From 36b71a8bfbc92e1ba164e9aec840c0180ee933b5 Mon Sep 17 00:00:00 2001 From: David Teigland Date: Thu, 26 Jul 2012 12:44:30 -0500 Subject: dlm: fix deadlock between dlm_send and dlm_controld A deadlock sometimes occurs between dlm_controld closing a lowcomms connection through configfs and dlm_send looking up the address for a new connection in configfs. dlm_controld does a configfs rmdir which calls dlm_lowcomms_close which waits for dlm_send to cancel work on the workqueues. The dlm_send workqueue thread has called tcp_connect_to_sock which calls dlm_nodeid_to_addr which does a configfs lookup and blocks on a lock held by dlm_controld in the rmdir path. The solution here is to save the node addresses within the lowcomms code so that the lowcomms workqueue does not need to step through configfs to get a node address. dlm_controld: wait_for_completion+0x1d/0x20 __cancel_work_timer+0x1b3/0x1e0 cancel_work_sync+0x10/0x20 dlm_lowcomms_close+0x4c/0xb0 [dlm] drop_comm+0x22/0x60 [dlm] client_drop_item+0x26/0x50 [configfs] configfs_rmdir+0x180/0x230 [configfs] vfs_rmdir+0xbd/0xf0 do_rmdir+0x103/0x120 sys_rmdir+0x16/0x20 dlm_send: mutex_lock+0x2b/0x50 get_comm+0x34/0x140 [dlm] dlm_nodeid_to_addr+0x18/0xd0 [dlm] tcp_connect_to_sock+0xf4/0x2d0 [dlm] process_send_sockets+0x1d2/0x260 [dlm] worker_thread+0x170/0x2a0 Signed-off-by: David Teigland --- fs/dlm/lowcomms.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/dlm/lowcomms.h') diff --git a/fs/dlm/lowcomms.h b/fs/dlm/lowcomms.h index 1311e642628..67462e54fc2 100644 --- a/fs/dlm/lowcomms.h +++ b/fs/dlm/lowcomms.h @@ -16,10 +16,12 @@ int dlm_lowcomms_start(void); void dlm_lowcomms_stop(void); +void dlm_lowcomms_exit(void); int dlm_lowcomms_close(int nodeid); void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc); void dlm_lowcomms_commit_buffer(void *mh); int dlm_lowcomms_connect_node(int nodeid); +int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len); #endif /* __LOWCOMMS_DOT_H__ */ -- cgit v1.2.3