cache *skbuff_head_cache __read_mostly; static struct kmem_cache *skbuff_fclone_cache __read_mostly; +int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; +EXPORT_SYMBOL(sysctl_max_skb_frags); /** * skb_panic - private function for out-of-line support @@ -3661,7 +3663,8 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->ee.ee_info = tstype; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; - if (sk->sk_protocol == IPPROTO_TCP) + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) serr->ee.ee_data -= sk->sk_tskey; } @@ -4200,7 +4203,8 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb) return NULL; } - memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + memmove(skb->data - ETH_HLEN, skb->data - skb->mac_len - VLAN_HLEN, + 2 * ETH_ALEN); skb->mac_header += VLAN_HLEN; return skb; } diff --git a/net/core/sock.c b/net/core/sock.c index dc30dc5bb1b8..47fc8bb3b946 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -421,8 +421,6 @@ static void sock_warn_obsolete_bsdism(const char *name) } } -#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) - static void sock_disable_timestamp(struct sock *sk, unsigned long flags) { if (sk->sk_flags & flags) { @@ -861,7 +859,8 @@ set_rcvbuf: if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { - if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_protocol == IPPROTO_TCP && + sk->sk_type == SOCK_STREAM) { if (sk->sk_state != TCP_ESTABLISHED) { ret = -EINVAL; break; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 95b6139d710c..a6beb7b6ae55 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -26,6 +26,7 @@ static int zero = 0; static int one = 1; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; +static int max_skb_frags = MAX_SKB_FRAGS; static int net_msg_warn; /* Unused, but still a sysctl */ @@ -392,6 +393,15 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "max_skb_frags", + .data = &sysctl_max_skb_frags, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &max_skb_frags, + }, { } }; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 30addee2dd03..838f524cf11a 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -48,8 +48,6 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) tw->tw_ipv6only = sk->sk_ipv6only; } #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) @@ -60,6 +58,8 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) timeo = DCCP_TIMEWAIT_LEN; inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &dccp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 754484b3cd0e..2783c538ec19 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -678,6 +678,9 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 03227ffd19ce..76d3bf70c31a 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1036,10 +1036,13 @@ source_ok: if (!fld.daddr) { fld.daddr = fld.saddr; - err = -EADDRNOTAVAIL; if (dev_out) dev_put(dev_out); + err = -EINVAL; dev_out = init_net.loopback_dev; + if (!dev_out->dn_ptr) + goto out; + err = -EADDRNOTAVAIL; dev_hold(dev_out); if (!fld.daddr) { fld.daddr = @@ -1112,6 +1115,8 @@ source_ok: if (dev_out == NULL) goto out; dn_db = rcu_dereference_raw(dev_out->dn_ptr); + if (!dn_db) + goto e_inval; /* Possible improvement - check all devices for local addr */ if (dn_dev_islocal(dev_out, fld.daddr)) { dev_put(dev_out); @@ -1153,6 +1158,8 @@ select_source: dev_put(dev_out); dev_out = init_net.loopback_dev; dev_hold(dev_out); + if (!dev_out->dn_ptr) + goto e_inval; fld.flowidn_oif = dev_out->ifindex; if (res.fi) dn_fib_info_put(res.fi); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a5aa54ea6533..0cc98b135b8f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -259,6 +259,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + sock->state = SS_UNCONNECTED; /* Look for the requested type/protocol pair. */ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 419d23c53ec7..a57056d87a43 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, ASSERT_RTNL(); + if (in_dev->dead) + goto no_promotions; + /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ @@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, fib_del_ifaddr(ifa, ifa1); } +no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; @@ -1839,7 +1843,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 872494e6e6eb..513b6aabc5b7 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -861,7 +861,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (!prim) { - pr_warn("%s: bug: prim == NULL\n", __func__); + /* if the device has been deleted, we don't perform + * address promotion + */ + if (!in_dev->dead) + pr_warn("%s: bug: prim == NULL\n", __func__); return; } if (iprim && iprim != prim) { @@ -876,6 +880,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) subnet = 1; } + if (in_dev->dead) + goto no_promotions; + /* Deletion is more complicated than add. * We should take care of not to delete too much :-) * @@ -951,6 +958,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) } } +no_promotions: if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); if (subnet && ifa->ifa_prefixlen < 31) { diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 34968cd5c146..4b67937692c9 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -24,6 +24,7 @@ struct fou { u16 type; struct udp_offload udp_offloads; struct list_head list; + struct rcu_head rcu; }; #define FOU_F_REMCSUM_NOPARTIAL BIT(0) @@ -421,7 +422,7 @@ static void fou_release(struct fou *fou) list_del(&fou->list); udp_tunnel_sock_release(sock); - kfree(fou); + kfree_rcu(fou, rcu); } static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg) diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a3a697f5ffba..218abf9fb1ed 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -353,9 +353,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 00ec8d5d7e7e..bb96c1c4edd6 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -153,13 +153,15 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, /* * Step 2: Hash TW into tcp ehash chain. * Notes : - * - tw_refcnt is set to 3 because : + * - tw_refcnt is set to 4 because : * - We have one reference from bhash chain. * - We have one reference from ehash chain. + * - We have one reference from timer. + * - One reference for ourself (our caller will release it). * We can use atomic_set() because prior spin_lock()/spin_unlock() * committed into memory all tw fields. */ - atomic_set(&tw->tw_refcnt, 1 + 1 + 1); + atomic_set(&tw->tw_refcnt, 4); inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ @@ -243,7 +245,7 @@ void inet_twsk_deschedule(struct inet_timewait_sock *tw) } EXPORT_SYMBOL(inet_twsk_deschedule); -void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) +void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) { /* timeout := RTO * 3.5 * @@ -271,12 +273,14 @@ void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) */ tw->tw_kill = timeo <= 4*HZ; - if (!mod_timer_pinned(&tw->tw_timer, jiffies + timeo)) { - atomic_inc(&tw->tw_refcnt); + if (!rearm) { + BUG_ON(mod_timer_pinned(&tw->tw_timer, jiffies + timeo)); atomic_inc(&tw->tw_dr->tw_count); + } else { + mod_timer_pending(&tw->tw_timer, jiffies + timeo); } } -EXPORT_SYMBOL_GPL(inet_twsk_schedule); +EXPORT_SYMBOL_GPL(__inet_twsk_schedule); void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c65b93a7b711..51573f8a39bc 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -235,6 +235,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb) * from host network stack. */ features = netif_skb_features(skb); + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); if (IS_ERR_OR_NULL(segs)) { kfree_skb(skb); @@ -893,7 +894,7 @@ static int __ip_append_data(struct sock *sk, if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, maxfraglen, flags); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6ddde89996f4..b6c7bdea4853 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 626d9e56a6bd..35080a708b59 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -652,6 +652,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + dst = tnl_params->daddr; if (dst == 0) { /* NBMA tunnel */ @@ -749,7 +751,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; - memset(IPCB(skb), 0, sizeof(*IPCB(skb))); dst_link_failure(skb); } else tunnel->err_count = 0; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index a61200754f4b..ebf5821caefb 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -354,18 +354,20 @@ unsigned int arpt_do_table(struct sk_buff *skb, } /* All zeroes == unconditional rule. */ -static inline bool unconditional(const struct arpt_arp *arp) +static inline bool unconditional(const struct arpt_entry *e) { static const struct arpt_arp uncond; - return memcmp(arp, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct arpt_entry) && + memcmp(&e->arp, &uncond, sizeof(uncond)) == 0; } /* Figures out from what hook each rule can be called: returns 0 if * there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, - unsigned int valid_hooks, void *entry0) + unsigned int valid_hooks, void *entry0, + unsigned int *offsets) { unsigned int hook; @@ -397,11 +399,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo, |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct arpt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->arp)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -434,6 +435,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo, size = e->next_offset; e = (struct arpt_entry *) (entry0 + pos + size); + if (pos + size >= newinfo->size) + return 0; e->counters.pcnt = pos; pos += size; } else { @@ -453,9 +456,16 @@ static int mark_source_chains(const struct xt_table_info *newinfo, /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); + if (!xt_find_jump_offset(offsets, newpos, + newinfo->number)) + return 0; + e = (struct arpt_entry *) + (entry0 + newpos); } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; + if (newpos >= newinfo->size) + return 0; } e = (struct arpt_entry *) (entry0 + newpos); @@ -469,25 +479,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo, return 1; } -static inline int check_entry(const struct arpt_entry *e, const char *name) -{ - const struct xt_entry_target *t; - - if (!arp_checkentry(&e->arp)) { - duprintf("arp_tables: arp check failed %p %s.\n", e, name); - return -EINVAL; - } - - if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) - return -EINVAL; - - t = arpt_get_target_c(e); - if (e->target_offset + t->u.target_size > e->next_offset) - return -EINVAL; - - return 0; -} - static inline int check_target(struct arpt_entry *e, const char *name) { struct xt_entry_target *t = arpt_get_target(e); @@ -517,10 +508,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size) struct xt_target *target; int ret; - ret = check_entry(e, name); - if (ret) - return ret; - t = arpt_get_target(e); target = xt_request_find_target(NFPROTO_ARP, t->u.user.name, t->u.user.revision); @@ -546,7 +533,7 @@ static bool check_underflow(const struct arpt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->arp)) + if (!unconditional(e)) return false; t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -565,9 +552,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -579,6 +568,14 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, return -EINVAL; } + if (!arp_checkentry(&e->arp)) + return -EINVAL; + + err = xt_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_ARP_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -587,9 +584,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -623,6 +620,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, const struct arpt_replace *repl) { struct arpt_entry *iter; + unsigned int *offsets; unsigned int i; int ret = 0; @@ -636,6 +634,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, } duprintf("translate_table: size %u\n", newinfo->size); + offsets = xt_alloc_entry_offsets(newinfo->number); + if (!offsets) + return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ @@ -646,20 +647,21 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, repl->underflow, repl->valid_hooks); if (ret != 0) - break; + goto out_free; + if (i < repl->num_entries) + offsets[i] = (void *)iter - entry0; ++i; if (strcmp(arpt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret); - if (ret != 0) - return ret; + ret = -EINVAL; if (i != repl->num_entries) { duprintf("translate_table: %u not %u entries\n", i, repl->num_entries); - return -EINVAL; + goto out_free; } /* Check hooks all assigned */ @@ -670,19 +672,20 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, if (newinfo->hook_entry[i] == 0xFFFFFFFF) { duprintf("Invalid hook entry %u %u\n", i, repl->hook_entry[i]); - return -EINVAL; + goto out_free; } if (newinfo->underflow[i] == 0xFFFFFFFF) { duprintf("Invalid underflow %u %u\n", i, repl->underflow[i]); - return -EINVAL; + goto out_free; } } - if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) { - duprintf("Looping hook\n"); - return -ELOOP; + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { + ret = -ELOOP; + goto out_free; } + kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; @@ -709,6 +712,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, } return ret; + out_free: + kvfree(offsets); + return ret; } static void get_counters(const struct xt_table_info *t, @@ -1118,56 +1124,18 @@ static int do_add_counters(struct net *net, const void __user *user, unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; - unsigned int num_counters; - const char *name; - int size; - void *ptmp; struct xt_table *t; const struct xt_table_info *private; int ret = 0; void *loc_cpu_entry; struct arpt_entry *iter; unsigned int addend; -#ifdef CONFIG_COMPAT - struct compat_xt_counters_info compat_tmp; - - if (compat) { - ptmp = &compat_tmp; - size = sizeof(struct compat_xt_counters_info); - } else -#endif - { - ptmp = &tmp; - size = sizeof(struct xt_counters_info); - } - if (copy_from_user(ptmp, user, size) != 0) - return -EFAULT; - -#ifdef CONFIG_COMPAT - if (compat) { - num_counters = compat_tmp.num_counters; - name = compat_tmp.name; - } else -#endif - { - num_counters = tmp.num_counters; - name = tmp.name; - } + paddc = xt_copy_counters_from_user(user, len, &tmp, compat); + if (IS_ERR(paddc)) + return PTR_ERR(paddc); - if (len != size + num_counters * sizeof(struct xt_counters)) - return -EINVAL; - - paddc = vmalloc(len - size); - if (!paddc) - return -ENOMEM; - - if (copy_from_user(paddc, user + size, len - size) != 0) { - ret = -EFAULT; - goto free; - } - - t = xt_find_table_lock(net, NFPROTO_ARP, name); + t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name); if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; @@ -1175,7 +1143,7 @@ static int do_add_counters(struct net *net, const void __user *user, local_bh_disable(); private = t->private; - if (private->number != num_counters) { + if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } @@ -1201,6 +1169,18 @@ static int do_add_counters(struct net *net, const void __user *user, } #ifdef CONFIG_COMPAT +struct compat_arpt_replace { + char name[XT_TABLE_MAXNAMELEN]; + u32 valid_hooks; + u32 num_entries; + u32 size; + u32 hook_entry[NF_ARP_NUMHOOKS]; + u32 underflow[NF_ARP_NUMHOOKS]; + u32 num_counters; + compat_uptr_t counters; + struct compat_arpt_entry entries[0]; +}; + static inline void compat_release_entry(struct compat_arpt_entry *e) { struct xt_entry_target *t; @@ -1209,24 +1189,22 @@ static inline void compat_release_entry(struct compat_arpt_entry *e) module_put(t->u.kernel.target->me); } -static inline int +static int check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, - const unsigned char *limit, - const unsigned int *hook_entries, - const unsigned int *underflows, - const char *name) + const unsigned char *limit) { struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; - int ret, off, h; + int ret, off; duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1238,8 +1216,11 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, return -EINVAL; } - /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct arpt_entry *)e, name); + if (!arp_checkentry(&e->arp)) + return -EINVAL; + + ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); if (ret) return ret; @@ -1263,17 +1244,6 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, if (ret) goto release_target; - /* Check hooks & underflows */ - for (h = 0; h < NF_ARP_NUMHOOKS; h++) { - if ((unsigned char *)e - base == hook_entries[h]) - newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) - newinfo->underflow[h] = underflows[h]; - } - - /* Clear counters and comefrom */ - memset(&e->counters, 0, sizeof(e->counters)); - e->comefrom = 0; return 0; release_target: @@ -1282,18 +1252,17 @@ out: return ret; } -static int +static void compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, - unsigned int *size, const char *name, + unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct xt_target *target; struct arpt_entry *de; unsigned int origsize; - int ret, h; + int h; - ret = 0; origsize = *size; de = (struct arpt_entry *)*dstptr; memcpy(de, e, sizeof(struct arpt_entry)); @@ -1314,144 +1283,81 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } - return ret; } -static int translate_compat_table(const char *name, - unsigned int valid_hooks, - struct xt_table_info **pinfo, +static int translate_compat_table(struct xt_table_info **pinfo, void **pentry0, - unsigned int total_size, - unsigned int number, - unsigned int *hook_entries, - unsigned int *underflows) + const struct compat_arpt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_arpt_entry *iter0; - struct arpt_entry *iter1; + struct arpt_replace repl; unsigned int size; int ret = 0; info = *pinfo; entry0 = *pentry0; - size = total_size; - info->number = number; - - /* Init all hooks to impossible value. */ - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - info->hook_entry[i] = 0xFFFFFFFF; - info->underflow[i] = 0xFFFFFFFF; - } + size = compatr->size; + info->number = compatr->num_entries; duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(NFPROTO_ARP); - xt_compat_init_offsets(NFPROTO_ARP, number); + xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries); /* Walk through entries, checking offsets. */ - xt_entry_foreach(iter0, entry0, total_size) { + xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, - entry0 + total_size, - hook_entries, - underflows, - name); + entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; - if (j != number) { + if (j != compatr->num_entries) { duprintf("translate_compat_table: %u not %u entries\n", - j, number); + j, compatr->num_entries); goto out_unlock; } - /* Check hooks all assigned */ - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - /* Only hooks which are valid */ - if (!(valid_hooks & (1 << i))) - continue; - if (info->hook_entry[i] == 0xFFFFFFFF) { - duprintf("Invalid hook entry %u %u\n", - i, hook_entries[i]); - goto out_unlock; - } - if (info->underflow[i] == 0xFFFFFFFF) { - duprintf("Invalid underflow %u %u\n", - i, underflows[i]); - goto out_unlock; - } - } - ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; - newinfo->number = number; + newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = info->hook_entry[i]; newinfo->underflow[i] = info->underflow[i]; } entry1 = newinfo->entries[raw_smp_processor_id()]; pos = entry1; - size = total_size; - xt_entry_foreach(iter0, entry0, total_size) { - ret = compat_copy_entry_from_user(iter0, &pos, &size, - name, newinfo, entry1); - if (ret != 0) - break; - } + size = compatr->size; + xt_entry_foreach(iter0, entry0, compatr->size) + compat_copy_entry_from_user(iter0, &pos, &size, + newinfo, entry1); + + /* all module references in entry0 are now gone */ + xt_compat_flush_offsets(NFPROTO_ARP); xt_compat_unlock(NFPROTO_ARP); - if (ret) - goto free_newinfo; - ret = -ELOOP; - if (!mark_source_chains(newinfo, valid_hooks, entry1)) - goto free_newinfo; + memcpy(&repl, compatr, sizeof(*compatr)); - i = 0; - xt_entry_foreach(iter1, entry1, newinfo->size) { - ret = check_target(iter1, name); - if (ret != 0) - break; - ++i; - if (strcmp(arpt_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; - } - if (ret) { - /* - * The first i matches need cleanup_entry (calls ->destroy) - * because they had called ->check already. The other j-i - * entries need only release. - */ - int skip = i; - j -= i; - xt_entry_foreach(iter0, entry0, newinfo->size) { - if (skip-- > 0) - continue; - if (j-- == 0) - break; - compat_release_entry(iter0); - } - xt_entry_foreach(iter1, entry1, newinfo->size) { - if (i-- == 0) - break; - cleanup_entry(iter1); - } - xt_free_table_info(newinfo); - return ret; + for (i = 0; i < NF_ARP_NUMHOOKS; i++) { + repl.hook_entry[i] = newinfo->hook_entry[i]; + repl.underflow[i] = newinfo->underflow[i]; } - /* And one copy for every other CPU */ - for_each_possible_cpu(i) - if (newinfo->entries[i] && newinfo->entries[i] != entry1) - memcpy(newinfo->entries[i], entry1, newinfo->size); + repl.num_counters = 0; + repl.counters = NULL; + repl.size = newinfo->size; + ret = translate_table(newinfo, entry1, &repl); + if (ret) + goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; @@ -1460,31 +1366,18 @@ static int translate_compat_table(const char *name, free_newinfo: xt_free_table_info(newinfo); -out: - xt_entry_foreach(iter0, entry0, total_size) { + return ret; +out_unlock: + xt_compat_flush_offsets(NFPROTO_ARP); + xt_compat_unlock(NFPROTO_ARP); + xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; -out_unlock: - xt_compat_flush_offsets(NFPROTO_ARP); - xt_compat_unlock(NFPROTO_ARP); - goto out; } -struct compat_arpt_replace { - char name[XT_TABLE_MAXNAMELEN]; - u32 valid_hooks; - u32 num_entries; - u32 size; - u32 hook_entry[NF_ARP_NUMHOOKS]; - u32 underflow[NF_ARP_NUMHOOKS]; - u32 num_counters; - compat_uptr_t counters; - struct compat_arpt_entry entries[0]; -}; - static int compat_do_replace(struct net *net, void __user *user, unsigned int len) { @@ -1518,10 +1411,7 @@ static int compat_do_replace(struct net *net, void __user *user, goto free_newinfo; } - ret = translate_compat_table(tmp.name, tmp.valid_hooks, - &newinfo, &loc_cpu_entry, tmp.size, - tmp.num_entries, tmp.hook_entry, - tmp.underflow); + ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2d0e265fef6e..8e729cba1e59 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline bool unconditional(const struct ipt_ip *ip) +static inline bool unconditional(const struct ipt_entry *e) { static const struct ipt_ip uncond; - return memcmp(ip, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct ipt_entry) && + memcmp(&e->ip, &uncond, sizeof(uncond)) == 0; #undef FWINV } @@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ipt_entry) && + if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && - t->verdict < 0 && - unconditional(&s->ip)) { + t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] @@ -442,7 +442,8 @@ ipt_do_table(struct sk_buff *skb, there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, - unsigned int valid_hooks, void *entry0) + unsigned int valid_hooks, void *entry0, + unsigned int *offsets) { unsigned int hook; @@ -471,11 +472,10 @@ mark_source_chains(const struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ipt_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && unconditional(&e->ip)) || - visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -516,6 +516,8 @@ mark_source_chains(const struct xt_table_info *newinfo, size = e->next_offset; e = (struct ipt_entry *) (entry0 + pos + size); + if (pos + size >= newinfo->size) + return 0; e->counters.pcnt = pos; pos += size; } else { @@ -534,9 +536,16 @@ mark_source_chains(const struct xt_table_info *newinfo, /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); + if (!xt_find_jump_offset(offsets, newpos, + newinfo->number)) + return 0; + e = (struct ipt_entry *) + (entry0 + newpos); } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; + if (newpos >= newinfo->size) + return 0; } e = (struct ipt_entry *) (entry0 + newpos); @@ -564,27 +573,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net) } static int -check_entry(const struct ipt_entry *e, const char *name) -{ - const struct xt_entry_target *t; - - if (!ip_checkentry(&e->ip)) { - duprintf("ip check failed %p %s.\n", e, name); - return -EINVAL; - } - - if (e->target_offset + sizeof(struct xt_entry_target) > - e->next_offset) - return -EINVAL; - - t = ipt_get_target_c(e); - if (e->target_offset + t->u.target_size > e->next_offset) - return -EINVAL; - - return 0; -} - -static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ipt_ip *ip = par->entryinfo; @@ -661,10 +649,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; - ret = check_entry(e, name); - if (ret) - return ret; - j = 0; mtpar.net = net; mtpar.table = name; @@ -708,7 +692,7 @@ static bool check_underflow(const struct ipt_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->ip)) + if (!unconditional(e)) return false; t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -728,9 +712,11 @@ check_entry_size_and_hooks(struct ipt_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -742,6 +728,14 @@ check_entry_size_and_hooks(struct ipt_entry *e, return -EINVAL; } + if (!ip_checkentry(&e->ip)) + return -EINVAL; + + err = xt_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -750,9 +744,9 @@ check_entry_size_and_hooks(struct ipt_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -793,6 +787,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ipt_replace *repl) { struct ipt_entry *iter; + unsigned int *offsets; unsigned int i; int ret = 0; @@ -806,6 +801,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, } duprintf("translate_table: size %u\n", newinfo->size); + offsets = xt_alloc_entry_offsets(newinfo->number); + if (!offsets) + return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { @@ -815,17 +813,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, repl->underflow, repl->valid_hooks); if (ret != 0) - return ret; + goto out_free; + if (i < repl->num_entries) + offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ipt_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } + ret = -EINVAL; if (i != repl->num_entries) { duprintf("translate_table: %u not %u entries\n", i, repl->num_entries); - return -EINVAL; + goto out_free; } /* Check hooks all assigned */ @@ -836,17 +837,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (newinfo->hook_entry[i] == 0xFFFFFFFF) { duprintf("Invalid hook entry %u %u\n", i, repl->hook_entry[i]); - return -EINVAL; + goto out_free; } if (newinfo->underflow[i] == 0xFFFFFFFF) { duprintf("Invalid underflow %u %u\n", i, repl->underflow[i]); - return -EINVAL; + goto out_free; } } - if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) - return -ELOOP; + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { + ret = -ELOOP; + goto out_free; + } + kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; @@ -873,6 +877,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, } return ret; + out_free: + kvfree(offsets); + return ret; } static void @@ -1306,56 +1313,18 @@ do_add_counters(struct net *net, const void __user *user, unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; - unsigned int num_counters; - const char *name; - int size; - void *ptmp; struct xt_table *t; const struct xt_table_info *private; int ret = 0; void *loc_cpu_entry; struct ipt_entry *iter; unsigned int addend; -#ifdef CONFIG_COMPAT - struct compat_xt_counters_info compat_tmp; - - if (compat) { - ptmp = &compat_tmp; - size = sizeof(struct compat_xt_counters_info); - } else -#endif - { - ptmp = &tmp; - size = sizeof(struct xt_counters_info); - } - if (copy_from_user(ptmp, user, size) != 0) - return -EFAULT; + paddc = xt_copy_counters_from_user(user, len, &tmp, compat); + if (IS_ERR(paddc)) + return PTR_ERR(paddc); -#ifdef CONFIG_COMPAT - if (compat) { - num_counters = compat_tmp.num_counters; - name = compat_tmp.name; - } else -#endif - { - num_counters = tmp.num_counters; - name = tmp.name; - } - - if (len != size + num_counters * sizeof(struct xt_counters)) - return -EINVAL; - - paddc = vmalloc(len - size); - if (!paddc) - return -ENOMEM; - - if (copy_from_user(paddc, user + size, len - size) != 0) { - ret = -EFAULT; - goto free; - } - - t = xt_find_table_lock(net, AF_INET, name); + t = xt_find_table_lock(net, AF_INET, tmp.name); if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; @@ -1363,7 +1332,7 @@ do_add_counters(struct net *net, const void __user *user, local_bh_disable(); private = t->private; - if (private->number != num_counters) { + if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } @@ -1442,7 +1411,6 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, static int compat_find_calc_match(struct xt_entry_match *m, - const char *name, const struct ipt_ip *ip, unsigned int hookmask, int *size) @@ -1478,21 +1446,19 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, - const unsigned char *limit, - const unsigned int *hook_entries, - const unsigned int *underflows, - const char *name) + const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; - int ret, off, h; + int ret, off; duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1504,8 +1470,11 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, return -EINVAL; } - /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct ipt_entry *)e, name); + if (!ip_checkentry(&e->ip)) + return -EINVAL; + + ret = xt_compat_check_entry_offsets(e, e->elems, + e->target_offset, e->next_offset); if (ret) return ret; @@ -1513,8 +1482,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { - ret = compat_find_calc_match(ematch, name, - &e->ip, e->comefrom, &off); + ret = compat_find_calc_match(ematch, &e->ip, e->comefrom, + &off); if (ret != 0) goto release_matches; ++j; @@ -1537,17 +1506,6 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, if (ret) goto out; - /* Check hooks & underflows */ - for (h = 0; h < NF_INET_NUMHOOKS; h++) { - if ((unsigned char *)e - base == hook_entries[h]) - newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) - newinfo->underflow[h] = underflows[h]; - } - - /* Clear counters and comefrom */ - memset(&e->counters, 0, sizeof(e->counters)); - e->comefrom = 0; return 0; out: @@ -1561,19 +1519,18 @@ release_matches: return ret; } -static int +static void compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, - unsigned int *size, const char *name, + unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct xt_target *target; struct ipt_entry *de; unsigned int origsize; - int ret, h; + int h; struct xt_entry_match *ematch; - ret = 0; origsize = *size; de = (struct ipt_entry *)*dstptr; memcpy(de, e, sizeof(struct ipt_entry)); @@ -1582,198 +1539,104 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, *dstptr += sizeof(struct ipt_entry); *size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry); - xt_ematch_foreach(ematch, e) { - ret = xt_compat_match_from_user(ematch, dstptr, size); - if (ret != 0) - return ret; - } + xt_ematch_foreach(ematch, e) + xt_compat_match_from_user(ematch, dstptr, size); + de->target_offset = e->target_offset - (origsize - *size); t = compat_ipt_get_target(e); target = t->u.kernel.target; xt_compat_target_from_user(t, dstptr, size); de->next_offset = e->next_offset - (origsize - *size); + for (h = 0; h < NF_INET_NUMHOOKS; h++) { if ((unsigned char *)de - base < newinfo->hook_entry[h]) newinfo->hook_entry[h] -= origsize - *size; if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } - return ret; -} - -static int -compat_check_entry(struct ipt_entry *e, struct net *net, const char *name) -{ - struct xt_entry_match *ematch; - struct xt_mtchk_param mtpar; - unsigned int j; - int ret = 0; - - j = 0; - mtpar.net = net; - mtpar.table = name; - mtpar.entryinfo = &e->ip; - mtpar.hook_mask = e->comefrom; - mtpar.family = NFPROTO_IPV4; - xt_ematch_foreach(ematch, e) { - ret = check_match(ematch, &mtpar); - if (ret != 0) - goto cleanup_matches; - ++j; - } - - ret = check_target(e, net, name); - if (ret) - goto cleanup_matches; - return 0; - - cleanup_matches: - xt_ematch_foreach(ematch, e) { - if (j-- == 0) - break; - cleanup_match(ematch, net); - } - return ret; } static int translate_compat_table(struct net *net, - const char *name, - unsigned int valid_hooks, struct xt_table_info **pinfo, void **pentry0, - unsigned int total_size, - unsigned int number, - unsigned int *hook_entries, - unsigned int *underflows) + const struct compat_ipt_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ipt_entry *iter0; - struct ipt_entry *iter1; + struct ipt_replace repl; unsigned int size; int ret; info = *pinfo; entry0 = *pentry0; - size = total_size; - info->number = number; - - /* Init all hooks to impossible value. */ - for (i = 0; i < NF_INET_NUMHOOKS; i++) { - info->hook_entry[i] = 0xFFFFFFFF; - info->underflow[i] = 0xFFFFFFFF; - } + size = compatr->size; + info->number = compatr->num_entries; duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET); - xt_compat_init_offsets(AF_INET, number); + xt_compat_init_offsets(AF_INET, compatr->num_entries); /* Walk through entries, checking offsets. */ - xt_entry_foreach(iter0, entry0, total_size) { + xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, - entry0 + total_size, - hook_entries, - underflows, - name); + entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; - if (j != number) { + if (j != compatr->num_entries) { duprintf("translate_compat_table: %u not %u entries\n", - j, number); + j, compatr->num_entries); goto out_unlock; } - /* Check hooks all assigned */ - for (i = 0; i < NF_INET_NUMHOOKS; i++) { - /* Only hooks which are valid */ - if (!(valid_hooks & (1 << i))) - continue; - if (info->hook_entry[i] == 0xFFFFFFFF) { - duprintf("Invalid hook entry %u %u\n", - i, hook_entries[i]); - goto out_unlock; - } - if (info->underflow[i] == 0xFFFFFFFF) { - duprintf("Invalid underflow %u %u\n", - i, underflows[i]); - goto out_unlock; - } - } - ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; - newinfo->number = number; + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries[raw_smp_processor_id()]; pos = entry1; - size = total_size; - xt_entry_foreach(iter0, entry0, total_size) { - ret = compat_copy_entry_from_user(iter0, &pos, &size, - name, newinfo, entry1); - if (ret != 0) - break; - } + size = compatr->size; + xt_entry_foreach(iter0, entry0, compatr->size) + compat_copy_entry_from_user(iter0, &pos, &size, + newinfo, entry1); + + /* all module references in entry0 are now gone. + * entry1/newinfo contains a 64bit ruleset that looks exactly as + * generated by 64bit userspace. + * + * Call standard translate_table() to validate all hook_entrys, + * underflows, check for loops, etc. + */ xt_compat_flush_offsets(AF_INET); xt_compat_unlock(AF_INET); - if (ret) - goto free_newinfo; - ret = -ELOOP; - if (!mark_source_chains(newinfo, valid_hooks, entry1)) - goto free_newinfo; + memcpy(&repl, compatr, sizeof(*compatr)); - i = 0; - xt_entry_foreach(iter1, entry1, newinfo->size) { - ret = compat_check_entry(iter1, net, name); - if (ret != 0) - break; - ++i; - if (strcmp(ipt_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; - } - if (ret) { - /* - * The first i matches need cleanup_entry (calls ->destroy) - * because they had called ->check already. The other j-i - * entries need only release. - */ - int skip = i; - j -= i; - xt_entry_foreach(iter0, entry0, newinfo->size) { - if (skip-- > 0) - continue; - if (j-- == 0) - break; - compat_release_entry(iter0); - } - xt_entry_foreach(iter1, entry1, newinfo->size) { - if (i-- == 0) - break; - cleanup_entry(iter1, net); - } - xt_free_table_info(newinfo); - return ret; + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + repl.hook_entry[i] = newinfo->hook_entry[i]; + repl.underflow[i] = newinfo->underflow[i]; } - /* And one copy for every other CPU */ - for_each_possible_cpu(i) - if (newinfo->entries[i] && newinfo->entries[i] != entry1) - memcpy(newinfo->entries[i], entry1, newinfo->size); + repl.num_counters = 0; + repl.counters = NULL; + repl.size = newinfo->size; + ret = translate_table(net, newinfo, entry1, &repl); + if (ret) + goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; @@ -1782,17 +1645,16 @@ translate_compat_table(struct net *net, free_newinfo: xt_free_table_info(newinfo); -out: - xt_entry_foreach(iter0, entry0, total_size) { + return ret; +out_unlock: + xt_compat_flush_offsets(AF_INET); + xt_compat_unlock(AF_INET); + xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; -out_unlock: - xt_compat_flush_offsets(AF_INET); - xt_compat_unlock(AF_INET); - goto out; } static int @@ -1829,10 +1691,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_compat_table(net, tmp.name, tmp.valid_hooks, - &newinfo, &loc_cpu_entry, tmp.size, - tmp.num_entries, tmp.hook_entry, - tmp.underflow); + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index c6eb42100e9a..ea91058b5f6f 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev; + struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev; struct netdev_notifier_info info; - netdev_notifier_info_init(&info, dev); + /* The masq_dev_notifier will catch the case of the device going + * down. So if the inetdev is dead and being destroyed we have + * no work to do. Otherwise this is an individual address removal + * and we have to perform the flush. + */ + if (idev->dead) + return NOTIFY_DONE; + + netdev_notifier_info_init(&info, idev->dev); return masq_device_event(this, event, &info); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05ff44b758df..f6ee0d561aab 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -745,8 +745,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 561cd4b8fc6e..c77aac75759d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -543,8 +543,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); goto out; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f45f2a12f37b..eb1d9839a257 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -125,6 +125,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ @@ -753,7 +754,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, 0); + 0, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1538,6 +1539,36 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1592,11 +1623,20 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) + if (fnhe) { rth = rcu_dereference(fnhe->fnhe_rth_input); - else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(&FIB_RES_NH(*res), daddr); + fnhe = NULL; + } else { + goto rt_cache; + } + } + + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); +rt_cache: if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -1936,6 +1976,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res, */ if (fi && res->prefixlen < 4) fi = NULL; + } else if ((type == RTN_LOCAL) && (orig_oif != 0) && + (orig_oif != dev_out->ifindex)) { + /* For local routes that require a particular output interface + * we do not want to cache the result. Caching the result + * causes incorrect behaviour when there are multiple source + * addresses on the interface, the end result being that if the + * intended recipient is waiting on that interface for the + * packet he won't receive it because it will be delivered on + * the loopback interface and the IP_PKTINFO ipi_ifindex will + * be set to the loopback interface as well. + */ + fi = NULL; } fnhe = NULL; @@ -1945,19 +1997,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); - if (fnhe) + if (fnhe) { prth = &fnhe->fnhe_rth_output; - else { - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; + rth = rcu_dereference(*prth); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(nh, fl4->daddr); + fnhe = NULL; + } else { + goto rt_cache; } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } + + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); + +rt_cache: if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; @@ -2504,7 +2566,6 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bb2ce74f6004..19d385a0f02d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <asm/uaccess.h> #include <asm/ioctls.h> +#include <asm/unaligned.h> #include <net/busy_poll.h> int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; @@ -921,7 +922,7 @@ new_segment: i = skb_shinfo(skb)->nr_frags; can_coalesce = skb_can_coalesce(skb, i, page, offset); - if (!can_coalesce && i >= MAX_SKB_FRAGS) { + if (!can_coalesce && i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1187,7 +1188,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i == MAX_SKB_FRAGS || !sg) { + if (i == sysctl_max_skb_frags || !sg) { tcp_mark_push(tp, skb); goto new_segment; } @@ -2603,6 +2604,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; unsigned int start; + u64 rate64; u32 rate; memset(info, 0, sizeof(*info)); @@ -2665,15 +2667,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_retrans = tp->total_retrans; rate = READ_ONCE(sk->sk_pacing_rate); - info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_pacing_rate); rate = READ_ONCE(sk->sk_max_pacing_rate); - info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + rate64 = rate != ~0U ? rate : ~0ULL; + put_unaligned(rate64, &info->tcpi_max_pacing_rate); do { start = u64_stats_fetch_begin_irq(&tp->syncp); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; + put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked); + put_unaligned(tp->bytes_received, &info->tcpi_bytes_received); } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 06d3d665a9fd..3ce0b861cc0e 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -151,6 +151,27 @@ static void bictcp_init(struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } +static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) +{ + if (event == CA_EVENT_TX_START) { + struct bictcp *ca = inet_csk_ca(sk); + u32 now = tcp_time_stamp; + s32 delta; + + delta = now - tcp_sk(sk)->lsndtime; + + /* We were application limited (idle) for a while. + * Shift epoch_start to keep cwnd growth to cubic curve. + */ + if (ca->epoch_start && delta > 0) { + ca->epoch_start += delta; + if (after(ca->epoch_start, now)) + ca->epoch_start = now; + } + return; + } +} + /* calculate the cubic root of x using a table lookup followed by one * Newton-Raphson iteration. * Avg err ~= 0.195% @@ -450,6 +471,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, .undo_cwnd = bictcp_undo_cwnd, + .cwnd_event = bictcp_cwnd_event, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "cubic", diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 87463c814896..36b93adfd7da 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -89,7 +89,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); /* rfc5961 challenge ack rate limiting */ -int sysctl_tcp_challenge_ack_limit = 100; +int sysctl_tcp_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; @@ -3343,6 +3343,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, + u32 *last_oow_ack_time) +{ + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS @@ -3356,21 +3373,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; + return false; -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ + return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ @@ -3380,21 +3385,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); - u32 now; + u32 count, now; /* First check our per-socket dupack rate limit. */ - if (tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) + if (__tcp_oow_rate_limited(sock_net(sk), + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) return; - /* Then check the check host-wide RFC 5961 rate limit. */ + /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { + u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + challenge_timestamp = now; - challenge_count = 0; + WRITE_ONCE(challenge_count, half + + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + count = READ_ONCE(challenge_count); + if (count > 0) { + WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 88203e755af8..13b92d595138 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -705,7 +705,8 @@ release_sk1: outside socket context is ugly, certainly. What can I do? */ -static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, +static void tcp_v4_send_ack(struct net *net, + struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) @@ -720,7 +721,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack, ]; } rep; struct ip_reply_arg arg; - struct net *net = dev_net(skb_dst(skb)->dev); memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -782,7 +782,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); - tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, + tcp_v4_send_ack(sock_net(sk), skb, + tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, @@ -801,8 +802,10 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? - tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : + tcp_sk(sk)->snd_nxt; + + tcp_v4_send_ack(sock_net(sk), skb, seq, tcp_rsk(req)->rcv_nxt, req->rcv_wnd, tcp_time_stamp, req->ts_recent, @@ -1509,7 +1512,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) if (likely(sk->sk_rx_dst)) skb_dst_drop(skb); else - skb_dst_force(skb); + skb_dst_force_safe(skb); __skb_queue_tail(&tp->ucopy.prequeue, skb); tp->ucopy.memory += skb->truesize; @@ -1714,8 +1717,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { - dst_hold(dst); + if (dst && dst_hold_safe(dst)) { sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index a51d63a43e33..9c840c5c6047 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -566,7 +566,7 @@ reset: */ if (crtt > tp->srtt_us) { /* Set RTO like tcp_rtt_estimator(), but from cached RTT. */ - crtt /= 8 * USEC_PER_MSEC; + crtt /= 8 * USEC_PER_SEC / HZ; inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk)); } else if (tp->srtt_us == 0) { /* RFC6298: 5.7 We've failed to get a valid RTT sample from diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 17e7339ee5ca..fec2907b85e8 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -163,9 +163,9 @@ kill_with_rst: if (tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp && tcp_tw_remember_stamp(tw)) - inet_twsk_schedule(tw, tw->tw_timeout); + inet_twsk_reschedule(tw, tw->tw_timeout); else - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return TCP_TW_ACK; } @@ -203,7 +203,7 @@ kill: return TCP_TW_SUCCESS; } } - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; @@ -253,7 +253,7 @@ kill: * Do not reschedule in the last case. */ if (paws_reject || th->ack) - inet_twsk_schedule(tw, TCP_TIMEWAIT_LEN); + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); return tcp_timewait_check_oow_rate_limit( tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT); @@ -324,9 +324,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } while (0); #endif - /* Linkage updates. */ - __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); - /* Get the TIME_WAIT timeout firing. */ if (timeo < rto) timeo = rto; @@ -340,6 +337,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) } inet_twsk_schedule(tw, timeo); + /* Linkage updates. */ + __inet_twsk_hashdance(tw, sk, &tcp_hashinfo); inet_twsk_put(tw); } else { /* Sorry, if we're out of memory, just CLOSE this diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 986440b24978..ae66c8426ad0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2627,8 +2627,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || skb_headroom(skb) >= 0xFFFF)) { - struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, - GFP_ATOMIC); + struct sk_buff *nskb; + + skb_mstamp_get(&skb->skb_mstamp); + nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; } else { @@ -3143,7 +3145,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; - int syn_loss = 0, space, err = 0, copied; + int syn_loss = 0, space, err = 0; unsigned long last_syn_loss = 0; struct sk_buff *syn_data; @@ -3181,17 +3183,18 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); - copied = copy_from_iter(skb_put(syn_data, space), space, - &fo->data->msg_iter); - if (unlikely(!copied)) { - kfree_skb(syn_data); - goto fallback; - } - if (copied != space) { - skb_trim(syn_data, copied); - space = copied; + if (space) { + int copied = copy_from_iter(skb_put(syn_data, space), space, + &fo->data->msg_iter); + if (unlikely(!copied)) { + kfree_skb(syn_data); + goto fallback; + } + if (copied != space) { + skb_trim(syn_data, copied); + space = copied; + } } - /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 17d35662930d..3e6a472e6b88 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) yeah->fast_count = 0; yeah->reno_count = max(yeah->reno_count>>1, 2U); - return tp->snd_cwnd - reduction; + return max_t(int, tp->snd_cwnd - reduction, 2); } static struct tcp_congestion_ops tcp_yeah __read_mostly = { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b8c5ba7d5f7..031752efe1ab 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -963,8 +963,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, sk->sk_family == AF_INET6); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; connected = 0; @@ -1977,10 +1979,14 @@ void udp_v4_early_demux(struct sk_buff *skb) if (!in_dev) return; - ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, - iph->protocol); - if (!ours) - return; + /* we are supposed to accept bcast packets */ + if (skb->pkt_type == PACKET_MULTICAST) { + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return; + } + sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, uh->source, iph->saddr, dif); } else if (skb->pkt_type == PACKET_HOST) { diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 6bb98cc193c9..7b534ac04056 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -90,6 +90,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb, uh->source = src_port; uh->len = htons(skb->len); + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + udp_set_csum(nocheck, skb, src, dst, skb->len); return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index bff69746e05f..78526087126d 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -230,7 +230,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xfrm_dst_ifdown(dst, dev); } -static struct dst_ops xfrm4_dst_ops = { +static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, @@ -244,7 +244,7 @@ static struct dst_ops xfrm4_dst_ops = { static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .family = AF_INET, - .dst_ops = &xfrm4_dst_ops, + .dst_ops = &xfrm4_dst_ops_template, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, .decode_session = _decode_session4, @@ -266,7 +266,7 @@ static struct ctl_table xfrm4_policy_table[] = { { } }; -static int __net_init xfrm4_net_init(struct net *net) +static int __net_init xfrm4_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -294,7 +294,7 @@ err_alloc: return -ENOMEM; } -static void __net_exit xfrm4_net_exit(struct net *net) +static void __net_exit xfrm4_net_sysctl_exit(struct net *net) { struct ctl_table *table; @@ -306,12 +306,44 @@ static void __net_exit xfrm4_net_exit(struct net *net) if (!net_eq(net, &init_net)) kfree(table); } +#else /* CONFIG_SYSCTL */ +static int inline xfrm4_net_sysctl_init(struct net *net) +{ + return 0; +} + +static void inline xfrm4_net_sysctl_exit(struct net *net) +{ +} +#endif + +static int __net_init xfrm4_net_init(struct net *net) +{ + int ret; + + memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, + sizeof(xfrm4_dst_ops_template)); + ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); + if (ret) + return ret; + + ret = xfrm4_net_sysctl_init(net); + if (ret) + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); + + return ret; +} + +static void __net_exit xfrm4_net_exit(struct net *net) +{ + xfrm4_net_sysctl_exit(net); + dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); +} static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, }; -#endif static void __init xfrm4_policy_init(void) { @@ -320,13 +352,9 @@ static void __init xfrm4_policy_init(void) void __init xfrm4_init(void) { - dst_entries_init(&xfrm4_dst_ops); - xfrm4_state_init(); xfrm4_policy_init(); xfrm4_protocol_init(); -#ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm4_net_ops); -#endif } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index fd3aa6148dd1..f555f4fc1d62 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -195,6 +195,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -236,6 +237,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .max_addresses = IPV6_MAX_ADDRESSES, .accept_ra_defrtr = 1, .accept_ra_from_local = 0, + .accept_ra_min_hop_limit= 1, .accept_ra_pinfo = 1, #ifdef CONFIG_IPV6_ROUTER_PREF .accept_ra_rtr_pref = 1, @@ -343,6 +345,12 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev) setup_timer(&ndev->rs_timer, addrconf_rs_timer, (unsigned long)ndev); memcpy(&ndev->cnf, dev_net(dev)->ipv6.devconf_dflt, sizeof(ndev->cnf)); + + if (ndev->cnf.stable_secret.initialized) + ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY; + else + ndev->addr_gen_mode = IN6_ADDR_GEN_MODE_EUI64; + ndev->cnf.mtu6 = dev->mtu; ndev->cnf.sysctl = NULL; ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl); @@ -561,7 +569,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; @@ -2384,7 +2392,7 @@ ok: #ifdef CONFIG_IPV6_OPTIMISTIC_DAD if (in6_dev->cnf.optimistic_dad && !net->ipv6.devconf_all->forwarding && sllao) - addr_flags = IFA_F_OPTIMISTIC; + addr_flags |= IFA_F_OPTIMISTIC; #endif /* Do not allow to create too much of autoconfigured @@ -3415,6 +3423,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) { struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; + bool notify = false; addrconf_join_solict(dev, &ifp->addr); @@ -3460,7 +3469,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ - ipv6_ifa_notify(RTM_NEWADDR, ifp); + notify = true; } } @@ -3468,6 +3477,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) out: spin_unlock(&ifp->lock); read_unlock_bh(&idev->lock); + if (notify) + ipv6_ifa_notify(RTM_NEWADDR, ifp); } static void addrconf_dad_start(struct inet6_ifaddr *ifp) @@ -4559,6 +4570,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_MAX_DESYNC_FACTOR] = cnf->max_desync_factor; array[DEVCONF_MAX_ADDRESSES] = cnf->max_addresses; array[DEVCONF_ACCEPT_RA_DEFRTR] = cnf->accept_ra_defrtr; + array[DEVCONF_ACCEPT_RA_MIN_HOP_LIMIT] = cnf->accept_ra_min_hop_limit; array[DEVCONF_ACCEPT_RA_PINFO] = cnf->accept_ra_pinfo; #ifdef CONFIG_IPV6_ROUTER_PREF array[DEVCONF_ACCEPT_RA_RTR_PREF] = cnf->accept_ra_rtr_pref; @@ -5261,13 +5273,10 @@ static int addrconf_sysctl_stable_secret(struct ctl_table *ctl, int write, goto out; } - if (!write) { - err = snprintf(str, sizeof(str), "%pI6", - &secret->secret); - if (err >= sizeof(str)) { - err = -EIO; - goto out; - } + err = snprintf(str, sizeof(str), "%pI6", &secret->secret); + if (err >= sizeof(str)) { + err = -EIO; + goto out; } err = proc_dostring(&lctl, write, buffer, lenp, ppos); @@ -5455,6 +5464,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "accept_ra_min_hop_limit", + .data = &ipv6_devconf.accept_ra_min_hop_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "accept_ra_pinfo", .data = &ipv6_devconf.accept_ra_pinfo, .maxlen = sizeof(int), diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 882124ebb438..a8f6986dcbe5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -552,7 +552,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh) rcu_read_lock(); p = __ipv6_addr_label(net, addr, ipv6_addr_type(addr), ifal->ifal_index); - if (p && ip6addrlbl_hold(p)) + if (p && !ip6addrlbl_hold(p)) p = NULL; lseq = ip6addrlbl_table.seq; rcu_read_unlock(); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2d044d2a2ccf..bad62fa5e70f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -109,6 +109,9 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, int try_loading_module = 0; int err; + if (protocol < 0 || protocol >= IPPROTO_MAX) + return -EINVAL; + /* Look for the requested type/protocol pair. */ lookup_protocol: err = -ESOCKTNOSUPPORT; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 13ca4cf5616f..8e6cb3f14326 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -162,6 +162,9 @@ ipv4_connected: fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; + if (!fl6.flowi6_oif) + fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) fl6.flowi6_oif = np->mcast_oif; diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 5c5d23e59da5..9508a20fbf61 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, *fragoff = _frag_off; return hp->nexthdr; } - return -ENOENT; + if (!found) + return -ENOENT; + if (fragoff) + *fragoff = _frag_off; + break; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index d491125011c4..db939e4ac68a 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -540,12 +540,13 @@ int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; - (sfl = rcu_dereference(*sflp)) != NULL; + (sfl = rcu_dereference_protected(*sflp, + lockdep_is_held(&ip6_sk_fl_lock))) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; - *sflp = rcu_dereference(sfl->next); + *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69f4f689f06a..b1311da5d7b8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -783,6 +783,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) __u32 mtu; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; @@ -1553,13 +1555,11 @@ static int ip6gre_changelink(struct net_device *dev, struct nlattr *tb[], return -EEXIST; } else { t = nt; - - ip6gre_tunnel_unlink(ign, t); - ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); - ip6gre_tunnel_link(ign, t); - netdev_state_change(dev); } + ip6gre_tunnel_unlink(ign, t); + ip6gre_tnl_change(t, &p, !tb[IFLA_MTU]); + ip6gre_tunnel_link(ign, t); return 0; } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index bc09cb97b840..06bf4010d3ed 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -376,6 +376,9 @@ int ip6_forward(struct sk_buff *skb) if (skb->pkt_type != PACKET_HOST) goto drop; + if (unlikely(skb->sk)) + goto drop; + if (skb_warn_if_lro(skb)) goto drop; @@ -885,6 +888,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, struct rt6_info *rt; #endif int err; + int flags = 0; /* The correct way to handle this would be to do * ip6_route_get_saddr, and then ip6_route_output; however, @@ -916,10 +920,13 @@ static int ip6_dst_lookup_tail(struct sock *sk, dst_release(*dst); *dst = NULL; } + + if (fl6->flowi6_oif) + flags |= RT6_LOOKUP_F_IFACE; } if (!*dst) - *dst = ip6_route_output(net, sk, fl6); + *dst = ip6_route_output_flags(net, sk, fl6, flags); err = (*dst)->error; if (err) @@ -1329,7 +1336,7 @@ emsgsize: (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && (rt->dst.dev->features & NETIF_F_UFO) && - (sk->sk_type == SOCK_DGRAM)) { + (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) { err = ip6_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, mtu, flags, rt); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5cafd92c2312..c7c2c33aa4af 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -284,12 +284,12 @@ static int ip6_tnl_create2(struct net_device *dev) t = netdev_priv(dev); + dev->rtnl_link_ops = &ip6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); - dev->rtnl_link_ops = &ip6_link_ops; dev_hold(dev); ip6_tnl_link(ip6n, t); @@ -1124,6 +1124,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 41e3b5ee8d0b..9a63110b6548 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) return NULL; skb->priority = TC_PRIO_CONTROL; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 96f153c0846b..abb0bdda759a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1225,18 +1225,16 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); - if (ra_msg->icmph.icmp6_hop_limit) { - /* Only set hop_limit on the interface if it is higher than - * the current hop_limit. - */ - if (in6_dev->cnf.hop_limit < ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && + ra_msg->icmph.icmp6_hop_limit) { + if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; + if (rt) + dst_metric_set(&rt->dst, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } else { - ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than current\n"); + ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } - if (rt) - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, - ra_msg->icmph.icmp6_hop_limit); } skip_defrtr: diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 62f5b0d0bc9b..98e99fa833f1 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -198,11 +198,12 @@ get_entry(const void *base, unsigned int offset) /* All zeroes == unconditional rule. */ /* Mildly perf critical (only if packet tracing is on) */ -static inline bool unconditional(const struct ip6t_ip6 *ipv6) +static inline bool unconditional(const struct ip6t_entry *e) { static const struct ip6t_ip6 uncond; - return memcmp(ipv6, &uncond, sizeof(uncond)) == 0; + return e->target_offset == sizeof(struct ip6t_entry) && + memcmp(&e->ipv6, &uncond, sizeof(uncond)) == 0; } static inline const struct xt_entry_target * @@ -258,11 +259,10 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ip6t_entry) && + if (unconditional(s) && strcmp(t->target.u.kernel.target->name, XT_STANDARD_TARGET) == 0 && - t->verdict < 0 && - unconditional(&s->ipv6)) { + t->verdict < 0) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] @@ -455,7 +455,8 @@ ip6t_do_table(struct sk_buff *skb, there are loops. Puts hook bitmask in comefrom. */ static int mark_source_chains(const struct xt_table_info *newinfo, - unsigned int valid_hooks, void *entry0) + unsigned int valid_hooks, void *entry0, + unsigned int *offsets) { unsigned int hook; @@ -484,11 +485,10 @@ mark_source_chains(const struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ip6t_entry) && + if ((unconditional(e) && (strcmp(t->target.u.user.name, XT_STANDARD_TARGET) == 0) && - t->verdict < 0 && - unconditional(&e->ipv6)) || visited) { + t->verdict < 0) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -529,6 +529,8 @@ mark_source_chains(const struct xt_table_info *newinfo, size = e->next_offset; e = (struct ip6t_entry *) (entry0 + pos + size); + if (pos + size >= newinfo->size) + return 0; e->counters.pcnt = pos; pos += size; } else { @@ -547,9 +549,16 @@ mark_source_chains(const struct xt_table_info *newinfo, /* This a jump; chase it. */ duprintf("Jump rule %u -> %u\n", pos, newpos); + if (!xt_find_jump_offset(offsets, newpos, + newinfo->number)) + return 0; + e = (struct ip6t_entry *) + (entry0 + newpos); } else { /* ... this is a fallthru */ newpos = pos + e->next_offset; + if (newpos >= newinfo->size) + return 0; } e = (struct ip6t_entry *) (entry0 + newpos); @@ -576,27 +585,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net) module_put(par.match->me); } -static int -check_entry(const struct ip6t_entry *e, const char *name) -{ - const struct xt_entry_target *t; - - if (!ip6_checkentry(&e->ipv6)) { - duprintf("ip_tables: ip check failed %p %s.\n", e, name); - return -EINVAL; - } - - if (e->target_offset + sizeof(struct xt_entry_target) > - e->next_offset) - return -EINVAL; - - t = ip6t_get_target_c(e); - if (e->target_offset + t->u.target_size > e->next_offset) - return -EINVAL; - - return 0; -} - static int check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ip6t_ip6 *ipv6 = par->entryinfo; @@ -675,10 +663,6 @@ find_check_entry(struct ip6t_entry *e, struct net *net, const char *name, struct xt_mtchk_param mtpar; struct xt_entry_match *ematch; - ret = check_entry(e, name); - if (ret) - return ret; - j = 0; mtpar.net = net; mtpar.table = name; @@ -722,7 +706,7 @@ static bool check_underflow(const struct ip6t_entry *e) const struct xt_entry_target *t; unsigned int verdict; - if (!unconditional(&e->ipv6)) + if (!unconditional(e)) return false; t = ip6t_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) @@ -742,9 +726,11 @@ check_entry_size_and_hooks(struct ip6t_entry *e, unsigned int valid_hooks) { unsigned int h; + int err; if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || - (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -756,6 +742,14 @@ check_entry_size_and_hooks(struct ip6t_entry *e, return -EINVAL; } + if (!ip6_checkentry(&e->ipv6)) + return -EINVAL; + + err = xt_check_entry_offsets(e, e->elems, e->target_offset, + e->next_offset); + if (err) + return err; + /* Check hooks & underflows */ for (h = 0; h < NF_INET_NUMHOOKS; h++) { if (!(valid_hooks & (1 << h))) @@ -764,9 +758,9 @@ check_entry_size_and_hooks(struct ip6t_entry *e, newinfo->hook_entry[h] = hook_entries[h]; if ((unsigned char *)e - base == underflows[h]) { if (!check_underflow(e)) { - pr_err("Underflows must be unconditional and " - "use the STANDARD target with " - "ACCEPT/DROP\n"); + pr_debug("Underflows must be unconditional and " + "use the STANDARD target with " + "ACCEPT/DROP\n"); return -EINVAL; } newinfo->underflow[h] = underflows[h]; @@ -806,6 +800,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, const struct ip6t_replace *repl) { struct ip6t_entry *iter; + unsigned int *offsets; unsigned int i; int ret = 0; @@ -819,6 +814,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, } duprintf("translate_table: size %u\n", newinfo->size); + offsets = xt_alloc_entry_offsets(newinfo->number); + if (!offsets) + return -ENOMEM; i = 0; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter, entry0, newinfo->size) { @@ -828,17 +826,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, repl->underflow, repl->valid_hooks); if (ret != 0) - return ret; + goto out_free; + if (i < repl->num_entries) + offsets[i] = (void *)iter - entry0; ++i; if (strcmp(ip6t_get_target(iter)->u.user.name, XT_ERROR_TARGET) == 0) ++newinfo->stacksize; } + ret = -EINVAL; if (i != repl->num_entries) { duprintf("translate_table: %u not %u entries\n", i, repl->num_entries); - return -EINVAL; + goto out_free; } /* Check hooks all assigned */ @@ -849,17 +850,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (newinfo->hook_entry[i] == 0xFFFFFFFF) { duprintf("Invalid hook entry %u %u\n", i, repl->hook_entry[i]); - return -EINVAL; + goto out_free; } if (newinfo->underflow[i] == 0xFFFFFFFF) { duprintf("Invalid underflow %u %u\n", i, repl->underflow[i]); - return -EINVAL; + goto out_free; } } - if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) - return -ELOOP; + if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { + ret = -ELOOP; + goto out_free; + } + kvfree(offsets); /* Finally, each sanity check must pass */ i = 0; @@ -886,6 +890,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, } return ret; + out_free: + kvfree(offsets); + return ret; } static void @@ -1319,56 +1326,17 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, unsigned int i, curcpu; struct xt_counters_info tmp; struct xt_counters *paddc; - unsigned int num_counters; - char *name; - int size; - void *ptmp; struct xt_table *t; const struct xt_table_info *private; int ret = 0; const void *loc_cpu_entry; struct ip6t_entry *iter; unsigned int addend; -#ifdef CONFIG_COMPAT - struct compat_xt_counters_info compat_tmp; - - if (compat) { - ptmp = &compat_tmp; - size = sizeof(struct compat_xt_counters_info); - } else -#endif - { - ptmp = &tmp; - size = sizeof(struct xt_counters_info); - } - - if (copy_from_user(ptmp, user, size) != 0) - return -EFAULT; - -#ifdef CONFIG_COMPAT - if (compat) { - num_counters = compat_tmp.num_counters; - name = compat_tmp.name; - } else -#endif - { - num_counters = tmp.num_counters; - name = tmp.name; - } - - if (len != size + num_counters * sizeof(struct xt_counters)) - return -EINVAL; - - paddc = vmalloc(len - size); - if (!paddc) - return -ENOMEM; - - if (copy_from_user(paddc, user + size, len - size) != 0) { - ret = -EFAULT; - goto free; - } - t = xt_find_table_lock(net, AF_INET6, name); + paddc = xt_copy_counters_from_user(user, len, &tmp, compat); + if (IS_ERR(paddc)) + return PTR_ERR(paddc); + t = xt_find_table_lock(net, AF_INET6, tmp.name); if (IS_ERR_OR_NULL(t)) { ret = t ? PTR_ERR(t) : -ENOENT; goto free; @@ -1377,7 +1345,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len, local_bh_disable(); private = t->private; - if (private->number != num_counters) { + if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; } @@ -1457,7 +1425,6 @@ compat_copy_entry_to_user(struct ip6t_entry *e, void __user **dstptr, static int compat_find_calc_match(struct xt_entry_match *m, - const char *name, const struct ip6t_ip6 *ipv6, unsigned int hookmask, int *size) @@ -1493,21 +1460,19 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, struct xt_table_info *newinfo, unsigned int *size, const unsigned char *base, - const unsigned char *limit, - const unsigned int *hook_entries, - const unsigned int *underflows, - const char *name) + const unsigned char *limit) { struct xt_entry_match *ematch; struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; - int ret, off, h; + int ret, off; duprintf("check_compat_entry_size_and_hooks %p\n", e); if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || - (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit || + (unsigned char *)e + e->next_offset > limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } @@ -1519,8 +1484,11 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, return -EINVAL; } - /* For purposes of check_entry casting the compat entry is fine */ - ret = check_entry((struct ip6t_entry *)e, name); + if (!ip6_checkentry(&e->ipv6)) + return -EINVAL; + + ret = xt_compat_check_entry_offsets(e, e->elems, + e->target_offset, e->next_offset); if (ret) return ret; @@ -1528,8 +1496,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, entry_offset = (void *)e - (void *)base; j = 0; xt_ematch_foreach(ematch, e) { - ret = compat_find_calc_match(ematch, name, - &e->ipv6, e->comefrom, &off); + ret = compat_find_calc_match(ematch, &e->ipv6, e->comefrom, + &off); if (ret != 0) goto release_matches; ++j; @@ -1552,17 +1520,6 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, if (ret) goto out; - /* Check hooks & underflows */ - for (h = 0; h < NF_INET_NUMHOOKS; h++) { - if ((unsigned char *)e - base == hook_entries[h]) - newinfo->hook_entry[h] = hook_entries[h]; - if ((unsigned char *)e - base == underflows[h]) - newinfo->underflow[h] = underflows[h]; - } - - /* Clear counters and comefrom */ - memset(&e->counters, 0, sizeof(e->counters)); - e->comefrom = 0; return 0; out: @@ -1576,18 +1533,17 @@ release_matches: return ret; } -static int +static void compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, - unsigned int *size, const char *name, + unsigned int *size, struct xt_table_info *newinfo, unsigned char *base) { struct xt_entry_target *t; struct ip6t_entry *de; unsigned int origsize; - int ret, h; + int h; struct xt_entry_match *ematch; - ret = 0; origsize = *size; de = (struct ip6t_entry *)*dstptr; memcpy(de, e, sizeof(struct ip6t_entry)); @@ -1596,11 +1552,9 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, *dstptr += sizeof(struct ip6t_entry); *size += sizeof(struct ip6t_entry) - sizeof(struct compat_ip6t_entry); - xt_ematch_foreach(ematch, e) { - ret = xt_compat_match_from_user(ematch, dstptr, size); - if (ret != 0) - return ret; - } + xt_ematch_foreach(ematch, e) + xt_compat_match_from_user(ematch, dstptr, size); + de->target_offset = e->target_offset - (origsize - *size); t = compat_ip6t_get_target(e); xt_compat_target_from_user(t, dstptr, size); @@ -1612,181 +1566,82 @@ compat_copy_entry_from_user(struct compat_ip6t_entry *e, void **dstptr, if ((unsigned char *)de - base < newinfo->underflow[h]) newinfo->underflow[h] -= origsize - *size; } - return ret; -} - -static int compat_check_entry(struct ip6t_entry *e, struct net *net, - const char *name) -{ - unsigned int j; - int ret = 0; - struct xt_mtchk_param mtpar; - struct xt_entry_match *ematch; - - j = 0; - mtpar.net = net; - mtpar.table = name; - mtpar.entryinfo = &e->ipv6; - mtpar.hook_mask = e->comefrom; - mtpar.family = NFPROTO_IPV6; - xt_ematch_foreach(ematch, e) { - ret = check_match(ematch, &mtpar); - if (ret != 0) - goto cleanup_matches; - ++j; - } - - ret = check_target(e, net, name); - if (ret) - goto cleanup_matches; - return 0; - - cleanup_matches: - xt_ematch_foreach(ematch, e) { - if (j-- == 0) - break; - cleanup_match(ematch, net); - } - return ret; } static int translate_compat_table(struct net *net, - const char *name, - unsigned int valid_hooks, struct xt_table_info **pinfo, void **pentry0, - unsigned int total_size, - unsigned int number, - unsigned int *hook_entries, - unsigned int *underflows) + const struct compat_ip6t_replace *compatr) { unsigned int i, j; struct xt_table_info *newinfo, *info; void *pos, *entry0, *entry1; struct compat_ip6t_entry *iter0; - struct ip6t_entry *iter1; + struct ip6t_replace repl; unsigned int size; int ret = 0; info = *pinfo; entry0 = *pentry0; - size = total_size; - info->number = number; - - /* Init all hooks to impossible value. */ - for (i = 0; i < NF_INET_NUMHOOKS; i++) { - info->hook_entry[i] = 0xFFFFFFFF; - info->underflow[i] = 0xFFFFFFFF; - } + size = compatr->size; + info->number = compatr->num_entries; duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET6); - xt_compat_init_offsets(AF_INET6, number); + xt_compat_init_offsets(AF_INET6, compatr->num_entries); /* Walk through entries, checking offsets. */ - xt_entry_foreach(iter0, entry0, total_size) { + xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, entry0, - entry0 + total_size, - hook_entries, - underflows, - name); + entry0 + compatr->size); if (ret != 0) goto out_unlock; ++j; } ret = -EINVAL; - if (j != number) { + if (j != compatr->num_entries) { duprintf("translate_compat_table: %u not %u entries\n", - j, number); + j, compatr->num_entries); goto out_unlock; } - /* Check hooks all assigned */ - for (i = 0; i < NF_INET_NUMHOOKS; i++) { - /* Only hooks which are valid */ - if (!(valid_hooks & (1 << i))) - continue; - if (info->hook_entry[i] == 0xFFFFFFFF) { - duprintf("Invalid hook entry %u %u\n", - i, hook_entries[i]); - goto out_unlock; - } - if (info->underflow[i] == 0xFFFFFFFF) { - duprintf("Invalid underflow %u %u\n", - i, underflows[i]); - goto out_unlock; - } - } - ret = -ENOMEM; newinfo = xt_alloc_table_info(size); if (!newinfo) goto out_unlock; - newinfo->number = number; + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries[raw_smp_processor_id()]; pos = entry1; - size = total_size; - xt_entry_foreach(iter0, entry0, total_size) { - ret = compat_copy_entry_from_user(iter0, &pos, &size, - name, newinfo, entry1); - if (ret != 0) - break; - } + size = compatr->size; + xt_entry_foreach(iter0, entry0, compatr->size) + compat_copy_entry_from_user(iter0, &pos, &size, + newinfo, entry1); + + /* all module references in entry0 are now gone. */ xt_compat_flush_offsets(AF_INET6); xt_compat_unlock(AF_INET6); - if (ret) - goto free_newinfo; - ret = -ELOOP; - if (!mark_source_chains(newinfo, valid_hooks, entry1)) - goto free_newinfo; + memcpy(&repl, compatr, sizeof(*compatr)); - i = 0; - xt_entry_foreach(iter1, entry1, newinfo->size) { - ret = compat_check_entry(iter1, net, name); - if (ret != 0) - break; - ++i; - if (strcmp(ip6t_get_target(iter1)->u.user.name, - XT_ERROR_TARGET) == 0) - ++newinfo->stacksize; - } - if (ret) { - /* - * The first i matches need cleanup_entry (calls ->destroy) - * because they had called ->check already. The other j-i - * entries need only release. - */ - int skip = i; - j -= i; - xt_entry_foreach(iter0, entry0, newinfo->size) { - if (skip-- > 0) - continue; - if (j-- == 0) - break; - compat_release_entry(iter0); - } - xt_entry_foreach(iter1, entry1, newinfo->size) { - if (i-- == 0) - break; - cleanup_entry(iter1, net); - } - xt_free_table_info(newinfo); - return ret; + for (i = 0; i < NF_INET_NUMHOOKS; i++) { + repl.hook_entry[i] = newinfo->hook_entry[i]; + repl.underflow[i] = newinfo->underflow[i]; } - /* And one copy for every other CPU */ - for_each_possible_cpu(i) - if (newinfo->entries[i] && newinfo->entries[i] != entry1) - memcpy(newinfo->entries[i], entry1, newinfo->size); + repl.num_counters = 0; + repl.counters = NULL; + repl.size = newinfo->size; + ret = translate_table(net, newinfo, entry1, &repl); + if (ret) + goto free_newinfo; *pinfo = newinfo; *pentry0 = entry1; @@ -1795,17 +1650,16 @@ translate_compat_table(struct net *net, free_newinfo: xt_free_table_info(newinfo); -out: - xt_entry_foreach(iter0, entry0, total_size) { + return ret; +out_unlock: + xt_compat_flush_offsets(AF_INET6); + xt_compat_unlock(AF_INET6); + xt_entry_foreach(iter0, entry0, compatr->size) { if (j-- == 0) break; compat_release_entry(iter0); } return ret; -out_unlock: - xt_compat_flush_offsets(AF_INET6); - xt_compat_unlock(AF_INET6); - goto out; } static int @@ -1842,10 +1696,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) goto free_newinfo; } - ret = translate_compat_table(net, tmp.name, tmp.valid_hooks, - &newinfo, &loc_cpu_entry, tmp.size, - tmp.num_entries, tmp.hook_entry, - tmp.underflow); + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f371fefa7fdc..fe70bd6a7516 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1030,11 +1030,9 @@ static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags); } -struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, - struct flowi6 *fl6) +struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, + struct flowi6 *fl6, int flags) { - int flags = 0; - fl6->flowi6_iif = LOOPBACK_IFINDEX; if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) @@ -1047,7 +1045,7 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output); } -EXPORT_SYMBOL(ip6_route_output); +EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index cfb27f56c62f..ac6c40d08ac5 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { + if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - dst_hold(dst); sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; if (rt->rt6i_node) @@ -466,8 +465,10 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); skb_set_queue_mapping(skb, queue_mapping); + rcu_read_lock(); err = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass); + rcu_read_unlock(); err = net_xmit_eval(err); } @@ -1690,7 +1691,9 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) destp = ntohs(inet->inet_dport); srcp = ntohs(inet->inet_sport); - if (icsk->icsk_pending == ICSK_TIME_RETRANS) { + if (icsk->icsk_pending == ICSK_TIME_RETRANS || + icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS || + icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk->icsk_timeout; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7333f3575fc5..1173557ea551 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -834,8 +834,8 @@ start_lookup: flush_stack(stack, count, skb, count - 1); } else { if (!inner_flushed) - UDP_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, - proto == IPPROTO_UDPLITE); + UDP6_INC_STATS_BH(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); consume_skb(skb); } return 0; @@ -913,11 +913,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ + /* a return value > 0 means to resubmit the input */ if (ret > 0) - return -ret; + return ret; return 0; } diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 901ef6f8addc..5266ad2d6419 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -24,7 +24,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(ipv6_get_dsfield(outer_iph))) - IP6_ECN_set_ce(inner_iph); + IP6_ECN_set_ce(skb, inner_iph); } /* Add encapsulation header. diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f337a908a76a..4fb94f6ee15b 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -289,7 +289,7 @@ static void xfrm6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, xfrm_dst_ifdown(dst, dev); } -static struct dst_ops xfrm6_dst_ops = { +static struct dst_ops xfrm6_dst_ops_template = { .family = AF_INET6, .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, @@ -303,7 +303,7 @@ static struct dst_ops xfrm6_dst_ops = { static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .family = AF_INET6, - .dst_ops = &xfrm6_dst_ops, + .dst_ops = &xfrm6_dst_ops_template, .dst_lookup = xfrm6_dst_lookup, .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, @@ -336,7 +336,7 @@ static struct ctl_table xfrm6_policy_table[] = { { } }; -static int __net_init xfrm6_net_init(struct net *net) +static int __net_init xfrm6_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; @@ -364,7 +364,7 @@ err_alloc: return -ENOMEM; } -static void __net_exit xfrm6_net_exit(struct net *net) +static void __net_exit xfrm6_net_sysctl_exit(struct net *net) { struct ctl_table *table; @@ -376,24 +376,52 @@ static void __net_exit xfrm6_net_exit(struct net *net) if (!net_eq(net, &init_net)) kfree(table); } +#else /* CONFIG_SYSCTL */ +static int inline xfrm6_net_sysctl_init(struct net *net) +{ + return 0; +} + +static void inline xfrm6_net_sysctl_exit(struct net *net) +{ +} +#endif + +static int __net_init xfrm6_net_init(struct net *net) +{ + int ret; + + memcpy(&net->xfrm.xfrm6_dst_ops, &xfrm6_dst_ops_template, + sizeof(xfrm6_dst_ops_template)); + ret = dst_entries_init(&net->xfrm.xfrm6_dst_ops); + if (ret) + return ret; + + ret = xfrm6_net_sysctl_init(net); + if (ret) + dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); + + return ret; +} + +static void __net_exit xfrm6_net_exit(struct net *net) +{ + xfrm6_net_sysctl_exit(net); + dst_entries_destroy(&net->xfrm.xfrm6_dst_ops); +} static struct pernet_operations xfrm6_net_ops = { .init = xfrm6_net_init, .exit = xfrm6_net_exit, }; -#endif int __init xfrm6_init(void) { int ret; - dst_entries_init(&xfrm6_dst_ops); - ret = xfrm6_policy_init(); - if (ret) { - dst_entries_destroy(&xfrm6_dst_ops); + if (ret) goto out; - } ret = xfrm6_state_init(); if (ret) goto out_policy; @@ -402,9 +430,7 @@ int __init xfrm6_init(void) if (ret) goto out_state; -#ifdef CONFIG_SYSCTL register_pernet_subsys(&xfrm6_net_ops); -#endif out: return ret; out_state: @@ -416,11 +442,8 @@ out_policy: void xfrm6_fini(void) { -#ifdef CONFIG_SYSCTL unregister_pernet_subsys(&xfrm6_net_ops); -#endif xfrm6_protocol_fini(); xfrm6_policy_fini(); xfrm6_state_fini(); - dst_entries_destroy(&xfrm6_dst_ops); } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index ee0ea25c8e7a..eca46d3d3ff3 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr, } /* Check if we have opened a local TSAP */ - if (!self->tsap) - irda_open_tsap(self, LSAP_ANY, addr->sir_name); + if (!self->tsap) { + err = irda_open_tsap(self, LSAP_ANY, addr->sir_name); + if (err) + goto out; + } /* Move to connecting socket, start sending Connect Requests */ sock->state = SS_CONNECTING; @@ -1086,6 +1089,9 @@ static int irda_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; struct irda_sock *self; + if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + return -EINVAL; + if (net != &init_net) return -EAFNOSUPPORT; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 6daa52a18d40..123f6f9f854c 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -709,6 +709,9 @@ static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, if (!addr || addr->sa_family != AF_IUCV) return -EINVAL; + if (addr_len < sizeof(struct sockaddr_iucv)) + return -EINVAL; + lock_sock(sk); if (sk->sk_state != IUCV_OPEN) { err = -EBADFD; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 79649937ec71..44ee0683b14b 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -123,12 +123,11 @@ static int l2tp_ip_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; int length; - /* Point to L2TP header */ - optr = ptr = skb->data; - if (!pskb_may_pull(skb, 4)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; session_id = ntohl(*((__be32 *) ptr)); ptr += 4; @@ -156,6 +155,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) if (!pskb_may_pull(skb, length)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; + ptr += 4; pr_debug("%s: ip recv\n", tunnel->name); print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 0ce9da948ad7..36f8fa223a78 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -135,12 +135,11 @@ static int l2tp_ip6_recv(struct sk_buff *skb) struct l2tp_tunnel *tunnel = NULL; int length; - /* Point to L2TP header */ - optr = ptr = skb->data; - if (!pskb_may_pull(skb, 4)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; session_id = ntohl(*((__be32 *) ptr)); ptr += 4; @@ -168,6 +167,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) if (!pskb_may_pull(skb, length)) goto discard; + /* Point to L2TP header */ + optr = ptr = skb->data; + ptr += 4; pr_debug("%s: ip recv\n", tunnel->name); print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 9e13c2ff8789..fe92a08b3cd5 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family, ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); @@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family, ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, session, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 17a8dff06090..c58f242c00f1 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -626,6 +626,7 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb) if (llc->cmsg_flags & LLC_CMSG_PKTINFO) { struct llc_pktinfo info; + memset(&info, 0, sizeof(info)); info.lpi_ifindex = llc_sk(skb->sk)->dev->ifindex; llc_pdu_decode_dsap(skb, &info.lpi_sap); llc_pdu_decode_da(skb, info.lpi_mac); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 5c564a68fb50..d71edcbd0c58 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -289,7 +289,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta, } /* prepare A-MPDU MLME for Rx aggregation */ - tid_agg_rx = kmalloc(sizeof(struct tid_ampdu_rx), GFP_KERNEL); + tid_agg_rx = kzalloc(sizeof(*tid_agg_rx), GFP_KERNEL); if (!tid_agg_rx) goto end; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index f06d42267306..89ed0206882c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -907,7 +907,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) /* free all potentially still buffered bcast frames */ local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf); - skb_queue_purge(&sdata->u.ap.ps.bc_buf); + ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf); mutex_lock(&local->mtx); ieee80211_vif_copy_chanctx_to_vlans(sdata, true); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index a9c9d961f039..6f1f3bdddea2 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -7,6 +7,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2009, Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1479,14 +1480,21 @@ static void ieee80211_sta_find_ibss(struct ieee80211_sub_if_data *sdata) sdata_info(sdata, "Trigger new scan to find an IBSS to join\n"); - num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy, - &ifibss->chandef, - channels, - ARRAY_SIZE(channels)); scan_width = cfg80211_chandef_to_scan_width(&ifibss->chandef); - ieee80211_request_ibss_scan(sdata, ifibss->ssid, - ifibss->ssid_len, channels, num, - scan_width); + + if (ifibss->fixed_channel) { + num = ieee80211_ibss_setup_scan_channels(local->hw.wiphy, + &ifibss->chandef, + channels, + ARRAY_SIZE(channels)); + ieee80211_request_ibss_scan(sdata, ifibss->ssid, + ifibss->ssid_len, channels, + num, scan_width); + } else { + ieee80211_request_ibss_scan(sdata, ifibss->ssid, + ifibss->ssid_len, NULL, + 0, scan_width); + } } else { int interval = IEEE80211_SCAN_INTERVAL; @@ -1727,7 +1735,6 @@ void ieee80211_ibss_notify_scan_completed(struct ieee80211_local *local) if (sdata->vif.type != NL80211_IFTYPE_ADHOC) continue; sdata->u.ibss.last_scan_completed = jiffies; - ieee80211_queue_work(&local->hw, &sdata->work); } mutex_unlock(&local->iflist_mtx); } diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c0a9187bc3a9..cdf8609a6240 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -90,7 +90,7 @@ struct ieee80211_fragment_entry { unsigned int last_frag; unsigned int extra_len; struct sk_buff_head skb_list; - int ccmp; /* Whether fragments were encrypted with CCMP */ + bool check_sequential_pn; /* needed for CCMP/GCMP */ u8 last_pn[6]; /* PN of the last fragment if CCMP was used */ }; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 84cef600c573..6e89ab8eac44 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -980,7 +980,10 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, if (sdata->vif.txq) { struct txq_info *txqi = to_txq_info(sdata->vif.txq); + spin_lock_bh(&txqi->queue.lock); ieee80211_purge_tx_queue(&local->hw, &txqi->queue); + spin_unlock_bh(&txqi->queue.lock); + atomic_set(&sdata->txqs_len[txqi->txq.ac], 0); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 817098add1d6..c5af4e3d4497 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -161,6 +161,10 @@ void mesh_sta_cleanup(struct sta_info *sta) del_timer_sync(&sta->plink_timer); } + /* make sure no readers can access nexthop sta from here on */ + mesh_path_flush_by_nexthop(sta); + synchronize_net(); + if (changed) ieee80211_mbss_info_change_notify(sdata, changed); } @@ -1299,17 +1303,6 @@ out: sdata_unlock(sdata); } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) -{ - struct ieee80211_sub_if_data *sdata; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) - if (ieee80211_vif_is_mesh(&sdata->vif) && - ieee80211_sdata_running(sdata)) - ieee80211_queue_work(&local->hw, &sdata->work); - rcu_read_unlock(); -} void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata) { diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index 50c8473cf9dc..472bdc73e950 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -358,14 +358,10 @@ static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) return sdata->u.mesh.mesh_pp_id == IEEE80211_PATH_PROTOCOL_HWMP; } -void ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local); - void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata); void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata); void ieee80211s_stop(void); #else -static inline void -ieee80211_mesh_notify_scan_completed(struct ieee80211_local *local) {} static inline bool mesh_path_sel_is_hwmp(struct ieee80211_sub_if_data *sdata) { return false; } static inline void mesh_path_flush_by_iface(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a93906103f8b..844825829992 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4002,8 +4002,6 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) if (!(flags & IEEE80211_HW_CONNECTION_MONITOR)) ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.monitor_work); - /* and do all the other regular work too */ - ieee80211_queue_work(&sdata->local->hw, &sdata->work); } } diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 3ece7d1034c8..b54f398cda5d 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -711,7 +711,7 @@ static u32 minstrel_get_expected_throughput(void *priv_sta) * computing cur_tp */ tmp_mrs = &mi->r[idx].stats; - tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma); + tmp_cur_tp = minstrel_get_tp_avg(&mi->r[idx], tmp_mrs->prob_ewma) * 10; tmp_cur_tp = tmp_cur_tp * 1200 * 8 / 1024; return tmp_cur_tp; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 7430a1df2ab1..1ec889dc2e46 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -691,7 +691,7 @@ minstrel_aggr_check(struct ieee80211_sta *pubsta, struct sk_buff *skb) if (likely(sta->ampdu_mlme.tid_tx[tid])) return; - ieee80211_start_tx_ba_session(pubsta, tid, 5000); + ieee80211_start_tx_ba_session(pubsta, tid, 0); } static void @@ -1328,7 +1328,8 @@ static u32 minstrel_ht_get_expected_throughput(void *priv_sta) prob = mi->groups[i].rates[j].prob_ewma; /* convert tp_avg from pkt per second in kbps */ - tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * AVG_PKT_SIZE * 8 / 1024; + tp_avg = minstrel_ht_get_tp_avg(mi, i, j, prob) * 10; + tp_avg = tp_avg * AVG_PKT_SIZE * 8 / 1024; return tp_avg; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5793f75c5ffd..3073164a6fcf 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1725,7 +1725,7 @@ ieee80211_reassemble_add(struct ieee80211_sub_if_data *sdata, entry->seq = seq; entry->rx_queue = rx_queue; entry->last_frag = frag; - entry->ccmp = 0; + entry->check_sequential_pn = false; entry->extra_len = 0; return entry; @@ -1821,15 +1821,27 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) rx->seqno_idx, &(rx->skb)); if (rx->key && (rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP || - rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256) && + rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP_256 || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP || + rx->key->conf.cipher == WLAN_CIPHER_SUITE_GCMP_256) && ieee80211_has_protected(fc)) { int queue = rx->security_idx; - /* Store CCMP PN so that we can verify that the next - * fragment has a sequential PN value. */ - entry->ccmp = 1; + + /* Store CCMP/GCMP PN so that we can verify that the + * next fragment has a sequential PN value. + */ + entry->check_sequential_pn = true; memcpy(entry->last_pn, rx->key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); + BUILD_BUG_ON(offsetof(struct ieee80211_key, + u.ccmp.rx_pn) != + offsetof(struct ieee80211_key, + u.gcmp.rx_pn)); + BUILD_BUG_ON(sizeof(rx->key->u.ccmp.rx_pn[queue]) != + sizeof(rx->key->u.gcmp.rx_pn[queue])); + BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != + IEEE80211_GCMP_PN_LEN); } return RX_QUEUED; } @@ -1844,15 +1856,21 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) return RX_DROP_MONITOR; } - /* Verify that MPDUs within one MSDU have sequential PN values. - * (IEEE 802.11i, 8.3.3.4.5) */ - if (entry->ccmp) { + /* "The receiver shall discard MSDUs and MMPDUs whose constituent + * MPDU PN values are not incrementing in steps of 1." + * see IEEE P802.11-REVmc/D5.0, 12.5.3.4.4, item d (for CCMP) + * and IEEE P802.11-REVmc/D5.0, 12.5.5.4.4, item d (for GCMP) + */ + if (entry->check_sequential_pn) { int i; u8 pn[IEEE80211_CCMP_PN_LEN], *rpn; int queue; + if (!rx->key || (rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP && - rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256)) + rx->key->conf.cipher != WLAN_CIPHER_SUITE_CCMP_256 && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP && + rx->key->conf.cipher != WLAN_CIPHER_SUITE_GCMP_256)) return RX_DROP_UNUSABLE; memcpy(pn, entry->last_pn, IEEE80211_CCMP_PN_LEN); for (i = IEEE80211_CCMP_PN_LEN - 1; i >= 0; i--) { @@ -2209,7 +2227,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; - u16 q, hdrlen; + u16 ac, q, hdrlen; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -2279,7 +2297,8 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) ether_addr_equal(sdata->vif.addr, hdr->addr3)) return RX_CONTINUE; - q = ieee80211_select_queue_80211(sdata, skb, hdr); + ac = ieee80211_select_queue_80211(sdata, skb, hdr); + q = sdata->vif.hw_queue[ac]; if (ieee80211_queue_stopped(&local->hw, q)) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion); return RX_DROP_MONITOR; @@ -3359,6 +3378,7 @@ static bool prepare_for_handlers(struct ieee80211_rx_data *rx, return false; /* ignore action frames to TDLS-peers */ if (ieee80211_is_action(hdr->frame_control) && + !is_broadcast_ether_addr(bssid) && !ether_addr_equal(bssid, hdr->addr1)) return false; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 7bb6a9383f58..ee9351affa5b 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -310,6 +310,7 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) bool was_scanning = local->scanning; struct cfg80211_scan_request *scan_req; struct ieee80211_sub_if_data *scan_sdata; + struct ieee80211_sub_if_data *sdata; lockdep_assert_held(&local->mtx); @@ -369,7 +370,16 @@ static void __ieee80211_scan_completed(struct ieee80211_hw *hw, bool aborted) ieee80211_mlme_notify_scan_completed(local); ieee80211_ibss_notify_scan_completed(local); - ieee80211_mesh_notify_scan_completed(local); + + /* Requeue all the work that might have been ignored while + * the scan was in progress; if there was none this will + * just be a no-op for the particular interface. + */ + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + if (ieee80211_sdata_running(sdata)) + ieee80211_queue_work(&sdata->local->hw, &sdata->work); + } + if (was_scanning) ieee80211_start_next_roc(local); } diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2880f2ae99ab..bcdbda289d75 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -252,11 +252,11 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) } /* Caller must hold local->sta_mtx */ -static void sta_info_hash_add(struct ieee80211_local *local, - struct sta_info *sta) +static int sta_info_hash_add(struct ieee80211_local *local, + struct sta_info *sta) { - rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, - sta_rht_params); + return rhashtable_insert_fast(&local->sta_hash, &sta->hash_node, + sta_rht_params); } static void sta_deliver_ps_frames(struct work_struct *wk) @@ -472,11 +472,17 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - struct station_info sinfo; + struct station_info *sinfo; int err = 0; lockdep_assert_held(&local->sta_mtx); + sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL); + if (!sinfo) { + err = -ENOMEM; + goto out_err; + } + /* check if STA exists already */ if (sta_info_get_bss(sdata, sta->sta.addr)) { err = -EEXIST; @@ -491,7 +497,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) set_sta_flag(sta, WLAN_STA_BLOCK_BA); /* make the station visible */ - sta_info_hash_add(local, sta); + err = sta_info_hash_add(local, sta); + if (err) + goto out_drop_sta; list_add_tail_rcu(&sta->list, &local->sta_list); @@ -508,10 +516,9 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) ieee80211_sta_debugfs_add(sta); rate_control_add_sta_debugfs(sta); - memset(&sinfo, 0, sizeof(sinfo)); - sinfo.filled = 0; - sinfo.generation = local->sta_generation; - cfg80211_new_sta(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); + sinfo->generation = local->sta_generation; + cfg80211_new_sta(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); + kfree(sinfo); sta_dbg(sdata, "Inserted STA %pM\n", sta->sta.addr); @@ -526,6 +533,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) out_remove: sta_info_hash_del(local, sta); list_del_rcu(&sta->list); + out_drop_sta: local->num_sta--; synchronize_net(); __cleanup_single_sta(sta); @@ -873,7 +881,7 @@ static void __sta_info_destroy_part2(struct sta_info *sta) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; - struct station_info sinfo = {}; + struct station_info *sinfo; int ret; /* @@ -911,8 +919,11 @@ static void __sta_info_destroy_part2(struct sta_info *sta) sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr); - sta_set_sinfo(sta, &sinfo); - cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, &sinfo, GFP_KERNEL); + sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); + if (sinfo) + sta_set_sinfo(sta, sinfo); + cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); + kfree(sinfo); rate_control_remove_sta_debugfs(sta); ieee80211_sta_debugfs_remove(sta); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 5787f15a3a12..8dbdbaea70fd 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -355,7 +355,7 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) skb = skb_dequeue(&ps->bc_buf); if (skb) { purged++; - dev_kfree_skb(skb); + ieee80211_free_txskb(&local->hw, skb); } total += skb_queue_len(&ps->bc_buf); } @@ -438,7 +438,7 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (skb_queue_len(&ps->bc_buf) >= AP_MAX_BC_BUFFER) { ps_dbg(tx->sdata, "BC TX buffer full - dropping the oldest frame\n"); - dev_kfree_skb(skb_dequeue(&ps->bc_buf)); + ieee80211_free_txskb(&tx->local->hw, skb_dequeue(&ps->bc_buf)); } else tx->local->total_ps_buffered++; @@ -3247,7 +3247,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb)) break; - dev_kfree_skb_any(skb); + ieee80211_free_txskb(hw, skb); } info = IEEE80211_SKB_CB(skb); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 38fbc194b9cb..a26bd6532829 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1689,15 +1689,34 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) cp = pp->conn_in_get(af, skb, &iph, 0); conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && - is_new_conn(skb, &iph) && cp && - ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && - unlikely(!atomic_read(&cp->dest->weight))) || - unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) { - if (!atomic_read(&cp->n_control)) - ip_vs_conn_expire_now(cp); - __ip_vs_conn_put(cp); - cp = NULL; + if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + bool uses_ct = false, resched = false; + + if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && + unlikely(!atomic_read(&cp->dest->weight))) { + resched = true; + uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + if (!atomic_read(&cp->n_control)) { + resched = true; + } else { + /* Do not reschedule controlling connection + * that uses conntrack while it is still + * referenced by controlled connection(s). + */ + resched = !uses_ct; + } + } + + if (resched) { + if (!atomic_read(&cp->n_control)) + ip_vs_conn_expire_now(cp); + __ip_vs_conn_put(cp); + if (uses_ct) + return NF_DROP; + cp = NULL; + } } if (unlikely(!cp) && !iph.fragoffs) { diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index bed5f7042529..bb318e4623a3 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -88,7 +88,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) dptr = skb->data + dataoff; datalen = skb->len - dataoff; - if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen)) + if (get_callid(dptr, 0, datalen, &matchoff, &matchlen)) return -EINVAL; /* N.B: pe_data is only set on success, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 13fad8668f83..bc3f791845aa 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1735,6 +1735,7 @@ void nf_conntrack_init_end(void) int nf_conntrack_init_net(struct net *net) { + static atomic64_t unique_id; int ret = -ENOMEM; int cpu; @@ -1758,7 +1759,8 @@ int nf_conntrack_init_net(struct net *net) if (!net->ct.stat) goto err_pcpu_lists; - net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net); + net->ct.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%llu", + (u64)atomic64_inc_return(&unique_id)); if (!net->ct.slabname) goto err_slabname; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 51a459c3c649..703fc9ba6f20 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -418,6 +418,47 @@ int xt_check_match(struct xt_mtchk_param *par, } EXPORT_SYMBOL_GPL(xt_check_match); +/** xt_check_entry_match - check that matches end before start of target + * + * @match: beginning of xt_entry_match + * @target: beginning of this rules target (alleged end of matches) + * @alignment: alignment requirement of match structures + * + * Validates that all matches add up to the beginning of the target, + * and that each match covers at least the base structure size. + * + * Return: 0 on success, negative errno on failure. + */ +static int xt_check_entry_match(const char *match, const char *target, + const size_t alignment) +{ + const struct xt_entry_match *pos; + int length = target - match; + + if (length == 0) /* no matches */ + return 0; + + pos = (struct xt_entry_match *)match; + do { + if ((unsigned long)pos % alignment) + return -EINVAL; + + if (length < (int)sizeof(struct xt_entry_match)) + return -EINVAL; + + if (pos->u.match_size < sizeof(struct xt_entry_match)) + return -EINVAL; + + if (pos->u.match_size > length) + return -EINVAL; + + length -= pos->u.match_size; + pos = ((void *)((char *)(pos) + (pos)->u.match_size)); + } while (length > 0); + + return 0; +} + #ifdef CONFIG_COMPAT int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { @@ -487,13 +528,14 @@ int xt_compat_match_offset(const struct xt_match *match) } EXPORT_SYMBOL_GPL(xt_compat_match_offset); -int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, - unsigned int *size) +void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, + unsigned int *size) { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; int pad, off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; + char name[sizeof(m->u.user.name)]; m = *dstptr; memcpy(m, cm, sizeof(*cm)); @@ -507,10 +549,12 @@ int xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, msize += off; m->u.user.match_size = msize; + strlcpy(name, match->name, sizeof(name)); + module_put(match->me); + strncpy(m->u.user.name, name, sizeof(m->u.user.name)); *size += off; *dstptr += msize; - return 0; } EXPORT_SYMBOL_GPL(xt_compat_match_from_user); @@ -541,8 +585,175 @@ int xt_compat_match_to_user(const struct xt_entry_match *m, return 0; } EXPORT_SYMBOL_GPL(xt_compat_match_to_user); + +/* non-compat version may have padding after verdict */ +struct compat_xt_standard_target { + struct compat_xt_entry_target t; + compat_uint_t verdict; +}; + +int xt_compat_check_entry_offsets(const void *base, const char *elems, + unsigned int target_offset, + unsigned int next_offset) +{ + long size_of_base_struct = elems - (const char *)base; + const struct compat_xt_entry_target *t; + const char *e = base; + + if (target_offset < size_of_base_struct) + return -EINVAL; + + if (target_offset + sizeof(*t) > next_offset) + return -EINVAL; + + t = (void *)(e + target_offset); + if (t->u.target_size < sizeof(*t)) + return -EINVAL; + + if (target_offset + t->u.target_size > next_offset) + return -EINVAL; + + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 && + COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset) + return -EINVAL; + + /* compat_xt_entry match has less strict aligment requirements, + * otherwise they are identical. In case of padding differences + * we need to add compat version of xt_check_entry_match. + */ + BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match)); + + return xt_check_entry_match(elems, base + target_offset, + __alignof__(struct compat_xt_entry_match)); +} +EXPORT_SYMBOL(xt_compat_check_entry_offsets); #endif /* CONFIG_COMPAT */ +/** + * xt_check_entry_offsets - validate arp/ip/ip6t_entry + * + * @base: pointer to arp/ip/ip6t_entry + * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems + * @target_offset: the arp/ip/ip6_t->target_offset + * @next_offset: the arp/ip/ip6_t->next_offset + * + * validates that target_offset and next_offset are sane and that all + * match sizes (if any) align with the target offset. + * + * This function does not validate the targets or matches themselves, it + * only tests that all the offsets and sizes are correct, that all + * match structures are aligned, and that the last structure ends where + * the target structure begins. + * + * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version. + * + * The arp/ip/ip6t_entry structure @base must have passed following tests: + * - it must point to a valid memory location + * - base to base + next_offset must be accessible, i.e. not exceed allocated + * length. + * + * A well-formed entry looks like this: + * + * ip(6)t_entry match [mtdata] match [mtdata] target [tgdata] ip(6)t_entry + * e->elems[]-----' | | + * matchsize | | + * matchsize | | + * | | + * target_offset---------------------------------' | + * next_offset---------------------------------------------------' + * + * elems[]: flexible array member at end of ip(6)/arpt_entry struct. + * This is where matches (if any) and the target reside. + * target_offset: beginning of target. + * next_offset: start of the next rule; also: size of this rule. + * Since targets have a minimum size, target_offset + minlen <= next_offset. + * + * Every match stores its size, sum of sizes must not exceed target_offset. + * + * Return: 0 on success, negative errno on failure. + */ +int xt_check_entry_offsets(const void *base, + const char *elems, + unsigned int target_offset, + unsigned int next_offset) +{ + long size_of_base_struct = elems - (const char *)base; + const struct xt_entry_target *t; + const char *e = base; + + /* target start is within the ip/ip6/arpt_entry struct */ + if (target_offset < size_of_base_struct) + return -EINVAL; + + if (target_offset + sizeof(*t) > next_offset) + return -EINVAL; + + t = (void *)(e + target_offset); + if (t->u.target_size < sizeof(*t)) + return -EINVAL; + + if (target_offset + t->u.target_size > next_offset) + return -EINVAL; + + if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 && + XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset) + return -EINVAL; + + return xt_check_entry_match(elems, base + target_offset, + __alignof__(struct xt_entry_match)); +} +EXPORT_SYMBOL(xt_check_entry_offsets); + +/** + * xt_alloc_entry_offsets - allocate array to store rule head offsets + * + * @size: number of entries + * + * Return: NULL or kmalloc'd or vmalloc'd array + */ +unsigned int *xt_alloc_entry_offsets(unsigned int size) +{ + unsigned int *off; + + off = kcalloc(size, sizeof(unsigned int), GFP_KERNEL | __GFP_NOWARN); + + if (off) + return off; + + if (size < (SIZE_MAX / sizeof(unsigned int))) + off = vmalloc(size * sizeof(unsigned int)); + + return off; +} +EXPORT_SYMBOL(xt_alloc_entry_offsets); + +/** + * xt_find_jump_offset - check if target is a valid jump offset + * + * @offsets: array containing all valid rule start offsets of a rule blob + * @target: the jump target to search for + * @size: entries in @offset + */ +bool xt_find_jump_offset(const unsigned int *offsets, + unsigned int target, unsigned int size) +{ + int m, low = 0, hi = size; + + while (hi > low) { + m = (low + hi) / 2u; + + if (offsets[m] > target) + hi = m; + else if (offsets[m] < target) + low = m + 1; + else + return true; + } + + return false; +} +EXPORT_SYMBOL(xt_find_jump_offset); + int xt_check_target(struct xt_tgchk_param *par, unsigned int size, u_int8_t proto, bool inv_proto) { @@ -593,6 +804,80 @@ int xt_check_target(struct xt_tgchk_param *par, } EXPORT_SYMBOL_GPL(xt_check_target); +/** + * xt_copy_counters_from_user - copy counters and metadata from userspace + * + * @user: src pointer to userspace memory + * @len: alleged size of userspace memory + * @info: where to store the xt_counters_info metadata + * @compat: true if we setsockopt call is done by 32bit task on 64bit kernel + * + * Copies counter meta data from @user and stores it in @info. + * + * vmallocs memory to hold the counters, then copies the counter data + * from @user to the new memory and returns a pointer to it. + * + * If @compat is true, @info gets converted automatically to the 64bit + * representation. + * + * The metadata associated with the counters is stored in @info. + * + * Return: returns pointer that caller has to test via IS_ERR(). + * If IS_ERR is false, caller has to vfree the pointer. + */ +void *xt_copy_counters_from_user(const void __user *user, unsigned int len, + struct xt_counters_info *info, bool compat) +{ + void *mem; + u64 size; + +#ifdef CONFIG_COMPAT + if (compat) { + /* structures only differ in size due to alignment */ + struct compat_xt_counters_info compat_tmp; + + if (len <= sizeof(compat_tmp)) + return ERR_PTR(-EINVAL); + + len -= sizeof(compat_tmp); + if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0) + return ERR_PTR(-EFAULT); + + strlcpy(info->name, compat_tmp.name, sizeof(info->name)); + info->num_counters = compat_tmp.num_counters; + user += sizeof(compat_tmp); + } else +#endif + { + if (len <= sizeof(*info)) + return ERR_PTR(-EINVAL); + + len -= sizeof(*info); + if (copy_from_user(info, user, sizeof(*info)) != 0) + return ERR_PTR(-EFAULT); + + info->name[sizeof(info->name) - 1] = '\0'; + user += sizeof(*info); + } + + size = sizeof(struct xt_counters); + size *= info->num_counters; + + if (size != (u64)len) + return ERR_PTR(-EINVAL); + + mem = vmalloc(len); + if (!mem) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(mem, user, len) == 0) + return mem; + + vfree(mem); + return ERR_PTR(-EFAULT); +} +EXPORT_SYMBOL_GPL(xt_copy_counters_from_user); + #ifdef CONFIG_COMPAT int xt_compat_target_offset(const struct xt_target *target) { @@ -608,6 +893,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; int pad, off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; + char name[sizeof(t->u.user.name)]; t = *dstptr; memcpy(t, ct, sizeof(*ct)); @@ -621,6 +907,9 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, tsize += off; t->u.user.target_size = tsize; + strlcpy(name, target->name, sizeof(name)); + module_put(target->me); + strncpy(t->u.user.name, name, sizeof(t->u.user.name)); *size += off; *dstptr += tsize; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 28cddc85b700..bfa2b6d5b5cf 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -824,7 +824,11 @@ socket_setattr_return: */ void netlbl_sock_delattr(struct sock *sk) { - cipso_v4_sock_delattr(sk); + switch (sk->sk_family) { + case AF_INET: + cipso_v4_sock_delattr(sk); + break; + } } /** @@ -987,7 +991,11 @@ req_setattr_return: */ void netlbl_req_delattr(struct request_sock *req) { - cipso_v4_req_delattr(req); + switch (req->rsk_ops->family) { + case AF_INET: + cipso_v4_req_delattr(req); + break; + } } /** diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0d6038c87bef..dbc32b19c574 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1290,7 +1290,7 @@ static int netlink_release(struct socket *sock) skb_queue_purge(&sk->sk_write_queue); - if (nlk->portid) { + if (nlk->portid && nlk->bound) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, @@ -2683,6 +2683,7 @@ static int netlink_dump(struct sock *sk) struct netlink_callback *cb; struct sk_buff *skb = NULL; struct nlmsghdr *nlh; + struct module *module; int len, err = -ENOBUFS; int alloc_min_size; int alloc_size; @@ -2762,9 +2763,11 @@ static int netlink_dump(struct sock *sk) cb->done(cb); nlk->cb_running = false; + module = cb->module; + skb = cb->skb; mutex_unlock(nlk->cb_mutex); - module_put(cb->module); - consume_skb(cb->skb); + module_put(module); + consume_skb(skb); return 0; errout_skb: diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index b491c1c296fe..9920f7502f6d 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -441,7 +441,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, mask_ipv6_addr(saddr, key->ipv6_src, mask->ipv6_src, masked); if (unlikely(memcmp(saddr, masked, sizeof(masked)))) { - set_ipv6_addr(skb, key->ipv6_proto, saddr, masked, + set_ipv6_addr(skb, flow_key->ip.proto, saddr, masked, true); memcpy(&flow_key->ipv6.addr.src, masked, sizeof(flow_key->ipv6.addr.src)); @@ -463,7 +463,7 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, NULL, &flags) != NEXTHDR_ROUTING); - set_ipv6_addr(skb, key->ipv6_proto, daddr, masked, + set_ipv6_addr(skb, flow_key->ip.proto, daddr, masked, recalc_csum); memcpy(&flow_key->ipv6.addr.dst, masked, sizeof(flow_key->ipv6.addr.dst)); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 27e14962b504..b3fe02a2339e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -337,12 +337,10 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, unsigned short gso_type = skb_shinfo(skb)->gso_type; struct sw_flow_key later_key; struct sk_buff *segs, *nskb; - struct ovs_skb_cb ovs_cb; int err; - ovs_cb = *OVS_CB(skb); + BUILD_BUG_ON(sizeof(*OVS_CB(skb)) > SKB_SGO_CB_OFFSET); segs = __skb_gso_segment(skb, NETIF_F_SG, false); - *OVS_CB(skb) = ovs_cb; if (IS_ERR(segs)) return PTR_ERR(segs); if (segs == NULL) @@ -360,7 +358,6 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, /* Queue all of the segments. */ skb = segs; do { - *OVS_CB(skb) = ovs_cb; if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ebc39e66d704..a3654d929814 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1699,6 +1699,10 @@ retry: goto retry; } + if (!dev_validate_header(dev, skb->data, len)) { + err = -EINVAL; + goto out_unlock; + } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; @@ -2109,18 +2113,6 @@ static void tpacket_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } -static bool ll_header_truncated(const struct net_device *dev, int len) -{ - /* net device doesn't like empty head */ - if (unlikely(len <= dev->hard_header_len)) { - net_warn_ratelimited("%s: packet size is too short (%d <= %d)\n", - current->comm, len, dev->hard_header_len); - return true; - } - - return false; -} - static void tpacket_set_protocol(const struct net_device *dev, struct sk_buff *skb) { @@ -2203,19 +2195,19 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, if (unlikely(err < 0)) return -EINVAL; } else if (dev->hard_header_len) { - if (ll_header_truncated(dev, tp_len)) - return -EINVAL; + int hdrlen = min_t(int, dev->hard_header_len, tp_len); skb_push(skb, dev->hard_header_len); - err = skb_store_bits(skb, 0, data, - dev->hard_header_len); + err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; + if (!dev_validate_header(dev, skb->data, hdrlen)) + return -EINVAL; if (!skb->protocol) tpacket_set_protocol(dev, skb); - data += dev->hard_header_len; - to_write -= dev->hard_header_len; + data += hdrlen; + to_write -= hdrlen; } offset = offset_in_page(data); @@ -2538,9 +2530,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; - } else { - if (ll_header_truncated(dev, len)) - goto out_free; } /* Returns -EFAULT on error */ @@ -2548,6 +2537,12 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (err) goto out_free; + if (sock->type == SOCK_RAW && + !dev_validate_header(dev, skb->data, len)) { + err = -EINVAL; + goto out_free; + } + sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); if (!gso_type && (len > dev->mtu + reserve + extra_len) && @@ -3212,6 +3207,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); + memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; i->next = po->mclist; po->mclist = i; diff --git a/net/phonet/af_phonet.c b/net/phonet/af_phonet.c index 32ab87d34828..11d0b29ce4b8 100644 --- a/net/phonet/af_phonet.c +++ b/net/phonet/af_phonet.c @@ -377,6 +377,10 @@ static int phonet_rcv(struct sk_buff *skb, struct net_device *dev, struct sockaddr_pn sa; u16 len; + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + /* check we have at least a full Phonet header */ if (!pskb_pull(skb, sizeof(struct phonethdr))) goto out; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index fa7cd792791c..a97bb7332607 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1081,17 +1081,6 @@ static unsigned int rfkill_fop_poll(struct file *file, poll_table *wait) return res; } -static bool rfkill_readable(struct rfkill_data *data) -{ - bool r; - - mutex_lock(&data->mtx); - r = !list_empty(&data->events); - mutex_unlock(&data->mtx); - - return r; -} - static ssize_t rfkill_fop_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { @@ -1108,8 +1097,11 @@ static ssize_t rfkill_fop_read(struct file *file, char __user *buf, goto out; } mutex_unlock(&data->mtx); + /* since we re-check and it just compares pointers, + * using !list_empty() without locking isn't a problem + */ ret = wait_event_interruptible(data->read_wait, - rfkill_readable(data)); + !list_empty(&data->events)); mutex_lock(&data->mtx); if (ret) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d4b6f3682c14..c244a49ae4ac 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -744,14 +744,15 @@ static u32 qdisc_alloc_handle(struct net_device *dev) return 0; } -void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) +void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, + unsigned int len) { const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; int drops; - if (n == 0) + if (n == 0 && len == 0) return; drops = max_t(int, n, 0); rcu_read_lock(); @@ -774,11 +775,12 @@ void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) cops->put(sch, cl); } sch->q.qlen -= n; + sch->qstats.backlog -= len; __qdisc_qstats_drop(sch, drops); } rcu_read_unlock(); } -EXPORT_SYMBOL(qdisc_tree_decrease_qlen); +EXPORT_SYMBOL(qdisc_tree_reduce_backlog); static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, @@ -950,7 +952,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, } lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) - sch->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + sch->flags |= TCQ_F_ONETXQUEUE; } sch->handle = handle; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index beeb75f80fdb..f6e7a60012b1 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1624,13 +1624,8 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new->reshape_fail = cbq_reshape_fail; #endif } - sch_tree_lock(sch); - *old = cl->q; - cl->q = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->q); return 0; } @@ -1914,7 +1909,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl = (struct cbq_class *)arg; - unsigned int qlen; + unsigned int qlen, backlog; if (cl->filters || cl->children || cl == &q->link) return -EBUSY; @@ -1922,8 +1917,9 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); qlen = cl->q->q.qlen; + backlog = cl->q->qstats.backlog; qdisc_reset(cl->q); - qdisc_tree_decrease_qlen(cl->q, qlen); + qdisc_tree_reduce_backlog(cl->q, qlen, backlog); if (cl->next_alive) cbq_deactivate_class(cl); diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index c009eb9045ce..3f6437db9b0f 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -128,8 +128,8 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx) choke_zap_tail_holes(q); qdisc_qstats_backlog_dec(sch, skb); + qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_drop(skb, sch); - qdisc_tree_decrease_qlen(sch, 1); --sch->q.qlen; } @@ -449,6 +449,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) old = q->tab; if (old) { unsigned int oqlen = sch->q.qlen, tail = 0; + unsigned dropped = 0; while (q->head != q->tail) { struct sk_buff *skb = q->tab[q->head]; @@ -460,11 +461,12 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt) ntab[tail++] = skb; continue; } + dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); --sch->q.qlen; qdisc_drop(skb, sch); } - qdisc_tree_decrease_qlen(sch, oqlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped); q->head = 0; q->tail = tail; } diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c index 7a0bdb16ac92..9a9068d00833 100644 --- a/net/sched/sch_codel.c +++ b/net/sched/sch_codel.c @@ -79,12 +79,13 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch) skb = codel_dequeue(sch, &q->params, &q->vars, &q->stats, dequeue); - /* We cant call qdisc_tree_decrease_qlen() if our qlen is 0, + /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, * or HTB crashes. Defer it for next round. */ if (q->stats.drop_count && sch->q.qlen) { - qdisc_tree_decrease_qlen(sch, q->stats.drop_count); + qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len); q->stats.drop_count = 0; + q->stats.drop_len = 0; } if (skb) qdisc_bstats_update(sch, skb); @@ -115,7 +116,7 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) { struct codel_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CODEL_MAX + 1]; - unsigned int qlen; + unsigned int qlen, dropped = 0; int err; if (!opt) @@ -149,10 +150,11 @@ static int codel_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = __skb_dequeue(&sch->q); + dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); qdisc_drop(skb, sch); } - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 338706092c27..e599803caa1e 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -53,9 +53,10 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid) static void drr_purge_queue(struct drr_class *cl) { unsigned int len = cl->qdisc->q.qlen; + unsigned int backlog = cl->qdisc->qstats.backlog; qdisc_reset(cl->qdisc); - qdisc_tree_decrease_qlen(cl->qdisc, len); + qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); } static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = { @@ -226,11 +227,7 @@ static int drr_graft_class(struct Qdisc *sch, unsigned long arg, new = &noop_qdisc; } - sch_tree_lock(sch); - drr_purge_queue(cl); - *old = cl->qdisc; - cl->qdisc = new; - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 66700a6116aa..7288dda2a7fb 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -67,13 +67,7 @@ static int dsmark_graft(struct Qdisc *sch, unsigned long arg, new = &noop_qdisc; } - sch_tree_lock(sch); - *old = p->q; - p->q = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &p->q); return 0; } @@ -262,6 +256,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch) return err; } + qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; @@ -284,6 +279,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) return NULL; qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; index = skb->tc_index & (p->indices - 1); @@ -399,6 +395,7 @@ static void dsmark_reset(struct Qdisc *sch) pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); qdisc_reset(p->q); + sch->qstats.backlog = 0; sch->q.qlen = 0; } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index f377702d4b91..4816778566d3 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -659,6 +659,7 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) struct fq_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_FQ_MAX + 1]; int err, drop_count = 0; + unsigned drop_len = 0; u32 fq_log; if (!opt) @@ -733,10 +734,11 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt) if (!skb) break; + drop_len += qdisc_pkt_len(skb); kfree_skb(skb); drop_count++; } - qdisc_tree_decrease_qlen(sch, drop_count); + qdisc_tree_reduce_backlog(sch, drop_count, drop_len); sch_tree_unlock(sch); return err; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 9291598b5aad..96971c7ab228 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -173,7 +173,7 @@ static unsigned int fq_codel_drop(struct Qdisc *sch) static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fq_codel_sched_data *q = qdisc_priv(sch); - unsigned int idx; + unsigned int idx, prev_backlog; struct fq_codel_flow *flow; int uninitialized_var(ret); @@ -201,6 +201,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (++sch->q.qlen <= sch->limit) return NET_XMIT_SUCCESS; + prev_backlog = sch->qstats.backlog; q->drop_overlimit++; /* Return Congestion Notification only if we dropped a packet * from this flow. @@ -209,7 +210,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_CN; /* As we dropped a packet, better let upper stack know this */ - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog); return NET_XMIT_SUCCESS; } @@ -239,6 +240,7 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch) struct fq_codel_flow *flow; struct list_head *head; u32 prev_drop_count, prev_ecn_mark; + unsigned int prev_backlog; begin: head = &q->new_flows; @@ -257,6 +259,7 @@ begin: prev_drop_count = q->cstats.drop_count; prev_ecn_mark = q->cstats.ecn_mark; + prev_backlog = sch->qstats.backlog; skb = codel_dequeue(sch, &q->cparams, &flow->cvars, &q->cstats, dequeue); @@ -274,12 +277,14 @@ begin: } qdisc_bstats_update(sch, skb); flow->deficit -= qdisc_pkt_len(skb); - /* We cant call qdisc_tree_decrease_qlen() if our qlen is 0, + /* We cant call qdisc_tree_reduce_backlog() if our qlen is 0, * or HTB crashes. Defer it for next round. */ if (q->cstats.drop_count && sch->q.qlen) { - qdisc_tree_decrease_qlen(sch, q->cstats.drop_count); + qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, + q->cstats.drop_len); q->cstats.drop_count = 0; + q->cstats.drop_len = 0; } return skb; } @@ -347,11 +352,13 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = fq_codel_dequeue(sch); + q->cstats.drop_len += qdisc_pkt_len(skb); kfree_skb(skb); q->cstats.drop_count++; } - qdisc_tree_decrease_qlen(sch, q->cstats.drop_count); + qdisc_tree_reduce_backlog(sch, q->cstats.drop_count, q->cstats.drop_len); q->cstats.drop_count = 0; + q->cstats.drop_len = 0; sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b453270be3fd..9821e6d641bb 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -159,12 +159,15 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, if (validate) skb = validate_xmit_skb_list(skb, dev); - if (skb) { + if (likely(skb)) { HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); HARD_TX_UNLOCK(dev, txq); + } else { + spin_lock(root_lock); + return qdisc_qlen(q); } spin_lock(root_lock); @@ -666,8 +669,10 @@ static void qdisc_rcu_free(struct rcu_head *head) { struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head); - if (qdisc_is_percpu_stats(qdisc)) + if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); + free_percpu(qdisc->cpu_qstats); + } kfree((char *) qdisc - qdisc->padded); } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index e6c7416d0332..d3e21dac8b40 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -895,9 +895,10 @@ static void hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl) { unsigned int len = cl->qdisc->q.qlen; + unsigned int backlog = cl->qdisc->qstats.backlog; qdisc_reset(cl->qdisc); - qdisc_tree_decrease_qlen(cl->qdisc, len); + qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); } static void @@ -1215,11 +1216,7 @@ hfsc_graft_class(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, new = &noop_qdisc; } - sch_tree_lock(sch); - hfsc_purge_queue(sch, cl); - *old = cl->qdisc; - cl->qdisc = new; - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 15d3aabfe250..792c6f330f77 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -390,6 +390,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) struct hhf_sched_data *q = qdisc_priv(sch); enum wdrr_bucket_idx idx; struct wdrr_bucket *bucket; + unsigned int prev_backlog; idx = hhf_classify(skb, sch); @@ -417,6 +418,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) if (++sch->q.qlen <= sch->limit) return NET_XMIT_SUCCESS; + prev_backlog = sch->qstats.backlog; q->drop_overlimit++; /* Return Congestion Notification only if we dropped a packet from this * bucket. @@ -425,7 +427,7 @@ static int hhf_enqueue(struct sk_buff *skb, struct Qdisc *sch) return NET_XMIT_CN; /* As we dropped a packet, better let upper stack know this. */ - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, prev_backlog - sch->qstats.backlog); return NET_XMIT_SUCCESS; } @@ -535,7 +537,7 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) { struct hhf_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_HHF_MAX + 1]; - unsigned int qlen; + unsigned int qlen, prev_backlog; int err; u64 non_hh_quantum; u32 new_quantum = q->quantum; @@ -585,12 +587,14 @@ static int hhf_change(struct Qdisc *sch, struct nlattr *opt) } qlen = sch->q.qlen; + prev_backlog = sch->qstats.backlog; while (sch->q.qlen > sch->limit) { struct sk_buff *skb = hhf_dequeue(sch); kfree_skb(skb); } - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, + prev_backlog - sch->qstats.backlog); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index f1acb0f60dc3..ccff00640713 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -600,6 +600,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch) htb_activate(q, cl); } + qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return NET_XMIT_SUCCESS; } @@ -889,6 +890,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) ok: qdisc_bstats_update(sch, skb); qdisc_unthrottled(sch); + qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; return skb; } @@ -955,6 +957,7 @@ static unsigned int htb_drop(struct Qdisc *sch) unsigned int len; if (cl->un.leaf.q->ops->drop && (len = cl->un.leaf.q->ops->drop(cl->un.leaf.q))) { + sch->qstats.backlog -= len; sch->q.qlen--; if (!cl->un.leaf.q->q.qlen) htb_deactivate(q, cl); @@ -984,12 +987,12 @@ static void htb_reset(struct Qdisc *sch) } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; - } } qdisc_watchdog_cancel(&q->watchdog); __skb_queue_purge(&q->direct_queue); sch->q.qlen = 0; + sch->qstats.backlog = 0; memset(q->hlevel, 0, sizeof(q->hlevel)); memset(q->row_mask, 0, sizeof(q->row_mask)); for (i = 0; i < TC_HTB_NUMPRIO; i++) @@ -1165,14 +1168,7 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->common.classid)) == NULL) return -ENOBUFS; - sch_tree_lock(sch); - *old = cl->un.leaf.q; - cl->un.leaf.q = new; - if (*old != NULL) { - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - } - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->un.leaf.q); return 0; } @@ -1274,7 +1270,6 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) { struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)arg; - unsigned int qlen; struct Qdisc *new_q = NULL; int last_child = 0; @@ -1294,9 +1289,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); if (!cl->level) { - qlen = cl->un.leaf.q->q.qlen; + unsigned int qlen = cl->un.leaf.q->q.qlen; + unsigned int backlog = cl->un.leaf.q->qstats.backlog; + qdisc_reset(cl->un.leaf.q); - qdisc_tree_decrease_qlen(cl->un.leaf.q, qlen); + qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog); } /* delete from hash and active; remainder in destroy_class */ @@ -1430,10 +1427,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, sch_tree_lock(sch); if (parent && !parent->level) { unsigned int qlen = parent->un.leaf.q->q.qlen; + unsigned int backlog = parent->un.leaf.q->qstats.backlog; /* turn parent into inner node */ qdisc_reset(parent->un.leaf.q); - qdisc_tree_decrease_qlen(parent->un.leaf.q, qlen); + qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); qdisc_destroy(parent->un.leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 42dd218871e0..23437d62a8db 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -218,7 +218,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) if (q->queues[i] != &noop_qdisc) { struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; - qdisc_tree_decrease_qlen(child, child->q.qlen); + qdisc_tree_reduce_backlog(child, child->q.qlen, + child->qstats.backlog); qdisc_destroy(child); } } @@ -238,8 +239,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt) q->queues[i] = child; if (old != &noop_qdisc) { - qdisc_tree_decrease_qlen(old, - old->q.qlen); + qdisc_tree_reduce_backlog(old, + old->q.qlen, + old->qstats.backlog); qdisc_destroy(old); } sch_tree_unlock(sch); @@ -303,13 +305,7 @@ static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->queues[band]; - q->queues[band] = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->queues[band]); return 0; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 956ead2cab9a..80124c1edbba 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -395,6 +395,25 @@ static void tfifo_enqueue(struct sk_buff *nskb, struct Qdisc *sch) sch->q.qlen++; } +/* netem can't properly corrupt a megapacket (like we get from GSO), so instead + * when we statistically choose to corrupt one, we instead segment it, returning + * the first packet to be corrupted, and re-enqueue the remaining frames + */ +static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch) +{ + struct sk_buff *segs; + netdev_features_t features = netif_skb_features(skb); + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + + if (IS_ERR_OR_NULL(segs)) { + qdisc_reshape_fail(skb, sch); + return NULL; + } + consume_skb(skb); + return segs; +} + /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -407,7 +426,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* We don't fill cb now as skb_unshare() may invalidate it */ struct netem_skb_cb *cb; struct sk_buff *skb2; + struct sk_buff *segs = NULL; + unsigned int len = 0, last_len, prev_len = qdisc_pkt_len(skb); + int nb = 0; int count = 1; + int rc = NET_XMIT_SUCCESS; /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) @@ -453,10 +476,23 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) * do it now in software before we mangle it. */ if (q->corrupt && q->corrupt >= get_crandom(&q->corrupt_cor)) { + if (skb_is_gso(skb)) { + segs = netem_segment(skb, sch); + if (!segs) + return NET_XMIT_DROP; + } else { + segs = skb; + } + + skb = segs; + segs = segs->next; + if (!(skb = skb_unshare(skb, GFP_ATOMIC)) || (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb))) - return qdisc_drop(skb, sch); + skb_checksum_help(skb))) { + rc = qdisc_drop(skb, sch); + goto finish_segs; + } skb->data[prandom_u32() % skb_headlen(skb)] ^= 1<<(prandom_u32() % 8); @@ -516,6 +552,27 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) sch->qstats.requeues++; } +finish_segs: + if (segs) { + while (segs) { + skb2 = segs->next; + segs->next = NULL; + qdisc_skb_cb(segs)->pkt_len = segs->len; + last_len = segs->len; + rc = qdisc_enqueue(segs, sch); + if (rc != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(rc)) + qdisc_qstats_drop(sch); + } else { + nb++; + len += last_len; + } + segs = skb2; + } + sch->q.qlen += nb; + if (nb > 1) + qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); + } return NET_XMIT_SUCCESS; } @@ -598,7 +655,8 @@ deliver: if (unlikely(err != NET_XMIT_SUCCESS)) { if (net_xmit_drop_count(err)) { qdisc_qstats_drop(sch); - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, + qdisc_pkt_len(skb)); } } goto tfifo_dequeue; @@ -1037,15 +1095,7 @@ static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, { struct netem_sched_data *q = qdisc_priv(sch); - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - if (*old) { - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - } - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c index b783a446d884..71ae3b9629f9 100644 --- a/net/sched/sch_pie.c +++ b/net/sched/sch_pie.c @@ -183,7 +183,7 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt) { struct pie_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_PIE_MAX + 1]; - unsigned int qlen; + unsigned int qlen, dropped = 0; int err; if (!opt) @@ -232,10 +232,11 @@ static int pie_change(struct Qdisc *sch, struct nlattr *opt) while (sch->q.qlen > sch->limit) { struct sk_buff *skb = __skb_dequeue(&sch->q); + dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); qdisc_drop(skb, sch); } - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); sch_tree_unlock(sch); return 0; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 8e5cd34aaa74..e671b1a4e815 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -191,7 +191,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; if (child != &noop_qdisc) { - qdisc_tree_decrease_qlen(child, child->q.qlen); + qdisc_tree_reduce_backlog(child, child->q.qlen, child->qstats.backlog); qdisc_destroy(child); } } @@ -210,8 +210,9 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) q->queues[i] = child; if (old != &noop_qdisc) { - qdisc_tree_decrease_qlen(old, - old->q.qlen); + qdisc_tree_reduce_backlog(old, + old->q.qlen, + old->qstats.backlog); qdisc_destroy(old); } sch_tree_unlock(sch); @@ -268,13 +269,7 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->queues[band]; - q->queues[band] = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->queues[band]); return 0; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 3ec7e88a43ca..e2b8fd47008b 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -221,9 +221,10 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) static void qfq_purge_queue(struct qfq_class *cl) { unsigned int len = cl->qdisc->q.qlen; + unsigned int backlog = cl->qdisc->qstats.backlog; qdisc_reset(cl->qdisc); - qdisc_tree_decrease_qlen(cl->qdisc, len); + qdisc_tree_reduce_backlog(cl->qdisc, len, backlog); } static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { @@ -619,11 +620,7 @@ static int qfq_graft_class(struct Qdisc *sch, unsigned long arg, new = &noop_qdisc; } - sch_tree_lock(sch); - qfq_purge_queue(cl); - *old = cl->qdisc; - cl->qdisc = new; - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &cl->qdisc); return 0; } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 6c0534cc7758..8c0508c0e287 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -210,7 +210,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) q->flags = ctl->flags; q->limit = ctl->limit; if (child) { - qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, + q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; } @@ -313,12 +314,7 @@ static int red_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 5819dd82630d..e1d634e3c255 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -518,7 +518,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt) sch_tree_lock(sch); - qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, + q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; @@ -614,12 +615,7 @@ static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b877140beda5..4417fb25166f 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -369,7 +369,7 @@ static int sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); - unsigned int hash; + unsigned int hash, dropped; sfq_index x, qlen; struct sfq_slot *slot; int uninitialized_var(ret); @@ -484,7 +484,7 @@ enqueue: return NET_XMIT_SUCCESS; qlen = slot->qlen; - sfq_drop(sch); + dropped = sfq_drop(sch); /* Return Congestion Notification only if we dropped a packet * from this flow. */ @@ -492,7 +492,7 @@ enqueue: return NET_XMIT_CN; /* As we dropped a packet, better let upper stack know this */ - qdisc_tree_decrease_qlen(sch, 1); + qdisc_tree_reduce_backlog(sch, 1, dropped); return NET_XMIT_SUCCESS; } @@ -560,6 +560,7 @@ static void sfq_rehash(struct Qdisc *sch) struct sfq_slot *slot; struct sk_buff_head list; int dropped = 0; + unsigned int drop_len = 0; __skb_queue_head_init(&list); @@ -588,6 +589,7 @@ static void sfq_rehash(struct Qdisc *sch) if (x >= SFQ_MAX_FLOWS) { drop: qdisc_qstats_backlog_dec(sch, skb); + drop_len += qdisc_pkt_len(skb); kfree_skb(skb); dropped++; continue; @@ -617,7 +619,7 @@ drop: } } sch->q.qlen -= dropped; - qdisc_tree_decrease_qlen(sch, dropped); + qdisc_tree_reduce_backlog(sch, dropped, drop_len); } static void sfq_perturbation(unsigned long arg) @@ -641,7 +643,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) struct sfq_sched_data *q = qdisc_priv(sch); struct tc_sfq_qopt *ctl = nla_data(opt); struct tc_sfq_qopt_v1 *ctl_v1 = NULL; - unsigned int qlen; + unsigned int qlen, dropped = 0; struct red_parms *p = NULL; if (opt->nla_len < nla_attr_size(sizeof(*ctl))) @@ -690,8 +692,8 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) qlen = sch->q.qlen; while (sch->q.qlen > q->limit) - sfq_drop(sch); - qdisc_tree_decrease_qlen(sch, qlen - sch->q.qlen); + dropped += sfq_drop(sch); + qdisc_tree_reduce_backlog(sch, qlen - sch->q.qlen, dropped); del_timer(&q->perturb_timer); if (q->perturb_period) { diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index a4afde14e865..c2fbde742f37 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -160,6 +160,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) struct tbf_sched_data *q = qdisc_priv(sch); struct sk_buff *segs, *nskb; netdev_features_t features = netif_skb_features(skb); + unsigned int len = 0, prev_len = qdisc_pkt_len(skb); int ret, nb; segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); @@ -172,6 +173,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) nskb = segs->next; segs->next = NULL; qdisc_skb_cb(segs)->pkt_len = segs->len; + len += segs->len; ret = qdisc_enqueue(segs, q->qdisc); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) @@ -183,7 +185,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) } sch->q.qlen += nb; if (nb > 1) - qdisc_tree_decrease_qlen(sch, 1 - nb); + qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); consume_skb(skb); return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } @@ -399,7 +401,8 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt) sch_tree_lock(sch); if (child) { - qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, + q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); q->qdisc = child; } @@ -502,13 +505,7 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->qdisc); return 0; } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0e4198ee2370..18361cbfc882 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -519,6 +519,8 @@ static int sctp_v6_cmp_addr(const union sctp_addr *addr1, } return 0; } + if (addr1->v6.sin6_port != addr2->v6.sin6_port) + return 0; if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; /* If this is a linklocal address, compare the scope_id. */ @@ -634,6 +636,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, struct sock *newsk; struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; + struct ipv6_txoptions *opt; newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot); if (!newsk) @@ -653,6 +656,13 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) + opt = ipv6_dup_options(newsk, opt); + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); + /* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname() * and getpeername(). */ diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e13c3c3ea4ac..9d134ab3351f 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -60,6 +60,8 @@ #include <net/inet_common.h> #include <net/inet_ecn.h> +#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) + /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; @@ -1332,6 +1334,8 @@ static __init int sctp_init(void) unsigned long limit; int max_share; int order; + int num_entries; + int max_entry_order; sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); @@ -1384,14 +1388,24 @@ static __init int sctp_init(void) /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. + * Though not identical. Start by getting a goal size */ if (totalram_pages >= (128 * 1024)) goal = totalram_pages >> (22 - PAGE_SHIFT); else goal = totalram_pages >> (24 - PAGE_SHIFT); - for (order = 0; (1UL << order) < goal; order++) - ; + /* Then compute the page order for said goal */ + order = get_order(goal); + + /* Now compute the required page order for the maximum sized table we + * want to create + */ + max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * + sizeof(struct sctp_bind_hashbucket)); + + /* Limit the page order by that maximum hash table size */ + order = min(order, max_entry_order); do { sctp_assoc_hashsize = (1UL << order) * PAGE_SIZE / @@ -1425,27 +1439,42 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } - /* Allocate and initialize the SCTP port hash table. */ + /* Allocate and initialize the SCTP port hash table. + * Note that order is initalized to start at the max sized + * table we want to support. If we can't get that many pages + * reduce the order and try again + */ do { - sctp_port_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_bind_hashbucket); - if ((sctp_port_hashsize > (64 * 1024)) && order > 0) - continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); + if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } + + /* Now compute the number of entries that will fit in the + * port hash space we allocated + */ + num_entries = (1UL << order) * PAGE_SIZE / + sizeof(struct sctp_bind_hashbucket); + + /* And finish by rounding it down to the nearest power of two + * this wastes some memory of course, but its needed because + * the hash function operates based on the assumption that + * that the number of entries is a power of two + */ + sctp_port_hashsize = rounddown_pow_of_two(num_entries); + for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); } - pr_info("Hash tables configured (established %d bind %d)\n", - sctp_assoc_hashsize, sctp_port_hashsize); + pr_info("Hash tables configured (established %d bind %d/%d)\n", + sctp_assoc_hashsize, sctp_port_hashsize, num_entries); sctp_sysctl_register(); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 06320c8c1c86..83a07d468644 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1652,7 +1652,7 @@ static sctp_cookie_param_t *sctp_pack_cookie(const struct sctp_endpoint *ep, /* Set an expiration time for the cookie. */ cookie->c.expiration = ktime_add(asoc->cookie_life, - ktime_get()); + ktime_get_real()); /* Copy the peer's init packet. */ memcpy(&cookie->c.peer_init[0], init_chunk->chunk_hdr, @@ -1780,7 +1780,7 @@ no_hmac: if (sock_flag(ep->base.sk, SOCK_TIMESTAMP)) kt = skb_get_ktime(skb); else - kt = ktime_get(); + kt = ktime_get_real(); if (!asoc && ktime_before(bear_cookie->expiration, kt)) { /* diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index fef2acdf4a2e..ecae5561b912 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -244,12 +244,13 @@ void sctp_generate_t3_rtx_event(unsigned long peer) int error; struct sctp_transport *transport = (struct sctp_transport *) peer; struct sctp_association *asoc = transport->asoc; - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); /* Check whether a task is in the sock. */ - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ @@ -272,10 +273,10 @@ void sctp_generate_t3_rtx_event(unsigned long peer) transport, GFP_ATOMIC); if (error) - asoc->base.sk->sk_err = -error; + sk->sk_err = -error; out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_transport_put(transport); } @@ -285,11 +286,12 @@ out_unlock: static void sctp_generate_timeout_event(struct sctp_association *asoc, sctp_event_timeout_t timeout_type) { - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); int error = 0; - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy: timer %d\n", __func__, timeout_type); @@ -312,10 +314,10 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc, (void *)timeout_type, GFP_ATOMIC); if (error) - asoc->base.sk->sk_err = -error; + sk->sk_err = -error; out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_association_put(asoc); } @@ -365,10 +367,11 @@ void sctp_generate_heartbeat_event(unsigned long data) int error = 0; struct sctp_transport *transport = (struct sctp_transport *) data; struct sctp_association *asoc = transport->asoc; - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ @@ -389,10 +392,10 @@ void sctp_generate_heartbeat_event(unsigned long data) transport, GFP_ATOMIC); if (error) - asoc->base.sk->sk_err = -error; + sk->sk_err = -error; out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_transport_put(transport); } @@ -403,10 +406,11 @@ void sctp_generate_proto_unreach_event(unsigned long data) { struct sctp_transport *transport = (struct sctp_transport *) data; struct sctp_association *asoc = transport->asoc; - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ @@ -427,7 +431,7 @@ void sctp_generate_proto_unreach_event(unsigned long data) asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_association_put(asoc); } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 3ee27b7704ff..e6bb98e583fb 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4829,7 +4829,8 @@ sctp_disposition_t sctp_sf_do_9_1_prm_abort( retval = SCTP_DISPOSITION_CONSUME; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + if (abort) + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); /* Even if we can't send the ABORT due to low memory delete the * TCB. This is a departure from our typical NOMEM handling. @@ -4966,7 +4967,8 @@ sctp_disposition_t sctp_sf_cookie_wait_prm_abort( SCTP_TO(SCTP_EVENT_TIMEOUT_T1_INIT)); retval = SCTP_DISPOSITION_CONSUME; - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); + if (abort) + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(abort)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, SCTP_STATE(SCTP_STATE_CLOSED)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 66d796075050..3c5833058b03 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1513,8 +1513,7 @@ static void sctp_close(struct sock *sk, long timeout) struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); - if (chunk) - sctp_primitive_ABORT(net, asoc, chunk); + sctp_primitive_ABORT(net, asoc, chunk); } else sctp_primitive_SHUTDOWN(net, asoc, NULL); } @@ -5556,6 +5555,7 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, struct sctp_hmac_algo_param *hmacs; __u16 data_len = 0; u32 num_idents; + int i; if (!ep->auth_enable) return -EACCES; @@ -5573,8 +5573,12 @@ static int sctp_getsockopt_hmac_ident(struct sock *sk, int len, return -EFAULT; if (put_user(num_idents, &p->shmac_num_idents)) return -EFAULT; - if (copy_to_user(p->shmac_idents, hmacs->hmac_ids, data_len)) - return -EFAULT; + for (i = 0; i < num_idents; i++) { + __u16 hmacid = ntohs(hmacs->hmac_ids[i]); + + if (copy_to_user(&p->shmac_idents[i], &hmacid, sizeof(__u16))) + return -EFAULT; + } return 0; } @@ -6654,6 +6658,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->srinfo->sinfo_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -6677,6 +6682,7 @@ static int sctp_msghdr_parse(const struct msghdr *msg, sctp_cmsgs_t *cmsgs) if (cmsgs->sinfo->snd_flags & ~(SCTP_UNORDERED | SCTP_ADDR_OVER | + SCTP_SACK_IMMEDIATELY | SCTP_ABORT | SCTP_EOF)) return -EINVAL; break; @@ -7175,6 +7181,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; newsk->sk_flags = sk->sk_flags; + newsk->sk_tsflags = sk->sk_tsflags; newsk->sk_no_check_tx = sk->sk_no_check_tx; newsk->sk_no_check_rx = sk->sk_no_check_rx; newsk->sk_reuse = sk->sk_reuse; @@ -7207,6 +7214,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->mc_ttl = 1; newinet->mc_index = 0; newinet->mc_list = NULL; + + if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) + net_enable_timestamp(); } static inline void sctp_copy_descendant(struct sock *sk_to, diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 26d50c565f54..3e0fc5127225 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -320,7 +320,7 @@ static int proc_sctp_do_hmac_alg(struct ctl_table *ctl, int write, struct ctl_table tbl; bool changed = false; char *none = "none"; - char tmp[8]; + char tmp[8] = {0}; int ret; memset(&tbl, 0, sizeof(struct ctl_table)); diff --git a/net/socket.c b/net/socket.c index 884e32997698..e66e4f357506 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1705,6 +1705,7 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, msg.msg_name = addr ? (struct sockaddr *)&address : NULL; /* We assume all kernel code knows the size of sockaddr_storage */ msg.msg_namelen = 0; + msg.msg_iocb = NULL; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, iov_iter_count(&msg.msg_iter), flags); @@ -2246,31 +2247,31 @@ int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, break; } -out_put: - fput_light(sock->file, fput_needed); - if (err == 0) - return datagrams; + goto out_put; - if (datagrams != 0) { + if (datagrams == 0) { + datagrams = err; + goto out_put; + } + + /* + * We may return less entries than requested (vlen) if the + * sock is non block and there aren't enough datagrams... + */ + if (err != -EAGAIN) { /* - * We may return less entries than requested (vlen) if the - * sock is non block and there aren't enough datagrams... + * ... or if recvmsg returns an error after we + * received some datagrams, where we record the + * error to return on the next call or if the + * app asks about it using getsockopt(SO_ERROR). */ - if (err != -EAGAIN) { - /* - * ... or if recvmsg returns an error after we - * received some datagrams, where we record the - * error to return on the next call or if the - * app asks about it using getsockopt(SO_ERROR). - */ - sock->sk->sk_err = -err; - } - - return datagrams; + sock->sk->sk_err = -err; } +out_put: + fput_light(sock->file, fput_needed); - return err; + return datagrams; } SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 1095be9c80ab..4605dc73def6 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -857,8 +857,8 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g goto out; if (svc_getnl(&buf->head[0]) != seq) goto out; - /* trim off the mic at the end before returning */ - xdr_buf_trim(buf, mic.len + 4); + /* trim off the mic and padding at the end before returning */ + xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4); stat = 0; out: kfree(mic.data); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2928afffbb81..9ec709b9707c 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1175,14 +1175,14 @@ int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h) } crq->q.reader = 0; - crq->item = cache_get(h); crq->buf = buf; crq->len = 0; crq->readers = 0; spin_lock(&queue_lock); - if (test_bit(CACHE_PENDING, &h->flags)) + if (test_bit(CACHE_PENDING, &h->flags)) { + crq->item = cache_get(h); list_add_tail(&crq->q.list, &detail->queue); - else + } else /* Lost a race, no longer PENDING, so don't enqueue */ ret = -EAGAIN; spin_unlock(&queue_lock); @@ -1218,7 +1218,7 @@ int qword_get(char **bpp, char *dest, int bufsize) if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; - while (len < bufsize) { + while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index e6ce1517367f..16e831dcfde0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -442,7 +442,7 @@ out_no_rpciod: return ERR_PTR(err); } -struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, +static struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, struct rpc_xprt *xprt) { struct rpc_clnt *clnt = NULL; @@ -474,7 +474,6 @@ struct rpc_clnt *rpc_create_xprt(struct rpc_create_args *args, return clnt; } -EXPORT_SYMBOL_GPL(rpc_create_xprt); /** * rpc_create - create an RPC client and transport with one call @@ -500,6 +499,15 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) }; char servername[48]; + if (args->bc_xprt) { + WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP); + xprt = args->bc_xprt->xpt_bc_xprt; + if (xprt) { + xprt_get(xprt); + return rpc_create_xprt(args, xprt); + } + } + if (args->flags & RPC_CLNT_CREATE_INFINITE_SLOTS) xprtargs.flags |= XPRT_CREATE_INFINITE_SLOTS; if (args->flags & RPC_CLNT_CREATE_NO_IDLE_TIMEOUT) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 055453d48668..a8dbe8001e46 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -15,6 +15,7 @@ #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/netdevice.h> +#include <linux/rtnetlink.h> #include <net/ip_fib.h> #include <net/switchdev.h> @@ -64,7 +65,6 @@ int netdev_switch_port_stp_update(struct net_device *dev, u8 state) } EXPORT_SYMBOL_GPL(netdev_switch_port_stp_update); -static DEFINE_MUTEX(netdev_switch_mutex); static RAW_NOTIFIER_HEAD(netdev_switch_notif_chain); /** @@ -79,9 +79,9 @@ int register_netdev_switch_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); + rtnl_lock(); err = raw_notifier_chain_register(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(register_netdev_switch_notifier); @@ -97,9 +97,9 @@ int unregister_netdev_switch_notifier(struct notifier_block *nb) { int err; - mutex_lock(&netdev_switch_mutex); + rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_switch_notif_chain, nb); - mutex_unlock(&netdev_switch_mutex); + rtnl_unlock(); return err; } EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); @@ -113,16 +113,17 @@ EXPORT_SYMBOL_GPL(unregister_netdev_switch_notifier); * Call all network notifier blocks. This should be called by driver * when it needs to propagate hardware event. * Return values are same as for atomic_notifier_call_chain(). + * rtnl_lock must be held. */ int call_netdev_switch_notifiers(unsigned long val, struct net_device *dev, struct netdev_switch_notifier_info *info) { int err; + ASSERT_RTNL(); + info->dev = dev; - mutex_lock(&netdev_switch_mutex); err = raw_notifier_call_chain(&netdev_switch_notif_chain, val, info); - mutex_unlock(&netdev_switch_mutex); return err; } EXPORT_SYMBOL_GPL(call_netdev_switch_notifiers); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index ce9121e8e990..e5ec86dd8dc1 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -712,7 +712,7 @@ static int tipc_nl_compat_name_table_dump(struct tipc_nl_compat_msg *msg, goto out; tipc_tlv_sprintf(msg->rep, "%-10u %s", - nla_get_u32(publ[TIPC_NLA_PUBL_REF]), + nla_get_u32(publ[TIPC_NLA_PUBL_KEY]), scope_str[nla_get_u32(publ[TIPC_NLA_PUBL_SCOPE])]); out: tipc_tlv_sprintf(msg->rep, "\n"); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 20cc6df07157..d41d424b9913 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2804,6 +2804,9 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (!attrs[TIPC_NLA_SOCK]) + return -EINVAL; + err = nla_parse_nested(sock, TIPC_NLA_SOCK_MAX, attrs[TIPC_NLA_SOCK], tipc_nl_sock_policy); diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 1c147c869c2e..948f316019d7 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -302,11 +302,10 @@ static void subscr_conn_msg_event(struct net *net, int conid, struct tipc_net *tn = net_generic(net, tipc_net_id); spin_lock_bh(&subscriber->lock); - subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub); - if (sub) - tipc_nametbl_subscribe(sub); - else + if (subscr_subscribe(net, (struct tipc_subscr *)buf, subscriber, &sub)) tipc_conn_terminate(tn->topsrv, subscriber->conid); + else + tipc_nametbl_subscribe(sub); spin_unlock_bh(&subscriber->lock); } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1975fd8d1c10..03da879008d7 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -935,32 +935,20 @@ fail: return NULL; } -static int unix_mknod(const char *sun_path, umode_t mode, struct path *res) +static int unix_mknod(struct dentry *dentry, struct path *path, umode_t mode, + struct path *res) { - struct dentry *dentry; - struct path path; - int err = 0; - /* - * Get the parent directory, calculate the hash for last - * component. - */ - dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); - err = PTR_ERR(dentry); - if (IS_ERR(dentry)) - return err; + int err; - /* - * All right, let's create it. - */ - err = security_path_mknod(&path, dentry, mode, 0); + err = security_path_mknod(path, dentry, mode, 0); if (!err) { - err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0); + err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0); if (!err) { - res->mnt = mntget(path.mnt); + res->mnt = mntget(path->mnt); res->dentry = dget(dentry); } } - done_path_create(&path, dentry); + return err; } @@ -971,10 +959,12 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; char *sun_path = sunaddr->sun_path; - int err; + int err, name_err; unsigned int hash; struct unix_address *addr; struct hlist_head *list; + struct path path; + struct dentry *dentry; err = -EINVAL; if (sunaddr->sun_family != AF_UNIX) @@ -990,14 +980,34 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; addr_len = err; + name_err = 0; + dentry = NULL; + if (sun_path[0]) { + /* Get the parent directory, calculate the hash for last + * component. + */ + dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0); + + if (IS_ERR(dentry)) { + /* delay report until after 'already bound' check */ + name_err = PTR_ERR(dentry); + dentry = NULL; + } + } + err = mutex_lock_interruptible(&u->readlock); if (err) - goto out; + goto out_path; err = -EINVAL; if (u->addr) goto out_up; + if (name_err) { + err = name_err == -EEXIST ? -EADDRINUSE : name_err; + goto out_up; + } + err = -ENOMEM; addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL); if (!addr) @@ -1008,11 +1018,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) addr->hash = hash ^ sk->sk_type; atomic_set(&addr->refcnt, 1); - if (sun_path[0]) { - struct path path; + if (dentry) { + struct path u_path; umode_t mode = S_IFSOCK | (SOCK_INODE(sock)->i_mode & ~current_umask()); - err = unix_mknod(sun_path, mode, &path); + err = unix_mknod(dentry, &path, mode, &u_path); if (err) { if (err == -EEXIST) err = -EADDRINUSE; @@ -1020,9 +1030,9 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out_up; } addr->hash = UNIX_HASH_SIZE; - hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE-1); + hash = d_backing_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1); spin_lock(&unix_table_lock); - u->path = path; + u->path = u_path; list = &unix_socket_table[hash]; } else { spin_lock(&unix_table_lock); @@ -1045,6 +1055,10 @@ out_unlock: spin_unlock(&unix_table_lock); out_up: mutex_unlock(&u->readlock); +out_path: + if (dentry) + done_path_create(&path, dentry); + out: return err; } @@ -1464,7 +1478,7 @@ static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb) UNIXCB(skb).fp = NULL; for (i = scm->fp->count-1; i >= 0; i--) - unix_notinflight(scm->fp->fp[i]); + unix_notinflight(scm->fp->user, scm->fp->fp[i]); } static void unix_destruct_scm(struct sk_buff *skb) @@ -1481,6 +1495,21 @@ static void unix_destruct_scm(struct sk_buff *skb) sock_wfree(skb); } +/* + * The "user->unix_inflight" variable is protected by the garbage + * collection lock, and we just read it locklessly here. If you go + * over the limit, there might be a tiny race in actually noticing + * it across threads. Tough. + */ +static inline bool too_many_unix_fds(struct task_struct *p) +{ + struct user_struct *user = current_user(); + + if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE))) + return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); + return false; +} + #define MAX_RECURSION_LEVEL 4 static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) @@ -1489,6 +1518,9 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) unsigned char max_level = 0; int unix_sock_count = 0; + if (too_many_unix_fds(current)) + return -ETOOMANYREFS; + for (i = scm->fp->count - 1; i >= 0; i--) { struct sock *sk = unix_get_socket(scm->fp->fp[i]); @@ -1510,10 +1542,8 @@ static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb) if (!UNIXCB(skb).fp) return -ENOMEM; - if (unix_sock_count) { - for (i = scm->fp->count - 1; i >= 0; i--) - unix_inflight(scm->fp->fp[i]); - } + for (i = scm->fp->count - 1; i >= 0; i--) + unix_inflight(scm->fp->user, scm->fp->fp[i]); return max_level; } @@ -1698,7 +1728,12 @@ restart_locked: goto out_unlock; } - if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + /* other == sk && unix_peer(other) != sk if + * - unix_peer(sk) == NULL, destination address bound to sk + * - unix_peer(sk) == sk by time of get but disconnected before lock + */ + if (other != sk && + unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); @@ -2072,14 +2107,7 @@ static int unix_stream_recvmsg(struct socket *sock, struct msghdr *msg, memset(&scm, 0, sizeof(scm)); - err = mutex_lock_interruptible(&u->readlock); - if (unlikely(err)) { - /* recvmsg() in non blocking mode is supposed to return -EAGAIN - * sk_rcvtimeo is not honored by mutex_lock_interruptible() - */ - err = noblock ? -EAGAIN : -ERESTARTSYS; - goto out; - } + mutex_lock(&u->readlock); if (flags & MSG_PEEK) skip = sk_peek_offset(sk, flags); @@ -2120,12 +2148,13 @@ again: timeo = unix_stream_data_wait(sk, timeo, last); - if (signal_pending(current) - || mutex_lock_interruptible(&u->readlock)) { + if (signal_pending(current)) { err = sock_intr_errno(timeo); + scm_destroy(&scm); goto out; } + mutex_lock(&u->readlock); continue; unlock: unix_state_unlock(sk); diff --git a/net/unix/diag.c b/net/unix/diag.c index c512f64d5287..4d9679701a6d 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -220,7 +220,7 @@ done: return skb->len; } -static struct sock *unix_lookup_by_ino(int ino) +static struct sock *unix_lookup_by_ino(unsigned int ino) { int i; struct sock *sk; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index a73a226f2d33..6a0d48525fcf 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -116,15 +116,15 @@ struct sock *unix_get_socket(struct file *filp) * descriptor if it is for an AF_UNIX socket. */ -void unix_inflight(struct file *fp) +void unix_inflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); - if (atomic_long_inc_return(&u->inflight) == 1) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); @@ -132,25 +132,28 @@ void unix_inflight(struct file *fp) BUG_ON(list_empty(&u->link)); } unix_tot_inflight++; - spin_unlock(&unix_gc_lock); } + user->unix_inflight++; + spin_unlock(&unix_gc_lock); } -void unix_notinflight(struct file *fp) +void unix_notinflight(struct user_struct *user, struct file *fp) { struct sock *s = unix_get_socket(fp); + spin_lock(&unix_gc_lock); + if (s) { struct unix_sock *u = unix_sk(s); - spin_lock(&unix_gc_lock); BUG_ON(list_empty(&u->link)); if (atomic_long_dec_and_test(&u->inflight)) list_del_init(&u->link); unix_tot_inflight--; - spin_unlock(&unix_gc_lock); } + user->unix_inflight--; + spin_unlock(&unix_gc_lock); } static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *), diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 2ec86e652a19..e1c69b216db3 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1794,27 +1794,8 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, else if (sk->sk_shutdown & RCV_SHUTDOWN) err = 0; - if (copied > 0) { - /* We only do these additional bookkeeping/notification steps - * if we actually copied something out of the queue pair - * instead of just peeking ahead. - */ - - if (!(flags & MSG_PEEK)) { - /* If the other side has shutdown for sending and there - * is nothing more to read, then modify the socket - * state. - */ - if (vsk->peer_shutdown & SEND_SHUTDOWN) { - if (vsock_stream_has_data(vsk) <= 0) { - sk->sk_state = SS_UNCONNECTED; - sock_set_flag(sk, SOCK_DONE); - sk->sk_state_change(sk); - } - } - } + if (copied > 0) err = copied; - } out_wait: finish_wait(sk_sleep(sk), &wait); diff --git a/net/wireless/core.c b/net/wireless/core.c index 2a0bbd22854b..71e9b84847f3 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1138,6 +1138,8 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb, return NOTIFY_DONE; } + wireless_nlevent_flush(); + return NOTIFY_OK; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 04b6f3f6ee0b..f24138681b80 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12777,7 +12777,7 @@ static int nl80211_netlink_notify(struct notifier_block * nb, struct wireless_dev *wdev; struct cfg80211_beacon_registration *reg, *tmp; - if (state != NETLINK_URELEASE) + if (state != NETLINK_URELEASE || notify->protocol != NETLINK_GENERIC) return NOTIFY_DONE; rcu_read_lock(); diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index c8717c1d082e..c753211cb83f 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -342,6 +342,40 @@ static const int compat_event_type_size[] = { /* IW event code */ +void wireless_nlevent_flush(void) +{ + struct sk_buff *skb; + struct net *net; + + ASSERT_RTNL(); + + for_each_net(net) { + while ((skb = skb_dequeue(&net->wext_nlevents))) + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, + GFP_KERNEL); + } +} +EXPORT_SYMBOL_GPL(wireless_nlevent_flush); + +static int wext_netdev_notifier_call(struct notifier_block *nb, + unsigned long state, void *ptr) +{ + /* + * When a netdev changes state in any way, flush all pending messages + * to avoid them going out in a strange order, e.g. RTM_NEWLINK after + * RTM_DELLINK, or with IFF_UP after without IFF_UP during dev_close() + * or similar - all of which could otherwise happen due to delays from + * schedule_work(). + */ + wireless_nlevent_flush(); + + return NOTIFY_OK; +} + +static struct notifier_block wext_netdev_notifier = { + .notifier_call = wext_netdev_notifier_call, +}; + static int __net_init wext_pernet_init(struct net *net) { skb_queue_head_init(&net->wext_nlevents); @@ -360,7 +394,12 @@ static struct pernet_operations wext_pernet_ops = { static int __init wireless_nlevent_init(void) { - return register_pernet_subsys(&wext_pernet_ops); + int err = register_pernet_subsys(&wext_pernet_ops); + + if (err) + return err; + + return register_netdevice_notifier(&wext_netdev_notifier); } subsys_initcall(wireless_nlevent_init); @@ -368,17 +407,8 @@ subsys_initcall(wireless_nlevent_init); /* Process events generated by the wireless layer or the driver. */ static void wireless_nlevent_process(struct work_struct *work) { - struct sk_buff *skb; - struct net *net; - rtnl_lock(); - - for_each_net(net) { - while ((skb = skb_dequeue(&net->wext_nlevents))) - rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, - GFP_KERNEL); - } - + wireless_nlevent_flush(); rtnl_unlock(); } @@ -925,8 +955,29 @@ static int wireless_process_ioctl(struct net *net, struct ifreq *ifr, return private(dev, iwr, cmd, info, handler); } /* Old driver API : call driver ioctl handler */ - if (dev->netdev_ops->ndo_do_ioctl) - return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); + if (dev->netdev_ops->ndo_do_ioctl) { +#ifdef CONFIG_COMPAT + if (info->flags & IW_REQUEST_FLAG_COMPAT) { + int ret = 0; + struct iwreq iwr_lcl; + struct compat_iw_point *iwp_compat = (void *) &iwr->u.data; + + memcpy(&iwr_lcl, iwr, sizeof(struct iwreq)); + iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer); + iwr_lcl.u.data.length = iwp_compat->length; + iwr_lcl.u.data.flags = iwp_compat->flags; + + ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd); + + iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer); + iwp_compat->length = iwr_lcl.u.data.length; + iwp_compat->flags = iwr_lcl.u.data.flags; + + return ret; + } else +#endif + return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd); + } return -EOPNOTSUPP; } diff --git a/net/x25/x25_facilities.c b/net/x25/x25_facilities.c index 7ecd04c21360..997ff7b2509b 100644 --- a/net/x25/x25_facilities.c +++ b/net/x25/x25_facilities.c @@ -277,6 +277,7 @@ int x25_negotiate_facilities(struct sk_buff *skb, struct sock *sk, memset(&theirs, 0, sizeof(theirs)); memcpy(new, ours, sizeof(*new)); + memset(dte, 0, sizeof(*dte)); len = x25_parse_facilities(skb, &theirs, dte, &x25->vc_facil_mask); if (len < 0) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index b58286ecd156..cbaf52c837f4 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -292,12 +292,15 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; skb_dst_force(skb); + dev_hold(skb->dev); nexthdr = x->type->input(x, skb); if (nexthdr == -EINPROGRESS) return 0; resume: + dev_put(skb->dev); + spin_lock(&x->lock); if (nexthdr <= 0) { if (nexthdr == -EBADMSG) { diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index fbcedbe33190..5097dce5b916 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -153,6 +153,8 @@ static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb) { struct sk_buff *segs; + BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); + BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET); segs = skb_gso_segment(skb, 0); kfree_skb(skb); if (IS_ERR(segs)) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 638af0655aaf..4cd2076ff84b 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2806,7 +2806,6 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { - struct net *net; int err = 0; if (unlikely(afinfo == NULL)) return -EINVAL; @@ -2837,26 +2836,6 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) } spin_unlock(&xfrm_policy_afinfo_lock); - rtnl_lock(); - for_each_net(net) { - struct dst_ops *xfrm_dst_ops; - - switch (afinfo->family) { - case AF_INET: - xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops; - break; -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops; - break; -#endif - default: - BUG(); - } - *xfrm_dst_ops = *afinfo->dst_ops; - } - rtnl_unlock(); - return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); @@ -2892,22 +2871,6 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); -static void __net_init xfrm_dst_ops_init(struct net *net) -{ - struct xfrm_policy_afinfo *afinfo; - - rcu_read_lock(); - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET]); - if (afinfo) - net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops; -#if IS_ENABLED(CONFIG_IPV6) - afinfo = rcu_dereference(xfrm_policy_afinfo[AF_INET6]); - if (afinfo) - net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops; -#endif - rcu_read_unlock(); -} - static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); @@ -3056,7 +3019,6 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; - xfrm_dst_ops_init(net); rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; |