summaryrefslogtreecommitdiff
path: root/drivers/mmc/core/queue.c
blob: fa5324ceeebe479b0546a0eace0d91fb107b37c9 (plain)
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
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  Copyright (C) 2003 Russell King, All Rights Reserved.
 *  Copyright 2006-2007 Pierre Ossman
 */
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/freezer.h>
#include <linux/scatterlist.h>
#include <linux/dma-mapping.h>
#include <linux/backing-dev.h>

#include <linux/mmc/card.h>
#include <linux/mmc/host.h>

#include "queue.h"
#include "block.h"
#include "core.h"
#include "card.h"
#include "crypto.h"
#include "host.h"

#define MMC_DMA_MAP_MERGE_SEGMENTS	512

static inline bool mmc_cqe_dcmd_busy(struct mmc_queue *mq)
{
	/* Allow only 1 DCMD at a time */
	return mq->in_flight[MMC_ISSUE_DCMD];
}

void mmc_cqe_check_busy(struct mmc_queue *mq)
{
	if ((mq->cqe_busy & MMC_CQE_DCMD_BUSY) && !mmc_cqe_dcmd_busy(mq))
		mq->cqe_busy &= ~MMC_CQE_DCMD_BUSY;
}

static inline bool mmc_cqe_can_dcmd(struct mmc_host *host)
{
	return host->caps2 & MMC_CAP2_CQE_DCMD;
}

static enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
					      struct request *req)
{
	switch (req_op(req)) {
	case REQ_OP_DRV_IN:
	case REQ_OP_DRV_OUT:
	case REQ_OP_DISCARD:
	case REQ_OP_SECURE_ERASE:
		return MMC_ISSUE_SYNC;
	case REQ_OP_FLUSH:
		return mmc_cqe_can_dcmd(host) ? MMC_ISSUE_DCMD : MMC_ISSUE_SYNC;
	default:
		return MMC_ISSUE_ASYNC;
	}
}

enum mmc_issue_type mmc_issue_type(struct mmc_queue *mq, struct request *req)
{
	struct mmc_host *host = mq->card->host;

	if (host->cqe_enabled && !host->hsq_enabled)
		return mmc_cqe_issue_type(host, req);

	if (req_op(req) == REQ_OP_READ || req_op(req) == REQ_OP_WRITE)
		return MMC_ISSUE_ASYNC;

	return MMC_ISSUE_SYNC;
}

static void __mmc_cqe_recovery_notifier(struct mmc_queue *mq)
{
	if (!mq->recovery_needed) {
		mq->recovery_needed = true;
		schedule_work(&mq->recovery_work);
	}
}

void mmc_cqe_recovery_notifier(struct mmc_request *mrq)
{
	struct mmc_queue_req *mqrq = container_of(mrq, struct mmc_queue_req,
						  brq.mrq);
	struct request *req = mmc_queue_req_to_req(mqrq);
	struct request_queue *q = req->q;
	struct mmc_queue *mq = q->queuedata;
	unsigned long flags;

	spin_lock_irqsave(&mq->lock, flags);
	__mmc_cqe_recovery_notifier(mq);
	spin_unlock_irqrestore(&mq->lock, flags);
}

static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req)
{
	struct mmc_queue_req *mqrq = req_to_mmc_queue_req(req);
	struct mmc_request *mrq = &mqrq->brq.mrq;
	struct mmc_queue *mq = req->q->queuedata;
	struct mmc_host *host = mq->card->host;
	enum mmc_issue_type issue_type = mmc_issue_type(mq, req);
	bool recovery_needed = false;

	switch (issue_type) {
	case MMC_ISSUE_ASYNC:
	case MMC_ISSUE_DCMD:
		if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) {
			if (recovery_needed)
				mmc_cqe_recovery_notifier(mrq);
			return BLK_EH_RESET_TIMER;
		}
		/* The request has gone already */
		return BLK_EH_DONE;
	default:
		/* Timeout is handled by mmc core */
		return BLK_EH_RESET_TIMER;
	}
}

static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req,
						 bool reserved)
{
	struct request_queue *q = req->q;
	struct mmc_queue *mq = q->queuedata;
	struct mmc_card *card = mq->card;
	struct mmc_host *host = card->host;
	unsigned long flags;
	bool ignore_tout;

	spin_lock_irqsave(&mq->lock, flags);
	ignore_tout = mq->recovery_needed || !host->cqe_enabled || host->hsq_enabled;
	spin_unlock_irqrestore(&mq->lock, flags);

	return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req);
}

static void mmc_mq_recovery_handler(struct work_struct *work)
{
	struct mmc_queue *mq = container_of(work, struct mmc_queue,
					    recovery_work);
	struct request_queue *q = mq->queue;
	struct mmc_host *host = mq->card->host;

	mmc_get_card(mq->card, &mq->ctx);

	mq->in_recovery = true;

	if (host->cqe_enabled && !host->hsq_enabled)
		mmc_blk_cqe_recovery(mq);
	else
		mmc_blk_mq_recovery(mq);

	mq->in_recovery = false;

	spin_lock_irq(&mq->lock);
	mq->recovery_needed = false;
	spin_unlock_irq(&mq->lock);

	if (host->hsq_enabled)
		host->cqe_ops->cqe_recovery_finish(host);

	mmc_put_card(mq->card, &mq->ctx);

	blk_mq_run_hw_queues(q, true);
}

static struct scatterlist *mmc_alloc_sg(unsigned short sg_len, gfp_t gfp)
{
	struct scatterlist *sg;

	sg = kmalloc_array(sg_len, sizeof(*sg), gfp);
	if (sg)
		sg_init_table(sg, sg_len);

	return sg;
}

static void mmc_queue_setup_discard(struct request_queue *q,
				    struct mmc_card *card)
{
	unsigned max_discard;

	max_discard = mmc_calc_max_discard(card);
	if (!max_discard)
		return;

	blk_queue_max_discard_sectors(q, max_discard);
	q->limits.discard_granularity = card->pref_erase << 9;
	/* granularity must not be greater than max. discard */
	if (card->pref_erase > max_discard)
		q->limits.discard_granularity = SECTOR_SIZE;
	if (mmc_can_secure_erase_trim(card))
		blk_queue_max_secure_erase_sectors(q, max_discard);
	if (mmc_can_trim(card) && card->erased_byte == 0)
		blk_queue_max_write_zeroes_sectors(q, max_discard);
}

static unsigned short mmc_get_max_segments(struct mmc_host *host)
{
	return host->can_dma_map_merge ? MMC_DMA_MAP_MERGE_SEGMENTS :
					 host->max_segs;
}

static int mmc_mq_init_request(struct blk_mq_tag_set *set, struct request *req,
			       unsigned int hctx_idx, unsigned int numa_node)
{
	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
	struct mmc_queue *mq = set->driver_data;
	struct mmc_card *card = mq->card;
	struct mmc_host *host = card->host;

	mq_rq->sg = mmc_alloc_sg(mmc_get_max_segments(host), GFP_KERNEL);
	if (!mq_rq->sg)
		return -ENOMEM;

	return 0;
}

static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req,
				unsigned int hctx_idx)
{
	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);

	kfree(mq_rq->sg);
	mq_rq->sg = NULL;
}

static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
				    const struct blk_mq_queue_data *bd)
{
	struct request *req = bd->rq;
	struct request_queue *q = req->q;
	struct mmc_queue *mq = q->queuedata;
	struct mmc_card *card = mq->card;
	struct mmc_host *host = card->host;
	enum mmc_issue_type issue_type;
	enum mmc_issued issued;
	bool get_card, cqe_retune_ok;
	blk_status_t ret;

	if (mmc_card_removed(mq->card)) {
		req->rq_flags |= RQF_QUIET;
		return BLK_STS_IOERR;
	}

	issue_type = mmc_issue_type(mq, req);

	spin_lock_irq(&mq->lock);

	if (mq->recovery_needed || mq->busy) {
		spin_unlock_irq(&mq->lock);
		return BLK_STS_RESOURCE;
	}

	switch (issue_type) {
	case MMC_ISSUE_DCMD:
		if (mmc_cqe_dcmd_busy(mq)) {
			mq->cqe_busy |= MMC_CQE_DCMD_BUSY;
			spin_unlock_irq(&mq->lock);
			return BLK_STS_RESOURCE;
		}
		break;
	case MMC_ISSUE_ASYNC:
		/*
		 * For MMC host software queue, we only allow 2 requests in
		 * flight to avoid a long latency.
		 */
		if (host->hsq_enabled && mq->in_flight[issue_type] > 2) {
			spin_unlock_irq(&mq->lock);
			return BLK_STS_RESOURCE;
		}
		break;
	default:
		/*
		 * Timeouts are handled by mmc core, and we don't have a host
		 * API to abort requests, so we can't handle the timeout anyway.
		 * However, when the timeout happens, blk_mq_complete_request()
		 * no longer works (to stop the request disappearing under us).
		 * To avoid racing with that, set a large timeout.
		 */
		req->timeout = 600 * HZ;
		break;
	}

	/* Parallel dispatch of requests is not supported at the moment */
	mq->busy = true;

	mq->in_flight[issue_type] += 1;
	get_card = (mmc_tot_in_flight(mq) == 1);
	cqe_retune_ok = (mmc_cqe_qcnt(mq) == 1);

	spin_unlock_irq(&mq->lock);

	if (!(req->rq_flags & RQF_DONTPREP)) {
		req_to_mmc_queue_req(req)->retries = 0;
		req->rq_flags |= RQF_DONTPREP;
	}

	if (get_card)
		mmc_get_card(card, &mq->ctx);

	if (host->cqe_enabled) {
		host->retune_now = host->need_retune && cqe_retune_ok &&
				   !host->hold_retune;
	}

	blk_mq_start_request(req);

	issued = mmc_blk_mq_issue_rq(mq, req);

	switch (issued) {
	case MMC_REQ_BUSY:
		ret = BLK_STS_RESOURCE;
		break;
	case MMC_REQ_FAILED_TO_START:
		ret = BLK_STS_IOERR;
		break;
	default:
		ret = BLK_STS_OK;
		break;
	}

	if (issued != MMC_REQ_STARTED) {
		bool put_card = false;

		spin_lock_irq(&mq->lock);
		mq->in_flight[issue_type] -= 1;
		if (mmc_tot_in_flight(mq) == 0)
			put_card = true;
		mq->busy = false;
		spin_unlock_irq(&mq->lock);
		if (put_card)
			mmc_put_card(card, &mq->ctx);
	} else {
		WRITE_ONCE(mq->busy, false);
	}

	return ret;
}

static const struct blk_mq_ops mmc_mq_ops = {
	.queue_rq	= mmc_mq_queue_rq,
	.init_request	= mmc_mq_init_request,
	.exit_request	= mmc_mq_exit_request,
	.complete	= mmc_blk_mq_complete,
	.timeout	= mmc_mq_timed_out,
};

static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card)
{
	struct mmc_host *host = card->host;
	unsigned block_size = 512;

	blk_queue_flag_set(QUEUE_FLAG_NONROT, mq->queue);
	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, mq->queue);
	if (mmc_can_erase(card))
		mmc_queue_setup_discard(mq->queue, card);

	if (!mmc_dev(host)->dma_mask || !*mmc_dev(host)->dma_mask)
		blk_queue_bounce_limit(mq->queue, BLK_BOUNCE_HIGH);
	blk_queue_max_hw_sectors(mq->queue,
		min(host->max_blk_count, host->max_req_size / 512));
	if (host->can_dma_map_merge)
		WARN(!blk_queue_can_use_dma_map_merging(mq->queue,
							mmc_dev(host)),
		     "merging was advertised but not possible");
	blk_queue_max_segments(mq->queue, mmc_get_max_segments(host));

	if (mmc_card_mmc(card) && card->ext_csd.data_sector_size) {
		block_size = card->ext_csd.data_sector_size;
		WARN_ON(block_size != 512 && block_size != 4096);
	}

	blk_queue_logical_block_size(mq->queue, block_size);
	/*
	 * After blk_queue_can_use_dma_map_merging() was called with succeed,
	 * since it calls blk_queue_virt_boundary(), the mmc should not call
	 * both blk_queue_max_segment_size().
	 */
	if (!host->can_dma_map_merge)
		blk_queue_max_segment_size(mq->queue,
			round_down(host->max_seg_size, block_size));

	dma_set_max_seg_size(mmc_dev(host), queue_max_segment_size(mq->queue));

	INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler);
	INIT_WORK(&mq->complete_work, mmc_blk_mq_complete_work);

	mutex_init(&mq->complete_lock);

	init_waitqueue_head(&mq->wait);

	mmc_crypto_setup_queue(mq->queue, host);
}

static inline bool mmc_merge_capable(struct mmc_host *host)
{
	return host->caps2 & MMC_CAP2_MERGE_CAPABLE;
}

/* Set queue depth to get a reasonable value for q->nr_requests */
#define MMC_QUEUE_DEPTH 64

/**
 * mmc_init_queue - initialise a queue structure.
 * @mq: mmc queue
 * @card: mmc card to attach this queue
 *
 * Initialise a MMC card request queue.
 */
struct gendisk *mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card)
{
	struct mmc_host *host = card->host;
	struct gendisk *disk;
	int ret;

	mq->card = card;
	
	spin_lock_init(&mq->lock);

	memset(&mq->tag_set, 0, sizeof(mq->tag_set));
	mq->tag_set.ops = &mmc_mq_ops;
	/*
	 * The queue depth for CQE must match the hardware because the request
	 * tag is used to index the hardware queue.
	 */
	if (host->cqe_enabled && !host->hsq_enabled)
		mq->tag_set.queue_depth =
			min_t(int, card->ext_csd.cmdq_depth, host->cqe_qdepth);
	else
		mq->tag_set.queue_depth = MMC_QUEUE_DEPTH;
	mq->tag_set.numa_node = NUMA_NO_NODE;
	mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
	mq->tag_set.nr_hw_queues = 1;
	mq->tag_set.cmd_size = sizeof(struct mmc_queue_req);
	mq->tag_set.driver_data = mq;

	/*
	 * Since blk_mq_alloc_tag_set() calls .init_request() of mmc_mq_ops,
	 * the host->can_dma_map_merge should be set before to get max_segs
	 * from mmc_get_max_segments().
	 */
	if (mmc_merge_capable(host) &&
	    host->max_segs < MMC_DMA_MAP_MERGE_SEGMENTS &&
	    dma_get_merge_boundary(mmc_dev(host)))
		host->can_dma_map_merge = 1;
	else
		host->can_dma_map_merge = 0;

	ret = blk_mq_alloc_tag_set(&mq->tag_set);
	if (ret)
		return ERR_PTR(ret);
		

	disk = blk_mq_alloc_disk(&mq->tag_set, mq);
	if (IS_ERR(disk)) {
		blk_mq_free_tag_set(&mq->tag_set);
		return disk;
	}
	mq->queue = disk->queue;

	if (mmc_host_is_spi(host) && host->use_spi_crc)
		blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, mq->queue);
	blk_queue_rq_timeout(mq->queue, 60 * HZ);

	mmc_setup_queue(mq, card);
	return disk;
}

void mmc_queue_suspend(struct mmc_queue *mq)
{
	blk_mq_quiesce_queue(mq->queue);

	/*
	 * The host remains claimed while there are outstanding requests, so
	 * simply claiming and releasing here ensures there are none.
	 */
	mmc_claim_host(mq->card->host);
	mmc_release_host(mq->card->host);
}

void mmc_queue_resume(struct mmc_queue *mq)
{
	blk_mq_unquiesce_queue(mq->queue);
}

void mmc_cleanup_queue(struct mmc_queue *mq)
{
	struct request_queue *q = mq->queue;

	/*
	 * The legacy code handled the possibility of being suspended,
	 * so do that here too.
	 */
	if (blk_queue_quiesced(q))
		blk_mq_unquiesce_queue(q);

	blk_cleanup_queue(q);
	blk_mq_free_tag_set(&mq->tag_set);

	/*
	 * A request can be completed before the next request, potentially
	 * leaving a complete_work with nothing to do. Such a work item might
	 * still be queued at this point. Flush it.
	 */
	flush_work(&mq->complete_work);

	mq->card = NULL;
}

/*
 * Prepare the sg list(s) to be handed of to the host driver
 */
unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
{
	struct request *req = mmc_queue_req_to_req(mqrq);

	return blk_rq_map_sg(mq->queue, req, mqrq->sg);
}