summaryrefslogtreecommitdiffstats
path: root/lib/librte_vhost/iotlb.c
blob: b74cc6a78f8d340ec721cb741236dde1402d3177 (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
/*-
 *   BSD LICENSE
 *
 *   Copyright (c) 2017 Red Hat, Inc.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#ifdef RTE_LIBRTE_VHOST_NUMA
#include <numaif.h>
#endif

#include <rte_tailq.h>

#include "iotlb.h"
#include "vhost.h"

struct vhost_iotlb_entry {
	TAILQ_ENTRY(vhost_iotlb_entry) next;

	uint64_t iova;
	uint64_t uaddr;
	uint64_t size;
	uint8_t perm;
};

#define IOTLB_CACHE_SIZE 2048

static void
vhost_user_iotlb_pending_remove_all(struct vhost_virtqueue *vq)
{
	struct vhost_iotlb_entry *node, *temp_node;

	rte_rwlock_write_lock(&vq->iotlb_pending_lock);

	TAILQ_FOREACH_SAFE(node, &vq->iotlb_pending_list, next, temp_node) {
		TAILQ_REMOVE(&vq->iotlb_pending_list, node, next);
		rte_mempool_put(vq->iotlb_pool, node);
	}

	rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
}

bool
vhost_user_iotlb_pending_miss(struct vhost_virtqueue *vq, uint64_t iova,
				uint8_t perm)
{
	struct vhost_iotlb_entry *node;
	bool found = false;

	rte_rwlock_read_lock(&vq->iotlb_pending_lock);

	TAILQ_FOREACH(node, &vq->iotlb_pending_list, next) {
		if ((node->iova == iova) && (node->perm == perm)) {
			found = true;
			break;
		}
	}

	rte_rwlock_read_unlock(&vq->iotlb_pending_lock);

	return found;
}

void
vhost_user_iotlb_pending_insert(struct vhost_virtqueue *vq,
				uint64_t iova, uint8_t perm)
{
	struct vhost_iotlb_entry *node;
	int ret;

	ret = rte_mempool_get(vq->iotlb_pool, (void **)&node);
	if (ret) {
		RTE_LOG(INFO, VHOST_CONFIG,
				"IOTLB pool empty, clear pending misses\n");
		vhost_user_iotlb_pending_remove_all(vq);
		ret = rte_mempool_get(vq->iotlb_pool, (void **)&node);
		if (ret) {
			RTE_LOG(ERR, VHOST_CONFIG, "IOTLB pool still empty, failure\n");
			return;
		}
	}

	node->iova = iova;
	node->perm = perm;

	rte_rwlock_write_lock(&vq->iotlb_pending_lock);

	TAILQ_INSERT_TAIL(&vq->iotlb_pending_list, node, next);

	rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
}

static void
vhost_user_iotlb_pending_remove(struct vhost_virtqueue *vq,
				uint64_t iova, uint64_t size, uint8_t perm)
{
	struct vhost_iotlb_entry *node, *temp_node;

	rte_rwlock_write_lock(&vq->iotlb_pending_lock);

	TAILQ_FOREACH_SAFE(node, &vq->iotlb_pending_list, next, temp_node) {
		if (node->iova < iova)
			continue;
		if (node->iova >= iova + size)
			continue;
		if ((node->perm & perm) != node->perm)
			continue;
		TAILQ_REMOVE(&vq->iotlb_pending_list, node, next);
		rte_mempool_put(vq->iotlb_pool, node);
	}

	rte_rwlock_write_unlock(&vq->iotlb_pending_lock);
}

static void
vhost_user_iotlb_cache_remove_all(struct vhost_virtqueue *vq)
{
	struct vhost_iotlb_entry *node, *temp_node;

	rte_rwlock_write_lock(&vq->iotlb_lock);

	TAILQ_FOREACH_SAFE(node, &vq->iotlb_list, next, temp_node) {
		TAILQ_REMOVE(&vq->iotlb_list, node, next);
		rte_mempool_put(vq->iotlb_pool, node);
	}

	vq->iotlb_cache_nr = 0;

	rte_rwlock_write_unlock(&vq->iotlb_lock);
}

static void
vhost_user_iotlb_cache_random_evict(struct vhost_virtqueue *vq)
{
	struct vhost_iotlb_entry *node, *temp_node;
	int entry_idx;

	rte_rwlock_write_lock(&vq->iotlb_lock);

	entry_idx = rte_rand() % vq->iotlb_cache_nr;

	TAILQ_FOREACH_SAFE(node, &vq->iotlb_list, next, temp_node) {
		if (!entry_idx) {
			TAILQ_REMOVE(&vq->iotlb_list, node, next);
			rte_mempool_put(vq->iotlb_pool, node);
			vq->iotlb_cache_nr--;
			break;
		}
		entry_idx--;
	}

	rte_rwlock_write_unlock(&vq->iotlb_lock);
}

void
vhost_user_iotlb_cache_insert(struct vhost_virtqueue *vq, uint64_t iova,
				uint64_t uaddr, uint64_t size, uint8_t perm)
{
	struct vhost_iotlb_entry *node, *new_node;
	int ret;

	ret = rte_mempool_get(vq->iotlb_pool, (void **)&new_node);
	if (ret) {
		RTE_LOG(DEBUG, VHOST_CONFIG, "IOTLB pool empty, evict one entry\n");
		vhost_user_iotlb_cache_random_evict(vq);
		ret = rte_mempool_get(vq->iotlb_pool, (void **)&new_node);
		if (ret) {
			RTE_LOG(ERR, VHOST_CONFIG, "IOTLB pool still empty, failure\n");
			return;
		}
	}

	new_node->iova = iova;
	new_node->uaddr = uaddr;
	new_node->size = size;
	new_node->perm = perm;

	rte_rwlock_write_lock(&vq->iotlb_lock);

	TAILQ_FOREACH(node, &vq->iotlb_list, next) {
		/*
		 * Entries must be invalidated before being updated.
		 * So if iova already in list, assume identical.
		 */
		if (node->iova == new_node->iova) {
			rte_mempool_put(vq->iotlb_pool, new_node);
			goto unlock;
		} else if (node->iova > new_node->iova) {
			TAILQ_INSERT_BEFORE(node, new_node, next);
			vq->iotlb_cache_nr++;
			goto unlock;
		}
	}

	TAILQ_INSERT_TAIL(&vq->iotlb_list, new_node, next);
	vq->iotlb_cache_nr++;

unlock:
	vhost_user_iotlb_pending_remove(vq, iova, size, perm);

	rte_rwlock_write_unlock(&vq->iotlb_lock);

}

void
vhost_user_iotlb_cache_remove(struct vhost_virtqueue *vq,
					uint64_t iova, uint64_t size)
{
	struct vhost_iotlb_entry *node, *temp_node;

	if (unlikely(!size))
		return;

	rte_rwlock_write_lock(&vq->iotlb_lock);

	TAILQ_FOREACH_SAFE(node, &vq->iotlb_list, next, temp_node) {
		/* Sorted list */
		if (unlikely(iova + size < node->iova))
			break;

		if (iova < node->iova + node->size) {
			TAILQ_REMOVE(&vq->iotlb_list, node, next);
			rte_mempool_put(vq->iotlb_pool, node);
			vq->iotlb_cache_nr--;
		}
	}

	rte_rwlock_write_unlock(&vq->iotlb_lock);
}

uint64_t
vhost_user_iotlb_cache_find(struct vhost_virtqueue *vq, uint64_t iova,
						uint64_t *size, uint8_t perm)
{
	struct vhost_iotlb_entry *node;
	uint64_t offset, vva = 0, mapped = 0;

	if (unlikely(!*size))
		goto out;

	TAILQ_FOREACH(node, &vq->iotlb_list, next) {
		/* List sorted by iova */
		if (unlikely(iova < node->iova))
			break;

		if (iova >= node->iova + node->size)
			continue;

		if (unlikely((perm & node->perm) != perm)) {
			vva = 0;
			break;
		}

		offset = iova - node->iova;
		if (!vva)
			vva = node->uaddr + offset;

		mapped += node->size - offset;
		iova = node->iova + node->size;

		if (mapped >= *size)
			break;
	}

out:
	/* Only part of the requested chunk is mapped */
	if (unlikely(mapped < *size))
		*size = mapped;

	return vva;
}

int
vhost_user_iotlb_init(struct virtio_net *dev, int vq_index)
{
	char pool_name[RTE_MEMPOOL_NAMESIZE];
	struct vhost_virtqueue *vq = dev->virtqueue[vq_index];
	int socket = 0;

	if (vq->iotlb_pool) {
		/*
		 * The cache has already been initialized,
		 * just drop all cached and pending entries.
		 */
		vhost_user_iotlb_cache_remove_all(vq);
		vhost_user_iotlb_pending_remove_all(vq);
	}

#ifdef RTE_LIBRTE_VHOST_NUMA
	if (get_mempolicy(&socket, NULL, 0, vq, MPOL_F_NODE | MPOL_F_ADDR) != 0)
		socket = 0;
#endif

	rte_rwlock_init(&vq->iotlb_lock);
	rte_rwlock_init(&vq->iotlb_pending_lock);

	TAILQ_INIT(&vq->iotlb_list);
	TAILQ_INIT(&vq->iotlb_pending_list);

	snprintf(pool_name, sizeof(pool_name), "iotlb_cache_%d_%d",
			dev->vid, vq_index);

	/* If already created, free it and recreate */
	vq->iotlb_pool = rte_mempool_lookup(pool_name);
	if (vq->iotlb_pool)
		rte_mempool_free(vq->iotlb_pool);

	vq->iotlb_pool = rte_mempool_create(pool_name,
			IOTLB_CACHE_SIZE, sizeof(struct vhost_iotlb_entry), 0,
			0, 0, NULL, NULL, NULL, socket,
			MEMPOOL_F_NO_CACHE_ALIGN |
			MEMPOOL_F_SP_PUT |
			MEMPOOL_F_SC_GET);
	if (!vq->iotlb_pool) {
		RTE_LOG(ERR, VHOST_CONFIG,
				"Failed to create IOTLB cache pool (%s)\n",
				pool_name);
		return -1;
	}

	vq->iotlb_cache_nr = 0;

	return 0;
}