From: Xuanqiang Luo Add two functions to atomically replace RCU-protected hlist_nulls entries. Keep using WRITE_ONCE() to assign values to ->next and ->pprev, as mentioned in the patch below: commit efd04f8a8b45 ("rcu: Use WRITE_ONCE() for assignments to ->next for rculist_nulls") commit 860c8802ace1 ("rcu: Use WRITE_ONCE() for assignments to ->pprev for hlist_nulls") Reviewed-by: Kuniyuki Iwashima Reviewed-by: Frederic Weisbecker Signed-off-by: Xuanqiang Luo --- include/linux/rculist_nulls.h | 59 +++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 89186c499dd4..c26cb83ca071 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -52,6 +52,13 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) #define hlist_nulls_next_rcu(node) \ (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) +/** + * hlist_nulls_pprev_rcu - returns the dereferenced pprev of @node. + * @node: element of the list. + */ +#define hlist_nulls_pprev_rcu(node) \ + (*((struct hlist_nulls_node __rcu __force **)(node)->pprev)) + /** * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. @@ -152,6 +159,58 @@ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); } +/** + * hlist_nulls_replace_rcu - replace an old entry by a new one + * @old: the element to be replaced + * @new: the new element to insert + * + * Description: + * Replace the old entry with the new one in a RCU-protected 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(). + */ +static inline void hlist_nulls_replace_rcu(struct hlist_nulls_node *old, + struct hlist_nulls_node *new) +{ + struct hlist_nulls_node *next = old->next; + + WRITE_ONCE(new->next, next); + WRITE_ONCE(new->pprev, old->pprev); + rcu_assign_pointer(hlist_nulls_pprev_rcu(new), new); + if (!is_a_nulls(next)) + WRITE_ONCE(next->pprev, &new->next); +} + +/** + * hlist_nulls_replace_init_rcu - replace an old entry by a new one and + * initialize the old + * @old: the element to be replaced + * @new: the new element to insert + * + * Description: + * Replace the old entry with the new one in a RCU-protected hlist_nulls, while + * permitting racing traversals, and reinitialize the old entry. + * + * Note: @old must be hashed. + * + * 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(). + */ +static inline void hlist_nulls_replace_init_rcu(struct hlist_nulls_node *old, + struct hlist_nulls_node *new) +{ + hlist_nulls_replace_rcu(old, new); + WRITE_ONCE(old->pprev, NULL); +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. -- 2.25.1 From: Xuanqiang Luo Since ehash lookups are lockless, if one CPU performs a lookup while another concurrently deletes and inserts (removing reqsk and inserting sk), the lookup may fail to find the socket, an RST may be sent. The call trace map is drawn as follows: CPU 0 CPU 1 ----- ----- inet_ehash_insert() spin_lock() sk_nulls_del_node_init_rcu(osk) __inet_lookup_established() (lookup failed) __sk_nulls_add_node_rcu(sk, list) spin_unlock() As both deletion and insertion operate on the same ehash chain, this patch introduces a new sk_nulls_replace_node_init_rcu() helper functions to implement atomic replacement. Fixes: 5e0724d027f0 ("tcp/dccp: fix hashdance race for passive sessions") Reviewed-by: Kuniyuki Iwashima Signed-off-by: Xuanqiang Luo --- include/net/sock.h | 14 ++++++++++++++ net/ipv4/inet_hashtables.c | 8 ++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index 60bcb13f045c..5d299a954859 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -858,6 +858,20 @@ static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) return rc; } +static inline bool sk_nulls_replace_node_init_rcu(struct sock *old, + struct sock *new) +{ + if (sk_hashed(old)) { + hlist_nulls_replace_init_rcu(&old->sk_nulls_node, + &new->sk_nulls_node); + DEBUG_NET_WARN_ON_ONCE(refcount_read(&old->sk_refcnt) == 1); + __sock_put(old); + return true; + } + + return false; +} + static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index b7024e3d9ac3..f5826ec4bcaa 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -720,8 +720,11 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_nulls_del_node_init_rcu(osk); - } else if (found_dup_sk) { + ret = sk_nulls_replace_node_init_rcu(osk, sk); + goto unlock; + } + + if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -730,6 +733,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); +unlock: spin_unlock(lock); return ret; -- 2.25.1 From: Xuanqiang Luo Since ehash lookups are lockless, if another CPU is converting sk to tw concurrently, fetching the newly inserted tw with tw->tw_refcnt == 0 cause lookup failure. The call trace map is drawn as follows: CPU 0 CPU 1 ----- ----- inet_twsk_hashdance_schedule() spin_lock() inet_twsk_add_node_rcu(tw, ...) __inet_lookup_established() (find tw, failure due to tw_refcnt = 0) __sk_nulls_del_node_init_rcu(sk) refcount_set(&tw->tw_refcnt, 3) spin_unlock() By replacing sk with tw atomically via hlist_nulls_replace_init_rcu() after setting tw_refcnt, we ensure that tw is either fully initialized or not visible to other CPUs, eliminating the race. It's worth noting that we held lock_sock() before the replacement, so there's no need to check if sk is hashed. Thanks to Kuniyuki Iwashima! Fixes: 3ab5aee7fe84 ("net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls") Reviewed-by: Kuniyuki Iwashima Signed-off-by: Xuanqiang Luo --- net/ipv4/inet_timewait_sock.c | 35 ++++++++++++----------------------- 1 file changed, 12 insertions(+), 23 deletions(-) diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c96d61d08854..d4c781a0667f 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -88,12 +88,6 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) -{ - hlist_nulls_add_head_rcu(&tw->tw_node, list); -} - static void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, false); @@ -113,13 +107,12 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); struct inet_bind_hashbucket *bhead, *bhead2; - /* Step 1: Put TW into bind hash. Original socket stays there too. - Note, that any socket with inet->num != 0 MUST be bound in - binding cache, even if it is closed. + /* Put TW into bind hash. Original socket stays there too. + * Note, that any socket with inet->num != 0 MUST be bound in + * binding cache, even if it is closed. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; @@ -141,19 +134,6 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, spin_lock(lock); - /* Step 2: Hash TW into tcp ehash chain */ - inet_twsk_add_node_rcu(tw, &ehead->chain); - - /* Step 3: Remove SK from hash chain */ - if (__sk_nulls_del_node_init_rcu(sk)) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - - - /* Ensure above writes are committed into memory before updating the - * refcount. - * Provides ordering vs later refcount_inc(). - */ - smp_wmb(); /* tw_refcnt is set to 3 because we have : * - one reference for bhash chain. * - one reference for ehash chain. @@ -163,6 +143,15 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, */ refcount_set(&tw->tw_refcnt, 3); + /* Ensure tw_refcnt has been set before tw is published. + * smp_wmb() provides the necessary memory barrier to enforce this + * ordering. + */ + smp_wmb(); + + hlist_nulls_replace_init_rcu(&sk->sk_nulls_node, &tw->tw_node); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + inet_twsk_schedule(tw, timeo); spin_unlock(lock); -- 2.25.1