aboutsummaryrefslogtreecommitdiffstats
path: root/fs/dlm/member.c
blob: e9cdcab306e2a06037c4e0c32ac1c0e7be3097dc (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
/******************************************************************************
*******************************************************************************
**
**  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
**  of the GNU General Public License v.2.
**
*******************************************************************************
******************************************************************************/

#include "dlm_internal.h"
#include "lockspace.h"
#include "member.h"
#include "recoverd.h"
#include "recover.h"
#include "rcom.h"
#include "config.h"

static void add_ordered_member(struct dlm_ls *ls, struct dlm_member *new)
{
	struct dlm_member *memb = NULL;
	struct list_head *tmp;
	struct list_head *newlist = &new->list;
	struct list_head *head = &ls->ls_nodes;

	list_for_each(tmp, head) {
		memb = list_entry(tmp, struct dlm_member, list);
		if (new->nodeid < memb->nodeid)
			break;
	}

	if (!memb)
		list_add_tail(newlist, head);
	else {
		/* FIXME: can use list macro here */
		newlist->prev = tmp->prev;
		newlist->next = tmp;
		tmp->prev->next = newlist;
		tmp->prev = newlist;
	}
}

static int dlm_add_member(struct dlm_ls *ls, int nodeid)
{
	struct dlm_member *memb;
	int w;

	memb = kzalloc(sizeof(struct dlm_member), GFP_KERNEL);
	if (!memb)
		return -ENOMEM;

	w = dlm_node_weight(ls->ls_name, nodeid);
	if (w < 0) {
		kfree(memb);
		return w;
	}

	memb->nodeid = nodeid;
	memb->weight = w;
	add_ordered_member(ls, memb);
	ls->ls_num_nodes++;
	return 0;
}

static void dlm_remove_member(struct dlm_ls *ls, struct dlm_member *memb)
{
	list_move(&memb->list, &ls->ls_nodes_gone);
	ls->ls_num_nodes--;
}

static int dlm_is_member(struct dlm_ls *ls, int nodeid)
{
	struct dlm_member *memb;

	list_for_each_entry(memb, &ls->ls_nodes, list) {
		if (memb->nodeid == nodeid)
			return 1;
	}
	return 0;
}

int dlm_is_removed(struct dlm_ls *ls, int nodeid)
{
	struct dlm_member *memb;

	list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
		if (memb->nodeid == nodeid)
			return 1;
	}
	return 0;
}

static void clear_memb_list(struct list_head *head)
{
	struct dlm_member *memb;

	while (!list_empty(head)) {
		memb = list_entry(head->next, struct dlm_member, list);
		list_del(&memb->list);
		kfree(memb);
	}
}

void dlm_clear_members(struct dlm_ls *ls)
{
	clear_memb_list(&ls->ls_nodes);
	ls->ls_num_nodes = 0;
}

void dlm_clear_members_gone(struct dlm_ls *ls)
{
	clear_memb_list(&ls->ls_nodes_gone);
}

static void make_member_array(struct dlm_ls *ls)
{
	struct dlm_member *memb;
	int i, w, x = 0, total = 0, all_zero = 0, *array;

	kfree(ls->ls_node_array);
	ls->ls_node_array = NULL;

	list_for_each_entry(memb, &ls->ls_nodes, list) {
		if (memb->weight)
			total += memb->weight;
	}

	/* all nodes revert to weight of 1 if all have weight 0 */

	if (!total) {
		total = ls->ls_num_nodes;
		all_zero = 1;
	}

	ls->ls_total_weight = total;

	array = kmalloc(sizeof(int) * total, GFP_KERNEL);
	if (!array)
		return;

	list_for_each_entry(memb, &ls->ls_nodes, list) {
		if (!all_zero && !memb->weight)
			continue;

		if (all_zero)
			w = 1;
		else
			w = memb->weight;

		DLM_ASSERT(x < total, printk("total %d x %d\n", total, x););

		for (i = 0; i < w; i++)
			array[x++] = memb->nodeid;
	}

	ls->ls_node_array = array;
}

/* send a status request to all members just to establish comms connections */

static int ping_members(struct dlm_ls *ls)
{
	struct dlm_member *memb;
	int error = 0;

	list_for_each_entry(memb, &ls->ls_nodes, list) {
		error = dlm_recovery_stopped(ls);
		if (error)
			break;
		error = dlm_rcom_status(ls, memb->nodeid);
		if (error)
			break;
	}
	if (error)
		log_debug(ls, "ping_members aborted %d last nodeid %d",
			  error, ls->ls_recover_nodeid);
	return error;
}

int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
{
	struct dlm_member *memb, *safe;
	int i, error, found, pos = 0, neg = 0, low = -1;

	/* previously removed members that we've not finished removing need to
	   count as a negative change so the "neg" recovery steps will happen */

	list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
		log_debug(ls, "prev removed member %d", memb->nodeid);
		neg++;
	}

	/* move departed members from ls_nodes to ls_nodes_gone */

	list_for_each_entry_safe(memb, safe, &ls->ls_nodes, list) {
		found = 0;
		for (i = 0; i < rv->node_count; i++) {
			if (memb->nodeid == rv->nodeids[i]) {
				found = 1;
				break;
			}
		}

		if (!found) {
			neg++;
			dlm_remove_member(ls, memb);
			log_debug(ls, "remove member %d", memb->nodeid);
		}
	}

	/* add new members to ls_nodes */

	for (i = 0; i < rv->node_count; i++) {
		if (dlm_is_member(ls, rv->nodeids[i]))
			continue;
		dlm_add_member(ls, rv->nodeids[i]);
		pos++;
		log_debug(ls, "add member %d", rv->nodeids[i]);
	}

	list_for_each_entry(memb, &ls->ls_nodes, list) {
		if (low == -1 || memb->nodeid < low)
			low = memb->nodeid;
	}
	ls->ls_low_nodeid = low;

	make_member_array(ls);
	dlm_set_recover_status(ls, DLM_RS_NODES);
	*neg_out = neg;

	error = ping_members(ls);
	if (!error || error == -EPROTO) {
		/* new_lockspace() may be waiting to know if the config
		   is good or bad */
		ls->ls_members_result = error;
		complete(&ls->ls_members_done);
	}
	if (error)
		goto out;

	error = dlm_recover_members_wait(ls);
 out:
	log_debug(ls, "total members %d error %d", ls->ls_num_nodes, error);
	return error;
}

/* Userspace guarantees that dlm_ls_stop() has completed on all nodes before
   dlm_ls_start() is called on any of them to start the new recovery. */

int dlm_ls_stop(struct dlm_ls *ls)
{
	int new;

	/*
	 * Prevent dlm_recv from being in the middle of something when we do
	 * the stop.  This includes ensuring dlm_recv isn't processing a
	 * recovery message (rcom), while dlm_recoverd is aborting and
	 * resetting things from an in-progress recovery.  i.e. we want
	 * dlm_recoverd to abort its recovery without worrying about dlm_recv
	 * processing an rcom at the same time.  Stopping dlm_recv also makes
	 * it easy for dlm_receive_message() to check locking stopped and add a
	 * message to the requestqueue without races.
	 */

	down_write(&ls->ls_recv_active);

	/*
	 * Abort any recovery that's in progress (see RECOVERY_STOP,
	 * dlm_recovery_stopped()) and tell any other threads running in the
	 * dlm to quit any processing (see RUNNING, dlm_locking_stopped()).
	 */

	spin_lock(&ls->ls_recover_lock);
	set_bit(LSFL_RECOVERY_STOP, &ls->ls_flags);
	new = test_and_clear_bit(LSFL_RUNNING, &ls->ls_flags);
	ls->ls_recover_seq++;
	spin_unlock(&ls->ls_recover_lock);

	/*
	 * Let dlm_recv run again, now any normal messages will be saved on the
	 * requestqueue for later.
	 */

	up_write(&ls->ls_recv_active);

	/*
	 * This in_recovery lock does two things:
	 * 1) Keeps this function from returning until all threads are out
	 *    of locking routines and locking is truely stopped.
	 * 2) Keeps any new requests from being processed until it's unlocked
	 *    when recovery is complete.
	 */

	if (new)
		down_write(&ls->ls_in_recovery);

	/*
	 * The recoverd suspend/resume makes sure that dlm_recoverd (if
	 * running) has noticed RECOVERY_STOP above and quit processing the
	 * previous recovery.
	 */

	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;
}

int dlm_ls_start(struct dlm_ls *ls)
{
	struct dlm_recover *rv = NULL, *rv_old;
	int *ids = NULL;
	int error, count;

	rv = kzalloc(sizeof(struct dlm_recover), GFP_KERNEL);
	if (!rv)
		return -ENOMEM;

	error = count = dlm_nodeid_list(ls->ls_name, &ids);
	if (error <= 0)
		goto fail;

	spin_lock(&ls->ls_recover_lock);

	/* the lockspace needs to be stopped before it can be started */

	if (!dlm_locking_stopped(ls)) {
		spin_unlock(&ls->ls_recover_lock);
		log_error(ls, "start ignored: lockspace running");
		error = -EINVAL;
		goto fail;
	}

	rv->nodeids = ids;
	rv->node_count = count;
	rv->seq = ++ls->ls_recover_seq;
	rv_old = ls->ls_recover_args;
	ls->ls_recover_args = rv;
	spin_unlock(&ls->ls_recover_lock);

	if (rv_old) {
		kfree(rv_old->nodeids);
		kfree(rv_old);
	}

	dlm_recoverd_kick(ls);
	return 0;

 fail:
	kfree(rv);
	kfree(ids);
	return error;
}