summaryrefslogtreecommitdiffstats
path: root/drivers/block/null_blk_zoned.c
blob: 9e4bcdad1a80f700562a447cca6c533b828369d0 (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
// SPDX-License-Identifier: GPL-2.0
#include <linux/vmalloc.h>
#include "null_blk.h"

#define CREATE_TRACE_POINTS
#include "null_blk_trace.h"

/* zone_size in MBs to sectors. */
#define ZONE_SIZE_SHIFT		11

static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
{
	return sect >> ilog2(dev->zone_size_sects);
}

int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
{
	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
	sector_t sector = 0;
	unsigned int i;

	if (!is_power_of_2(dev->zone_size)) {
		pr_err("zone_size must be power-of-two\n");
		return -EINVAL;
	}

	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
	dev->nr_zones = dev_size >>
				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone),
			GFP_KERNEL | __GFP_ZERO);
	if (!dev->zones)
		return -ENOMEM;

	if (dev->zone_nr_conv >= dev->nr_zones) {
		dev->zone_nr_conv = dev->nr_zones - 1;
		pr_info("changed the number of conventional zones to %u",
			dev->zone_nr_conv);
	}

	for (i = 0; i <  dev->zone_nr_conv; i++) {
		struct blk_zone *zone = &dev->zones[i];

		zone->start = sector;
		zone->len = dev->zone_size_sects;
		zone->wp = zone->start + zone->len;
		zone->type = BLK_ZONE_TYPE_CONVENTIONAL;
		zone->cond = BLK_ZONE_COND_NOT_WP;

		sector += dev->zone_size_sects;
	}

	for (i = dev->zone_nr_conv; i < dev->nr_zones; i++) {
		struct blk_zone *zone = &dev->zones[i];

		zone->start = zone->wp = sector;
		zone->len = dev->zone_size_sects;
		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
		zone->cond = BLK_ZONE_COND_EMPTY;

		sector += dev->zone_size_sects;
	}

	q->limits.zoned = BLK_ZONED_HM;
	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);

	return 0;
}

int null_register_zoned_dev(struct nullb *nullb)
{
	struct request_queue *q = nullb->q;

	if (queue_is_mq(q))
		return blk_revalidate_disk_zones(nullb->disk);

	blk_queue_chunk_sectors(q, nullb->dev->zone_size_sects);
	q->nr_zones = blkdev_nr_zones(nullb->disk);

	return 0;
}

void null_free_zoned_dev(struct nullb_device *dev)
{
	kvfree(dev->zones);
}

int null_report_zones(struct gendisk *disk, sector_t sector,
		unsigned int nr_zones, report_zones_cb cb, void *data)
{
	struct nullb *nullb = disk->private_data;
	struct nullb_device *dev = nullb->dev;
	unsigned int first_zone, i;
	struct blk_zone zone;
	int error;

	first_zone = null_zone_no(dev, sector);
	if (first_zone >= dev->nr_zones)
		return 0;

	nr_zones = min(nr_zones, dev->nr_zones - first_zone);
	trace_nullb_report_zones(nullb, nr_zones);

	for (i = 0; i < nr_zones; i++) {
		/*
		 * Stacked DM target drivers will remap the zone information by
		 * modifying the zone information passed to the report callback.
		 * So use a local copy to avoid corruption of the device zone
		 * array.
		 */
		memcpy(&zone, &dev->zones[first_zone + i],
		       sizeof(struct blk_zone));
		error = cb(&zone, i, data);
		if (error)
			return error;
	}

	return nr_zones;
}

size_t null_zone_valid_read_len(struct nullb *nullb,
				sector_t sector, unsigned int len)
{
	struct nullb_device *dev = nullb->dev;
	struct blk_zone *zone = &dev->zones[null_zone_no(dev, sector)];
	unsigned int nr_sectors = len >> SECTOR_SHIFT;

	/* Read must be below the write pointer position */
	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL ||
	    sector + nr_sectors <= zone->wp)
		return len;

	if (sector > zone->wp)
		return 0;

	return (zone->wp - sector) << SECTOR_SHIFT;
}

static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
		     unsigned int nr_sectors)
{
	struct nullb_device *dev = cmd->nq->dev;
	unsigned int zno = null_zone_no(dev, sector);
	struct blk_zone *zone = &dev->zones[zno];
	blk_status_t ret;

	trace_nullb_zone_op(cmd, zno, zone->cond);

	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
		return null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);

	switch (zone->cond) {
	case BLK_ZONE_COND_FULL:
		/* Cannot write to a full zone */
		return BLK_STS_IOERR;
	case BLK_ZONE_COND_EMPTY:
	case BLK_ZONE_COND_IMP_OPEN:
	case BLK_ZONE_COND_EXP_OPEN:
	case BLK_ZONE_COND_CLOSED:
		/* Writes must be at the write pointer position */
		if (sector != zone->wp)
			return BLK_STS_IOERR;

		if (zone->cond != BLK_ZONE_COND_EXP_OPEN)
			zone->cond = BLK_ZONE_COND_IMP_OPEN;

		ret = null_process_cmd(cmd, REQ_OP_WRITE, sector, nr_sectors);
		if (ret != BLK_STS_OK)
			return ret;

		zone->wp += nr_sectors;
		if (zone->wp == zone->start + zone->len)
			zone->cond = BLK_ZONE_COND_FULL;
		return BLK_STS_OK;
	default:
		/* Invalid zone condition */
		return BLK_STS_IOERR;
	}
}

static blk_status_t null_zone_mgmt(struct nullb_cmd *cmd, enum req_opf op,
				   sector_t sector)
{
	struct nullb_device *dev = cmd->nq->dev;
	unsigned int zone_no = null_zone_no(dev, sector);
	struct blk_zone *zone = &dev->zones[zone_no];
	size_t i;

	switch (op) {
	case REQ_OP_ZONE_RESET_ALL:
		for (i = 0; i < dev->nr_zones; i++) {
			if (zone[i].type == BLK_ZONE_TYPE_CONVENTIONAL)
				continue;
			zone[i].cond = BLK_ZONE_COND_EMPTY;
			zone[i].wp = zone[i].start;
		}
		break;
	case REQ_OP_ZONE_RESET:
		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
			return BLK_STS_IOERR;

		zone->cond = BLK_ZONE_COND_EMPTY;
		zone->wp = zone->start;
		break;
	case REQ_OP_ZONE_OPEN:
		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
			return BLK_STS_IOERR;
		if (zone->cond == BLK_ZONE_COND_FULL)
			return BLK_STS_IOERR;

		zone->cond = BLK_ZONE_COND_EXP_OPEN;
		break;
	case REQ_OP_ZONE_CLOSE:
		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
			return BLK_STS_IOERR;
		if (zone->cond == BLK_ZONE_COND_FULL)
			return BLK_STS_IOERR;

		if (zone->wp == zone->start)
			zone->cond = BLK_ZONE_COND_EMPTY;
		else
			zone->cond = BLK_ZONE_COND_CLOSED;
		break;
	case REQ_OP_ZONE_FINISH:
		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
			return BLK_STS_IOERR;

		zone->cond = BLK_ZONE_COND_FULL;
		zone->wp = zone->start + zone->len;
		break;
	default:
		return BLK_STS_NOTSUPP;
	}

	trace_nullb_zone_op(cmd, zone_no, zone->cond);
	return BLK_STS_OK;
}

blk_status_t null_process_zoned_cmd(struct nullb_cmd *cmd, enum req_opf op,
				    sector_t sector, sector_t nr_sectors)
{
	switch (op) {
	case REQ_OP_WRITE:
		return null_zone_write(cmd, sector, nr_sectors);
	case REQ_OP_ZONE_RESET:
	case REQ_OP_ZONE_RESET_ALL:
	case REQ_OP_ZONE_OPEN:
	case REQ_OP_ZONE_CLOSE:
	case REQ_OP_ZONE_FINISH:
		return null_zone_mgmt(cmd, op, sector);
	default:
		return null_process_cmd(cmd, op, sector, nr_sectors);
	}
}