summaryrefslogtreecommitdiff
path: root/drivers/nvme/host/pr.c
blob: 7347ddf85f00b350ed04531bbceb428e0c78da7d (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2015 Intel Corporation
 *	Keith Busch <kbusch@kernel.org>
 */
#include <linux/blkdev.h>
#include <linux/pr.h>
#include <asm/unaligned.h>

#include "nvme.h"

static enum nvme_pr_type nvme_pr_type_from_blk(enum pr_type type)
{
	switch (type) {
	case PR_WRITE_EXCLUSIVE:
		return NVME_PR_WRITE_EXCLUSIVE;
	case PR_EXCLUSIVE_ACCESS:
		return NVME_PR_EXCLUSIVE_ACCESS;
	case PR_WRITE_EXCLUSIVE_REG_ONLY:
		return NVME_PR_WRITE_EXCLUSIVE_REG_ONLY;
	case PR_EXCLUSIVE_ACCESS_REG_ONLY:
		return NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY;
	case PR_WRITE_EXCLUSIVE_ALL_REGS:
		return NVME_PR_WRITE_EXCLUSIVE_ALL_REGS;
	case PR_EXCLUSIVE_ACCESS_ALL_REGS:
		return NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS;
	}

	return 0;
}

static enum pr_type block_pr_type_from_nvme(enum nvme_pr_type type)
{
	switch (type) {
	case NVME_PR_WRITE_EXCLUSIVE:
		return PR_WRITE_EXCLUSIVE;
	case NVME_PR_EXCLUSIVE_ACCESS:
		return PR_EXCLUSIVE_ACCESS;
	case NVME_PR_WRITE_EXCLUSIVE_REG_ONLY:
		return PR_WRITE_EXCLUSIVE_REG_ONLY;
	case NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY:
		return PR_EXCLUSIVE_ACCESS_REG_ONLY;
	case NVME_PR_WRITE_EXCLUSIVE_ALL_REGS:
		return PR_WRITE_EXCLUSIVE_ALL_REGS;
	case NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS:
		return PR_EXCLUSIVE_ACCESS_ALL_REGS;
	}

	return 0;
}

static int nvme_send_ns_head_pr_command(struct block_device *bdev,
		struct nvme_command *c, void *data, unsigned int data_len)
{
	struct nvme_ns_head *head = bdev->bd_disk->private_data;
	int srcu_idx = srcu_read_lock(&head->srcu);
	struct nvme_ns *ns = nvme_find_path(head);
	int ret = -EWOULDBLOCK;

	if (ns) {
		c->common.nsid = cpu_to_le32(ns->head->ns_id);
		ret = nvme_submit_sync_cmd(ns->queue, c, data, data_len);
	}
	srcu_read_unlock(&head->srcu, srcu_idx);
	return ret;
}

static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
		void *data, unsigned int data_len)
{
	c->common.nsid = cpu_to_le32(ns->head->ns_id);
	return nvme_submit_sync_cmd(ns->queue, c, data, data_len);
}

static int nvme_status_to_pr_err(int status)
{
	if (nvme_is_path_error(status))
		return PR_STS_PATH_FAILED;

	switch (status & NVME_SCT_SC_MASK) {
	case NVME_SC_SUCCESS:
		return PR_STS_SUCCESS;
	case NVME_SC_RESERVATION_CONFLICT:
		return PR_STS_RESERVATION_CONFLICT;
	case NVME_SC_ONCS_NOT_SUPPORTED:
		return -EOPNOTSUPP;
	case NVME_SC_BAD_ATTRIBUTES:
	case NVME_SC_INVALID_OPCODE:
	case NVME_SC_INVALID_FIELD:
	case NVME_SC_INVALID_NS:
		return -EINVAL;
	default:
		return PR_STS_IOERR;
	}
}

static int nvme_send_pr_command(struct block_device *bdev,
		struct nvme_command *c, void *data, unsigned int data_len)
{
	if (nvme_disk_is_ns_head(bdev->bd_disk))
		return nvme_send_ns_head_pr_command(bdev, c, data, data_len);

	return nvme_send_ns_pr_command(bdev->bd_disk->private_data, c, data,
				       data_len);
}

static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
				u64 key, u64 sa_key, u8 op)
{
	struct nvme_command c = { };
	u8 data[16] = { 0, };
	int ret;

	put_unaligned_le64(key, &data[0]);
	put_unaligned_le64(sa_key, &data[8]);

	c.common.opcode = op;
	c.common.cdw10 = cpu_to_le32(cdw10);

	ret = nvme_send_pr_command(bdev, &c, data, sizeof(data));
	if (ret < 0)
		return ret;

	return nvme_status_to_pr_err(ret);
}

static int nvme_pr_register(struct block_device *bdev, u64 old,
		u64 new, unsigned flags)
{
	u32 cdw10;

	if (flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;

	cdw10 = old ? 2 : 0;
	cdw10 |= (flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0;
	cdw10 |= (1 << 30) | (1 << 31); /* PTPL=1 */
	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_register);
}

static int nvme_pr_reserve(struct block_device *bdev, u64 key,
		enum pr_type type, unsigned flags)
{
	u32 cdw10;

	if (flags & ~PR_FL_IGNORE_KEY)
		return -EOPNOTSUPP;

	cdw10 = nvme_pr_type_from_blk(type) << 8;
	cdw10 |= ((flags & PR_FL_IGNORE_KEY) ? 1 << 3 : 0);
	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_acquire);
}

static int nvme_pr_preempt(struct block_device *bdev, u64 old, u64 new,
		enum pr_type type, bool abort)
{
	u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (abort ? 2 : 1);

	return nvme_pr_command(bdev, cdw10, old, new, nvme_cmd_resv_acquire);
}

static int nvme_pr_clear(struct block_device *bdev, u64 key)
{
	u32 cdw10 = 1 | (key ? 0 : 1 << 3);

	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
}

static int nvme_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
{
	u32 cdw10 = nvme_pr_type_from_blk(type) << 8 | (key ? 0 : 1 << 3);

	return nvme_pr_command(bdev, cdw10, key, 0, nvme_cmd_resv_release);
}

static int nvme_pr_resv_report(struct block_device *bdev, void *data,
		u32 data_len, bool *eds)
{
	struct nvme_command c = { };
	int ret;

	c.common.opcode = nvme_cmd_resv_report;
	c.common.cdw10 = cpu_to_le32(nvme_bytes_to_numd(data_len));
	c.common.cdw11 = cpu_to_le32(NVME_EXTENDED_DATA_STRUCT);
	*eds = true;

retry:
	ret = nvme_send_pr_command(bdev, &c, data, data_len);
	if (ret == NVME_SC_HOST_ID_INCONSIST &&
	    c.common.cdw11 == cpu_to_le32(NVME_EXTENDED_DATA_STRUCT)) {
		c.common.cdw11 = 0;
		*eds = false;
		goto retry;
	}

	if (ret < 0)
		return ret;

	return nvme_status_to_pr_err(ret);
}

static int nvme_pr_read_keys(struct block_device *bdev,
		struct pr_keys *keys_info)
{
	u32 rse_len, num_keys = keys_info->num_keys;
	struct nvme_reservation_status_ext *rse;
	int ret, i;
	bool eds;

	/*
	 * Assume we are using 128-bit host IDs and allocate a buffer large
	 * enough to get enough keys to fill the return keys buffer.
	 */
	rse_len = struct_size(rse, regctl_eds, num_keys);
	rse = kzalloc(rse_len, GFP_KERNEL);
	if (!rse)
		return -ENOMEM;

	ret = nvme_pr_resv_report(bdev, rse, rse_len, &eds);
	if (ret)
		goto free_rse;

	keys_info->generation = le32_to_cpu(rse->gen);
	keys_info->num_keys = get_unaligned_le16(&rse->regctl);

	num_keys = min(num_keys, keys_info->num_keys);
	for (i = 0; i < num_keys; i++) {
		if (eds) {
			keys_info->keys[i] =
					le64_to_cpu(rse->regctl_eds[i].rkey);
		} else {
			struct nvme_reservation_status *rs;

			rs = (struct nvme_reservation_status *)rse;
			keys_info->keys[i] = le64_to_cpu(rs->regctl_ds[i].rkey);
		}
	}

free_rse:
	kfree(rse);
	return ret;
}

static int nvme_pr_read_reservation(struct block_device *bdev,
		struct pr_held_reservation *resv)
{
	struct nvme_reservation_status_ext tmp_rse, *rse;
	int ret, i, num_regs;
	u32 rse_len;
	bool eds;

get_num_regs:
	/*
	 * Get the number of registrations so we know how big to allocate
	 * the response buffer.
	 */
	ret = nvme_pr_resv_report(bdev, &tmp_rse, sizeof(tmp_rse), &eds);
	if (ret)
		return ret;

	num_regs = get_unaligned_le16(&tmp_rse.regctl);
	if (!num_regs) {
		resv->generation = le32_to_cpu(tmp_rse.gen);
		return 0;
	}

	rse_len = struct_size(rse, regctl_eds, num_regs);
	rse = kzalloc(rse_len, GFP_KERNEL);
	if (!rse)
		return -ENOMEM;

	ret = nvme_pr_resv_report(bdev, rse, rse_len, &eds);
	if (ret)
		goto free_rse;

	if (num_regs != get_unaligned_le16(&rse->regctl)) {
		kfree(rse);
		goto get_num_regs;
	}

	resv->generation = le32_to_cpu(rse->gen);
	resv->type = block_pr_type_from_nvme(rse->rtype);

	for (i = 0; i < num_regs; i++) {
		if (eds) {
			if (rse->regctl_eds[i].rcsts) {
				resv->key = le64_to_cpu(rse->regctl_eds[i].rkey);
				break;
			}
		} else {
			struct nvme_reservation_status *rs;

			rs = (struct nvme_reservation_status *)rse;
			if (rs->regctl_ds[i].rcsts) {
				resv->key = le64_to_cpu(rs->regctl_ds[i].rkey);
				break;
			}
		}
	}

free_rse:
	kfree(rse);
	return ret;
}

const struct pr_ops nvme_pr_ops = {
	.pr_register	= nvme_pr_register,
	.pr_reserve	= nvme_pr_reserve,
	.pr_release	= nvme_pr_release,
	.pr_preempt	= nvme_pr_preempt,
	.pr_clear	= nvme_pr_clear,
	.pr_read_keys	= nvme_pr_read_keys,
	.pr_read_reservation = nvme_pr_read_reservation,
};