diff options
Diffstat (limited to 'net')
45 files changed, 640 insertions, 463 deletions
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index d5d71ac96c8a..c24c481b666f 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -127,21 +127,17 @@ 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 5a31420513e1..7b12ea8ea29d 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -75,18 +75,6 @@ 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/multicast.c b/net/batman-adv/multicast.c index eb76386f8d4b..75fa5013af72 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -802,7 +802,9 @@ void batadv_mcast_free(struct batadv_priv *bat_priv) batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 1); batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 1); + spin_lock_bh(&bat_priv->tt.commit_lock); batadv_mcast_mla_tt_retract(bat_priv, NULL); + spin_unlock_bh(&bat_priv->tt.commit_lock); } /** diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index c98b0ab85449..cc63b44f0d2e 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -203,28 +203,25 @@ 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 3c782a33bdac..fe578f75c391 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -163,142 +163,101 @@ 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_hardif_neigh_free_rcu - free the hardif neigh_node - * @rcu: rcu pointer of the neigh_node + * batadv_hardif_neigh_release - release hardif neigh node from lists and + * queue for free after rcu grace period + * @hardif_neigh: hardif neigh neighbor to free */ -static void batadv_hardif_neigh_free_rcu(struct rcu_head *rcu) +static void +batadv_hardif_neigh_release(struct batadv_hardif_neigh_node *hardif_neigh) { - struct batadv_hardif_neigh_node *hardif_neigh; - - hardif_neigh = container_of(rcu, struct batadv_hardif_neigh_node, rcu); - spin_lock_bh(&hardif_neigh->if_incoming->neigh_list_lock); hlist_del_init_rcu(&hardif_neigh->list); spin_unlock_bh(&hardif_neigh->if_incoming->neigh_list_lock); - batadv_hardif_free_ref_now(hardif_neigh->if_incoming); - kfree(hardif_neigh); -} - -/** - * batadv_hardif_neigh_free_now - decrement the hardif neighbors refcounter - * and possibly free it (without rcu callback) - * @hardif_neigh: hardif neigh neighbor to free - */ -static void -batadv_hardif_neigh_free_now(struct batadv_hardif_neigh_node *hardif_neigh) -{ - if (atomic_dec_and_test(&hardif_neigh->refcount)) - batadv_hardif_neigh_free_rcu(&hardif_neigh->rcu); + batadv_hardif_free_ref(hardif_neigh->if_incoming); + kfree_rcu(hardif_neigh, rcu); } /** * batadv_hardif_neigh_free_ref - decrement the hardif neighbors refcounter - * and possibly free it + * and possibly release it * @hardif_neigh: hardif neigh neighbor to free */ void batadv_hardif_neigh_free_ref(struct batadv_hardif_neigh_node *hardif_neigh) { if (atomic_dec_and_test(&hardif_neigh->refcount)) - call_rcu(&hardif_neigh->rcu, batadv_hardif_neigh_free_rcu); + batadv_hardif_neigh_release(hardif_neigh); } /** - * 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_hardif_neigh_node *hardif_neigh; struct batadv_neigh_ifinfo *neigh_ifinfo; struct batadv_algo_ops *bao; - neigh_node = container_of(rcu, struct batadv_neigh_node, rcu); bao = neigh_node->orig_node->bat_priv->bat_algo_ops; 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); } hardif_neigh = batadv_hardif_neigh_get(neigh_node->if_incoming, neigh_node->addr); if (hardif_neigh) { /* batadv_hardif_neigh_get() increases refcount too */ - batadv_hardif_neigh_free_now(hardif_neigh); - batadv_hardif_neigh_free_now(hardif_neigh); + batadv_hardif_neigh_free_ref(hardif_neigh); + batadv_hardif_neigh_free_ref(hardif_neigh); } if (bao->bat_neigh_free) bao->bat_neigh_free(neigh_node); - batadv_hardif_free_ref_now(neigh_node->if_incoming); - - kfree(neigh_node); -} + batadv_hardif_free_ref(neigh_node->if_incoming); -/** - * 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); } /** @@ -727,108 +686,99 @@ int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset) } /** - * 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 29557753d552..cf0730414ed2 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -38,7 +38,6 @@ 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 u8 *addr); struct batadv_hardif_neigh_node * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index a22080c53401..cdfc85fa2743 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -240,20 +240,6 @@ 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 @@ -349,13 +335,25 @@ 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/bridge/br_device.c b/net/bridge/br_device.c index 5e88d3e17546..2c8095a5d824 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/core/dev.c b/net/core/dev.c index 0ca95d5d7af0..8cba3d852f25 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2695,6 +2695,8 @@ 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) @@ -2709,6 +2711,9 @@ 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; @@ -4346,6 +4351,7 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb) diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= skb_metadata_dst_cmp(p, skb); if (maclen == ETH_HLEN) diffs |= compare_ether_header(skb_mac_header(p), skb_mac_header(skb)); @@ -4543,10 +4549,12 @@ static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) break; case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) { + skb_dst_drop(skb); kmem_cache_free(skbuff_head_cache, skb); - else + } else { __kfree_skb(skb); + } break; case GRO_HELD: diff --git a/net/core/sock.c b/net/core/sock.c index 51270238e269..6c1c8bc93412 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -195,44 +195,6 @@ bool sk_net_capable(const struct sock *sk, int cap) } EXPORT_SYMBOL(sk_net_capable); - -#ifdef CONFIG_MEMCG_KMEM -int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - struct proto *proto; - int ret = 0; - - mutex_lock(&proto_list_mutex); - list_for_each_entry(proto, &proto_list, node) { - if (proto->init_cgroup) { - ret = proto->init_cgroup(memcg, ss); - if (ret) - goto out; - } - } - - mutex_unlock(&proto_list_mutex); - return ret; -out: - list_for_each_entry_continue_reverse(proto, &proto_list, node) - if (proto->destroy_cgroup) - proto->destroy_cgroup(memcg); - mutex_unlock(&proto_list_mutex); - return ret; -} - -void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) -{ - struct proto *proto; - - mutex_lock(&proto_list_mutex); - list_for_each_entry_reverse(proto, &proto_list, node) - if (proto->destroy_cgroup) - proto->destroy_cgroup(memcg); - mutex_unlock(&proto_list_mutex); -} -#endif - /* * Each address family might have different locking rules, so we have * one slock key per address family: @@ -240,11 +202,6 @@ void mem_cgroup_sockets_destroy(struct mem_cgroup *memcg) static struct lock_class_key af_family_keys[AF_MAX]; static struct lock_class_key af_family_slock_keys[AF_MAX]; -#if defined(CONFIG_MEMCG_KMEM) -struct static_key memcg_socket_limit_enabled; -EXPORT_SYMBOL(memcg_socket_limit_enabled); -#endif - /* * Make lock validator output more readable. (we pre-construct these * strings build-time, so that runtime initialization of socket @@ -1507,12 +1464,6 @@ void sk_free(struct sock *sk) } EXPORT_SYMBOL(sk_free); -static void sk_update_clone(const struct sock *sk, struct sock *newsk) -{ - if (mem_cgroup_sockets_enabled && sk->sk_cgrp) - sock_update_memcg(newsk); -} - /** * sk_clone_lock - clone a socket, and lock its clone * @sk: the socket to clone @@ -1607,7 +1558,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) sk_set_socket(newsk, NULL); newsk->sk_wq = NULL; - sk_update_clone(sk, newsk); + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + sock_update_memcg(newsk); if (newsk->sk_prot->sockets_allocated) sk_sockets_allocated_inc(newsk); @@ -2089,27 +2041,27 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) struct proto *prot = sk->sk_prot; int amt = sk_mem_pages(size); long allocated; - int parent_status = UNDER_LIMIT; sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - allocated = sk_memory_allocated_add(sk, amt, &parent_status); + allocated = sk_memory_allocated_add(sk, amt); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg && + !mem_cgroup_charge_skmem(sk->sk_memcg, amt)) + goto suppress_allocation; /* Under limit. */ - if (parent_status == UNDER_LIMIT && - allocated <= sk_prot_mem_limits(sk, 0)) { + if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); return 1; } - /* Under pressure. (we or our parents) */ - if ((parent_status > SOFT_LIMIT) || - allocated > sk_prot_mem_limits(sk, 1)) + /* Under pressure. */ + if (allocated > sk_prot_mem_limits(sk, 1)) sk_enter_memory_pressure(sk); - /* Over hard limit (we or our parents) */ - if ((parent_status == OVER_LIMIT) || - (allocated > sk_prot_mem_limits(sk, 2))) + /* Over hard limit. */ + if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; /* guarantee minimum buffer size under pressure */ @@ -2158,6 +2110,9 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); + return 0; } EXPORT_SYMBOL(__sk_mem_schedule); @@ -2173,6 +2128,9 @@ void __sk_mem_reclaim(struct sock *sk, int amount) sk_memory_allocated_sub(sk, amount); sk->sk_forward_alloc -= amount << SK_MEM_QUANTUM_SHIFT; + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_uncharge_skmem(sk->sk_memcg, amount); + if (sk_under_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 1df98c557440..e92b759d906c 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -93,10 +93,17 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) * @sk2: Socket belonging to the existing reuseport group. * May return ENOMEM and not add socket to group under memory pressure. */ -int reuseport_add_sock(struct sock *sk, const struct sock *sk2) +int reuseport_add_sock(struct sock *sk, struct sock *sk2) { struct sock_reuseport *reuse; + if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { + int err = reuseport_alloc(sk2); + + if (err) + return err; + } + spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)), diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8bb8e7ad8548..6029157a19ed 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -361,13 +361,20 @@ struct sock *inet_diag_find_one_icsk(struct net *net, req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); #if IS_ENABLED(CONFIG_IPV6) - else if (req->sdiag_family == AF_INET6) - sk = inet6_lookup(net, hashinfo, - (struct in6_addr *)req->id.idiag_dst, - req->id.idiag_dport, - (struct in6_addr *)req->id.idiag_src, - req->id.idiag_sport, - req->id.idiag_if); + else if (req->sdiag_family == AF_INET6) { + if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) && + ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src)) + sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3], + req->id.idiag_dport, req->id.idiag_src[3], + req->id.idiag_sport, req->id.idiag_if); + else + sk = inet6_lookup(net, hashinfo, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + req->id.idiag_if); + } #endif else return ERR_PTR(-EINVAL); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 512a44778cf2..64878efa045c 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -239,6 +239,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, * 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); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7bb1b091efd1..fd17eec93525 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -422,7 +422,8 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - sock_update_memcg(sk); + if (mem_cgroup_sockets_enabled) + sock_update_memcg(sk); sk_sockets_allocated_inc(sk); local_bh_enable(); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 65947c1f4733..c7d1fb50f381 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1818,7 +1818,9 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); - sock_release_memcg(sk); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2342,11 +2344,6 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_MEMCG_KMEM - .init_cgroup = tcp_init_cgroup, - .destroy_cgroup = tcp_destroy_cgroup, - .proto_cgroup = tcp_proto_cgroup, -#endif .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c index 2379c1b4efb2..18bc7f745e9c 100644 --- a/net/ipv4/tcp_memcontrol.c +++ b/net/ipv4/tcp_memcontrol.c @@ -8,75 +8,49 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct page_counter *counter_parent = NULL; /* * The root cgroup does not use page_counters, but rather, * rely on the data already collected by the network * subsystem */ - struct mem_cgroup *parent = parent_mem_cgroup(memcg); - struct page_counter *counter_parent = NULL; - struct cg_proto *cg_proto, *parent_cg; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - cg_proto->sysctl_mem[0] = sysctl_tcp_mem[0]; - cg_proto->sysctl_mem[1] = sysctl_tcp_mem[1]; - cg_proto->sysctl_mem[2] = sysctl_tcp_mem[2]; - cg_proto->memory_pressure = 0; - cg_proto->memcg = memcg; + memcg->tcp_mem.memory_pressure = 0; - parent_cg = tcp_prot.proto_cgroup(parent); - if (parent_cg) - counter_parent = &parent_cg->memory_allocated; + if (parent) + counter_parent = &parent->tcp_mem.memory_allocated; - page_counter_init(&cg_proto->memory_allocated, counter_parent); - percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL); + page_counter_init(&memcg->tcp_mem.memory_allocated, counter_parent); return 0; } -EXPORT_SYMBOL(tcp_init_cgroup); void tcp_destroy_cgroup(struct mem_cgroup *memcg) { - struct cg_proto *cg_proto; - - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return; - percpu_counter_destroy(&cg_proto->sockets_allocated); - - if (test_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) - static_key_slow_dec(&memcg_socket_limit_enabled); - + if (memcg->tcp_mem.active) + static_branch_dec(&memcg_sockets_enabled_key); } -EXPORT_SYMBOL(tcp_destroy_cgroup); static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) { - struct cg_proto *cg_proto; - int i; int ret; - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return -EINVAL; - ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages); + ret = page_counter_limit(&memcg->tcp_mem.memory_allocated, nr_pages); if (ret) return ret; - for (i = 0; i < 3; i++) - cg_proto->sysctl_mem[i] = min_t(long, nr_pages, - sysctl_tcp_mem[i]); - - if (nr_pages == PAGE_COUNTER_MAX) - clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); - else { + if (!memcg->tcp_mem.active) { /* - * The active bit needs to be written after the static_key + * The active flag needs to be written after the static_key * update. This is what guarantees that the socket activation * function is the last one to run. See sock_update_memcg() for * details, and note that we don't mark any socket as belonging @@ -90,14 +64,9 @@ static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages) * We never race with the readers in sock_update_memcg(), * because when this value change, the code to process it is not * patched in yet. - * - * The activated bit is used to guarantee that no two writers - * will do the update in the same memcg. Without that, we can't - * properly shutdown the static key. */ - if (!test_and_set_bit(MEMCG_SOCK_ACTIVATED, &cg_proto->flags)) - static_key_slow_inc(&memcg_socket_limit_enabled); - set_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags); + static_branch_inc(&memcg_sockets_enabled_key); + memcg->tcp_mem.active = true; } return 0; @@ -141,32 +110,32 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of, static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg); u64 val; switch (cft->private) { case RES_LIMIT: - if (!cg_proto) - return PAGE_COUNTER_MAX; - val = cg_proto->memory_allocated.limit; + if (memcg == root_mem_cgroup) + val = PAGE_COUNTER_MAX; + else + val = memcg->tcp_mem.memory_allocated.limit; val *= PAGE_SIZE; break; case RES_USAGE: - if (!cg_proto) + if (memcg == root_mem_cgroup) val = atomic_long_read(&tcp_memory_allocated); else - val = page_counter_read(&cg_proto->memory_allocated); + val = page_counter_read(&memcg->tcp_mem.memory_allocated); val *= PAGE_SIZE; break; case RES_FAILCNT: - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - val = cg_proto->memory_allocated.failcnt; + val = memcg->tcp_mem.memory_allocated.failcnt; break; case RES_MAX_USAGE: - if (!cg_proto) + if (memcg == root_mem_cgroup) return 0; - val = cg_proto->memory_allocated.watermark; + val = memcg->tcp_mem.memory_allocated.watermark; val *= PAGE_SIZE; break; default: @@ -179,19 +148,17 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg; - struct cg_proto *cg_proto; memcg = mem_cgroup_from_css(of_css(of)); - cg_proto = tcp_prot.proto_cgroup(memcg); - if (!cg_proto) + if (memcg == root_mem_cgroup) return nbytes; switch (of_cft(of)->private) { case RES_MAX_USAGE: - page_counter_reset_watermark(&cg_proto->memory_allocated); + page_counter_reset_watermark(&memcg->tcp_mem.memory_allocated); break; case RES_FAILCNT: - cg_proto->memory_allocated.failcnt = 0; + memcg->tcp_mem.memory_allocated.failcnt = 0; break; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 412a920fe0ec..fda379cd600d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2813,13 +2813,16 @@ begin_fwd: */ void sk_forced_mem_schedule(struct sock *sk, int size) { - int amt, status; + int amt; if (size <= sk->sk_forward_alloc) return; amt = sk_mem_pages(size); sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; - sk_memory_allocated_add(sk, amt, &status); + sk_memory_allocated_add(sk, amt); + + if (mem_cgroup_sockets_enabled && sk->sk_memcg) + mem_cgroup_charge_skmem(sk->sk_memcg, amt); } /* Send a FIN. The caller locks the socket for us. diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index dc45b538e237..be0b21852b13 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -499,6 +499,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -512,14 +513,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -563,6 +568,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -601,14 +607,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index db9f1c318afc..4ad8edb46f7c 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1889,9 +1889,6 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_MEMCG_KMEM - .proto_cgroup = tcp_proto_cgroup, -#endif .clear_sk = tcp_v6_clear_sk, .diag_destroy = tcp_abort, }; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5d2c2afffe7b..22e28a44e3c8 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -257,6 +257,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -270,14 +271,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } @@ -321,6 +326,7 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -358,14 +364,18 @@ begin: badness = score; reuseport = sk->sk_reuseport; if (reuseport) { - struct sock *sk2; hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - sk2 = reuseport_select_sock(sk, hash, skb, + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (sk2) { - result = sk2; - goto found; + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } } matches = 1; } diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index f7fbdbabe50e..372855eeaf42 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -23,7 +23,7 @@ static inline void ipip6_ecn_decapsulate(struct sk_buff *skb) struct ipv6hdr *inner_iph = ipipv6_hdr(skb); if (INET_ECN_is_ce(XFRM_MODE_SKB_CB(skb)->tos)) - IP6_ECN_set_ce(inner_iph); + IP6_ECN_set_ce(skb, inner_iph); } /* Add encapsulation header. diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index ef50a94d3eb7..fc3598a922b0 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -708,6 +708,9 @@ 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/netlink/genetlink.c b/net/netlink/genetlink.c index d3f6b063467b..f830326b3b1d 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -185,7 +185,7 @@ static int genl_allocate_reserve_groups(int n_groups, int *first_id) } } - if (id + n_groups >= mc_groups_longs * BITS_PER_LONG) { + if (id + n_groups > mc_groups_longs * BITS_PER_LONG) { unsigned long new_longs = mc_groups_longs + BITS_TO_LONGS(n_groups); size_t nlen = new_longs * sizeof(unsigned long); diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index c88d0f2d3e01..2d59df521915 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1160,17 +1160,26 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, const struct sw_flow_actions *acts, struct sw_flow_key *key) { - int level = this_cpu_read(exec_actions_level); - int err; + static const int ovs_recursion_limit = 5; + int err, level; + + level = __this_cpu_inc_return(exec_actions_level); + if (unlikely(level > ovs_recursion_limit)) { + net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n", + ovs_dp_name(dp)); + kfree_skb(skb); + err = -ENETDOWN; + goto out; + } - this_cpu_inc(exec_actions_level); err = do_execute_actions(dp, skb, key, acts->actions, acts->actions_len); - if (!level) + if (level == 1) process_deferred_actions(dp); - this_cpu_dec(exec_actions_level); +out: + __this_cpu_dec(exec_actions_level); return err; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 91a8b004dc51..deadfdab1bc3 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -336,12 +336,10 @@ 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) @@ -359,7 +357,6 @@ 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/sctp/endpointola.c b/net/sctp/endpointola.c index 52838eaa1582..2522a6175291 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -333,7 +333,7 @@ struct sctp_association *sctp_endpoint_lookup_assoc( if (!ep->base.bind_addr.port) goto out; t = sctp_epaddr_lookup_transport(ep, paddr); - if (!t || t->asoc->temp) + if (!t) goto out; *transport = t; diff --git a/net/sctp/input.c b/net/sctp/input.c index d9a6e66c5c8a..bf61dfb8e09e 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -784,6 +784,7 @@ hit: /* rhashtable for transport */ struct sctp_hash_cmp_arg { + const struct sctp_endpoint *ep; const union sctp_addr *laddr; const union sctp_addr *paddr; const struct net *net; @@ -797,15 +798,20 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, struct sctp_association *asoc = t->asoc; const struct net *net = x->net; - if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port)) - return 1; if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr)) return 1; if (!net_eq(sock_net(asoc->base.sk), net)) return 1; - if (!sctp_bind_addr_match(&asoc->base.bind_addr, - x->laddr, sctp_sk(asoc->base.sk))) - return 1; + if (x->ep) { + if (x->ep != asoc->ep) + return 1; + } else { + if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port)) + return 1; + if (!sctp_bind_addr_match(&asoc->base.bind_addr, + x->laddr, sctp_sk(asoc->base.sk))) + return 1; + } return 0; } @@ -832,9 +838,11 @@ static inline u32 sctp_hash_key(const void *data, u32 len, u32 seed) const struct sctp_hash_cmp_arg *x = data; const union sctp_addr *paddr = x->paddr; const struct net *net = x->net; - u16 lport = x->laddr->v4.sin_port; + u16 lport; u32 addr; + lport = x->ep ? htons(x->ep->base.bind_addr.port) : + x->laddr->v4.sin_port; if (paddr->sa.sa_family == AF_INET6) addr = jhash(&paddr->v6.sin6_addr, 16, seed); else @@ -864,12 +872,12 @@ void sctp_transport_hashtable_destroy(void) void sctp_hash_transport(struct sctp_transport *t) { - struct sctp_sockaddr_entry *addr; struct sctp_hash_cmp_arg arg; - addr = list_entry(t->asoc->base.bind_addr.address_list.next, - struct sctp_sockaddr_entry, list); - arg.laddr = &addr->a; + if (t->asoc->temp) + return; + + arg.ep = t->asoc->ep; arg.paddr = &t->ipaddr; arg.net = sock_net(t->asoc->base.sk); @@ -881,6 +889,9 @@ reinsert: void sctp_unhash_transport(struct sctp_transport *t) { + if (t->asoc->temp) + return; + rhashtable_remove_fast(&sctp_transport_hashtable, &t->node, sctp_hash_params); } @@ -891,6 +902,7 @@ struct sctp_transport *sctp_addrs_lookup_transport( const union sctp_addr *paddr) { struct sctp_hash_cmp_arg arg = { + .ep = NULL, .laddr = laddr, .paddr = paddr, .net = net, @@ -904,13 +916,15 @@ struct sctp_transport *sctp_epaddr_lookup_transport( const struct sctp_endpoint *ep, const union sctp_addr *paddr) { - struct sctp_sockaddr_entry *addr; struct net *net = sock_net(ep->base.sk); + struct sctp_hash_cmp_arg arg = { + .ep = ep, + .paddr = paddr, + .net = net, + }; - addr = list_entry(ep->base.bind_addr.address_list.next, - struct sctp_sockaddr_entry, list); - - return sctp_addrs_lookup_transport(net, &addr->a, paddr); + return rhashtable_lookup_fast(&sctp_transport_hashtable, &arg, + sctp_hash_params); } /* Look up an association. */ @@ -923,7 +937,7 @@ static struct sctp_association *__sctp_lookup_association( struct sctp_transport *t; t = sctp_addrs_lookup_transport(net, local, peer); - if (!t || t->dead || t->asoc->temp) + if (!t || t->dead) return NULL; sctp_association_hold(t->asoc); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index dfa7eeccb537..684c5b31563b 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -310,7 +310,7 @@ static struct sctp_transport *sctp_transport_get_next(struct seq_file *seq) static struct sctp_transport *sctp_transport_get_idx(struct seq_file *seq, loff_t pos) { - void *obj; + void *obj = SEQ_START_TOKEN; while (pos && (obj = sctp_transport_get_next(seq)) && !IS_ERR(obj)) pos--; @@ -347,7 +347,7 @@ static void *sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos) if (err) return ERR_PTR(err); - return *pos ? sctp_transport_get_idx(seq, *pos) : SEQ_START_TOKEN; + return sctp_transport_get_idx(seq, *pos); } static void sctp_assocs_seq_stop(struct seq_file *seq, void *v) @@ -462,7 +462,7 @@ static void *sctp_remaddr_seq_start(struct seq_file *seq, loff_t *pos) if (err) return ERR_PTR(err); - return *pos ? sctp_transport_get_idx(seq, *pos) : SEQ_START_TOKEN; + return sctp_transport_get_idx(seq, *pos); } static void *sctp_remaddr_seq_next(struct seq_file *seq, void *v, loff_t *pos) diff --git a/net/socket.c b/net/socket.c index 91c2de6f5020..c044d1e8508c 100644 --- a/net/socket.c +++ b/net/socket.c @@ -294,7 +294,7 @@ static int init_inodecache(void) 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD | SLAB_ACCOUNT), init_once); if (sock_inode_cachep == NULL) return -ENOMEM; diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c index 59eeed43eda2..f0c6a8c78a56 100644 --- a/net/sunrpc/auth_gss/gss_rpc_upcall.c +++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c @@ -326,6 +326,9 @@ int gssp_accept_sec_context_upcall(struct net *net, if (data->found_creds && client_name.data != NULL) { char *c; + data->creds.cr_raw_principal = kstrndup(client_name.data, + client_name.len, GFP_KERNEL); + data->creds.cr_principal = kstrndup(client_name.data, client_name.len, GFP_KERNEL); if (data->creds.cr_principal) { diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 23608eb0ded2..b7f21044f4d8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1217,6 +1217,7 @@ static int rpc_anyaddr(int family, struct sockaddr *buf, size_t buflen) return -EINVAL; memcpy(buf, &rpc_in6addr_loopback, sizeof(rpc_in6addr_loopback)); + break; default: dprintk("RPC: %s: address family not supported\n", __func__); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index d81186d34558..14f45bf0410c 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1500,7 +1500,7 @@ int register_rpc_pipefs(void) rpc_inode_cachep = kmem_cache_create("rpc_inode_cache", sizeof(struct rpc_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| - SLAB_MEM_SPREAD), + SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); if (!rpc_inode_cachep) return -ENOMEM; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index a6cbb2104667..7422f28818b2 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -10,11 +10,13 @@ #include <linux/kthread.h> #include <linux/slab.h> #include <net/sock.h> +#include <linux/sunrpc/addr.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/xprt.h> #include <linux/module.h> +#include <linux/netdevice.h> #include <trace/events/sunrpc.h> #define RPCDBG_FACILITY RPCDBG_SVCXPRT @@ -938,6 +940,49 @@ static void svc_age_temp_xprts(unsigned long closure) mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ); } +/* Close temporary transports whose xpt_local matches server_addr immediately + * instead of waiting for them to be picked up by the timer. + * + * This is meant to be called from a notifier_block that runs when an ip + * address is deleted. + */ +void svc_age_temp_xprts_now(struct svc_serv *serv, struct sockaddr *server_addr) +{ + struct svc_xprt *xprt; + struct svc_sock *svsk; + struct socket *sock; + struct list_head *le, *next; + LIST_HEAD(to_be_closed); + struct linger no_linger = { + .l_onoff = 1, + .l_linger = 0, + }; + + spin_lock_bh(&serv->sv_lock); + list_for_each_safe(le, next, &serv->sv_tempsocks) { + xprt = list_entry(le, struct svc_xprt, xpt_list); + if (rpc_cmp_addr(server_addr, (struct sockaddr *) + &xprt->xpt_local)) { + dprintk("svc_age_temp_xprts_now: found %p\n", xprt); + list_move(le, &to_be_closed); + } + } + spin_unlock_bh(&serv->sv_lock); + + while (!list_empty(&to_be_closed)) { + le = to_be_closed.next; + list_del_init(le); + xprt = list_entry(le, struct svc_xprt, xpt_list); + dprintk("svc_age_temp_xprts_now: closing %p\n", xprt); + svsk = container_of(xprt, struct svc_sock, sk_xprt); + sock = svsk->sk_sock; + kernel_setsockopt(sock, SOL_SOCKET, SO_LINGER, + (char *)&no_linger, sizeof(no_linger)); + svc_close_xprt(xprt); + } +} +EXPORT_SYMBOL_GPL(svc_age_temp_xprts_now); + static void call_xpt_users(struct svc_xprt *xprt) { struct svc_xpt_user *u; diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 79c0f3459b5c..69841db1f533 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -55,6 +55,7 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp) spin_unlock(&authtab_lock); rqstp->rq_auth_slack = 0; + init_svc_cred(&rqstp->rq_cred); rqstp->rq_authop = aops; return aops->accept(rqstp, authp); @@ -63,6 +64,7 @@ EXPORT_SYMBOL_GPL(svc_authenticate); int svc_set_client(struct svc_rqst *rqstp) { + rqstp->rq_client = NULL; return rqstp->rq_authop->set_client(rqstp); } EXPORT_SYMBOL_GPL(svc_set_client); diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index 621ca7b4a155..dfacdc95b3f5 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -728,10 +728,6 @@ svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp) struct kvec *resv = &rqstp->rq_res.head[0]; struct svc_cred *cred = &rqstp->rq_cred; - cred->cr_group_info = NULL; - cred->cr_principal = NULL; - rqstp->rq_client = NULL; - if (argv->iov_len < 3*4) return SVC_GARBAGE; @@ -794,10 +790,6 @@ svcauth_unix_accept(struct svc_rqst *rqstp, __be32 *authp) u32 slen, i; int len = argv->iov_len; - cred->cr_group_info = NULL; - cred->cr_principal = NULL; - rqstp->rq_client = NULL; - if ((len -= 3*4) < 0) return SVC_GARBAGE; diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 2dcb44f69e53..cc1251d07297 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -15,7 +15,7 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -#define RPCRDMA_BACKCHANNEL_DEBUG +#undef RPCRDMA_BACKCHANNEL_DEBUG static void rpcrdma_bc_free_rqst(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst) @@ -42,8 +42,8 @@ static int rpcrdma_bc_setup_rqst(struct rpcrdma_xprt *r_xprt, size_t size; req = rpcrdma_create_req(r_xprt); - if (!req) - return -ENOMEM; + if (IS_ERR(req)) + return PTR_ERR(req); req->rl_backchannel = true; size = RPCRDMA_INLINE_WRITE_THRESHOLD(rqst); @@ -84,9 +84,7 @@ out_fail: static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt, unsigned int count) { - struct rpcrdma_buffer *buffers = &r_xprt->rx_buf; struct rpcrdma_rep *rep; - unsigned long flags; int rc = 0; while (count--) { @@ -98,9 +96,7 @@ static int rpcrdma_bc_setup_reps(struct rpcrdma_xprt *r_xprt, break; } - spin_lock_irqsave(&buffers->rb_lock, flags); - list_add(&rep->rr_list, &buffers->rb_recv_bufs); - spin_unlock_irqrestore(&buffers->rb_lock, flags); + rpcrdma_recv_buffer_put(rep); } return rc; @@ -140,6 +136,7 @@ int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs) __func__); goto out_free; } + dprintk("RPC: %s: new rqst %p\n", __func__, rqst); rqst->rq_xprt = &r_xprt->rx_xprt; INIT_LIST_HEAD(&rqst->rq_list); @@ -220,12 +217,14 @@ int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst) rpclen = rqst->rq_svec[0].iov_len; +#ifdef RPCRDMA_BACKCHANNEL_DEBUG pr_info("RPC: %s: rpclen %zd headerp 0x%p lkey 0x%x\n", __func__, rpclen, headerp, rdmab_lkey(req->rl_rdmabuf)); pr_info("RPC: %s: RPC/RDMA: %*ph\n", __func__, (int)RPCRDMA_HDRLEN_MIN, headerp); pr_info("RPC: %s: RPC: %*ph\n", __func__, (int)rpclen, rqst->rq_svec[0].iov_base); +#endif req->rl_send_iov[0].addr = rdmab_addr(req->rl_rdmabuf); req->rl_send_iov[0].length = RPCRDMA_HDRLEN_MIN; @@ -269,6 +268,9 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst) { struct rpc_xprt *xprt = rqst->rq_xprt; + dprintk("RPC: %s: freeing rqst %p (req %p)\n", + __func__, rqst, rpcr_to_rdmar(rqst)); + smp_mb__before_atomic(); WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state)); clear_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state); @@ -333,9 +335,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, struct rpc_rqst, rq_bc_pa_list); list_del(&rqst->rq_bc_pa_list); spin_unlock(&xprt->bc_pa_lock); -#ifdef RPCRDMA_BACKCHANNEL_DEBUG - pr_info("RPC: %s: using rqst %p\n", __func__, rqst); -#endif + dprintk("RPC: %s: using rqst %p\n", __func__, rqst); /* Prepare rqst */ rqst->rq_reply_bytes_recvd = 0; @@ -355,10 +355,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, * direction reply. */ req = rpcr_to_rdmar(rqst); -#ifdef RPCRDMA_BACKCHANNEL_DEBUG - pr_info("RPC: %s: attaching rep %p to req %p\n", + dprintk("RPC: %s: attaching rep %p to req %p\n", __func__, rep, req); -#endif req->rl_reply = rep; /* Defeat the retransmit detection logic in send_request */ diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index f1e8dafbd507..c14f3a4bff68 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -179,6 +179,69 @@ out_maperr: return rc; } +static void +__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct ib_device *device = r_xprt->rx_ia.ri_device; + struct rpcrdma_mw *mw = seg->rl_mw; + int nsegs = seg->mr_nsegs; + + seg->rl_mw = NULL; + + while (nsegs--) + rpcrdma_unmap_one(device, seg++); + + rpcrdma_put_mw(r_xprt, mw); +} + +/* Invalidate all memory regions that were registered for "req". + * + * Sleeps until it is safe for the host CPU to access the + * previously mapped memory regions. + */ +static void +fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +{ + struct rpcrdma_mr_seg *seg; + unsigned int i, nchunks; + struct rpcrdma_mw *mw; + LIST_HEAD(unmap_list); + int rc; + + dprintk("RPC: %s: req %p\n", __func__, req); + + /* ORDER: Invalidate all of the req's MRs first + * + * ib_unmap_fmr() is slow, so use a single call instead + * of one call per mapped MR. + */ + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + mw = seg->rl_mw; + + list_add(&mw->r.fmr.fmr->list, &unmap_list); + + i += seg->mr_nsegs; + } + rc = ib_unmap_fmr(&unmap_list); + if (rc) + pr_warn("%s: ib_unmap_fmr failed (%i)\n", __func__, rc); + + /* ORDER: Now DMA unmap all of the req's MRs, and return + * them to the free MW list. + */ + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + + __fmr_dma_unmap(r_xprt, seg); + + i += seg->mr_nsegs; + seg->mr_nsegs = 0; + } + + req->rl_nchunks = 0; +} + /* Use the ib_unmap_fmr() verb to prevent further remote * access via RDMA READ or RDMA WRITE. */ @@ -231,6 +294,7 @@ fmr_op_destroy(struct rpcrdma_buffer *buf) const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_map = fmr_op_map, + .ro_unmap_sync = fmr_op_unmap_sync, .ro_unmap = fmr_op_unmap, .ro_open = fmr_op_open, .ro_maxpages = fmr_op_maxpages, diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 88cf9e7269c2..c6836844bd0e 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -245,12 +245,14 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) rpcrdma_max_segments(r_xprt) * ia->ri_max_frmr_depth); } -/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs to be reset. */ +/* If FAST_REG or LOCAL_INV failed, indicate the frmr needs + * to be reset. + * + * WARNING: Only wr_id and status are reliable at this point + */ static void -frwr_sendcompletion(struct ib_wc *wc) +__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_mw *r) { - struct rpcrdma_mw *r; - if (likely(wc->status == IB_WC_SUCCESS)) return; @@ -261,9 +263,23 @@ frwr_sendcompletion(struct ib_wc *wc) else pr_warn("RPC: %s: frmr %p error, status %s (%d)\n", __func__, r, ib_wc_status_msg(wc->status), wc->status); + r->r.frmr.fr_state = FRMR_IS_STALE; } +static void +frwr_sendcompletion(struct ib_wc *wc) +{ + struct rpcrdma_mw *r = (struct rpcrdma_mw *)(unsigned long)wc->wr_id; + struct rpcrdma_frmr *f = &r->r.frmr; + + if (unlikely(wc->status != IB_WC_SUCCESS)) + __frwr_sendcompletion_flush(wc, r); + + if (f->fr_waiter) + complete(&f->fr_linv_done); +} + static int frwr_op_init(struct rpcrdma_xprt *r_xprt) { @@ -319,7 +335,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, struct rpcrdma_mw *mw; struct rpcrdma_frmr *frmr; struct ib_mr *mr; - struct ib_reg_wr reg_wr; + struct ib_reg_wr *reg_wr; struct ib_send_wr *bad_wr; int rc, i, n, dma_nents; u8 key; @@ -335,7 +351,9 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, } while (mw->r.frmr.fr_state != FRMR_IS_INVALID); frmr = &mw->r.frmr; frmr->fr_state = FRMR_IS_VALID; + frmr->fr_waiter = false; mr = frmr->fr_mr; + reg_wr = &frmr->fr_regwr; if (nsegs > ia->ri_max_frmr_depth) nsegs = ia->ri_max_frmr_depth; @@ -381,19 +399,19 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, key = (u8)(mr->rkey & 0x000000FF); ib_update_fast_reg_key(mr, ++key); - reg_wr.wr.next = NULL; - reg_wr.wr.opcode = IB_WR_REG_MR; - reg_wr.wr.wr_id = (uintptr_t)mw; - reg_wr.wr.num_sge = 0; - reg_wr.wr.send_flags = 0; - reg_wr.mr = mr; - reg_wr.key = mr->rkey; - reg_wr.access = writing ? - IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : - IB_ACCESS_REMOTE_READ; + reg_wr->wr.next = NULL; + reg_wr->wr.opcode = IB_WR_REG_MR; + reg_wr->wr.wr_id = (uintptr_t)mw; + reg_wr->wr.num_sge = 0; + reg_wr->wr.send_flags = 0; + reg_wr->mr = mr; + reg_wr->key = mr->rkey; + reg_wr->access = writing ? + IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE : + IB_ACCESS_REMOTE_READ; DECR_CQCOUNT(&r_xprt->rx_ep); - rc = ib_post_send(ia->ri_id->qp, ®_wr.wr, &bad_wr); + rc = ib_post_send(ia->ri_id->qp, ®_wr->wr, &bad_wr); if (rc) goto out_senderr; @@ -413,6 +431,116 @@ out_senderr: return rc; } +static struct ib_send_wr * +__frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg) +{ + struct rpcrdma_mw *mw = seg->rl_mw; + struct rpcrdma_frmr *f = &mw->r.frmr; + struct ib_send_wr *invalidate_wr; + + f->fr_waiter = false; + f->fr_state = FRMR_IS_INVALID; + invalidate_wr = &f->fr_invwr; + + memset(invalidate_wr, 0, sizeof(*invalidate_wr)); + invalidate_wr->wr_id = (unsigned long)(void *)mw; + invalidate_wr->opcode = IB_WR_LOCAL_INV; + invalidate_wr->ex.invalidate_rkey = f->fr_mr->rkey; + + return invalidate_wr; +} + +static void +__frwr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, + int rc) +{ + struct ib_device *device = r_xprt->rx_ia.ri_device; + struct rpcrdma_mw *mw = seg->rl_mw; + struct rpcrdma_frmr *f = &mw->r.frmr; + + seg->rl_mw = NULL; + + ib_dma_unmap_sg(device, f->sg, f->sg_nents, seg->mr_dir); + + if (!rc) + rpcrdma_put_mw(r_xprt, mw); + else + __frwr_queue_recovery(mw); +} + +/* Invalidate all memory regions that were registered for "req". + * + * Sleeps until it is safe for the host CPU to access the + * previously mapped memory regions. + */ +static void +frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +{ + struct ib_send_wr *invalidate_wrs, *pos, *prev, *bad_wr; + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct rpcrdma_mr_seg *seg; + unsigned int i, nchunks; + struct rpcrdma_frmr *f; + int rc; + + dprintk("RPC: %s: req %p\n", __func__, req); + + /* ORDER: Invalidate all of the req's MRs first + * + * Chain the LOCAL_INV Work Requests and post them with + * a single ib_post_send() call. + */ + invalidate_wrs = pos = prev = NULL; + seg = NULL; + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + + pos = __frwr_prepare_linv_wr(seg); + + if (!invalidate_wrs) + invalidate_wrs = pos; + else + prev->next = pos; + prev = pos; + + i += seg->mr_nsegs; + } + f = &seg->rl_mw->r.frmr; + + /* Strong send queue ordering guarantees that when the + * last WR in the chain completes, all WRs in the chain + * are complete. + */ + f->fr_invwr.send_flags = IB_SEND_SIGNALED; + f->fr_waiter = true; + init_completion(&f->fr_linv_done); + INIT_CQCOUNT(&r_xprt->rx_ep); + + /* Transport disconnect drains the receive CQ before it + * replaces the QP. The RPC reply handler won't call us + * unless ri_id->qp is a valid pointer. + */ + rc = ib_post_send(ia->ri_id->qp, invalidate_wrs, &bad_wr); + if (rc) + pr_warn("%s: ib_post_send failed %i\n", __func__, rc); + + wait_for_completion(&f->fr_linv_done); + + /* ORDER: Now DMA unmap all of the req's MRs, and return + * them to the free MW list. + */ + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + + __frwr_dma_unmap(r_xprt, seg, rc); + + i += seg->mr_nsegs; + seg->mr_nsegs = 0; + } + + req->rl_nchunks = 0; +} + /* Post a LOCAL_INV Work Request to prevent further remote access * via RDMA READ or RDMA WRITE. */ @@ -423,23 +551,24 @@ frwr_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_mw *mw = seg1->rl_mw; struct rpcrdma_frmr *frmr = &mw->r.frmr; - struct ib_send_wr invalidate_wr, *bad_wr; + struct ib_send_wr *invalidate_wr, *bad_wr; int rc, nsegs = seg->mr_nsegs; dprintk("RPC: %s: FRMR %p\n", __func__, mw); seg1->rl_mw = NULL; frmr->fr_state = FRMR_IS_INVALID; + invalidate_wr = &mw->r.frmr.fr_invwr; - memset(&invalidate_wr, 0, sizeof(invalidate_wr)); - invalidate_wr.wr_id = (unsigned long)(void *)mw; - invalidate_wr.opcode = IB_WR_LOCAL_INV; - invalidate_wr.ex.invalidate_rkey = frmr->fr_mr->rkey; + memset(invalidate_wr, 0, sizeof(*invalidate_wr)); + invalidate_wr->wr_id = (uintptr_t)mw; + invalidate_wr->opcode = IB_WR_LOCAL_INV; + invalidate_wr->ex.invalidate_rkey = frmr->fr_mr->rkey; DECR_CQCOUNT(&r_xprt->rx_ep); ib_dma_unmap_sg(ia->ri_device, frmr->sg, frmr->sg_nents, seg1->mr_dir); read_lock(&ia->ri_qplock); - rc = ib_post_send(ia->ri_id->qp, &invalidate_wr, &bad_wr); + rc = ib_post_send(ia->ri_id->qp, invalidate_wr, &bad_wr); read_unlock(&ia->ri_qplock); if (rc) goto out_err; @@ -471,6 +600,7 @@ frwr_op_destroy(struct rpcrdma_buffer *buf) const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_map = frwr_op_map, + .ro_unmap_sync = frwr_op_unmap_sync, .ro_unmap = frwr_op_unmap, .ro_open = frwr_op_open, .ro_maxpages = frwr_op_maxpages, diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c index 617b76f22154..dbb302ecf590 100644 --- a/net/sunrpc/xprtrdma/physical_ops.c +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -83,6 +83,18 @@ physical_op_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) return 1; } +/* DMA unmap all memory regions that were mapped for "req". + */ +static void +physical_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) +{ + struct ib_device *device = r_xprt->rx_ia.ri_device; + unsigned int i; + + for (i = 0; req->rl_nchunks; --req->rl_nchunks) + rpcrdma_unmap_one(device, &req->rl_segments[i++]); +} + static void physical_op_destroy(struct rpcrdma_buffer *buf) { @@ -90,6 +102,7 @@ physical_op_destroy(struct rpcrdma_buffer *buf) const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = { .ro_map = physical_op_map, + .ro_unmap_sync = physical_op_unmap_sync, .ro_unmap = physical_op_unmap, .ro_open = physical_op_open, .ro_maxpages = physical_op_maxpages, diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index c10d9699441c..0f28f2d743ed 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -804,6 +804,11 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) if (req->rl_reply) goto out_duplicate; + /* Sanity checking has passed. We are now committed + * to complete this transaction. + */ + list_del_init(&rqst->rq_list); + spin_unlock_bh(&xprt->transport_lock); dprintk("RPC: %s: reply 0x%p completes request 0x%p\n" " RPC request 0x%p xid 0x%08x\n", __func__, rep, req, rqst, @@ -888,12 +893,23 @@ badheader: break; } + /* Invalidate and flush the data payloads before waking the + * waiting application. This guarantees the memory region is + * properly fenced from the server before the application + * accesses the data. It also ensures proper send flow + * control: waking the next RPC waits until this RPC has + * relinquished all its Send Queue entries. + */ + if (req->rl_nchunks) + r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req); + credits = be32_to_cpu(headerp->rm_credit); if (credits == 0) credits = 1; /* don't deadlock */ else if (credits > r_xprt->rx_buf.rb_max_requests) credits = r_xprt->rx_buf.rb_max_requests; + spin_lock_bh(&xprt->transport_lock); cwnd = xprt->cwnd; xprt->cwnd = credits << RPC_CWNDSHIFT; if (xprt->cwnd > cwnd) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 8c545f7d7525..740bddcf3488 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -576,6 +576,9 @@ xprt_rdma_free(void *buffer) rb = container_of(buffer, struct rpcrdma_regbuf, rg_base[0]); req = rb->rg_owner; + if (req->rl_backchannel) + return; + r_xprt = container_of(req->rl_buffer, struct rpcrdma_xprt, rx_buf); dprintk("RPC: %s: called on 0x%p\n", __func__, req->rl_reply); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index eadd1655145a..732c71ce5dca 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -616,10 +616,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* set trigger for requesting send completion */ ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1; - if (ep->rep_cqinit > RPCRDMA_MAX_UNSIGNALED_SENDS) - ep->rep_cqinit = RPCRDMA_MAX_UNSIGNALED_SENDS; - else if (ep->rep_cqinit <= 2) - ep->rep_cqinit = 0; + if (ep->rep_cqinit <= 2) + ep->rep_cqinit = 0; /* always signal? */ INIT_CQCOUNT(ep); init_waitqueue_head(&ep->rep_connect_wait); INIT_DELAYED_WORK(&ep->rep_connect_worker, rpcrdma_connect_worker); @@ -852,10 +850,11 @@ retry: if (extras) { rc = rpcrdma_ep_post_extra_recv(r_xprt, extras); - if (rc) + if (rc) { pr_warn("%s: rpcrdma_ep_post_extra_recv: %i\n", __func__, rc); rc = 0; + } } } @@ -1337,15 +1336,14 @@ rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *r_xprt, unsigned int count) struct rpcrdma_ia *ia = &r_xprt->rx_ia; struct rpcrdma_ep *ep = &r_xprt->rx_ep; struct rpcrdma_rep *rep; - unsigned long flags; int rc; while (count--) { - spin_lock_irqsave(&buffers->rb_lock, flags); + spin_lock(&buffers->rb_lock); if (list_empty(&buffers->rb_recv_bufs)) goto out_reqbuf; rep = rpcrdma_buffer_get_rep_locked(buffers); - spin_unlock_irqrestore(&buffers->rb_lock, flags); + spin_unlock(&buffers->rb_lock); rc = rpcrdma_ep_post_recv(ia, ep, rep); if (rc) @@ -1355,7 +1353,7 @@ rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *r_xprt, unsigned int count) return 0; out_reqbuf: - spin_unlock_irqrestore(&buffers->rb_lock, flags); + spin_unlock(&buffers->rb_lock); pr_warn("%s: no extra receive buffers\n", __func__); return -ENOMEM; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index ac7f8d4f632a..728101ddc44b 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -88,12 +88,6 @@ struct rpcrdma_ep { struct delayed_work rep_connect_worker; }; -/* - * Force a signaled SEND Work Request every so often, - * in case the provider needs to do some housekeeping. - */ -#define RPCRDMA_MAX_UNSIGNALED_SENDS (32) - #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount) @@ -207,6 +201,12 @@ struct rpcrdma_frmr { enum rpcrdma_frmr_state fr_state; struct work_struct fr_work; struct rpcrdma_xprt *fr_xprt; + bool fr_waiter; + struct completion fr_linv_done;; + union { + struct ib_reg_wr fr_regwr; + struct ib_send_wr fr_invwr; + }; }; struct rpcrdma_fmr { @@ -364,6 +364,8 @@ struct rpcrdma_xprt; struct rpcrdma_memreg_ops { int (*ro_map)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *, int, bool); + void (*ro_unmap_sync)(struct rpcrdma_xprt *, + struct rpcrdma_req *); int (*ro_unmap)(struct rpcrdma_xprt *, struct rpcrdma_mr_seg *); int (*ro_open)(struct rpcrdma_ia *, diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 2ffaf6a79499..fde2138b81e7 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -398,7 +398,6 @@ static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, if (unlikely(!sock)) return -ENOTSOCK; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags); if (base != 0) { addr = NULL; addrlen = 0; @@ -442,7 +441,6 @@ static void xs_nospace_callback(struct rpc_task *task) struct sock_xprt *transport = container_of(task->tk_rqstp->rq_xprt, struct sock_xprt, xprt); transport->inet->sk_write_pending--; - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); } /** @@ -467,20 +465,11 @@ static int xs_nospace(struct rpc_task *task) /* Don't race with disconnect */ if (xprt_connected(xprt)) { - if (test_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags)) { - /* - * Notify TCP that we're limited by the application - * window size - */ - set_bit(SOCK_NOSPACE, &transport->sock->flags); - sk->sk_write_pending++; - /* ...and wait for more buffer space */ - xprt_wait_for_buffer_space(task, xs_nospace_callback); - } - } else { - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + /* wait for more buffer space */ + sk->sk_write_pending++; + xprt_wait_for_buffer_space(task, xs_nospace_callback); + } else ret = -ENOTCONN; - } spin_unlock_bh(&xprt->transport_lock); @@ -616,9 +605,6 @@ process_status: case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ENETUNREACH: case -ENOBUFS: case -EPIPE: @@ -626,7 +612,10 @@ process_status: case -EPERM: /* When the server has died, an ICMP port unreachable message * prompts ECONNREFUSED. */ - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -706,16 +695,16 @@ static int xs_tcp_send_request(struct rpc_task *task) case -EAGAIN: status = xs_nospace(task); break; - default: - dprintk("RPC: sendmsg returned unrecognized error %d\n", - -status); case -ECONNRESET: case -ECONNREFUSED: case -ENOTCONN: case -EADDRINUSE: case -ENOBUFS: case -EPIPE: - clear_bit(SOCKWQ_ASYNC_NOSPACE, &transport->sock->flags); + break; + default: + dprintk("RPC: sendmsg returned unrecognized error %d\n", + -status); } return status; @@ -1609,19 +1598,23 @@ static void xs_tcp_state_change(struct sock *sk) static void xs_write_space(struct sock *sk) { - struct socket *sock; + struct socket_wq *wq; struct rpc_xprt *xprt; - if (unlikely(!(sock = sk->sk_socket))) + if (!sk->sk_socket) return; - clear_bit(SOCK_NOSPACE, &sock->flags); + clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); if (unlikely(!(xprt = xprt_from_sock(sk)))) return; - if (test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sock->flags) == 0) - return; + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (!wq || test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags) == 0) + goto out; xprt_write_space(xprt); +out: + rcu_read_unlock(); } /** @@ -1907,18 +1900,6 @@ static inline void xs_reclassify_socket(int family, struct socket *sock) } } #else -static inline void xs_reclassify_socketu(struct socket *sock) -{ -} - -static inline void xs_reclassify_socket4(struct socket *sock) -{ -} - -static inline void xs_reclassify_socket6(struct socket *sock) -{ -} - static inline void xs_reclassify_socket(int family, struct socket *sock) { } @@ -2008,7 +1989,7 @@ static int xs_local_setup_socket(struct sock_xprt *transport) "transport socket (%d).\n", -status); goto out; } - xs_reclassify_socketu(sock); + xs_reclassify_socket(AF_LOCAL, sock); dprintk("RPC: worker connecting xprt %p via AF_LOCAL to %s\n", xprt, xprt->address_strings[RPC_DISPLAY_ADDR]); diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index cc3676eb6239..ff4a91fcab9f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -167,6 +167,8 @@ static int xfrm_output_gso(struct net *net, 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)) |