From 8dbd76e79a16b45b2ccb01d2f2e08dbf64e71e40 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 Dec 2019 18:20:41 -0800 Subject: tcp/dccp: fix possible race __inet_lookup_established() Michal Kubecek and Firo Yang did a very nice analysis of crashes happening in __inet_lookup_established(). Since a TCP socket can go from TCP_ESTABLISH to TCP_LISTEN (via a close()/socket()/listen() cycle) without a RCU grace period, I should not have changed listeners linkage in their hash table. They must use the nulls protocol (Documentation/RCU/rculist_nulls.txt), so that a lookup can detect a socket in a hash list was moved in another one. Since we added code in commit d296ba60d8e2 ("soreuseport: Resolve merge conflict for v4/v6 ordering fix"), we have to add hlist_nulls_add_tail_rcu() helper. Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood") Signed-off-by: Eric Dumazet Reported-by: Michal Kubecek Reported-by: Firo Yang Reviewed-by: Michal Kubecek Link: https://lore.kernel.org/netdev/20191120083919.GH27852@unicorn.suse.cz/ Signed-off-by: Jakub Kicinski --- include/linux/rculist_nulls.h | 37 +++++++++++++++++++++++++++++++++++++ include/net/inet_hashtables.h | 12 +++++++++--- include/net/sock.h | 5 +++++ 3 files changed, 51 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index bc8206a8f30e..61974c4c566b 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -100,6 +100,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, first->pprev = &n->next; } +/** + * hlist_nulls_add_tail_rcu + * @n: the element to add to the hash list. + * @h: the list to add to. + * + * Description: + * Adds the specified element to the specified hlist_nulls, + * while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() + * or hlist_nulls_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. Regardless of the type of CPU, the + * list-traversal primitive must be guarded by rcu_read_lock(). + */ +static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, + struct hlist_nulls_head *h) +{ + struct hlist_nulls_node *i, *last = NULL; + + /* Note: write side code, so rcu accessors are not needed. */ + for (i = h->first; !is_a_nulls(i); i = i->next) + last = i; + + if (last) { + n->next = last->next; + n->pprev = &last->next; + rcu_assign_pointer(hlist_next_rcu(last), n); + } else { + hlist_nulls_add_head_rcu(n, h); + } +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index af2b4c065a04..d0019d3395cf 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -103,13 +103,19 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; -/* - * Sockets can be hashed in established or listening table +/* Sockets can be hashed in established or listening table. + * We must use different 'nulls' end-of-chain value for all hash buckets : + * A socket might transition from ESTABLISH to LISTEN state without + * RCU grace period. A lookup in ehash table needs to handle this case. */ +#define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; unsigned int count; - struct hlist_head head; + union { + struct hlist_head head; + struct hlist_nulls_head nulls_head; + }; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ diff --git a/include/net/sock.h b/include/net/sock.h index 87d54ef57f00..04c274a20620 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -722,6 +722,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } +static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); +} + static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); -- cgit v1.2.3