| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 1 | /****************************************************************************** | 
 | 2 | ******************************************************************************* | 
 | 3 | ** | 
 | 4 | **  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved. | 
 | 5 | **  Copyright (C) 2004-2005 Red Hat, Inc.  All rights reserved. | 
 | 6 | ** | 
 | 7 | **  This copyrighted material is made available to anyone wishing to use, | 
 | 8 | **  modify, copy, or redistribute it subject to the terms and conditions | 
 | 9 | **  of the GNU General Public License v.2. | 
 | 10 | ** | 
 | 11 | ******************************************************************************* | 
 | 12 | ******************************************************************************/ | 
 | 13 |  | 
 | 14 | #include "dlm_internal.h" | 
 | 15 | #include "lockspace.h" | 
 | 16 | #include "dir.h" | 
 | 17 | #include "config.h" | 
 | 18 | #include "ast.h" | 
 | 19 | #include "memory.h" | 
 | 20 | #include "rcom.h" | 
 | 21 | #include "lock.h" | 
 | 22 | #include "lowcomms.h" | 
 | 23 | #include "member.h" | 
 | 24 | #include "recover.h" | 
 | 25 |  | 
 | 26 |  | 
 | 27 | /* | 
 | 28 |  * Recovery waiting routines: these functions wait for a particular reply from | 
 | 29 |  * a remote node, or for the remote node to report a certain status.  They need | 
 | 30 |  * to abort if the lockspace is stopped indicating a node has failed (perhaps | 
 | 31 |  * the one being waited for). | 
 | 32 |  */ | 
 | 33 |  | 
 | 34 | /* | 
 | 35 |  * Wait until given function returns non-zero or lockspace is stopped | 
 | 36 |  * (LS_RECOVERY_STOP set due to failure of a node in ls_nodes).  When another | 
 | 37 |  * function thinks it could have completed the waited-on task, they should wake | 
 | 38 |  * up ls_wait_general to get an immediate response rather than waiting for the | 
 | 39 |  * timer to detect the result.  A timer wakes us up periodically while waiting | 
 | 40 |  * to see if we should abort due to a node failure.  This should only be called | 
 | 41 |  * by the dlm_recoverd thread. | 
 | 42 |  */ | 
 | 43 |  | 
 | 44 | static void dlm_wait_timer_fn(unsigned long data) | 
 | 45 | { | 
 | 46 | 	struct dlm_ls *ls = (struct dlm_ls *) data; | 
| David Teigland | 68c817a | 2007-01-09 09:41:48 -0600 | [diff] [blame] | 47 | 	mod_timer(&ls->ls_timer, jiffies + (dlm_config.ci_recover_timer * HZ)); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 48 | 	wake_up(&ls->ls_wait_general); | 
 | 49 | } | 
 | 50 |  | 
 | 51 | int dlm_wait_function(struct dlm_ls *ls, int (*testfn) (struct dlm_ls *ls)) | 
 | 52 | { | 
 | 53 | 	int error = 0; | 
 | 54 |  | 
 | 55 | 	init_timer(&ls->ls_timer); | 
 | 56 | 	ls->ls_timer.function = dlm_wait_timer_fn; | 
 | 57 | 	ls->ls_timer.data = (long) ls; | 
| David Teigland | 68c817a | 2007-01-09 09:41:48 -0600 | [diff] [blame] | 58 | 	ls->ls_timer.expires = jiffies + (dlm_config.ci_recover_timer * HZ); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 59 | 	add_timer(&ls->ls_timer); | 
 | 60 |  | 
 | 61 | 	wait_event(ls->ls_wait_general, testfn(ls) || dlm_recovery_stopped(ls)); | 
 | 62 | 	del_timer_sync(&ls->ls_timer); | 
 | 63 |  | 
 | 64 | 	if (dlm_recovery_stopped(ls)) { | 
 | 65 | 		log_debug(ls, "dlm_wait_function aborted"); | 
 | 66 | 		error = -EINTR; | 
 | 67 | 	} | 
 | 68 | 	return error; | 
 | 69 | } | 
 | 70 |  | 
 | 71 | /* | 
 | 72 |  * An efficient way for all nodes to wait for all others to have a certain | 
 | 73 |  * status.  The node with the lowest nodeid polls all the others for their | 
 | 74 |  * status (wait_status_all) and all the others poll the node with the low id | 
 | 75 |  * for its accumulated result (wait_status_low).  When all nodes have set | 
 | 76 |  * status flag X, then status flag X_ALL will be set on the low nodeid. | 
 | 77 |  */ | 
 | 78 |  | 
 | 79 | uint32_t dlm_recover_status(struct dlm_ls *ls) | 
 | 80 | { | 
 | 81 | 	uint32_t status; | 
 | 82 | 	spin_lock(&ls->ls_recover_lock); | 
 | 83 | 	status = ls->ls_recover_status; | 
 | 84 | 	spin_unlock(&ls->ls_recover_lock); | 
 | 85 | 	return status; | 
 | 86 | } | 
 | 87 |  | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 88 | static void _set_recover_status(struct dlm_ls *ls, uint32_t status) | 
 | 89 | { | 
 | 90 | 	ls->ls_recover_status |= status; | 
 | 91 | } | 
 | 92 |  | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 93 | void dlm_set_recover_status(struct dlm_ls *ls, uint32_t status) | 
 | 94 | { | 
 | 95 | 	spin_lock(&ls->ls_recover_lock); | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 96 | 	_set_recover_status(ls, status); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 97 | 	spin_unlock(&ls->ls_recover_lock); | 
 | 98 | } | 
 | 99 |  | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 100 | static int wait_status_all(struct dlm_ls *ls, uint32_t wait_status, | 
 | 101 | 			   int save_slots) | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 102 | { | 
| Al Viro | 4007685 | 2008-01-25 03:01:51 -0500 | [diff] [blame] | 103 | 	struct dlm_rcom *rc = ls->ls_recover_buf; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 104 | 	struct dlm_member *memb; | 
 | 105 | 	int error = 0, delay; | 
 | 106 |  | 
 | 107 | 	list_for_each_entry(memb, &ls->ls_nodes, list) { | 
 | 108 | 		delay = 0; | 
 | 109 | 		for (;;) { | 
 | 110 | 			if (dlm_recovery_stopped(ls)) { | 
 | 111 | 				error = -EINTR; | 
 | 112 | 				goto out; | 
 | 113 | 			} | 
 | 114 |  | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 115 | 			error = dlm_rcom_status(ls, memb->nodeid, 0); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 116 | 			if (error) | 
 | 117 | 				goto out; | 
 | 118 |  | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 119 | 			if (save_slots) | 
 | 120 | 				dlm_slot_save(ls, rc, memb); | 
 | 121 |  | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 122 | 			if (rc->rc_result & wait_status) | 
 | 123 | 				break; | 
 | 124 | 			if (delay < 1000) | 
 | 125 | 				delay += 20; | 
 | 126 | 			msleep(delay); | 
 | 127 | 		} | 
 | 128 | 	} | 
 | 129 |  out: | 
 | 130 | 	return error; | 
 | 131 | } | 
 | 132 |  | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 133 | static int wait_status_low(struct dlm_ls *ls, uint32_t wait_status, | 
 | 134 | 			   uint32_t status_flags) | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 135 | { | 
| Al Viro | 4007685 | 2008-01-25 03:01:51 -0500 | [diff] [blame] | 136 | 	struct dlm_rcom *rc = ls->ls_recover_buf; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 137 | 	int error = 0, delay = 0, nodeid = ls->ls_low_nodeid; | 
 | 138 |  | 
 | 139 | 	for (;;) { | 
 | 140 | 		if (dlm_recovery_stopped(ls)) { | 
 | 141 | 			error = -EINTR; | 
 | 142 | 			goto out; | 
 | 143 | 		} | 
 | 144 |  | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 145 | 		error = dlm_rcom_status(ls, nodeid, status_flags); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 146 | 		if (error) | 
 | 147 | 			break; | 
 | 148 |  | 
 | 149 | 		if (rc->rc_result & wait_status) | 
 | 150 | 			break; | 
 | 151 | 		if (delay < 1000) | 
 | 152 | 			delay += 20; | 
 | 153 | 		msleep(delay); | 
 | 154 | 	} | 
 | 155 |  out: | 
 | 156 | 	return error; | 
 | 157 | } | 
 | 158 |  | 
 | 159 | static int wait_status(struct dlm_ls *ls, uint32_t status) | 
 | 160 | { | 
 | 161 | 	uint32_t status_all = status << 1; | 
 | 162 | 	int error; | 
 | 163 |  | 
 | 164 | 	if (ls->ls_low_nodeid == dlm_our_nodeid()) { | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 165 | 		error = wait_status_all(ls, status, 0); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 166 | 		if (!error) | 
 | 167 | 			dlm_set_recover_status(ls, status_all); | 
 | 168 | 	} else | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 169 | 		error = wait_status_low(ls, status_all, 0); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 170 |  | 
 | 171 | 	return error; | 
 | 172 | } | 
 | 173 |  | 
 | 174 | int dlm_recover_members_wait(struct dlm_ls *ls) | 
 | 175 | { | 
| David Teigland | 757a427 | 2011-10-20 13:26:28 -0500 | [diff] [blame] | 176 | 	struct dlm_member *memb; | 
 | 177 | 	struct dlm_slot *slots; | 
 | 178 | 	int num_slots, slots_size; | 
 | 179 | 	int error, rv; | 
 | 180 | 	uint32_t gen; | 
 | 181 |  | 
 | 182 | 	list_for_each_entry(memb, &ls->ls_nodes, list) { | 
 | 183 | 		memb->slot = -1; | 
 | 184 | 		memb->generation = 0; | 
 | 185 | 	} | 
 | 186 |  | 
 | 187 | 	if (ls->ls_low_nodeid == dlm_our_nodeid()) { | 
 | 188 | 		error = wait_status_all(ls, DLM_RS_NODES, 1); | 
 | 189 | 		if (error) | 
 | 190 | 			goto out; | 
 | 191 |  | 
 | 192 | 		/* slots array is sparse, slots_size may be > num_slots */ | 
 | 193 |  | 
 | 194 | 		rv = dlm_slots_assign(ls, &num_slots, &slots_size, &slots, &gen); | 
 | 195 | 		if (!rv) { | 
 | 196 | 			spin_lock(&ls->ls_recover_lock); | 
 | 197 | 			_set_recover_status(ls, DLM_RS_NODES_ALL); | 
 | 198 | 			ls->ls_num_slots = num_slots; | 
 | 199 | 			ls->ls_slots_size = slots_size; | 
 | 200 | 			ls->ls_slots = slots; | 
 | 201 | 			ls->ls_generation = gen; | 
 | 202 | 			spin_unlock(&ls->ls_recover_lock); | 
 | 203 | 		} else { | 
 | 204 | 			dlm_set_recover_status(ls, DLM_RS_NODES_ALL); | 
 | 205 | 		} | 
 | 206 | 	} else { | 
 | 207 | 		error = wait_status_low(ls, DLM_RS_NODES_ALL, DLM_RSF_NEED_SLOTS); | 
 | 208 | 		if (error) | 
 | 209 | 			goto out; | 
 | 210 |  | 
 | 211 | 		dlm_slots_copy_in(ls); | 
 | 212 | 	} | 
 | 213 |  out: | 
 | 214 | 	return error; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 215 | } | 
 | 216 |  | 
 | 217 | int dlm_recover_directory_wait(struct dlm_ls *ls) | 
 | 218 | { | 
 | 219 | 	return wait_status(ls, DLM_RS_DIR); | 
 | 220 | } | 
 | 221 |  | 
 | 222 | int dlm_recover_locks_wait(struct dlm_ls *ls) | 
 | 223 | { | 
 | 224 | 	return wait_status(ls, DLM_RS_LOCKS); | 
 | 225 | } | 
 | 226 |  | 
 | 227 | int dlm_recover_done_wait(struct dlm_ls *ls) | 
 | 228 | { | 
 | 229 | 	return wait_status(ls, DLM_RS_DONE); | 
 | 230 | } | 
 | 231 |  | 
 | 232 | /* | 
 | 233 |  * The recover_list contains all the rsb's for which we've requested the new | 
 | 234 |  * master nodeid.  As replies are returned from the resource directories the | 
 | 235 |  * rsb's are removed from the list.  When the list is empty we're done. | 
 | 236 |  * | 
 | 237 |  * The recover_list is later similarly used for all rsb's for which we've sent | 
 | 238 |  * new lkb's and need to receive new corresponding lkid's. | 
 | 239 |  * | 
 | 240 |  * We use the address of the rsb struct as a simple local identifier for the | 
 | 241 |  * rsb so we can match an rcom reply with the rsb it was sent for. | 
 | 242 |  */ | 
 | 243 |  | 
 | 244 | static int recover_list_empty(struct dlm_ls *ls) | 
 | 245 | { | 
 | 246 | 	int empty; | 
 | 247 |  | 
 | 248 | 	spin_lock(&ls->ls_recover_list_lock); | 
 | 249 | 	empty = list_empty(&ls->ls_recover_list); | 
 | 250 | 	spin_unlock(&ls->ls_recover_list_lock); | 
 | 251 |  | 
 | 252 | 	return empty; | 
 | 253 | } | 
 | 254 |  | 
 | 255 | static void recover_list_add(struct dlm_rsb *r) | 
 | 256 | { | 
 | 257 | 	struct dlm_ls *ls = r->res_ls; | 
 | 258 |  | 
 | 259 | 	spin_lock(&ls->ls_recover_list_lock); | 
 | 260 | 	if (list_empty(&r->res_recover_list)) { | 
 | 261 | 		list_add_tail(&r->res_recover_list, &ls->ls_recover_list); | 
 | 262 | 		ls->ls_recover_list_count++; | 
 | 263 | 		dlm_hold_rsb(r); | 
 | 264 | 	} | 
 | 265 | 	spin_unlock(&ls->ls_recover_list_lock); | 
 | 266 | } | 
 | 267 |  | 
 | 268 | static void recover_list_del(struct dlm_rsb *r) | 
 | 269 | { | 
 | 270 | 	struct dlm_ls *ls = r->res_ls; | 
 | 271 |  | 
 | 272 | 	spin_lock(&ls->ls_recover_list_lock); | 
 | 273 | 	list_del_init(&r->res_recover_list); | 
 | 274 | 	ls->ls_recover_list_count--; | 
 | 275 | 	spin_unlock(&ls->ls_recover_list_lock); | 
 | 276 |  | 
 | 277 | 	dlm_put_rsb(r); | 
 | 278 | } | 
 | 279 |  | 
 | 280 | static struct dlm_rsb *recover_list_find(struct dlm_ls *ls, uint64_t id) | 
 | 281 | { | 
 | 282 | 	struct dlm_rsb *r = NULL; | 
 | 283 |  | 
 | 284 | 	spin_lock(&ls->ls_recover_list_lock); | 
 | 285 |  | 
 | 286 | 	list_for_each_entry(r, &ls->ls_recover_list, res_recover_list) { | 
 | 287 | 		if (id == (unsigned long) r) | 
 | 288 | 			goto out; | 
 | 289 | 	} | 
 | 290 | 	r = NULL; | 
 | 291 |  out: | 
 | 292 | 	spin_unlock(&ls->ls_recover_list_lock); | 
 | 293 | 	return r; | 
 | 294 | } | 
 | 295 |  | 
 | 296 | static void recover_list_clear(struct dlm_ls *ls) | 
 | 297 | { | 
 | 298 | 	struct dlm_rsb *r, *s; | 
 | 299 |  | 
 | 300 | 	spin_lock(&ls->ls_recover_list_lock); | 
 | 301 | 	list_for_each_entry_safe(r, s, &ls->ls_recover_list, res_recover_list) { | 
 | 302 | 		list_del_init(&r->res_recover_list); | 
| David Teigland | 5206980 | 2006-11-02 09:49:02 -0600 | [diff] [blame] | 303 | 		r->res_recover_locks_count = 0; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 304 | 		dlm_put_rsb(r); | 
 | 305 | 		ls->ls_recover_list_count--; | 
 | 306 | 	} | 
 | 307 |  | 
 | 308 | 	if (ls->ls_recover_list_count != 0) { | 
 | 309 | 		log_error(ls, "warning: recover_list_count %d", | 
 | 310 | 			  ls->ls_recover_list_count); | 
 | 311 | 		ls->ls_recover_list_count = 0; | 
 | 312 | 	} | 
 | 313 | 	spin_unlock(&ls->ls_recover_list_lock); | 
 | 314 | } | 
 | 315 |  | 
 | 316 |  | 
 | 317 | /* Master recovery: find new master node for rsb's that were | 
 | 318 |    mastered on nodes that have been removed. | 
 | 319 |  | 
 | 320 |    dlm_recover_masters | 
 | 321 |    recover_master | 
 | 322 |    dlm_send_rcom_lookup            ->  receive_rcom_lookup | 
 | 323 |                                        dlm_dir_lookup | 
 | 324 |    receive_rcom_lookup_reply       <- | 
 | 325 |    dlm_recover_master_reply | 
 | 326 |    set_new_master | 
 | 327 |    set_master_lkbs | 
 | 328 |    set_lock_master | 
 | 329 | */ | 
 | 330 |  | 
 | 331 | /* | 
 | 332 |  * Set the lock master for all LKBs in a lock queue | 
 | 333 |  * If we are the new master of the rsb, we may have received new | 
 | 334 |  * MSTCPY locks from other nodes already which we need to ignore | 
 | 335 |  * when setting the new nodeid. | 
 | 336 |  */ | 
 | 337 |  | 
 | 338 | static void set_lock_master(struct list_head *queue, int nodeid) | 
 | 339 | { | 
 | 340 | 	struct dlm_lkb *lkb; | 
 | 341 |  | 
 | 342 | 	list_for_each_entry(lkb, queue, lkb_statequeue) | 
 | 343 | 		if (!(lkb->lkb_flags & DLM_IFL_MSTCPY)) | 
 | 344 | 			lkb->lkb_nodeid = nodeid; | 
 | 345 | } | 
 | 346 |  | 
 | 347 | static void set_master_lkbs(struct dlm_rsb *r) | 
 | 348 | { | 
 | 349 | 	set_lock_master(&r->res_grantqueue, r->res_nodeid); | 
 | 350 | 	set_lock_master(&r->res_convertqueue, r->res_nodeid); | 
 | 351 | 	set_lock_master(&r->res_waitqueue, r->res_nodeid); | 
 | 352 | } | 
 | 353 |  | 
 | 354 | /* | 
| Lucas De Marchi | 25985ed | 2011-03-30 22:57:33 -0300 | [diff] [blame] | 355 |  * Propagate the new master nodeid to locks | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 356 |  * The NEW_MASTER flag tells dlm_recover_locks() which rsb's to consider. | 
| David Teigland | f7da790 | 2006-07-25 13:53:33 -0500 | [diff] [blame] | 357 |  * The NEW_MASTER2 flag tells recover_lvb() and set_locks_purged() which | 
 | 358 |  * rsb's to consider. | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 359 |  */ | 
 | 360 |  | 
 | 361 | static void set_new_master(struct dlm_rsb *r, int nodeid) | 
 | 362 | { | 
 | 363 | 	lock_rsb(r); | 
 | 364 | 	r->res_nodeid = nodeid; | 
 | 365 | 	set_master_lkbs(r); | 
 | 366 | 	rsb_set_flag(r, RSB_NEW_MASTER); | 
 | 367 | 	rsb_set_flag(r, RSB_NEW_MASTER2); | 
 | 368 | 	unlock_rsb(r); | 
 | 369 | } | 
 | 370 |  | 
 | 371 | /* | 
 | 372 |  * We do async lookups on rsb's that need new masters.  The rsb's | 
 | 373 |  * waiting for a lookup reply are kept on the recover_list. | 
 | 374 |  */ | 
 | 375 |  | 
 | 376 | static int recover_master(struct dlm_rsb *r) | 
 | 377 | { | 
 | 378 | 	struct dlm_ls *ls = r->res_ls; | 
 | 379 | 	int error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid(); | 
 | 380 |  | 
 | 381 | 	dir_nodeid = dlm_dir_nodeid(r); | 
 | 382 |  | 
 | 383 | 	if (dir_nodeid == our_nodeid) { | 
 | 384 | 		error = dlm_dir_lookup(ls, our_nodeid, r->res_name, | 
 | 385 | 				       r->res_length, &ret_nodeid); | 
 | 386 | 		if (error) | 
 | 387 | 			log_error(ls, "recover dir lookup error %d", error); | 
 | 388 |  | 
 | 389 | 		if (ret_nodeid == our_nodeid) | 
 | 390 | 			ret_nodeid = 0; | 
 | 391 | 		set_new_master(r, ret_nodeid); | 
 | 392 | 	} else { | 
 | 393 | 		recover_list_add(r); | 
 | 394 | 		error = dlm_send_rcom_lookup(r, dir_nodeid); | 
 | 395 | 	} | 
 | 396 |  | 
 | 397 | 	return error; | 
 | 398 | } | 
 | 399 |  | 
 | 400 | /* | 
 | 401 |  * When not using a directory, most resource names will hash to a new static | 
 | 402 |  * master nodeid and the resource will need to be remastered. | 
 | 403 |  */ | 
 | 404 |  | 
 | 405 | static int recover_master_static(struct dlm_rsb *r) | 
 | 406 | { | 
 | 407 | 	int master = dlm_dir_nodeid(r); | 
 | 408 |  | 
 | 409 | 	if (master == dlm_our_nodeid()) | 
 | 410 | 		master = 0; | 
 | 411 |  | 
 | 412 | 	if (r->res_nodeid != master) { | 
 | 413 | 		if (is_master(r)) | 
 | 414 | 			dlm_purge_mstcpy_locks(r); | 
 | 415 | 		set_new_master(r, master); | 
 | 416 | 		return 1; | 
 | 417 | 	} | 
 | 418 | 	return 0; | 
 | 419 | } | 
 | 420 |  | 
 | 421 | /* | 
 | 422 |  * Go through local root resources and for each rsb which has a master which | 
 | 423 |  * has departed, get the new master nodeid from the directory.  The dir will | 
 | 424 |  * assign mastery to the first node to look up the new master.  That means | 
 | 425 |  * we'll discover in this lookup if we're the new master of any rsb's. | 
 | 426 |  * | 
 | 427 |  * We fire off all the dir lookup requests individually and asynchronously to | 
 | 428 |  * the correct dir node. | 
 | 429 |  */ | 
 | 430 |  | 
 | 431 | int dlm_recover_masters(struct dlm_ls *ls) | 
 | 432 | { | 
 | 433 | 	struct dlm_rsb *r; | 
 | 434 | 	int error = 0, count = 0; | 
 | 435 |  | 
 | 436 | 	log_debug(ls, "dlm_recover_masters"); | 
 | 437 |  | 
 | 438 | 	down_read(&ls->ls_root_sem); | 
 | 439 | 	list_for_each_entry(r, &ls->ls_root_list, res_root_list) { | 
 | 440 | 		if (dlm_recovery_stopped(ls)) { | 
 | 441 | 			up_read(&ls->ls_root_sem); | 
 | 442 | 			error = -EINTR; | 
 | 443 | 			goto out; | 
 | 444 | 		} | 
 | 445 |  | 
 | 446 | 		if (dlm_no_directory(ls)) | 
 | 447 | 			count += recover_master_static(r); | 
| David Teigland | 222d396 | 2007-01-15 10:28:22 -0600 | [diff] [blame] | 448 | 		else if (!is_master(r) && | 
 | 449 | 			 (dlm_is_removed(ls, r->res_nodeid) || | 
 | 450 | 			  rsb_flag(r, RSB_NEW_MASTER))) { | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 451 | 			recover_master(r); | 
 | 452 | 			count++; | 
 | 453 | 		} | 
 | 454 |  | 
 | 455 | 		schedule(); | 
 | 456 | 	} | 
 | 457 | 	up_read(&ls->ls_root_sem); | 
 | 458 |  | 
 | 459 | 	log_debug(ls, "dlm_recover_masters %d resources", count); | 
 | 460 |  | 
 | 461 | 	error = dlm_wait_function(ls, &recover_list_empty); | 
 | 462 |  out: | 
 | 463 | 	if (error) | 
 | 464 | 		recover_list_clear(ls); | 
 | 465 | 	return error; | 
 | 466 | } | 
 | 467 |  | 
 | 468 | int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc) | 
 | 469 | { | 
 | 470 | 	struct dlm_rsb *r; | 
 | 471 | 	int nodeid; | 
 | 472 |  | 
 | 473 | 	r = recover_list_find(ls, rc->rc_id); | 
 | 474 | 	if (!r) { | 
| David Teigland | 9013592 | 2006-01-20 08:47:07 +0000 | [diff] [blame] | 475 | 		log_error(ls, "dlm_recover_master_reply no id %llx", | 
| David Teigland | 9229f01 | 2006-05-24 09:21:30 -0400 | [diff] [blame] | 476 | 			  (unsigned long long)rc->rc_id); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 477 | 		goto out; | 
 | 478 | 	} | 
 | 479 |  | 
 | 480 | 	nodeid = rc->rc_result; | 
 | 481 | 	if (nodeid == dlm_our_nodeid()) | 
 | 482 | 		nodeid = 0; | 
 | 483 |  | 
 | 484 | 	set_new_master(r, nodeid); | 
 | 485 | 	recover_list_del(r); | 
 | 486 |  | 
 | 487 | 	if (recover_list_empty(ls)) | 
 | 488 | 		wake_up(&ls->ls_wait_general); | 
 | 489 |  out: | 
 | 490 | 	return 0; | 
 | 491 | } | 
 | 492 |  | 
 | 493 |  | 
 | 494 | /* Lock recovery: rebuild the process-copy locks we hold on a | 
 | 495 |    remastered rsb on the new rsb master. | 
 | 496 |  | 
 | 497 |    dlm_recover_locks | 
 | 498 |    recover_locks | 
 | 499 |    recover_locks_queue | 
 | 500 |    dlm_send_rcom_lock              ->  receive_rcom_lock | 
 | 501 |                                        dlm_recover_master_copy | 
 | 502 |    receive_rcom_lock_reply         <- | 
 | 503 |    dlm_recover_process_copy | 
 | 504 | */ | 
 | 505 |  | 
 | 506 |  | 
 | 507 | /* | 
 | 508 |  * keep a count of the number of lkb's we send to the new master; when we get | 
 | 509 |  * an equal number of replies then recovery for the rsb is done | 
 | 510 |  */ | 
 | 511 |  | 
 | 512 | static int recover_locks_queue(struct dlm_rsb *r, struct list_head *head) | 
 | 513 | { | 
 | 514 | 	struct dlm_lkb *lkb; | 
 | 515 | 	int error = 0; | 
 | 516 |  | 
 | 517 | 	list_for_each_entry(lkb, head, lkb_statequeue) { | 
 | 518 | 	   	error = dlm_send_rcom_lock(r, lkb); | 
 | 519 | 		if (error) | 
 | 520 | 			break; | 
 | 521 | 		r->res_recover_locks_count++; | 
 | 522 | 	} | 
 | 523 |  | 
 | 524 | 	return error; | 
 | 525 | } | 
 | 526 |  | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 527 | static int recover_locks(struct dlm_rsb *r) | 
 | 528 | { | 
 | 529 | 	int error = 0; | 
 | 530 |  | 
 | 531 | 	lock_rsb(r); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 532 |  | 
| David Teigland | a345da3 | 2006-08-18 11:54:25 -0500 | [diff] [blame] | 533 | 	DLM_ASSERT(!r->res_recover_locks_count, dlm_dump_rsb(r);); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 534 |  | 
 | 535 | 	error = recover_locks_queue(r, &r->res_grantqueue); | 
 | 536 | 	if (error) | 
 | 537 | 		goto out; | 
 | 538 | 	error = recover_locks_queue(r, &r->res_convertqueue); | 
 | 539 | 	if (error) | 
 | 540 | 		goto out; | 
 | 541 | 	error = recover_locks_queue(r, &r->res_waitqueue); | 
 | 542 | 	if (error) | 
 | 543 | 		goto out; | 
 | 544 |  | 
 | 545 | 	if (r->res_recover_locks_count) | 
 | 546 | 		recover_list_add(r); | 
 | 547 | 	else | 
 | 548 | 		rsb_clear_flag(r, RSB_NEW_MASTER); | 
 | 549 |  out: | 
 | 550 | 	unlock_rsb(r); | 
 | 551 | 	return error; | 
 | 552 | } | 
 | 553 |  | 
 | 554 | int dlm_recover_locks(struct dlm_ls *ls) | 
 | 555 | { | 
 | 556 | 	struct dlm_rsb *r; | 
 | 557 | 	int error, count = 0; | 
 | 558 |  | 
 | 559 | 	log_debug(ls, "dlm_recover_locks"); | 
 | 560 |  | 
 | 561 | 	down_read(&ls->ls_root_sem); | 
 | 562 | 	list_for_each_entry(r, &ls->ls_root_list, res_root_list) { | 
 | 563 | 		if (is_master(r)) { | 
 | 564 | 			rsb_clear_flag(r, RSB_NEW_MASTER); | 
 | 565 | 			continue; | 
 | 566 | 		} | 
 | 567 |  | 
 | 568 | 		if (!rsb_flag(r, RSB_NEW_MASTER)) | 
 | 569 | 			continue; | 
 | 570 |  | 
 | 571 | 		if (dlm_recovery_stopped(ls)) { | 
 | 572 | 			error = -EINTR; | 
 | 573 | 			up_read(&ls->ls_root_sem); | 
 | 574 | 			goto out; | 
 | 575 | 		} | 
 | 576 |  | 
 | 577 | 		error = recover_locks(r); | 
 | 578 | 		if (error) { | 
 | 579 | 			up_read(&ls->ls_root_sem); | 
 | 580 | 			goto out; | 
 | 581 | 		} | 
 | 582 |  | 
 | 583 | 		count += r->res_recover_locks_count; | 
 | 584 | 	} | 
 | 585 | 	up_read(&ls->ls_root_sem); | 
 | 586 |  | 
 | 587 | 	log_debug(ls, "dlm_recover_locks %d locks", count); | 
 | 588 |  | 
 | 589 | 	error = dlm_wait_function(ls, &recover_list_empty); | 
 | 590 |  out: | 
 | 591 | 	if (error) | 
 | 592 | 		recover_list_clear(ls); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 593 | 	return error; | 
 | 594 | } | 
 | 595 |  | 
 | 596 | void dlm_recovered_lock(struct dlm_rsb *r) | 
 | 597 | { | 
| David Teigland | a345da3 | 2006-08-18 11:54:25 -0500 | [diff] [blame] | 598 | 	DLM_ASSERT(rsb_flag(r, RSB_NEW_MASTER), dlm_dump_rsb(r);); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 599 |  | 
 | 600 | 	r->res_recover_locks_count--; | 
 | 601 | 	if (!r->res_recover_locks_count) { | 
 | 602 | 		rsb_clear_flag(r, RSB_NEW_MASTER); | 
 | 603 | 		recover_list_del(r); | 
 | 604 | 	} | 
 | 605 |  | 
 | 606 | 	if (recover_list_empty(r->res_ls)) | 
 | 607 | 		wake_up(&r->res_ls->ls_wait_general); | 
 | 608 | } | 
 | 609 |  | 
 | 610 | /* | 
 | 611 |  * The lvb needs to be recovered on all master rsb's.  This includes setting | 
 | 612 |  * the VALNOTVALID flag if necessary, and determining the correct lvb contents | 
 | 613 |  * based on the lvb's of the locks held on the rsb. | 
 | 614 |  * | 
 | 615 |  * RSB_VALNOTVALID is set if there are only NL/CR locks on the rsb.  If it | 
 | 616 |  * was already set prior to recovery, it's not cleared, regardless of locks. | 
 | 617 |  * | 
 | 618 |  * The LVB contents are only considered for changing when this is a new master | 
 | 619 |  * of the rsb (NEW_MASTER2).  Then, the rsb's lvb is taken from any lkb with | 
 | 620 |  * mode > CR.  If no lkb's exist with mode above CR, the lvb contents are taken | 
 | 621 |  * from the lkb with the largest lvb sequence number. | 
 | 622 |  */ | 
 | 623 |  | 
 | 624 | static void recover_lvb(struct dlm_rsb *r) | 
 | 625 | { | 
 | 626 | 	struct dlm_lkb *lkb, *high_lkb = NULL; | 
 | 627 | 	uint32_t high_seq = 0; | 
| David Teigland | 9013592 | 2006-01-20 08:47:07 +0000 | [diff] [blame] | 628 | 	int lock_lvb_exists = 0; | 
 | 629 | 	int big_lock_exists = 0; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 630 | 	int lvblen = r->res_ls->ls_lvblen; | 
 | 631 |  | 
 | 632 | 	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { | 
 | 633 | 		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) | 
 | 634 | 			continue; | 
 | 635 |  | 
| David Teigland | 9013592 | 2006-01-20 08:47:07 +0000 | [diff] [blame] | 636 | 		lock_lvb_exists = 1; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 637 |  | 
 | 638 | 		if (lkb->lkb_grmode > DLM_LOCK_CR) { | 
| David Teigland | 9013592 | 2006-01-20 08:47:07 +0000 | [diff] [blame] | 639 | 			big_lock_exists = 1; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 640 | 			goto setflag; | 
 | 641 | 		} | 
 | 642 |  | 
 | 643 | 		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { | 
 | 644 | 			high_lkb = lkb; | 
 | 645 | 			high_seq = lkb->lkb_lvbseq; | 
 | 646 | 		} | 
 | 647 | 	} | 
 | 648 |  | 
 | 649 | 	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { | 
 | 650 | 		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK)) | 
 | 651 | 			continue; | 
 | 652 |  | 
| David Teigland | 9013592 | 2006-01-20 08:47:07 +0000 | [diff] [blame] | 653 | 		lock_lvb_exists = 1; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 654 |  | 
 | 655 | 		if (lkb->lkb_grmode > DLM_LOCK_CR) { | 
| David Teigland | 9013592 | 2006-01-20 08:47:07 +0000 | [diff] [blame] | 656 | 			big_lock_exists = 1; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 657 | 			goto setflag; | 
 | 658 | 		} | 
 | 659 |  | 
 | 660 | 		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) { | 
 | 661 | 			high_lkb = lkb; | 
 | 662 | 			high_seq = lkb->lkb_lvbseq; | 
 | 663 | 		} | 
 | 664 | 	} | 
 | 665 |  | 
 | 666 |  setflag: | 
 | 667 | 	if (!lock_lvb_exists) | 
 | 668 | 		goto out; | 
 | 669 |  | 
 | 670 | 	if (!big_lock_exists) | 
 | 671 | 		rsb_set_flag(r, RSB_VALNOTVALID); | 
 | 672 |  | 
 | 673 | 	/* don't mess with the lvb unless we're the new master */ | 
 | 674 | 	if (!rsb_flag(r, RSB_NEW_MASTER2)) | 
 | 675 | 		goto out; | 
 | 676 |  | 
 | 677 | 	if (!r->res_lvbptr) { | 
| David Teigland | 52bda2b | 2007-11-07 09:06:49 -0600 | [diff] [blame] | 678 | 		r->res_lvbptr = dlm_allocate_lvb(r->res_ls); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 679 | 		if (!r->res_lvbptr) | 
 | 680 | 			goto out; | 
 | 681 | 	} | 
 | 682 |  | 
 | 683 | 	if (big_lock_exists) { | 
 | 684 | 		r->res_lvbseq = lkb->lkb_lvbseq; | 
 | 685 | 		memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen); | 
 | 686 | 	} else if (high_lkb) { | 
 | 687 | 		r->res_lvbseq = high_lkb->lkb_lvbseq; | 
 | 688 | 		memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen); | 
 | 689 | 	} else { | 
 | 690 | 		r->res_lvbseq = 0; | 
 | 691 | 		memset(r->res_lvbptr, 0, lvblen); | 
 | 692 | 	} | 
 | 693 |  out: | 
 | 694 | 	return; | 
 | 695 | } | 
 | 696 |  | 
 | 697 | /* All master rsb's flagged RECOVER_CONVERT need to be looked at.  The locks | 
 | 698 |    converting PR->CW or CW->PR need to have their lkb_grmode set. */ | 
 | 699 |  | 
 | 700 | static void recover_conversion(struct dlm_rsb *r) | 
 | 701 | { | 
 | 702 | 	struct dlm_lkb *lkb; | 
 | 703 | 	int grmode = -1; | 
 | 704 |  | 
 | 705 | 	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) { | 
 | 706 | 		if (lkb->lkb_grmode == DLM_LOCK_PR || | 
 | 707 | 		    lkb->lkb_grmode == DLM_LOCK_CW) { | 
 | 708 | 			grmode = lkb->lkb_grmode; | 
 | 709 | 			break; | 
 | 710 | 		} | 
 | 711 | 	} | 
 | 712 |  | 
 | 713 | 	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) { | 
 | 714 | 		if (lkb->lkb_grmode != DLM_LOCK_IV) | 
 | 715 | 			continue; | 
 | 716 | 		if (grmode == -1) | 
 | 717 | 			lkb->lkb_grmode = lkb->lkb_rqmode; | 
 | 718 | 		else | 
 | 719 | 			lkb->lkb_grmode = grmode; | 
 | 720 | 	} | 
 | 721 | } | 
 | 722 |  | 
| David Teigland | f7da790 | 2006-07-25 13:53:33 -0500 | [diff] [blame] | 723 | /* We've become the new master for this rsb and waiting/converting locks may | 
 | 724 |    need to be granted in dlm_grant_after_purge() due to locks that may have | 
 | 725 |    existed from a removed node. */ | 
 | 726 |  | 
 | 727 | static void set_locks_purged(struct dlm_rsb *r) | 
 | 728 | { | 
 | 729 | 	if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue)) | 
 | 730 | 		rsb_set_flag(r, RSB_LOCKS_PURGED); | 
 | 731 | } | 
 | 732 |  | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 733 | void dlm_recover_rsbs(struct dlm_ls *ls) | 
 | 734 | { | 
 | 735 | 	struct dlm_rsb *r; | 
 | 736 | 	int count = 0; | 
 | 737 |  | 
 | 738 | 	log_debug(ls, "dlm_recover_rsbs"); | 
 | 739 |  | 
 | 740 | 	down_read(&ls->ls_root_sem); | 
 | 741 | 	list_for_each_entry(r, &ls->ls_root_list, res_root_list) { | 
 | 742 | 		lock_rsb(r); | 
 | 743 | 		if (is_master(r)) { | 
 | 744 | 			if (rsb_flag(r, RSB_RECOVER_CONVERT)) | 
 | 745 | 				recover_conversion(r); | 
| David Teigland | f7da790 | 2006-07-25 13:53:33 -0500 | [diff] [blame] | 746 | 			if (rsb_flag(r, RSB_NEW_MASTER2)) | 
 | 747 | 				set_locks_purged(r); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 748 | 			recover_lvb(r); | 
 | 749 | 			count++; | 
 | 750 | 		} | 
 | 751 | 		rsb_clear_flag(r, RSB_RECOVER_CONVERT); | 
| David Teigland | f7da790 | 2006-07-25 13:53:33 -0500 | [diff] [blame] | 752 | 		rsb_clear_flag(r, RSB_NEW_MASTER2); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 753 | 		unlock_rsb(r); | 
 | 754 | 	} | 
 | 755 | 	up_read(&ls->ls_root_sem); | 
 | 756 |  | 
 | 757 | 	log_debug(ls, "dlm_recover_rsbs %d rsbs", count); | 
 | 758 | } | 
 | 759 |  | 
 | 760 | /* Create a single list of all root rsb's to be used during recovery */ | 
 | 761 |  | 
 | 762 | int dlm_create_root_list(struct dlm_ls *ls) | 
 | 763 | { | 
| Bob Peterson | 9beb3bf | 2011-10-26 15:24:55 -0500 | [diff] [blame] | 764 | 	struct rb_node *n; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 765 | 	struct dlm_rsb *r; | 
 | 766 | 	int i, error = 0; | 
 | 767 |  | 
 | 768 | 	down_write(&ls->ls_root_sem); | 
 | 769 | 	if (!list_empty(&ls->ls_root_list)) { | 
 | 770 | 		log_error(ls, "root list not empty"); | 
 | 771 | 		error = -EINVAL; | 
 | 772 | 		goto out; | 
 | 773 | 	} | 
 | 774 |  | 
 | 775 | 	for (i = 0; i < ls->ls_rsbtbl_size; i++) { | 
| David Teigland | c7be761 | 2009-01-07 16:50:41 -0600 | [diff] [blame] | 776 | 		spin_lock(&ls->ls_rsbtbl[i].lock); | 
| Bob Peterson | 9beb3bf | 2011-10-26 15:24:55 -0500 | [diff] [blame] | 777 | 		for (n = rb_first(&ls->ls_rsbtbl[i].keep); n; n = rb_next(n)) { | 
 | 778 | 			r = rb_entry(n, struct dlm_rsb, res_hashnode); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 779 | 			list_add(&r->res_root_list, &ls->ls_root_list); | 
 | 780 | 			dlm_hold_rsb(r); | 
 | 781 | 		} | 
| David Teigland | 85f0379 | 2008-01-16 13:02:31 -0600 | [diff] [blame] | 782 |  | 
 | 783 | 		/* If we're using a directory, add tossed rsbs to the root | 
 | 784 | 		   list; they'll have entries created in the new directory, | 
 | 785 | 		   but no other recovery steps should do anything with them. */ | 
 | 786 |  | 
 | 787 | 		if (dlm_no_directory(ls)) { | 
| David Teigland | c7be761 | 2009-01-07 16:50:41 -0600 | [diff] [blame] | 788 | 			spin_unlock(&ls->ls_rsbtbl[i].lock); | 
| David Teigland | 85f0379 | 2008-01-16 13:02:31 -0600 | [diff] [blame] | 789 | 			continue; | 
 | 790 | 		} | 
 | 791 |  | 
| Bob Peterson | 9beb3bf | 2011-10-26 15:24:55 -0500 | [diff] [blame] | 792 | 		for (n = rb_first(&ls->ls_rsbtbl[i].toss); n; n = rb_next(n)) { | 
 | 793 | 			r = rb_entry(n, struct dlm_rsb, res_hashnode); | 
| David Teigland | 85f0379 | 2008-01-16 13:02:31 -0600 | [diff] [blame] | 794 | 			list_add(&r->res_root_list, &ls->ls_root_list); | 
 | 795 | 			dlm_hold_rsb(r); | 
 | 796 | 		} | 
| David Teigland | c7be761 | 2009-01-07 16:50:41 -0600 | [diff] [blame] | 797 | 		spin_unlock(&ls->ls_rsbtbl[i].lock); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 798 | 	} | 
 | 799 |  out: | 
 | 800 | 	up_write(&ls->ls_root_sem); | 
 | 801 | 	return error; | 
 | 802 | } | 
 | 803 |  | 
 | 804 | void dlm_release_root_list(struct dlm_ls *ls) | 
 | 805 | { | 
 | 806 | 	struct dlm_rsb *r, *safe; | 
 | 807 |  | 
 | 808 | 	down_write(&ls->ls_root_sem); | 
 | 809 | 	list_for_each_entry_safe(r, safe, &ls->ls_root_list, res_root_list) { | 
 | 810 | 		list_del_init(&r->res_root_list); | 
 | 811 | 		dlm_put_rsb(r); | 
 | 812 | 	} | 
 | 813 | 	up_write(&ls->ls_root_sem); | 
 | 814 | } | 
 | 815 |  | 
| David Teigland | 85f0379 | 2008-01-16 13:02:31 -0600 | [diff] [blame] | 816 | /* If not using a directory, clear the entire toss list, there's no benefit to | 
 | 817 |    caching the master value since it's fixed.  If we are using a dir, keep the | 
 | 818 |    rsb's we're the master of.  Recovery will add them to the root list and from | 
 | 819 |    there they'll be entered in the rebuilt directory. */ | 
 | 820 |  | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 821 | void dlm_clear_toss_list(struct dlm_ls *ls) | 
 | 822 | { | 
| Bob Peterson | 9beb3bf | 2011-10-26 15:24:55 -0500 | [diff] [blame] | 823 | 	struct rb_node *n, *next; | 
 | 824 | 	struct dlm_rsb *rsb; | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 825 | 	int i; | 
 | 826 |  | 
 | 827 | 	for (i = 0; i < ls->ls_rsbtbl_size; i++) { | 
| David Teigland | c7be761 | 2009-01-07 16:50:41 -0600 | [diff] [blame] | 828 | 		spin_lock(&ls->ls_rsbtbl[i].lock); | 
| Bob Peterson | 9beb3bf | 2011-10-26 15:24:55 -0500 | [diff] [blame] | 829 | 		for (n = rb_first(&ls->ls_rsbtbl[i].toss); n; n = next) { | 
 | 830 | 			next = rb_next(n);; | 
 | 831 | 			rsb = rb_entry(n, struct dlm_rsb, res_hashnode); | 
 | 832 | 			if (dlm_no_directory(ls) || !is_master(rsb)) { | 
 | 833 | 				rb_erase(n, &ls->ls_rsbtbl[i].toss); | 
 | 834 | 				dlm_free_rsb(rsb); | 
| David Teigland | 85f0379 | 2008-01-16 13:02:31 -0600 | [diff] [blame] | 835 | 			} | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 836 | 		} | 
| David Teigland | c7be761 | 2009-01-07 16:50:41 -0600 | [diff] [blame] | 837 | 		spin_unlock(&ls->ls_rsbtbl[i].lock); | 
| David Teigland | e7fd417 | 2006-01-18 09:30:29 +0000 | [diff] [blame] | 838 | 	} | 
 | 839 | } | 
 | 840 |  |