summaryrefslogtreecommitdiff
path: root/drivers/infiniband/core/umem_dmabuf.c
blob: 0ec2e4120cc94bb0ba74cad6cd5e56a010f26b7f (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
// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
/*
 * Copyright (c) 2020 Intel Corporation. All rights reserved.
 */

#include <linux/dma-buf.h>
#include <linux/dma-resv.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>

#include "uverbs.h"

MODULE_IMPORT_NS("DMA_BUF");

int ib_umem_dmabuf_map_pages(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct sg_table *sgt;
	struct scatterlist *sg;
	unsigned long start, end, cur = 0;
	unsigned int nmap = 0;
	long ret;
	int i;

	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);

	if (umem_dmabuf->revoked)
		return -EINVAL;

	if (umem_dmabuf->sgt)
		goto wait_fence;

	sgt = dma_buf_map_attachment(umem_dmabuf->attach,
				     DMA_BIDIRECTIONAL);
	if (IS_ERR(sgt))
		return PTR_ERR(sgt);

	/* modify the sg list in-place to match umem address and length */

	start = ALIGN_DOWN(umem_dmabuf->umem.address, PAGE_SIZE);
	end = ALIGN(umem_dmabuf->umem.address + umem_dmabuf->umem.length,
		    PAGE_SIZE);
	for_each_sgtable_dma_sg(sgt, sg, i) {
		if (start < cur + sg_dma_len(sg) && cur < end)
			nmap++;
		if (cur <= start && start < cur + sg_dma_len(sg)) {
			unsigned long offset = start - cur;

			umem_dmabuf->first_sg = sg;
			umem_dmabuf->first_sg_offset = offset;
			sg_dma_address(sg) += offset;
			sg_dma_len(sg) -= offset;
			cur += offset;
		}
		if (cur < end && end <= cur + sg_dma_len(sg)) {
			unsigned long trim = cur + sg_dma_len(sg) - end;

			umem_dmabuf->last_sg = sg;
			umem_dmabuf->last_sg_trim = trim;
			sg_dma_len(sg) -= trim;
			break;
		}
		cur += sg_dma_len(sg);
	}

	umem_dmabuf->umem.sgt_append.sgt.sgl = umem_dmabuf->first_sg;
	umem_dmabuf->umem.sgt_append.sgt.nents = nmap;
	umem_dmabuf->sgt = sgt;

wait_fence:
	/*
	 * Although the sg list is valid now, the content of the pages
	 * may be not up-to-date. Wait for the exporter to finish
	 * the migration.
	 */
	ret = dma_resv_wait_timeout(umem_dmabuf->attach->dmabuf->resv,
				     DMA_RESV_USAGE_KERNEL,
				     false, MAX_SCHEDULE_TIMEOUT);
	if (ret < 0)
		return ret;
	if (ret == 0)
		return -ETIMEDOUT;
	return 0;
}
EXPORT_SYMBOL(ib_umem_dmabuf_map_pages);

void ib_umem_dmabuf_unmap_pages(struct ib_umem_dmabuf *umem_dmabuf)
{
	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);

	if (!umem_dmabuf->sgt)
		return;

	/* retore the original sg list */
	if (umem_dmabuf->first_sg) {
		sg_dma_address(umem_dmabuf->first_sg) -=
			umem_dmabuf->first_sg_offset;
		sg_dma_len(umem_dmabuf->first_sg) +=
			umem_dmabuf->first_sg_offset;
		umem_dmabuf->first_sg = NULL;
		umem_dmabuf->first_sg_offset = 0;
	}
	if (umem_dmabuf->last_sg) {
		sg_dma_len(umem_dmabuf->last_sg) +=
			umem_dmabuf->last_sg_trim;
		umem_dmabuf->last_sg = NULL;
		umem_dmabuf->last_sg_trim = 0;
	}

	dma_buf_unmap_attachment(umem_dmabuf->attach, umem_dmabuf->sgt,
				 DMA_BIDIRECTIONAL);

	umem_dmabuf->sgt = NULL;
}
EXPORT_SYMBOL(ib_umem_dmabuf_unmap_pages);

static struct ib_umem_dmabuf *
ib_umem_dmabuf_get_with_dma_device(struct ib_device *device,
				   struct device *dma_device,
				   unsigned long offset, size_t size,
				   int fd, int access,
				   const struct dma_buf_attach_ops *ops)
{
	struct dma_buf *dmabuf;
	struct ib_umem_dmabuf *umem_dmabuf;
	struct ib_umem *umem;
	unsigned long end;
	struct ib_umem_dmabuf *ret = ERR_PTR(-EINVAL);

	if (check_add_overflow(offset, (unsigned long)size, &end))
		return ret;

	if (unlikely(!ops || !ops->move_notify))
		return ret;

	dmabuf = dma_buf_get(fd);
	if (IS_ERR(dmabuf))
		return ERR_CAST(dmabuf);

	if (dmabuf->size < end)
		goto out_release_dmabuf;

	umem_dmabuf = kzalloc(sizeof(*umem_dmabuf), GFP_KERNEL);
	if (!umem_dmabuf) {
		ret = ERR_PTR(-ENOMEM);
		goto out_release_dmabuf;
	}

	umem = &umem_dmabuf->umem;
	umem->ibdev = device;
	umem->length = size;
	umem->address = offset;
	umem->writable = ib_access_writable(access);
	umem->is_dmabuf = 1;

	if (!ib_umem_num_pages(umem))
		goto out_free_umem;

	umem_dmabuf->attach = dma_buf_dynamic_attach(
					dmabuf,
					dma_device,
					ops,
					umem_dmabuf);
	if (IS_ERR(umem_dmabuf->attach)) {
		ret = ERR_CAST(umem_dmabuf->attach);
		goto out_free_umem;
	}
	return umem_dmabuf;

out_free_umem:
	kfree(umem_dmabuf);

out_release_dmabuf:
	dma_buf_put(dmabuf);
	return ret;
}

struct ib_umem_dmabuf *ib_umem_dmabuf_get(struct ib_device *device,
					  unsigned long offset, size_t size,
					  int fd, int access,
					  const struct dma_buf_attach_ops *ops)
{
	return ib_umem_dmabuf_get_with_dma_device(device, device->dma_device,
						  offset, size, fd, access, ops);
}
EXPORT_SYMBOL(ib_umem_dmabuf_get);

static void
ib_umem_dmabuf_unsupported_move_notify(struct dma_buf_attachment *attach)
{
	struct ib_umem_dmabuf *umem_dmabuf = attach->importer_priv;

	ibdev_warn_ratelimited(umem_dmabuf->umem.ibdev,
			       "Invalidate callback should not be called when memory is pinned\n");
}

static struct dma_buf_attach_ops ib_umem_dmabuf_attach_pinned_ops = {
	.allow_peer2peer = true,
	.move_notify = ib_umem_dmabuf_unsupported_move_notify,
};

struct ib_umem_dmabuf *
ib_umem_dmabuf_get_pinned_with_dma_device(struct ib_device *device,
					  struct device *dma_device,
					  unsigned long offset, size_t size,
					  int fd, int access)
{
	struct ib_umem_dmabuf *umem_dmabuf;
	int err;

	umem_dmabuf = ib_umem_dmabuf_get_with_dma_device(device, dma_device, offset,
							 size, fd, access,
							 &ib_umem_dmabuf_attach_pinned_ops);
	if (IS_ERR(umem_dmabuf))
		return umem_dmabuf;

	dma_resv_lock(umem_dmabuf->attach->dmabuf->resv, NULL);
	err = dma_buf_pin(umem_dmabuf->attach);
	if (err)
		goto err_release;
	umem_dmabuf->pinned = 1;

	err = ib_umem_dmabuf_map_pages(umem_dmabuf);
	if (err)
		goto err_unpin;
	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);

	return umem_dmabuf;

err_unpin:
	dma_buf_unpin(umem_dmabuf->attach);
err_release:
	dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv);
	ib_umem_release(&umem_dmabuf->umem);
	return ERR_PTR(err);
}
EXPORT_SYMBOL(ib_umem_dmabuf_get_pinned_with_dma_device);

struct ib_umem_dmabuf *ib_umem_dmabuf_get_pinned(struct ib_device *device,
						 unsigned long offset,
						 size_t size, int fd,
						 int access)
{
	return ib_umem_dmabuf_get_pinned_with_dma_device(device, device->dma_device,
							 offset, size, fd, access);
}
EXPORT_SYMBOL(ib_umem_dmabuf_get_pinned);

void ib_umem_dmabuf_revoke(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf;

	dma_resv_lock(dmabuf->resv, NULL);
	if (umem_dmabuf->revoked)
		goto end;
	ib_umem_dmabuf_unmap_pages(umem_dmabuf);
	if (umem_dmabuf->pinned) {
		dma_buf_unpin(umem_dmabuf->attach);
		umem_dmabuf->pinned = 0;
	}
	umem_dmabuf->revoked = 1;
end:
	dma_resv_unlock(dmabuf->resv);
}
EXPORT_SYMBOL(ib_umem_dmabuf_revoke);

void ib_umem_dmabuf_release(struct ib_umem_dmabuf *umem_dmabuf)
{
	struct dma_buf *dmabuf = umem_dmabuf->attach->dmabuf;

	ib_umem_dmabuf_revoke(umem_dmabuf);

	dma_buf_detach(dmabuf, umem_dmabuf->attach);
	dma_buf_put(dmabuf);
	kfree(umem_dmabuf);
}