xref: /kernel/linux/linux-5.10/fs/ocfs2/dlm/dlmast.c (revision 8c2ecf20) 
1// SPDX-License-Identifier: GPL-2.0-or-later
2/* -*- mode: c; c-basic-offset: 8; -*-
3 * vim: noexpandtab sw=8 ts=8 sts=0:
4 *
5 * dlmast.c
6 *
7 * AST and BAST functionality for local and remote nodes
8 *
9 * Copyright (C) 2004 Oracle.  All rights reserved.
10 */
11
12
13#include <linux/module.h>
14#include <linux/fs.h>
15#include <linux/types.h>
16#include <linux/highmem.h>
17#include <linux/init.h>
18#include <linux/sysctl.h>
19#include <linux/random.h>
20#include <linux/blkdev.h>
21#include <linux/socket.h>
22#include <linux/inet.h>
23#include <linux/spinlock.h>
24
25
26#include "../cluster/heartbeat.h"
27#include "../cluster/nodemanager.h"
28#include "../cluster/tcp.h"
29
30#include "dlmapi.h"
31#include "dlmcommon.h"
32
33#define MLOG_MASK_PREFIX ML_DLM
34#include "../cluster/masklog.h"
35
36static void dlm_update_lvb(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
37			   struct dlm_lock *lock);
38static int dlm_should_cancel_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
39
40/* Should be called as an ast gets queued to see if the new
41 * lock level will obsolete a pending bast.
42 * For example, if dlm_thread queued a bast for an EX lock that
43 * was blocking another EX, but before sending the bast the
44 * lock owner downconverted to NL, the bast is now obsolete.
45 * Only the ast should be sent.
46 * This is needed because the lock and convert paths can queue
47 * asts out-of-band (not waiting for dlm_thread) in order to
48 * allow for LKM_NOQUEUE to get immediate responses. */
49static int dlm_should_cancel_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
50{
51	assert_spin_locked(&dlm->ast_lock);
52	assert_spin_locked(&lock->spinlock);
53
54	if (lock->ml.highest_blocked == LKM_IVMODE)
55		return 0;
56	BUG_ON(lock->ml.highest_blocked == LKM_NLMODE);
57
58	if (lock->bast_pending &&
59	    list_empty(&lock->bast_list))
60		/* old bast already sent, ok */
61		return 0;
62
63	if (lock->ml.type == LKM_EXMODE)
64		/* EX blocks anything left, any bast still valid */
65		return 0;
66	else if (lock->ml.type == LKM_NLMODE)
67		/* NL blocks nothing, no reason to send any bast, cancel it */
68		return 1;
69	else if (lock->ml.highest_blocked != LKM_EXMODE)
70		/* PR only blocks EX */
71		return 1;
72
73	return 0;
74}
75
76void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
77{
78	struct dlm_lock_resource *res;
79
80	BUG_ON(!dlm);
81	BUG_ON(!lock);
82
83	res = lock->lockres;
84
85	assert_spin_locked(&dlm->ast_lock);
86
87	if (!list_empty(&lock->ast_list)) {
88		mlog(ML_ERROR, "%s: res %.*s, lock %u:%llu, "
89		     "AST list not empty, pending %d, newlevel %d\n",
90		     dlm->name, res->lockname.len, res->lockname.name,
91		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
92		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
93		     lock->ast_pending, lock->ml.type);
94		BUG();
95	}
96	if (lock->ast_pending)
97		mlog(0, "%s: res %.*s, lock %u:%llu, AST getting flushed\n",
98		     dlm->name, res->lockname.len, res->lockname.name,
99		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
100		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
101
102	/* putting lock on list, add a ref */
103	dlm_lock_get(lock);
104	spin_lock(&lock->spinlock);
105
106	/* check to see if this ast obsoletes the bast */
107	if (dlm_should_cancel_bast(dlm, lock)) {
108		mlog(0, "%s: res %.*s, lock %u:%llu, Cancelling BAST\n",
109		     dlm->name, res->lockname.len, res->lockname.name,
110		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
111		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
112		lock->bast_pending = 0;
113		list_del_init(&lock->bast_list);
114		lock->ml.highest_blocked = LKM_IVMODE;
115		/* removing lock from list, remove a ref.  guaranteed
116		 * this won't be the last ref because of the get above,
117		 * so res->spinlock will not be taken here */
118		dlm_lock_put(lock);
119		/* free up the reserved bast that we are cancelling.
120		 * guaranteed that this will not be the last reserved
121		 * ast because *both* an ast and a bast were reserved
122		 * to get to this point.  the res->spinlock will not be
123		 * taken here */
124		dlm_lockres_release_ast(dlm, res);
125	}
126	list_add_tail(&lock->ast_list, &dlm->pending_asts);
127	lock->ast_pending = 1;
128	spin_unlock(&lock->spinlock);
129}
130
131void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
132{
133	BUG_ON(!dlm);
134	BUG_ON(!lock);
135
136	spin_lock(&dlm->ast_lock);
137	__dlm_queue_ast(dlm, lock);
138	spin_unlock(&dlm->ast_lock);
139}
140
141
142void __dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
143{
144	struct dlm_lock_resource *res;
145
146	BUG_ON(!dlm);
147	BUG_ON(!lock);
148
149	assert_spin_locked(&dlm->ast_lock);
150
151	res = lock->lockres;
152
153	BUG_ON(!list_empty(&lock->bast_list));
154	if (lock->bast_pending)
155		mlog(0, "%s: res %.*s, lock %u:%llu, BAST getting flushed\n",
156		     dlm->name, res->lockname.len, res->lockname.name,
157		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
158		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
159
160	/* putting lock on list, add a ref */
161	dlm_lock_get(lock);
162	spin_lock(&lock->spinlock);
163	list_add_tail(&lock->bast_list, &dlm->pending_basts);
164	lock->bast_pending = 1;
165	spin_unlock(&lock->spinlock);
166}
167
168void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
169{
170	BUG_ON(!dlm);
171	BUG_ON(!lock);
172
173	spin_lock(&dlm->ast_lock);
174	__dlm_queue_bast(dlm, lock);
175	spin_unlock(&dlm->ast_lock);
176}
177
178static void dlm_update_lvb(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
179			   struct dlm_lock *lock)
180{
181	struct dlm_lockstatus *lksb = lock->lksb;
182	BUG_ON(!lksb);
183
184	/* only updates if this node masters the lockres */
185	spin_lock(&res->spinlock);
186	if (res->owner == dlm->node_num) {
187		/* check the lksb flags for the direction */
188		if (lksb->flags & DLM_LKSB_GET_LVB) {
189			mlog(0, "getting lvb from lockres for %s node\n",
190				  lock->ml.node == dlm->node_num ? "master" :
191				  "remote");
192			memcpy(lksb->lvb, res->lvb, DLM_LVB_LEN);
193		}
194		/* Do nothing for lvb put requests - they should be done in
195 		 * place when the lock is downconverted - otherwise we risk
196 		 * racing gets and puts which could result in old lvb data
197 		 * being propagated. We leave the put flag set and clear it
198 		 * here. In the future we might want to clear it at the time
199 		 * the put is actually done.
200		 */
201	}
202	spin_unlock(&res->spinlock);
203
204	/* reset any lvb flags on the lksb */
205	lksb->flags &= ~(DLM_LKSB_PUT_LVB|DLM_LKSB_GET_LVB);
206}
207
208void dlm_do_local_ast(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
209		      struct dlm_lock *lock)
210{
211	dlm_astlockfunc_t *fn;
212
213	mlog(0, "%s: res %.*s, lock %u:%llu, Local AST\n", dlm->name,
214	     res->lockname.len, res->lockname.name,
215	     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
216	     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
217
218	fn = lock->ast;
219	BUG_ON(lock->ml.node != dlm->node_num);
220
221	dlm_update_lvb(dlm, res, lock);
222	(*fn)(lock->astdata);
223}
224
225
226int dlm_do_remote_ast(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
227		      struct dlm_lock *lock)
228{
229	int ret;
230	struct dlm_lockstatus *lksb;
231	int lksbflags;
232
233	mlog(0, "%s: res %.*s, lock %u:%llu, Remote AST\n", dlm->name,
234	     res->lockname.len, res->lockname.name,
235	     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
236	     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
237
238	lksb = lock->lksb;
239	BUG_ON(lock->ml.node == dlm->node_num);
240
241	lksbflags = lksb->flags;
242	dlm_update_lvb(dlm, res, lock);
243
244	/* lock request came from another node
245	 * go do the ast over there */
246	ret = dlm_send_proxy_ast(dlm, res, lock, lksbflags);
247	return ret;
248}
249
250void dlm_do_local_bast(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
251		       struct dlm_lock *lock, int blocked_type)
252{
253	dlm_bastlockfunc_t *fn = lock->bast;
254
255	BUG_ON(lock->ml.node != dlm->node_num);
256
257	mlog(0, "%s: res %.*s, lock %u:%llu, Local BAST, blocked %d\n",
258	     dlm->name, res->lockname.len, res->lockname.name,
259	     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
260	     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
261	     blocked_type);
262
263	(*fn)(lock->astdata, blocked_type);
264}
265
266
267
268int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
269			  void **ret_data)
270{
271	int ret;
272	unsigned int locklen;
273	struct dlm_ctxt *dlm = data;
274	struct dlm_lock_resource *res = NULL;
275	struct dlm_lock *lock = NULL;
276	struct dlm_proxy_ast *past = (struct dlm_proxy_ast *) msg->buf;
277	char *name;
278	struct list_head *head = NULL;
279	__be64 cookie;
280	u32 flags;
281	u8 node;
282
283	if (!dlm_grab(dlm)) {
284		dlm_error(DLM_REJECTED);
285		return DLM_REJECTED;
286	}
287
288	mlog_bug_on_msg(!dlm_domain_fully_joined(dlm),
289			"Domain %s not fully joined!\n", dlm->name);
290
291	name = past->name;
292	locklen = past->namelen;
293	cookie = past->cookie;
294	flags = be32_to_cpu(past->flags);
295	node = past->node_idx;
296
297	if (locklen > DLM_LOCKID_NAME_MAX) {
298		ret = DLM_IVBUFLEN;
299		mlog(ML_ERROR, "Invalid name length (%d) in proxy ast "
300		     "handler!\n", locklen);
301		goto leave;
302	}
303
304	if ((flags & (LKM_PUT_LVB|LKM_GET_LVB)) ==
305	     (LKM_PUT_LVB|LKM_GET_LVB)) {
306		mlog(ML_ERROR, "Both PUT and GET lvb specified, (0x%x)\n",
307		     flags);
308		ret = DLM_BADARGS;
309		goto leave;
310	}
311
312	mlog(0, "lvb: %s\n", flags & LKM_PUT_LVB ? "put lvb" :
313		  (flags & LKM_GET_LVB ? "get lvb" : "none"));
314
315	mlog(0, "type=%d, blocked_type=%d\n", past->type, past->blocked_type);
316
317	if (past->type != DLM_AST &&
318	    past->type != DLM_BAST) {
319		mlog(ML_ERROR, "Unknown ast type! %d, cookie=%u:%llu"
320		     "name=%.*s, node=%u\n", past->type,
321		     dlm_get_lock_cookie_node(be64_to_cpu(cookie)),
322		     dlm_get_lock_cookie_seq(be64_to_cpu(cookie)),
323		     locklen, name, node);
324		ret = DLM_IVLOCKID;
325		goto leave;
326	}
327
328	res = dlm_lookup_lockres(dlm, name, locklen);
329	if (!res) {
330		mlog(0, "Got %sast for unknown lockres! cookie=%u:%llu, "
331		     "name=%.*s, node=%u\n", (past->type == DLM_AST ? "" : "b"),
332		     dlm_get_lock_cookie_node(be64_to_cpu(cookie)),
333		     dlm_get_lock_cookie_seq(be64_to_cpu(cookie)),
334		     locklen, name, node);
335		ret = DLM_IVLOCKID;
336		goto leave;
337	}
338
339	/* cannot get a proxy ast message if this node owns it */
340	BUG_ON(res->owner == dlm->node_num);
341
342	mlog(0, "%s: res %.*s\n", dlm->name, res->lockname.len,
343	     res->lockname.name);
344
345	spin_lock(&res->spinlock);
346	if (res->state & DLM_LOCK_RES_RECOVERING) {
347		mlog(0, "Responding with DLM_RECOVERING!\n");
348		ret = DLM_RECOVERING;
349		goto unlock_out;
350	}
351	if (res->state & DLM_LOCK_RES_MIGRATING) {
352		mlog(0, "Responding with DLM_MIGRATING!\n");
353		ret = DLM_MIGRATING;
354		goto unlock_out;
355	}
356	/* try convert queue for both ast/bast */
357	head = &res->converting;
358	lock = NULL;
359	list_for_each_entry(lock, head, list) {
360		if (lock->ml.cookie == cookie)
361			goto do_ast;
362	}
363
364	/* if not on convert, try blocked for ast, granted for bast */
365	if (past->type == DLM_AST)
366		head = &res->blocked;
367	else
368		head = &res->granted;
369
370	list_for_each_entry(lock, head, list) {
371		/* if lock is found but unlock is pending ignore the bast */
372		if (lock->ml.cookie == cookie) {
373			if (lock->unlock_pending)
374				break;
375			goto do_ast;
376		}
377	}
378
379	mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, "
380	     "node=%u\n", past->type == DLM_AST ? "" : "b",
381	     dlm_get_lock_cookie_node(be64_to_cpu(cookie)),
382	     dlm_get_lock_cookie_seq(be64_to_cpu(cookie)),
383	     locklen, name, node);
384
385	ret = DLM_NORMAL;
386unlock_out:
387	spin_unlock(&res->spinlock);
388	goto leave;
389
390do_ast:
391	ret = DLM_NORMAL;
392	if (past->type == DLM_AST) {
393		/* do not alter lock refcount.  switching lists. */
394		list_move_tail(&lock->list, &res->granted);
395		mlog(0, "%s: res %.*s, lock %u:%llu, Granted type %d => %d\n",
396		     dlm->name, res->lockname.len, res->lockname.name,
397		     dlm_get_lock_cookie_node(be64_to_cpu(cookie)),
398		     dlm_get_lock_cookie_seq(be64_to_cpu(cookie)),
399		     lock->ml.type, lock->ml.convert_type);
400
401		if (lock->ml.convert_type != LKM_IVMODE) {
402			lock->ml.type = lock->ml.convert_type;
403			lock->ml.convert_type = LKM_IVMODE;
404		} else {
405			// should already be there....
406		}
407
408		lock->lksb->status = DLM_NORMAL;
409
410		/* if we requested the lvb, fetch it into our lksb now */
411		if (flags & LKM_GET_LVB) {
412			BUG_ON(!(lock->lksb->flags & DLM_LKSB_GET_LVB));
413			memcpy(lock->lksb->lvb, past->lvb, DLM_LVB_LEN);
414		}
415	}
416	spin_unlock(&res->spinlock);
417
418	if (past->type == DLM_AST)
419		dlm_do_local_ast(dlm, res, lock);
420	else
421		dlm_do_local_bast(dlm, res, lock, past->blocked_type);
422
423leave:
424	if (res)
425		dlm_lockres_put(res);
426
427	dlm_put(dlm);
428	return ret;
429}
430
431
432
433int dlm_send_proxy_ast_msg(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
434			   struct dlm_lock *lock, int msg_type,
435			   int blocked_type, int flags)
436{
437	int ret = 0;
438	struct dlm_proxy_ast past;
439	struct kvec vec[2];
440	size_t veclen = 1;
441	int status;
442
443	mlog(0, "%s: res %.*s, to %u, type %d, blocked_type %d\n", dlm->name,
444	     res->lockname.len, res->lockname.name, lock->ml.node, msg_type,
445	     blocked_type);
446
447	memset(&past, 0, sizeof(struct dlm_proxy_ast));
448	past.node_idx = dlm->node_num;
449	past.type = msg_type;
450	past.blocked_type = blocked_type;
451	past.namelen = res->lockname.len;
452	memcpy(past.name, res->lockname.name, past.namelen);
453	past.cookie = lock->ml.cookie;
454
455	vec[0].iov_len = sizeof(struct dlm_proxy_ast);
456	vec[0].iov_base = &past;
457	if (flags & DLM_LKSB_GET_LVB) {
458		be32_add_cpu(&past.flags, LKM_GET_LVB);
459		vec[1].iov_len = DLM_LVB_LEN;
460		vec[1].iov_base = lock->lksb->lvb;
461		veclen++;
462	}
463
464	ret = o2net_send_message_vec(DLM_PROXY_AST_MSG, dlm->key, vec, veclen,
465				     lock->ml.node, &status);
466	if (ret < 0)
467		mlog(ML_ERROR, "%s: res %.*s, error %d send AST to node %u\n",
468		     dlm->name, res->lockname.len, res->lockname.name, ret,
469		     lock->ml.node);
470	else {
471		if (status == DLM_RECOVERING) {
472			mlog(ML_ERROR, "sent AST to node %u, it thinks this "
473			     "node is dead!\n", lock->ml.node);
474			BUG();
475		} else if (status == DLM_MIGRATING) {
476			mlog(ML_ERROR, "sent AST to node %u, it returned "
477			     "DLM_MIGRATING!\n", lock->ml.node);
478			BUG();
479		} else if (status != DLM_NORMAL && status != DLM_IVLOCKID) {
480			mlog(ML_ERROR, "AST to node %u returned %d!\n",
481			     lock->ml.node, status);
482			/* ignore it */
483		}
484		ret = 0;
485	}
486	return ret;
487}
488