36b71a8bfb
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>
54 lines
1.5 KiB
C
54 lines
1.5 KiB
C
/******************************************************************************
|
|
*******************************************************************************
|
|
**
|
|
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
|
|
** Copyright (C) 2004-2011 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.
|
|
**
|
|
*******************************************************************************
|
|
******************************************************************************/
|
|
|
|
#ifndef __CONFIG_DOT_H__
|
|
#define __CONFIG_DOT_H__
|
|
|
|
struct dlm_config_node {
|
|
int nodeid;
|
|
int weight;
|
|
int new;
|
|
uint32_t comm_seq;
|
|
};
|
|
|
|
#define DLM_MAX_ADDR_COUNT 3
|
|
|
|
struct dlm_config_info {
|
|
int ci_tcp_port;
|
|
int ci_buffer_size;
|
|
int ci_rsbtbl_size;
|
|
int ci_recover_timer;
|
|
int ci_toss_secs;
|
|
int ci_scan_secs;
|
|
int ci_log_debug;
|
|
int ci_protocol;
|
|
int ci_timewarn_cs;
|
|
int ci_waitwarn_us;
|
|
int ci_new_rsb_count;
|
|
int ci_recover_callbacks;
|
|
char ci_cluster_name[DLM_LOCKSPACE_LEN];
|
|
};
|
|
|
|
extern struct dlm_config_info dlm_config;
|
|
|
|
int dlm_config_init(void);
|
|
void dlm_config_exit(void);
|
|
int dlm_config_nodes(char *lsname, struct dlm_config_node **nodes_out,
|
|
int *count_out);
|
|
int dlm_comm_seq(int nodeid, uint32_t *seq);
|
|
int dlm_our_nodeid(void);
|
|
int dlm_our_addr(struct sockaddr_storage *addr, int num);
|
|
|
|
#endif /* __CONFIG_DOT_H__ */
|
|
|