linux_dsm_epyc7002/fs/dlm/main.c
David Teigland 36b71a8bfb 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 <teigland@redhat.com>
2012-08-08 11:33:35 -05:00

98 lines
2.0 KiB
C

/******************************************************************************
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
** of the GNU General Public License v.2.
**
*******************************************************************************
******************************************************************************/
#include "dlm_internal.h"
#include "lockspace.h"
#include "lock.h"
#include "user.h"
#include "memory.h"
#include "config.h"
#include "lowcomms.h"
static int __init init_dlm(void)
{
int error;
error = dlm_memory_init();
if (error)
goto out;
error = dlm_lockspace_init();
if (error)
goto out_mem;
error = dlm_config_init();
if (error)
goto out_lockspace;
error = dlm_register_debugfs();
if (error)
goto out_config;
error = dlm_user_init();
if (error)
goto out_debug;
error = dlm_netlink_init();
if (error)
goto out_user;
error = dlm_plock_init();
if (error)
goto out_netlink;
printk("DLM installed\n");
return 0;
out_netlink:
dlm_netlink_exit();
out_user:
dlm_user_exit();
out_debug:
dlm_unregister_debugfs();
out_config:
dlm_config_exit();
out_lockspace:
dlm_lockspace_exit();
out_mem:
dlm_memory_exit();
out:
return error;
}
static void __exit exit_dlm(void)
{
dlm_plock_exit();
dlm_netlink_exit();
dlm_user_exit();
dlm_config_exit();
dlm_memory_exit();
dlm_lockspace_exit();
dlm_lowcomms_exit();
dlm_unregister_debugfs();
}
module_init(init_dlm);
module_exit(exit_dlm);
MODULE_DESCRIPTION("Distributed Lock Manager");
MODULE_AUTHOR("Red Hat, Inc.");
MODULE_LICENSE("GPL");
EXPORT_SYMBOL_GPL(dlm_new_lockspace);
EXPORT_SYMBOL_GPL(dlm_release_lockspace);
EXPORT_SYMBOL_GPL(dlm_lock);
EXPORT_SYMBOL_GPL(dlm_unlock);