1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * multipath.c : Multiple Devices driver for Linux
4 *
5 * Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
6 *
7 * Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
8 *
9 * MULTIPATH management functions.
10 *
11 * derived from raid1.c.
12 */
13
14#include <linux/blkdev.h>
15#include <linux/module.h>
16#include <linux/raid/md_u.h>
17#include <linux/seq_file.h>
18#include <linux/slab.h>
19#include "md.h"
20#include "md-multipath.h"
21
22#define MAX_WORK_PER_DISK 128
23
24#define	NR_RESERVED_BUFS	32
25
26static int multipath_map (struct mpconf *conf)
27{
28	int i, disks = conf->raid_disks;
29
30	/*
31	 * Later we do read balancing on the read side
32	 * now we use the first available disk.
33	 */
34
35	rcu_read_lock();
36	for (i = 0; i < disks; i++) {
37		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
38		if (rdev && test_bit(In_sync, &rdev->flags) &&
39		    !test_bit(Faulty, &rdev->flags)) {
40			atomic_inc(&rdev->nr_pending);
41			rcu_read_unlock();
42			return i;
43		}
44	}
45	rcu_read_unlock();
46
47	pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n");
48	return (-1);
49}
50
51static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
52{
53	unsigned long flags;
54	struct mddev *mddev = mp_bh->mddev;
55	struct mpconf *conf = mddev->private;
56
57	spin_lock_irqsave(&conf->device_lock, flags);
58	list_add(&mp_bh->retry_list, &conf->retry_list);
59	spin_unlock_irqrestore(&conf->device_lock, flags);
60	md_wakeup_thread(mddev->thread);
61}
62
63/*
64 * multipath_end_bh_io() is called when we have finished servicing a multipathed
65 * operation and are ready to return a success/failure code to the buffer
66 * cache layer.
67 */
68static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
69{
70	struct bio *bio = mp_bh->master_bio;
71	struct mpconf *conf = mp_bh->mddev->private;
72
73	bio->bi_status = status;
74	bio_endio(bio);
75	mempool_free(mp_bh, &conf->pool);
76}
77
78static void multipath_end_request(struct bio *bio)
79{
80	struct multipath_bh *mp_bh = bio->bi_private;
81	struct mpconf *conf = mp_bh->mddev->private;
82	struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
83
84	if (!bio->bi_status)
85		multipath_end_bh_io(mp_bh, 0);
86	else if (!(bio->bi_opf & REQ_RAHEAD)) {
87		/*
88		 * oops, IO error:
89		 */
90		md_error (mp_bh->mddev, rdev);
91		pr_info("multipath: %pg: rescheduling sector %llu\n",
92			rdev->bdev,
93			(unsigned long long)bio->bi_iter.bi_sector);
94		multipath_reschedule_retry(mp_bh);
95	} else
96		multipath_end_bh_io(mp_bh, bio->bi_status);
97	rdev_dec_pending(rdev, conf->mddev);
98}
99
100static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
101{
102	struct mpconf *conf = mddev->private;
103	struct multipath_bh * mp_bh;
104	struct multipath_info *multipath;
105
106	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
107	    && md_flush_request(mddev, bio))
108		return true;
109
110	md_account_bio(mddev, &bio);
111	mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
112
113	mp_bh->master_bio = bio;
114	mp_bh->mddev = mddev;
115
116	mp_bh->path = multipath_map(conf);
117	if (mp_bh->path < 0) {
118		bio_io_error(bio);
119		mempool_free(mp_bh, &conf->pool);
120		return true;
121	}
122	multipath = conf->multipaths + mp_bh->path;
123
124	bio_init_clone(multipath->rdev->bdev, &mp_bh->bio, bio, GFP_NOIO);
125
126	mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
127	mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT;
128	mp_bh->bio.bi_end_io = multipath_end_request;
129	mp_bh->bio.bi_private = mp_bh;
130	mddev_check_write_zeroes(mddev, &mp_bh->bio);
131	submit_bio_noacct(&mp_bh->bio);
132	return true;
133}
134
135static void multipath_status(struct seq_file *seq, struct mddev *mddev)
136{
137	struct mpconf *conf = mddev->private;
138	int i;
139
140	seq_printf (seq, " [%d/%d] [", conf->raid_disks,
141		    conf->raid_disks - mddev->degraded);
142	rcu_read_lock();
143	for (i = 0; i < conf->raid_disks; i++) {
144		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
145		seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
146	}
147	rcu_read_unlock();
148	seq_putc(seq, ']');
149}
150
151/*
152 * Careful, this can execute in IRQ contexts as well!
153 */
154static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
155{
156	struct mpconf *conf = mddev->private;
157
158	if (conf->raid_disks - mddev->degraded <= 1) {
159		/*
160		 * Uh oh, we can do nothing if this is our last path, but
161		 * first check if this is a queued request for a device
162		 * which has just failed.
163		 */
164		pr_warn("multipath: only one IO path left and IO error.\n");
165		/* leave it active... it's all we have */
166		return;
167	}
168	/*
169	 * Mark disk as unusable
170	 */
171	if (test_and_clear_bit(In_sync, &rdev->flags)) {
172		unsigned long flags;
173		spin_lock_irqsave(&conf->device_lock, flags);
174		mddev->degraded++;
175		spin_unlock_irqrestore(&conf->device_lock, flags);
176	}
177	set_bit(Faulty, &rdev->flags);
178	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
179	pr_err("multipath: IO failure on %pg, disabling IO path.\n"
180	       "multipath: Operation continuing on %d IO paths.\n",
181	       rdev->bdev,
182	       conf->raid_disks - mddev->degraded);
183}
184
185static void print_multipath_conf (struct mpconf *conf)
186{
187	int i;
188	struct multipath_info *tmp;
189
190	pr_debug("MULTIPATH conf printout:\n");
191	if (!conf) {
192		pr_debug("(conf==NULL)\n");
193		return;
194	}
195	pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
196		 conf->raid_disks);
197
198	for (i = 0; i < conf->raid_disks; i++) {
199		tmp = conf->multipaths + i;
200		if (tmp->rdev)
201			pr_debug(" disk%d, o:%d, dev:%pg\n",
202				 i,!test_bit(Faulty, &tmp->rdev->flags),
203				 tmp->rdev->bdev);
204	}
205}
206
207static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
208{
209	struct mpconf *conf = mddev->private;
210	int err = -EEXIST;
211	int path;
212	struct multipath_info *p;
213	int first = 0;
214	int last = mddev->raid_disks - 1;
215
216	if (rdev->raid_disk >= 0)
217		first = last = rdev->raid_disk;
218
219	print_multipath_conf(conf);
220
221	for (path = first; path <= last; path++)
222		if ((p=conf->multipaths+path)->rdev == NULL) {
223			disk_stack_limits(mddev->gendisk, rdev->bdev,
224					  rdev->data_offset << 9);
225
226			err = md_integrity_add_rdev(rdev, mddev);
227			if (err)
228				break;
229			spin_lock_irq(&conf->device_lock);
230			mddev->degraded--;
231			rdev->raid_disk = path;
232			set_bit(In_sync, &rdev->flags);
233			spin_unlock_irq(&conf->device_lock);
234			rcu_assign_pointer(p->rdev, rdev);
235			err = 0;
236			break;
237		}
238
239	print_multipath_conf(conf);
240
241	return err;
242}
243
244static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
245{
246	struct mpconf *conf = mddev->private;
247	int err = 0;
248	int number = rdev->raid_disk;
249	struct multipath_info *p = conf->multipaths + number;
250
251	print_multipath_conf(conf);
252
253	if (rdev == p->rdev) {
254		if (test_bit(In_sync, &rdev->flags) ||
255		    atomic_read(&rdev->nr_pending)) {
256			pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number);
257			err = -EBUSY;
258			goto abort;
259		}
260		p->rdev = NULL;
261		if (!test_bit(RemoveSynchronized, &rdev->flags)) {
262			synchronize_rcu();
263			if (atomic_read(&rdev->nr_pending)) {
264				/* lost the race, try later */
265				err = -EBUSY;
266				p->rdev = rdev;
267				goto abort;
268			}
269		}
270		err = md_integrity_register(mddev);
271	}
272abort:
273
274	print_multipath_conf(conf);
275	return err;
276}
277
278/*
279 * This is a kernel thread which:
280 *
281 *	1.	Retries failed read operations on working multipaths.
282 *	2.	Updates the raid superblock when problems encounter.
283 *	3.	Performs writes following reads for array syncronising.
284 */
285
286static void multipathd(struct md_thread *thread)
287{
288	struct mddev *mddev = thread->mddev;
289	struct multipath_bh *mp_bh;
290	struct bio *bio;
291	unsigned long flags;
292	struct mpconf *conf = mddev->private;
293	struct list_head *head = &conf->retry_list;
294
295	md_check_recovery(mddev);
296	for (;;) {
297		spin_lock_irqsave(&conf->device_lock, flags);
298		if (list_empty(head))
299			break;
300		mp_bh = list_entry(head->prev, struct multipath_bh, retry_list);
301		list_del(head->prev);
302		spin_unlock_irqrestore(&conf->device_lock, flags);
303
304		bio = &mp_bh->bio;
305		bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
306
307		if ((mp_bh->path = multipath_map (conf))<0) {
308			pr_err("multipath: %pg: unrecoverable IO read error for block %llu\n",
309			       bio->bi_bdev,
310			       (unsigned long long)bio->bi_iter.bi_sector);
311			multipath_end_bh_io(mp_bh, BLK_STS_IOERR);
312		} else {
313			pr_err("multipath: %pg: redirecting sector %llu to another IO path\n",
314			       bio->bi_bdev,
315			       (unsigned long long)bio->bi_iter.bi_sector);
316			*bio = *(mp_bh->master_bio);
317			bio->bi_iter.bi_sector +=
318				conf->multipaths[mp_bh->path].rdev->data_offset;
319			bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev);
320			bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
321			bio->bi_end_io = multipath_end_request;
322			bio->bi_private = mp_bh;
323			submit_bio_noacct(bio);
324		}
325	}
326	spin_unlock_irqrestore(&conf->device_lock, flags);
327}
328
329static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks)
330{
331	WARN_ONCE(sectors || raid_disks,
332		  "%s does not support generic reshape\n", __func__);
333
334	return mddev->dev_sectors;
335}
336
337static int multipath_run (struct mddev *mddev)
338{
339	struct mpconf *conf;
340	int disk_idx;
341	struct multipath_info *disk;
342	struct md_rdev *rdev;
343	int working_disks;
344	int ret;
345
346	if (md_check_no_bitmap(mddev))
347		return -EINVAL;
348
349	if (mddev->level != LEVEL_MULTIPATH) {
350		pr_warn("multipath: %s: raid level not set to multipath IO (%d)\n",
351			mdname(mddev), mddev->level);
352		goto out;
353	}
354	/*
355	 * copy the already verified devices into our private MULTIPATH
356	 * bookkeeping area. [whatever we allocate in multipath_run(),
357	 * should be freed in multipath_free()]
358	 */
359
360	conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
361	mddev->private = conf;
362	if (!conf)
363		goto out;
364
365	conf->multipaths = kcalloc(mddev->raid_disks,
366				   sizeof(struct multipath_info),
367				   GFP_KERNEL);
368	if (!conf->multipaths)
369		goto out_free_conf;
370
371	working_disks = 0;
372	rdev_for_each(rdev, mddev) {
373		disk_idx = rdev->raid_disk;
374		if (disk_idx < 0 ||
375		    disk_idx >= mddev->raid_disks)
376			continue;
377
378		disk = conf->multipaths + disk_idx;
379		disk->rdev = rdev;
380		disk_stack_limits(mddev->gendisk, rdev->bdev,
381				  rdev->data_offset << 9);
382
383		if (!test_bit(Faulty, &rdev->flags))
384			working_disks++;
385	}
386
387	conf->raid_disks = mddev->raid_disks;
388	conf->mddev = mddev;
389	spin_lock_init(&conf->device_lock);
390	INIT_LIST_HEAD(&conf->retry_list);
391
392	if (!working_disks) {
393		pr_warn("multipath: no operational IO paths for %s\n",
394			mdname(mddev));
395		goto out_free_conf;
396	}
397	mddev->degraded = conf->raid_disks - working_disks;
398
399	ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS,
400					sizeof(struct multipath_bh));
401	if (ret)
402		goto out_free_conf;
403
404	rcu_assign_pointer(mddev->thread,
405			   md_register_thread(multipathd, mddev, "multipath"));
406	if (!mddev->thread)
407		goto out_free_conf;
408
409	pr_info("multipath: array %s active with %d out of %d IO paths\n",
410		mdname(mddev), conf->raid_disks - mddev->degraded,
411		mddev->raid_disks);
412	/*
413	 * Ok, everything is just fine now
414	 */
415	md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
416
417	if (md_integrity_register(mddev))
418		goto out_free_conf;
419
420	return 0;
421
422out_free_conf:
423	mempool_exit(&conf->pool);
424	kfree(conf->multipaths);
425	kfree(conf);
426	mddev->private = NULL;
427out:
428	return -EIO;
429}
430
431static void multipath_free(struct mddev *mddev, void *priv)
432{
433	struct mpconf *conf = priv;
434
435	mempool_exit(&conf->pool);
436	kfree(conf->multipaths);
437	kfree(conf);
438}
439
440static struct md_personality multipath_personality =
441{
442	.name		= "multipath",
443	.level		= LEVEL_MULTIPATH,
444	.owner		= THIS_MODULE,
445	.make_request	= multipath_make_request,
446	.run		= multipath_run,
447	.free		= multipath_free,
448	.status		= multipath_status,
449	.error_handler	= multipath_error,
450	.hot_add_disk	= multipath_add_disk,
451	.hot_remove_disk= multipath_remove_disk,
452	.size		= multipath_size,
453};
454
455static int __init multipath_init (void)
456{
457	return register_md_personality (&multipath_personality);
458}
459
460static void __exit multipath_exit (void)
461{
462	unregister_md_personality (&multipath_personality);
463}
464
465module_init(multipath_init);
466module_exit(multipath_exit);
467MODULE_LICENSE("GPL");
468MODULE_DESCRIPTION("simple multi-path personality for MD (deprecated)");
469MODULE_ALIAS("md-personality-7"); /* MULTIPATH */
470MODULE_ALIAS("md-multipath");
471MODULE_ALIAS("md-level--4");
472