From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtpng3.m.smailru.net (smtpng3.m.smailru.net [94.100.177.149]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by dev.tarantool.org (Postfix) with ESMTPS id 9C2C44429A8 for ; Wed, 23 Oct 2019 15:59:37 +0300 (MSK) From: Ilya Kosarev Date: Wed, 23 Oct 2019 15:59:03 +0300 Message-Id: <20191023125903.30261-1-i.kosarev@tarantool.org> In-Reply-To: <649183f1-0852-734d-fe75-5d6ed1e956eb@tarantool.org> References: <649183f1-0852-734d-fe75-5d6ed1e956eb@tarantool.org> Subject: [Tarantool-patches] [PATCH] replication: cancel replica joining thread at exit List-Id: Tarantool development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: tarantool-patches@dev.tarantool.org If a tarantool instance exits while joining replica is in progress, the replica joining thread can access already freed data resulting in a crash. Let's fix this the same way we did for checkpoint thread - simply cancel the thread forcefully and wait for it to terminate. Closes #4528 --- https://github.com/tarantool/tarantool/tree/i.kosarev/gh-4528-fix-shutdown-on-replica-join https://github.com/tarantool/tarantool/issues/4528 src/box/memtx_engine.c | 25 ++++++++++++++++++++++++- src/box/memtx_engine.h | 5 +++++ 2 files changed, 29 insertions(+), 1 deletion(-) diff --git a/src/box/memtx_engine.c b/src/box/memtx_engine.c index ecce3b1b6..23ccc4703 100644 --- a/src/box/memtx_engine.c +++ b/src/box/memtx_engine.c @@ -55,6 +55,9 @@ static void checkpoint_cancel(struct checkpoint *ckpt); +static void +replica_join_cancel(struct cord *replica_join_cord); + struct PACKED memtx_tuple { /* * sic: the header of the tuple is used @@ -129,6 +132,8 @@ memtx_engine_shutdown(struct engine *engine) struct memtx_engine *memtx = (struct memtx_engine *)engine; if (memtx->checkpoint != NULL) checkpoint_cancel(memtx->checkpoint); + if (memtx->replica_join_cord != NULL) + replica_join_cancel(memtx->replica_join_cord); mempool_destroy(&memtx->iterator_pool); if (mempool_is_initialized(&memtx->rtree_iterator_pool)) mempool_destroy(&memtx->rtree_iterator_pool); @@ -527,6 +532,18 @@ checkpoint_cancel(struct checkpoint *ckpt) checkpoint_delete(ckpt); } +static void +replica_join_cancel(struct cord *replica_join_cord) +{ + /* + * Cancel the thread being used to join replica if it's + * running and wait for it to terminate so as to + * eliminate the possibility of use-after-free. + */ + tt_pthread_cancel(replica_join_cord->id); + tt_pthread_join(replica_join_cord->id, NULL); +} + static int checkpoint_add_space(struct space *sp, void *data) { @@ -848,7 +865,11 @@ memtx_engine_join(struct engine *engine, void *arg, struct xstream *stream) struct cord cord; if (cord_costart(&cord, "initial_join", memtx_join_f, ctx) != 0) return -1; - return cord_cojoin(&cord); + struct memtx_engine *memtx = (struct memtx_engine *)engine; + memtx->replica_join_cord = &cord; + int res = cord_cojoin(&cord); + memtx->replica_join_cord = NULL; + return res; } static void @@ -1030,6 +1051,8 @@ memtx_engine_new(const char *snap_dirname, bool force_recovery, memtx->max_tuple_size = MAX_TUPLE_SIZE; memtx->force_recovery = force_recovery; + memtx->replica_join_cord = NULL; + memtx->base.vtab = &memtx_engine_vtab; memtx->base.name = "memtx"; diff --git a/src/box/memtx_engine.h b/src/box/memtx_engine.h index c092f5d8e..f562c66df 100644 --- a/src/box/memtx_engine.h +++ b/src/box/memtx_engine.h @@ -107,6 +107,11 @@ struct memtx_engine { uint64_t snap_io_rate_limit; /** Skip invalid snapshot records if this flag is set. */ bool force_recovery; + /** + * Cord being currently used to join replica. It is only + * needed to be able to cancel it on shutdown. + */ + struct cord *replica_join_cord; /** Common quota for tuples and indexes. */ struct quota quota; /** -- 2.17.1