From b246d3d11e9c04f76a4fd6aae9c61da82bba0afb Mon Sep 17 00:00:00 2001 From: Xue jiufei Date: Thu, 9 Oct 2014 15:28:26 -0700 Subject: [PATCH] ocfs2: fix a deadlock while o2net_wq doing direct memory reclaim Fix a deadlock problem caused by direct memory reclaim in o2net_wq. The situation is as follows: 1) Receive a connect message from another node, node queues a work_struct o2net_listen_work. 2) o2net_wq processes this work and call the following functions: o2net_wq -> o2net_accept_one -> sock_create_lite -> sock_alloc() -> kmem_cache_alloc with GFP_KERNEL -> ____cache_alloc_node ->__alloc_pages_nodemask -> do_try_to_free_pages -> shrink_slab -> evict -> ocfs2_evict_inode -> ocfs2_drop_lock -> dlmunlock -> o2net_send_message_vec then o2net_wq wait for the unlock reply from master. 3) tcp layer received the reply, call o2net_data_ready() and queue sc_rx_work, waiting o2net_wq to process this work. 4) o2net_wq is a single thread workqueue, it process the work one by one. Right now it is still doing o2net_listen_work and cannot handle sc_rx_work. so we deadlock. Junxiao Bi's patch "mm: clear __GFP_FS when PF_MEMALLOC_NOIO is set" (http://ozlabs.org/~akpm/mmots/broken-out/mm-clear-__gfp_fs-when-pf_memalloc_noio-is-set.patch) clears __GFP_FS in memalloc_noio_flags() besides __GFP_IO. We use memalloc_noio_save() to set process flag PF_MEMALLOC_NOIO so that all allocations done by this process are done as if GFP_NOIO was specified. We are not reentering filesystem while doing memory reclaim. Signed-off-by: joyce.xue Cc: Junxiao Bi Cc: Joel Becker Cc: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/tcp.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 509e6d5415e2..97de0fbd9f78 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1601,7 +1601,15 @@ static void o2net_start_connect(struct work_struct *work) struct sockaddr_in myaddr = {0, }, remoteaddr = {0, }; int ret = 0, stop; unsigned int timeout; + unsigned int noio_flag; + /* + * sock_create allocates the sock with GFP_KERNEL. We must set + * per-process flag PF_MEMALLOC_NOIO so that all allocations done + * by this process are done as if GFP_NOIO was specified. So we + * are not reentering filesystem while doing memory reclaim. + */ + noio_flag = memalloc_noio_save(); /* if we're greater we initiate tx, otherwise we accept */ if (o2nm_this_node() <= o2net_num_from_nn(nn)) goto out; @@ -1710,6 +1718,7 @@ out: if (mynode) o2nm_node_put(mynode); + memalloc_noio_restore(noio_flag); return; } @@ -1836,6 +1845,15 @@ static int o2net_accept_one(struct socket *sock, int *more) struct o2nm_node *local_node = NULL; struct o2net_sock_container *sc = NULL; struct o2net_node *nn; + unsigned int noio_flag; + + /* + * sock_create_lite allocates the sock with GFP_KERNEL. We must set + * per-process flag PF_MEMALLOC_NOIO so that all allocations done + * by this process are done as if GFP_NOIO was specified. So we + * are not reentering filesystem while doing memory reclaim. + */ + noio_flag = memalloc_noio_save(); BUG_ON(sock == NULL); *more = 0; @@ -1952,6 +1970,8 @@ out: o2nm_node_put(local_node); if (sc) sc_put(sc); + + memalloc_noio_restore(noio_flag); return ret; }