From 0099dc589bfa7caf6f2608c4cbc1181cfee22b0c Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Sep 2018 15:13:09 +0100 Subject: rxrpc: Make service call handling more robust Make the following changes to improve the robustness of the code that sets up a new service call: (1) Cache the rxrpc_sock struct obtained in rxrpc_data_ready() to do a service ID check and pass that along to rxrpc_new_incoming_call(). This means that I can remove the check from rxrpc_new_incoming_call() without the need to worry about the socket attached to the local endpoint getting replaced - which would invalidate the check. (2) Cache the rxrpc_peer struct, thereby allowing the peer search to be done once. The peer is passed to rxrpc_new_incoming_call(), thereby saving the need to repeat the search. This also reduces the possibility of rxrpc_publish_service_conn() BUG()'ing due to the detection of a duplicate connection, despite the initial search done by rxrpc_find_connection_rcu() having turned up nothing. This BUG() shouldn't ever get hit since rxrpc_data_ready() *should* be non-reentrant and the result of the initial search should still hold true, but it has proven possible to hit. I *think* this may be due to __rxrpc_lookup_peer_rcu() cutting short the iteration over the hash table if it finds a matching peer with a zero usage count, but I don't know for sure since it's only ever been hit once that I know of. Another possibility is that a bug in rxrpc_data_ready() that checked the wrong byte in the header for the RXRPC_CLIENT_INITIATED flag might've let through a packet that caused a spurious and invalid call to be set up. That is addressed in another patch. (3) Fix __rxrpc_lookup_peer_rcu() to skip peer records that have a zero usage count rather than stopping and returning not found, just in case there's another peer record behind it in the bucket. (4) Don't search the peer records in rxrpc_alloc_incoming_call(), but rather either use the peer cached in (2) or, if one wasn't found, preemptively install a new one. Fixes: 8496af50eb38 ("rxrpc: Use RCU to access a peer's service connection tree") Signed-off-by: David Howells --- net/rxrpc/peer_object.c | 35 +++++++++++------------------------ 1 file changed, 11 insertions(+), 24 deletions(-) (limited to 'net/rxrpc/peer_object.c') diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 1dc7648e3eff..70083e8fb6e5 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -124,11 +124,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu( struct rxrpc_net *rxnet = local->rxnet; hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) { - if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) { - if (atomic_read(&peer->usage) == 0) - return NULL; + if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 && + atomic_read(&peer->usage) > 0) return peer; - } } return NULL; @@ -299,34 +297,23 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, } /* - * Set up a new incoming peer. The address is prestored in the preallocated - * peer. + * Set up a new incoming peer. There shouldn't be any other matching peers + * since we've already done a search in the list from the non-reentrant context + * (the data_ready handler) that is the only place we can add new peers. */ -struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local, - struct rxrpc_peer *prealloc) +void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) { - struct rxrpc_peer *peer; struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; - hash_key = rxrpc_peer_hash_key(local, &prealloc->srx); - prealloc->local = local; - rxrpc_init_peer(prealloc, hash_key); + hash_key = rxrpc_peer_hash_key(local, &peer->srx); + peer->local = local; + rxrpc_init_peer(peer, hash_key); spin_lock(&rxnet->peer_hash_lock); - - /* Need to check that we aren't racing with someone else */ - peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key); - if (peer && !rxrpc_get_peer_maybe(peer)) - peer = NULL; - if (!peer) { - peer = prealloc; - hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); - list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); - } - + hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); + list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); spin_unlock(&rxnet->peer_hash_lock); - return peer; } /* -- cgit v1.2.3 From f334430316e7fd37c4821ebec627e27714bb5d76 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Sep 2018 15:13:09 +0100 Subject: rxrpc: Fix error distribution Fix error distribution by immediately delivering the errors to all the affected calls rather than deferring them to a worker thread. The problem with the latter is that retries and things can happen in the meantime when we want to stop that sooner. To this end: (1) Stop the error distributor from removing calls from the error_targets list so that peer->lock isn't needed to synchronise against other adds and removals. (2) Require the peer's error_targets list to be accessed with RCU, thereby avoiding the need to take peer->lock over distribution. (3) Don't attempt to affect a call's state if it is already marked complete. Signed-off-by: David Howells --- net/rxrpc/peer_object.c | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'net/rxrpc/peer_object.c') diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 70083e8fb6e5..01a9febfa367 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -220,8 +220,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) atomic_set(&peer->usage, 1); peer->local = local; INIT_HLIST_HEAD(&peer->error_targets); - INIT_WORK(&peer->error_distributor, - &rxrpc_peer_error_distributor); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); spin_lock_init(&peer->lock); @@ -402,21 +400,6 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) return peer; } -/* - * Queue a peer record. This passes the caller's ref to the workqueue. - */ -void __rxrpc_queue_peer_error(struct rxrpc_peer *peer) -{ - const void *here = __builtin_return_address(0); - int n; - - n = atomic_read(&peer->usage); - if (rxrpc_queue_work(&peer->error_distributor)) - trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here); - else - rxrpc_put_peer(peer); -} - /* * Discard a peer record. */ -- cgit v1.2.3