member.o \
memory.o \
midcomms.o \
+ netlink.o \
lowcomms.o \
rcom.o \
recover.o \
unsigned int cl_scan_secs;
unsigned int cl_log_debug;
unsigned int cl_protocol;
+ unsigned int cl_timewarn_cs;
};
enum {
CLUSTER_ATTR_SCAN_SECS,
CLUSTER_ATTR_LOG_DEBUG,
CLUSTER_ATTR_PROTOCOL,
+ CLUSTER_ATTR_TIMEWARN_CS,
};
struct cluster_attribute {
CLUSTER_ATTR(scan_secs, 1);
CLUSTER_ATTR(log_debug, 0);
CLUSTER_ATTR(protocol, 0);
+CLUSTER_ATTR(timewarn_cs, 1);
static struct configfs_attribute *cluster_attrs[] = {
[CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port.attr,
[CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs.attr,
[CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug.attr,
[CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol.attr,
+ [CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs.attr,
NULL,
};
#define DEFAULT_SCAN_SECS 5
#define DEFAULT_LOG_DEBUG 0
#define DEFAULT_PROTOCOL 0
+#define DEFAULT_TIMEWARN_CS 500 /* 5 sec = 500 centiseconds */
struct dlm_config_info dlm_config = {
.ci_tcp_port = DEFAULT_TCP_PORT,
.ci_toss_secs = DEFAULT_TOSS_SECS,
.ci_scan_secs = DEFAULT_SCAN_SECS,
.ci_log_debug = DEFAULT_LOG_DEBUG,
- .ci_protocol = DEFAULT_PROTOCOL
+ .ci_protocol = DEFAULT_PROTOCOL,
+ .ci_timewarn_cs = DEFAULT_TIMEWARN_CS
};
int ci_scan_secs;
int ci_log_debug;
int ci_protocol;
+ int ci_timewarn_cs;
};
extern struct dlm_config_info dlm_config;
#define DLM_IFL_OVERLAP_UNLOCK 0x00080000
#define DLM_IFL_OVERLAP_CANCEL 0x00100000
#define DLM_IFL_ENDOFLIFE 0x00200000
+#define DLM_IFL_WATCH_TIMEWARN 0x00400000
#define DLM_IFL_USER 0x00000001
#define DLM_IFL_ORPHAN 0x00000002
+#define DLM_IFL_TIMEOUT_CANCEL 0x00000004
struct dlm_lkb {
struct dlm_rsb *lkb_resource; /* the rsb */
struct list_head lkb_wait_reply; /* waiting for remote reply */
struct list_head lkb_astqueue; /* need ast to be sent */
struct list_head lkb_ownqueue; /* list of locks for a process */
+ struct list_head lkb_time_list;
+ unsigned long lkb_timestamp;
+ unsigned long lkb_timeout_cs;
char *lkb_lvbptr;
struct dlm_lksb *lkb_lksb; /* caller's status block */
struct mutex ls_orphans_mutex;
struct list_head ls_orphans;
+ struct mutex ls_timeout_mutex;
+ struct list_head ls_timeout;
+
struct list_head ls_nodes; /* current nodes in ls */
struct list_head ls_nodes_gone; /* dead node list, recovery */
int ls_num_nodes; /* number of nodes in ls */
struct task_struct *ls_recoverd_task;
struct mutex ls_recoverd_active;
spinlock_t ls_recover_lock;
+ unsigned long ls_recover_begin; /* jiffies timestamp */
uint32_t ls_recover_status; /* DLM_RS_ */
uint64_t ls_recover_seq;
struct dlm_recover *ls_recover_args;
#define LSFL_RCOM_READY 3
#define LSFL_RCOM_WAIT 4
#define LSFL_UEVENT_WAIT 5
+#define LSFL_TIMEWARN 6
/* much of this is just saving user space pointers associated with the
lock that we pass back to the user lib with an ast */
static int send_lookup(struct dlm_rsb *r, struct dlm_lkb *lkb);
static int send_remove(struct dlm_rsb *r);
static int _request_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
+static int _cancel_lock(struct dlm_rsb *r, struct dlm_lkb *lkb);
static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
struct dlm_message *ms);
static int receive_extralen(struct dlm_message *ms);
static void do_purge(struct dlm_ls *ls, int nodeid, int pid);
+static void del_timeout(struct dlm_lkb *lkb);
+void dlm_timeout_warn(struct dlm_lkb *lkb);
/*
* Lock compatibilty matrix - thanks Steve
if (is_master_copy(lkb))
return;
+ del_timeout(lkb);
+
DLM_ASSERT(lkb->lkb_lksb, dlm_print_lkb(lkb););
+ /* if the operation was a cancel, then return -DLM_ECANCEL, if a
+ timeout caused the cancel then return -ETIMEDOUT */
+ if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_TIMEOUT_CANCEL)) {
+ lkb->lkb_flags &= ~DLM_IFL_TIMEOUT_CANCEL;
+ rv = -ETIMEDOUT;
+ }
+
lkb->lkb_lksb->sb_status = rv;
lkb->lkb_lksb->sb_flags = lkb->lkb_sbflags;
kref_init(&lkb->lkb_ref);
INIT_LIST_HEAD(&lkb->lkb_ownqueue);
INIT_LIST_HEAD(&lkb->lkb_rsb_lookup);
+ INIT_LIST_HEAD(&lkb->lkb_time_list);
get_random_bytes(&bucket, sizeof(bucket));
bucket &= (ls->ls_lkbtbl_size - 1);
}
}
+static void add_timeout(struct dlm_lkb *lkb)
+{
+ struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+
+ if (is_master_copy(lkb))
+ return;
+
+ if (lkb->lkb_exflags & DLM_LKF_TIMEOUT)
+ goto add_it;
+
+ if (test_bit(LSFL_TIMEWARN, &ls->ls_flags) &&
+ !(lkb->lkb_exflags & DLM_LKF_NODLCKWT)) {
+ lkb->lkb_flags |= DLM_IFL_WATCH_TIMEWARN;
+ goto add_it;
+ }
+ return;
+
+ add_it:
+ DLM_ASSERT(list_empty(&lkb->lkb_time_list), dlm_print_lkb(lkb););
+ mutex_lock(&ls->ls_timeout_mutex);
+ hold_lkb(lkb);
+ lkb->lkb_timestamp = jiffies;
+ list_add_tail(&lkb->lkb_time_list, &ls->ls_timeout);
+ mutex_unlock(&ls->ls_timeout_mutex);
+}
+
+static void del_timeout(struct dlm_lkb *lkb)
+{
+ struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+
+ mutex_lock(&ls->ls_timeout_mutex);
+ if (!list_empty(&lkb->lkb_time_list)) {
+ list_del_init(&lkb->lkb_time_list);
+ unhold_lkb(lkb);
+ }
+ mutex_unlock(&ls->ls_timeout_mutex);
+}
+
+/* FIXME: is it safe to look at lkb_exflags, lkb_flags, lkb_timestamp, and
+ lkb_lksb_timeout without lock_rsb? Note: we can't lock timeout_mutex
+ and then lock rsb because of lock ordering in add_timeout. We may need
+ to specify some special timeout-related bits in the lkb that are just to
+ be accessed under the timeout_mutex. */
+
+void dlm_scan_timeout(struct dlm_ls *ls)
+{
+ struct dlm_rsb *r;
+ struct dlm_lkb *lkb;
+ int do_cancel, do_warn;
+
+ for (;;) {
+ if (dlm_locking_stopped(ls))
+ break;
+
+ do_cancel = 0;
+ do_warn = 0;
+ mutex_lock(&ls->ls_timeout_mutex);
+ list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) {
+
+ if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) &&
+ time_after_eq(jiffies, lkb->lkb_timestamp +
+ lkb->lkb_timeout_cs * HZ/100))
+ do_cancel = 1;
+
+ if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) &&
+ time_after_eq(jiffies, lkb->lkb_timestamp +
+ dlm_config.ci_timewarn_cs * HZ/100))
+ do_warn = 1;
+
+ if (!do_cancel && !do_warn)
+ continue;
+ hold_lkb(lkb);
+ break;
+ }
+ mutex_unlock(&ls->ls_timeout_mutex);
+
+ if (!do_cancel && !do_warn)
+ break;
+
+ r = lkb->lkb_resource;
+ hold_rsb(r);
+ lock_rsb(r);
+
+ if (do_warn) {
+ /* clear flag so we only warn once */
+ lkb->lkb_flags &= ~DLM_IFL_WATCH_TIMEWARN;
+ if (!(lkb->lkb_exflags & DLM_LKF_TIMEOUT))
+ del_timeout(lkb);
+ dlm_timeout_warn(lkb);
+ }
+
+ if (do_cancel) {
+ lkb->lkb_flags &= ~DLM_IFL_WATCH_TIMEWARN;
+ lkb->lkb_flags |= DLM_IFL_TIMEOUT_CANCEL;
+ del_timeout(lkb);
+ _cancel_lock(r, lkb);
+ }
+
+ unlock_rsb(r);
+ unhold_rsb(r);
+ dlm_put_lkb(lkb);
+ }
+}
+
+/* This is only called by dlm_recoverd, and we rely on dlm_ls_stop() stopping
+ dlm_recoverd before checking/setting ls_recover_begin. */
+
+void dlm_adjust_timeouts(struct dlm_ls *ls)
+{
+ struct dlm_lkb *lkb;
+ long adj = jiffies - ls->ls_recover_begin;
+
+ ls->ls_recover_begin = 0;
+ mutex_lock(&ls->ls_timeout_mutex);
+ list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list)
+ lkb->lkb_timestamp += adj;
+ mutex_unlock(&ls->ls_timeout_mutex);
+}
+
/* lkb is master or local copy */
static void set_lvb_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
if (is_overlap(lkb))
goto out;
+ /* don't let scand try to do a cancel */
+ del_timeout(lkb);
+
if (lkb->lkb_flags & DLM_IFL_RESEND) {
lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL;
rv = -EBUSY;
if (is_overlap_unlock(lkb))
goto out;
+ /* don't let scand try to do a cancel */
+ del_timeout(lkb);
+
if (lkb->lkb_flags & DLM_IFL_RESEND) {
lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK;
rv = -EBUSY;
error = -EINPROGRESS;
add_lkb(r, lkb, DLM_LKSTS_WAITING);
send_blocking_asts(r, lkb);
+ add_timeout(lkb);
goto out;
}
del_lkb(r, lkb);
add_lkb(r, lkb, DLM_LKSTS_CONVERT);
send_blocking_asts(r, lkb);
+ add_timeout(lkb);
goto out;
}
lkb->lkb_remid = ms->m_lkid;
if (is_altmode(lkb))
munge_altmode(lkb, ms);
- if (result)
+ if (result) {
add_lkb(r, lkb, DLM_LKSTS_WAITING);
- else {
+ add_timeout(lkb);
+ } else {
grant_lock_pc(r, lkb, ms);
queue_cast(r, lkb, 0);
}
munge_demoted(lkb, ms);
del_lkb(r, lkb);
add_lkb(r, lkb, DLM_LKSTS_CONVERT);
+ add_timeout(lkb);
break;
case 0:
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2007 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
void dlm_scan_rsbs(struct dlm_ls *ls);
int dlm_lock_recovery_try(struct dlm_ls *ls);
void dlm_unlock_recovery(struct dlm_ls *ls);
+void dlm_scan_timeout(struct dlm_ls *ls);
+void dlm_adjust_timeouts(struct dlm_ls *ls);
int dlm_purge_locks(struct dlm_ls *ls);
void dlm_purge_mstcpy_locks(struct dlm_rsb *r);
list_for_each_entry(ls, &lslist, ls_list) {
if (dlm_lock_recovery_try(ls)) {
dlm_scan_rsbs(ls);
+ dlm_scan_timeout(ls);
dlm_unlock_recovery(ls);
}
}
goto out;
memcpy(ls->ls_name, name, namelen);
ls->ls_namelen = namelen;
- ls->ls_exflags = flags;
ls->ls_lvblen = lvblen;
ls->ls_count = 0;
ls->ls_flags = 0;
+ /* ls_exflags are forced to match among nodes, and we don't
+ need to require all nodes to have TIMEWARN active */
+ if (flags & DLM_LSFL_TIMEWARN)
+ set_bit(LSFL_TIMEWARN, &ls->ls_flags);
+ ls->ls_exflags = (flags & ~DLM_LSFL_TIMEWARN);
+
size = dlm_config.ci_rsbtbl_size;
ls->ls_rsbtbl_size = size;
mutex_init(&ls->ls_waiters_mutex);
INIT_LIST_HEAD(&ls->ls_orphans);
mutex_init(&ls->ls_orphans_mutex);
+ INIT_LIST_HEAD(&ls->ls_timeout);
+ mutex_init(&ls->ls_timeout_mutex);
INIT_LIST_HEAD(&ls->ls_nodes);
INIT_LIST_HEAD(&ls->ls_nodes_gone);
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. 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
static inline int dlm_register_debugfs(void) { return 0; }
static inline void dlm_unregister_debugfs(void) { }
#endif
+int dlm_netlink_init(void);
+void dlm_netlink_exit(void);
static int __init init_dlm(void)
{
if (error)
goto out_debug;
+ error = dlm_netlink_init();
+ if (error)
+ goto out_user;
+
printk("DLM (built %s %s) installed\n", __DATE__, __TIME__);
return 0;
+ out_user:
+ dlm_user_exit();
out_debug:
dlm_unregister_debugfs();
out_config:
static void __exit exit_dlm(void)
{
+ dlm_netlink_exit();
dlm_user_exit();
dlm_config_exit();
dlm_memory_exit();
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2007 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
dlm_recoverd_suspend(ls);
ls->ls_recover_status = 0;
dlm_recoverd_resume(ls);
+
+ if (!ls->ls_recover_begin)
+ ls->ls_recover_begin = jiffies;
return 0;
}
--- /dev/null
+/*
+ * Copyright (C) 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 <net/genetlink.h>
+#include <linux/dlm.h>
+#include <linux/dlm_netlink.h>
+
+#include "dlm_internal.h"
+
+static uint32_t dlm_nl_seqnum;
+static uint32_t listener_nlpid;
+
+static struct genl_family family = {
+ .id = GENL_ID_GENERATE,
+ .name = DLM_GENL_NAME,
+ .version = DLM_GENL_VERSION,
+};
+
+static int prepare_data(u8 cmd, struct sk_buff **skbp, size_t size)
+{
+ struct sk_buff *skb;
+ void *data;
+
+ skb = genlmsg_new(size, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ /* add the message headers */
+ data = genlmsg_put(skb, 0, dlm_nl_seqnum++, &family, 0, cmd);
+ if (!data) {
+ nlmsg_free(skb);
+ return -EINVAL;
+ }
+
+ *skbp = skb;
+ return 0;
+}
+
+static struct dlm_lock_data *mk_data(struct sk_buff *skb)
+{
+ struct nlattr *ret;
+
+ ret = nla_reserve(skb, DLM_TYPE_LOCK, sizeof(struct dlm_lock_data));
+ if (!ret)
+ return NULL;
+ return nla_data(ret);
+}
+
+static int send_data(struct sk_buff *skb)
+{
+ struct genlmsghdr *genlhdr = nlmsg_data((struct nlmsghdr *)skb->data);
+ void *data = genlmsg_data(genlhdr);
+ int rv;
+
+ rv = genlmsg_end(skb, data);
+ if (rv < 0) {
+ nlmsg_free(skb);
+ return rv;
+ }
+
+ return genlmsg_unicast(skb, listener_nlpid);
+}
+
+static int user_cmd(struct sk_buff *skb, struct genl_info *info)
+{
+ listener_nlpid = info->snd_pid;
+ printk("user_cmd nlpid %u\n", listener_nlpid);
+ return 0;
+}
+
+static struct genl_ops dlm_nl_ops = {
+ .cmd = DLM_CMD_HELLO,
+ .doit = user_cmd,
+};
+
+int dlm_netlink_init(void)
+{
+ int rv;
+
+ rv = genl_register_family(&family);
+ if (rv)
+ return rv;
+
+ rv = genl_register_ops(&family, &dlm_nl_ops);
+ if (rv < 0)
+ goto err;
+ return 0;
+ err:
+ genl_unregister_family(&family);
+ return rv;
+}
+
+void dlm_netlink_exit(void)
+{
+ genl_unregister_ops(&family, &dlm_nl_ops);
+ genl_unregister_family(&family);
+}
+
+static void fill_data(struct dlm_lock_data *data, struct dlm_lkb *lkb)
+{
+ struct dlm_rsb *r = lkb->lkb_resource;
+ struct dlm_user_args *ua = (struct dlm_user_args *) lkb->lkb_astparam;
+
+ memset(data, 0, sizeof(struct dlm_lock_data));
+
+ data->version = DLM_LOCK_DATA_VERSION;
+ data->nodeid = lkb->lkb_nodeid;
+ data->ownpid = lkb->lkb_ownpid;
+ data->id = lkb->lkb_id;
+ data->remid = lkb->lkb_remid;
+ data->status = lkb->lkb_status;
+ data->grmode = lkb->lkb_grmode;
+ data->rqmode = lkb->lkb_rqmode;
+ data->timestamp = lkb->lkb_timestamp;
+ if (ua)
+ data->xid = ua->xid;
+ if (r) {
+ data->lockspace_id = r->res_ls->ls_global_id;
+ data->resource_namelen = r->res_length;
+ memcpy(data->resource_name, r->res_name, r->res_length);
+ }
+}
+
+void dlm_timeout_warn(struct dlm_lkb *lkb)
+{
+ struct dlm_lock_data *data;
+ struct sk_buff *send_skb;
+ size_t size;
+ int rv;
+
+ log_debug(lkb->lkb_resource->res_ls, "timeout_warn %x", lkb->lkb_id);
+
+ size = nla_total_size(sizeof(struct dlm_lock_data)) +
+ nla_total_size(0); /* why this? */
+
+ rv = prepare_data(DLM_CMD_TIMEOUT, &send_skb, size);
+ if (rv < 0)
+ return;
+
+ data = mk_data(send_skb);
+ if (!data) {
+ nlmsg_free(send_skb);
+ return;
+ }
+
+ fill_data(data, lkb);
+
+ send_data(send_skb);
+}
+
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. 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
dlm_clear_members_gone(ls);
+ dlm_adjust_timeouts(ls);
+
error = enable_locking(ls, rv->seq);
if (error) {
log_debug(ls, "enable_locking failed %d", error);
return -EPERM;
error = dlm_new_lockspace(params->name, strlen(params->name),
- &lockspace, 0, DLM_USER_LVB_LEN);
+ &lockspace, params->flags, DLM_USER_LVB_LEN);
if (error)
return error;
header-y += const.h
header-y += cycx_cfm.h
header-y += dlm_device.h
+header-y += dlm_netlink.h
header-y += dm-ioctl.h
header-y += dn.h
header-y += dqblk_v1.h
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. 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
#define DLM_LKF_ALTPR 0x00008000
#define DLM_LKF_ALTCW 0x00010000
#define DLM_LKF_FORCEUNLOCK 0x00020000
+#define DLM_LKF_TIMEOUT 0x00040000
/*
* Some return codes that are not in errno.h
char * sb_lvbptr;
};
+#define DLM_LSFL_NODIR 0x00000001
+#define DLM_LSFL_TIMEWARN 0x00000002
#ifdef __KERNEL__
-#define DLM_LSFL_NODIR 0x00000001
-
/*
* dlm_new_lockspace
*
--- /dev/null
+/*
+ * Copyright (C) 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.
+ */
+
+#ifndef _DLM_NETLINK_H
+#define _DLM_NETLINK_H
+
+enum {
+ DLM_STATUS_WAITING = 1,
+ DLM_STATUS_GRANTED = 2,
+ DLM_STATUS_CONVERT = 3,
+};
+
+#define DLM_LOCK_DATA_VERSION 1
+
+struct dlm_lock_data {
+ uint16_t version;
+ uint32_t lockspace_id;
+ int nodeid;
+ int ownpid;
+ uint32_t id;
+ uint32_t remid;
+ uint64_t xid;
+ int8_t status;
+ int8_t grmode;
+ int8_t rqmode;
+ unsigned long timestamp;
+ int resource_namelen;
+ char resource_name[DLM_RESNAME_MAXLEN];
+};
+
+enum {
+ DLM_CMD_UNSPEC = 0,
+ DLM_CMD_HELLO, /* user->kernel */
+ DLM_CMD_TIMEOUT, /* kernel->user */
+ __DLM_CMD_MAX,
+};
+
+#define DLM_CMD_MAX (__DLM_CMD_MAX - 1)
+
+enum {
+ DLM_TYPE_UNSPEC = 0,
+ DLM_TYPE_LOCK,
+ __DLM_TYPE_MAX,
+};
+
+#define DLM_TYPE_MAX (__DLM_TYPE_MAX - 1)
+
+#define DLM_GENL_VERSION 0x1
+#define DLM_GENL_NAME "DLM"
+
+#endif /* _DLM_NETLINK_H */
projects / karo-tx-linux.git / commitdiff