summaryrefslogtreecommitdiff
path: root/drivers/nvme/host/zns.c
blob: 722384bcc765cda778972c8a86345eaaf18a7353 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2020 Western Digital Corporation or its affiliates.
 */

#include <linux/blkdev.h>
#include <linux/vmalloc.h>
#include "nvme.h"

static int nvme_set_max_append(struct nvme_ctrl *ctrl)
{
	struct nvme_command c = { };
	struct nvme_id_ctrl_zns *id;
	int status;

	id = kzalloc(sizeof(*id), GFP_KERNEL);
	if (!id)
		return -ENOMEM;

	c.identify.opcode = nvme_admin_identify;
	c.identify.cns = NVME_ID_CNS_CS_CTRL;
	c.identify.csi = NVME_CSI_ZNS;

	status = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id));
	if (status) {
		kfree(id);
		return status;
	}

	if (id->zasl)
		ctrl->max_zone_append = 1 << (id->zasl + 3);
	else
		ctrl->max_zone_append = ctrl->max_hw_sectors;
	kfree(id);
	return 0;
}

int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
		struct queue_limits *lim)
{
	struct nvme_effects_log *log = ns->head->effects;
	struct nvme_command c = { };
	struct nvme_id_ns_zns *id;
	int status;

	/* Driver requires zone append support */
	if ((le32_to_cpu(log->iocs[nvme_cmd_zone_append]) &
			NVME_CMD_EFFECTS_CSUPP)) {
		if (test_and_clear_bit(NVME_NS_FORCE_RO, &ns->flags))
			dev_warn(ns->ctrl->device,
				 "Zone Append supported for zoned namespace:%d. Remove read-only mode\n",
				 ns->head->ns_id);
	} else {
		set_bit(NVME_NS_FORCE_RO, &ns->flags);
		dev_warn(ns->ctrl->device,
			 "Zone Append not supported for zoned namespace:%d. Forcing to read-only mode\n",
			 ns->head->ns_id);
	}

	/* Lazily query controller append limit for the first zoned namespace */
	if (!ns->ctrl->max_zone_append) {
		status = nvme_set_max_append(ns->ctrl);
		if (status)
			return status;
	}

	id = kzalloc(sizeof(*id), GFP_KERNEL);
	if (!id)
		return -ENOMEM;

	c.identify.opcode = nvme_admin_identify;
	c.identify.nsid = cpu_to_le32(ns->head->ns_id);
	c.identify.cns = NVME_ID_CNS_CS_NS;
	c.identify.csi = NVME_CSI_ZNS;

	status = nvme_submit_sync_cmd(ns->ctrl->admin_q, &c, id, sizeof(*id));
	if (status)
		goto free_data;

	/*
	 * We currently do not handle devices requiring any of the zoned
	 * operation characteristics.
	 */
	if (id->zoc) {
		dev_warn(ns->ctrl->device,
			"zone operations:%x not supported for namespace:%u\n",
			le16_to_cpu(id->zoc), ns->head->ns_id);
		status = -ENODEV;
		goto free_data;
	}

	ns->head->zsze =
		nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
	if (!is_power_of_2(ns->head->zsze)) {
		dev_warn(ns->ctrl->device,
			"invalid zone size:%llu for namespace:%u\n",
			ns->head->zsze, ns->head->ns_id);
		status = -ENODEV;
		goto free_data;
	}

	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
	lim->zoned = 1;
	lim->max_open_zones = le32_to_cpu(id->mor) + 1;
	lim->max_active_zones = le32_to_cpu(id->mar) + 1;
	lim->chunk_sectors = ns->head->zsze;
	lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
free_data:
	kfree(id);
	return status;
}

static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
					  unsigned int nr_zones, size_t *buflen)
{
	struct request_queue *q = ns->disk->queue;
	size_t bufsize;
	void *buf;

	const size_t min_bufsize = sizeof(struct nvme_zone_report) +
				   sizeof(struct nvme_zone_descriptor);

	nr_zones = min_t(unsigned int, nr_zones,
			 get_capacity(ns->disk) >> ilog2(ns->head->zsze));

	bufsize = sizeof(struct nvme_zone_report) +
		nr_zones * sizeof(struct nvme_zone_descriptor);
	bufsize = min_t(size_t, bufsize,
			queue_max_hw_sectors(q) << SECTOR_SHIFT);
	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);

	while (bufsize >= min_bufsize) {
		buf = __vmalloc(bufsize, GFP_KERNEL | __GFP_NORETRY);
		if (buf) {
			*buflen = bufsize;
			return buf;
		}
		bufsize >>= 1;
	}
	return NULL;
}

static int nvme_zone_parse_entry(struct nvme_ctrl *ctrl,
				 struct nvme_ns_head *head,
				 struct nvme_zone_descriptor *entry,
				 unsigned int idx, report_zones_cb cb,
				 void *data)
{
	struct blk_zone zone = { };

	if ((entry->zt & 0xf) != NVME_ZONE_TYPE_SEQWRITE_REQ) {
		dev_err(ctrl->device, "invalid zone type %#x\n",
				entry->zt);
		return -EINVAL;
	}

	zone.type = BLK_ZONE_TYPE_SEQWRITE_REQ;
	zone.cond = entry->zs >> 4;
	zone.len = head->zsze;
	zone.capacity = nvme_lba_to_sect(head, le64_to_cpu(entry->zcap));
	zone.start = nvme_lba_to_sect(head, le64_to_cpu(entry->zslba));
	if (zone.cond == BLK_ZONE_COND_FULL)
		zone.wp = zone.start + zone.len;
	else
		zone.wp = nvme_lba_to_sect(head, le64_to_cpu(entry->wp));

	return cb(&zone, idx, data);
}

int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
		unsigned int nr_zones, report_zones_cb cb, void *data)
{
	struct nvme_zone_report *report;
	struct nvme_command c = { };
	int ret, zone_idx = 0;
	unsigned int nz, i;
	size_t buflen;

	if (ns->head->ids.csi != NVME_CSI_ZNS)
		return -EINVAL;

	report = nvme_zns_alloc_report_buffer(ns, nr_zones, &buflen);
	if (!report)
		return -ENOMEM;

	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;

	sector &= ~(ns->head->zsze - 1);
	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
		memset(report, 0, buflen);

		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, sector));
		ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
		if (ret) {
			if (ret > 0)
				ret = -EIO;
			goto out_free;
		}

		nz = min((unsigned int)le64_to_cpu(report->nr_zones), nr_zones);
		if (!nz)
			break;

		for (i = 0; i < nz && zone_idx < nr_zones; i++) {
			ret = nvme_zone_parse_entry(ns->ctrl, ns->head,
						    &report->entries[i],
						    zone_idx, cb, data);
			if (ret)
				goto out_free;
			zone_idx++;
		}

		sector += ns->head->zsze * nz;
	}

	if (zone_idx > 0)
		ret = zone_idx;
	else
		ret = -EINVAL;
out_free:
	kvfree(report);
	return ret;
}

blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
		struct nvme_command *c, enum nvme_zone_mgmt_action action)
{
	memset(c, 0, sizeof(*c));

	c->zms.opcode = nvme_cmd_zone_mgmt_send;
	c->zms.nsid = cpu_to_le32(ns->head->ns_id);
	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns->head, blk_rq_pos(req)));
	c->zms.zsa = action;

	if (req_op(req) == REQ_OP_ZONE_RESET_ALL)
		c->zms.select_all = 1;

	return BLK_STS_OK;
}