summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/hfi1/mmu_rb.c
blob: e7b3ce123da677b9b4079f0b3123d8692143780a (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
351
352
353
/*
 * Copyright(c) 2016 - 2017 Intel Corporation.
 *
 * This file is provided under a dual BSD/GPLv2 license.  When using or
 * redistributing this file, you may do so under either license.
 *
 * GPL LICENSE SUMMARY
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * BSD LICENSE
 *
 * 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.
 *
 */
#include <linux/list.h>
#include <linux/rculist.h>
#include <linux/mmu_notifier.h>
#include <linux/interval_tree_generic.h>

#include "mmu_rb.h"
#include "trace.h"

struct mmu_rb_handler {
	struct mmu_notifier mn;
	struct rb_root_cached root;
	void *ops_arg;
	spinlock_t lock;        /* protect the RB tree */
	struct mmu_rb_ops *ops;
	struct mm_struct *mm;
	struct list_head lru_list;
	struct work_struct del_work;
	struct list_head del_list;
	struct workqueue_struct *wq;
};

static unsigned long mmu_node_start(struct mmu_rb_node *);
static unsigned long mmu_node_last(struct mmu_rb_node *);
static void mmu_notifier_range_start(struct mmu_notifier *,
				     struct mm_struct *,
				     unsigned long, unsigned long);
static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *,
					   unsigned long, unsigned long);
static void do_remove(struct mmu_rb_handler *handler,
		      struct list_head *del_list);
static void handle_remove(struct work_struct *work);

static const struct mmu_notifier_ops mn_opts = {
	.invalidate_range_start = mmu_notifier_range_start,
};

INTERVAL_TREE_DEFINE(struct mmu_rb_node, node, unsigned long, __last,
		     mmu_node_start, mmu_node_last, static, __mmu_int_rb);

static unsigned long mmu_node_start(struct mmu_rb_node *node)
{
	return node->addr & PAGE_MASK;
}

static unsigned long mmu_node_last(struct mmu_rb_node *node)
{
	return PAGE_ALIGN(node->addr + node->len) - 1;
}

int hfi1_mmu_rb_register(void *ops_arg, struct mm_struct *mm,
			 struct mmu_rb_ops *ops,
			 struct workqueue_struct *wq,
			 struct mmu_rb_handler **handler)
{
	struct mmu_rb_handler *handlr;
	int ret;

	handlr = kmalloc(sizeof(*handlr), GFP_KERNEL);
	if (!handlr)
		return -ENOMEM;

	handlr->root = RB_ROOT_CACHED;
	handlr->ops = ops;
	handlr->ops_arg = ops_arg;
	INIT_HLIST_NODE(&handlr->mn.hlist);
	spin_lock_init(&handlr->lock);
	handlr->mn.ops = &mn_opts;
	handlr->mm = mm;
	INIT_WORK(&handlr->del_work, handle_remove);
	INIT_LIST_HEAD(&handlr->del_list);
	INIT_LIST_HEAD(&handlr->lru_list);
	handlr->wq = wq;

	ret = mmu_notifier_register(&handlr->mn, handlr->mm);
	if (ret) {
		kfree(handlr);
		return ret;
	}

	*handler = handlr;
	return 0;
}

void hfi1_mmu_rb_unregister(struct mmu_rb_handler *handler)
{
	struct mmu_rb_node *rbnode;
	struct rb_node *node;
	unsigned long flags;
	struct list_head del_list;

	/* Unregister first so we don't get any more notifications. */
	mmu_notifier_unregister(&handler->mn, handler->mm);

	/*
	 * Make sure the wq delete handler is finished running.  It will not
	 * be triggered once the mmu notifiers are unregistered above.
	 */
	flush_work(&handler->del_work);

	INIT_LIST_HEAD(&del_list);

	spin_lock_irqsave(&handler->lock, flags);
	while ((node = rb_first_cached(&handler->root))) {
		rbnode = rb_entry(node, struct mmu_rb_node, node);
		rb_erase_cached(node, &handler->root);
		/* move from LRU list to delete list */
		list_move(&rbnode->list, &del_list);
	}
	spin_unlock_irqrestore(&handler->lock, flags);

	do_remove(handler, &del_list);

	kfree(handler);
}

int hfi1_mmu_rb_insert(struct mmu_rb_handler *handler,
		       struct mmu_rb_node *mnode)
{
	struct mmu_rb_node *node;
	unsigned long flags;
	int ret = 0;

	trace_hfi1_mmu_rb_insert(mnode->addr, mnode->len);
	spin_lock_irqsave(&handler->lock, flags);
	node = __mmu_rb_search(handler, mnode->addr, mnode->len);
	if (node) {
		ret = -EINVAL;
		goto unlock;
	}
	__mmu_int_rb_insert(mnode, &handler->root);
	list_add(&mnode->list, &handler->lru_list);

	ret = handler->ops->insert(handler->ops_arg, mnode);
	if (ret) {
		__mmu_int_rb_remove(mnode, &handler->root);
		list_del(&mnode->list); /* remove from LRU list */
	}
unlock:
	spin_unlock_irqrestore(&handler->lock, flags);
	return ret;
}

/* Caller must hold handler lock */
static struct mmu_rb_node *__mmu_rb_search(struct mmu_rb_handler *handler,
					   unsigned long addr,
					   unsigned long len)
{
	struct mmu_rb_node *node = NULL;

	trace_hfi1_mmu_rb_search(addr, len);
	if (!handler->ops->filter) {
		node = __mmu_int_rb_iter_first(&handler->root, addr,
					       (addr + len) - 1);
	} else {
		for (node = __mmu_int_rb_iter_first(&handler->root, addr,
						    (addr + len) - 1);
		     node;
		     node = __mmu_int_rb_iter_next(node, addr,
						   (addr + len) - 1)) {
			if (handler->ops->filter(node, addr, len))
				return node;
		}
	}
	return node;
}

bool hfi1_mmu_rb_remove_unless_exact(struct mmu_rb_handler *handler,
				     unsigned long addr, unsigned long len,
				     struct mmu_rb_node **rb_node)
{
	struct mmu_rb_node *node;
	unsigned long flags;
	bool ret = false;

	spin_lock_irqsave(&handler->lock, flags);
	node = __mmu_rb_search(handler, addr, len);
	if (node) {
		if (node->addr == addr && node->len == len)
			goto unlock;
		__mmu_int_rb_remove(node, &handler->root);
		list_del(&node->list); /* remove from LRU list */
		ret = true;
	}
unlock:
	spin_unlock_irqrestore(&handler->lock, flags);
	*rb_node = node;
	return ret;
}

void hfi1_mmu_rb_evict(struct mmu_rb_handler *handler, void *evict_arg)
{
	struct mmu_rb_node *rbnode, *ptr;
	struct list_head del_list;
	unsigned long flags;
	bool stop = false;

	INIT_LIST_HEAD(&del_list);

	spin_lock_irqsave(&handler->lock, flags);
	list_for_each_entry_safe_reverse(rbnode, ptr, &handler->lru_list,
					 list) {
		if (handler->ops->evict(handler->ops_arg, rbnode, evict_arg,
					&stop)) {
			__mmu_int_rb_remove(rbnode, &handler->root);
			/* move from LRU list to delete list */
			list_move(&rbnode->list, &del_list);
		}
		if (stop)
			break;
	}
	spin_unlock_irqrestore(&handler->lock, flags);

	while (!list_empty(&del_list)) {
		rbnode = list_first_entry(&del_list, struct mmu_rb_node, list);
		list_del(&rbnode->list);
		handler->ops->remove(handler->ops_arg, rbnode);
	}
}

/*
 * It is up to the caller to ensure that this function does not race with the
 * mmu invalidate notifier which may be calling the users remove callback on
 * 'node'.
 */
void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler,
			struct mmu_rb_node *node)
{
	unsigned long flags;

	/* Validity of handler and node pointers has been checked by caller. */
	trace_hfi1_mmu_rb_remove(node->addr, node->len);
	spin_lock_irqsave(&handler->lock, flags);
	__mmu_int_rb_remove(node, &handler->root);
	list_del(&node->list); /* remove from LRU list */
	spin_unlock_irqrestore(&handler->lock, flags);

	handler->ops->remove(handler->ops_arg, node);
}

static void mmu_notifier_range_start(struct mmu_notifier *mn,
				     struct mm_struct *mm,
				     unsigned long start,
				     unsigned long end)
{
	struct mmu_rb_handler *handler =
		container_of(mn, struct mmu_rb_handler, mn);
	struct rb_root_cached *root = &handler->root;
	struct mmu_rb_node *node, *ptr = NULL;
	unsigned long flags;
	bool added = false;

	spin_lock_irqsave(&handler->lock, flags);
	for (node = __mmu_int_rb_iter_first(root, start, end - 1);
	     node; node = ptr) {
		/* Guard against node removal. */
		ptr = __mmu_int_rb_iter_next(node, start, end - 1);
		trace_hfi1_mmu_mem_invalidate(node->addr, node->len);
		if (handler->ops->invalidate(handler->ops_arg, node)) {
			__mmu_int_rb_remove(node, root);
			/* move from LRU list to delete list */
			list_move(&node->list, &handler->del_list);
			added = true;
		}
	}
	spin_unlock_irqrestore(&handler->lock, flags);

	if (added)
		queue_work(handler->wq, &handler->del_work);
}

/*
 * Call the remove function for the given handler and the list.  This
 * is expected to be called with a delete list extracted from handler.
 * The caller should not be holding the handler lock.
 */
static void do_remove(struct mmu_rb_handler *handler,
		      struct list_head *del_list)
{
	struct mmu_rb_node *node;

	while (!list_empty(del_list)) {
		node = list_first_entry(del_list, struct mmu_rb_node, list);
		list_del(&node->list);
		handler->ops->remove(handler->ops_arg, node);
	}
}

/*
 * Work queue function to remove all nodes that have been queued up to
 * be removed.  The key feature is that mm->mmap_sem is not being held
 * and the remove callback can sleep while taking it, if needed.
 */
static void handle_remove(struct work_struct *work)
{
	struct mmu_rb_handler *handler = container_of(work,
						struct mmu_rb_handler,
						del_work);
	struct list_head del_list;
	unsigned long flags;

	/* remove anything that is queued to get removed */
	spin_lock_irqsave(&handler->lock, flags);
	list_replace_init(&handler->del_list, &del_list);
	spin_unlock_irqrestore(&handler->lock, flags);

	do_remove(handler, &del_list);
}