summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/core/uverbs_mem.c
blob: db12cc0841df251273e62fed86966cd9e60b08e6 (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
/*
 * Copyright (c) 2005 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005 Cisco Systems.  All rights reserved.
 * Copyright (c) 2005 Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     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.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 * $Id: uverbs_mem.c 2743 2005-06-28 22:27:59Z roland $
 */

#include <linux/mm.h>
#include <linux/dma-mapping.h>

#include "uverbs.h"

struct ib_umem_account_work {
	struct work_struct work;
	struct mm_struct  *mm;
	unsigned long      diff;
};


static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)
{
	struct ib_umem_chunk *chunk, *tmp;
	int i;

	list_for_each_entry_safe(chunk, tmp, &umem->chunk_list, list) {
		dma_unmap_sg(dev->dma_device, chunk->page_list,
			     chunk->nents, DMA_BIDIRECTIONAL);
		for (i = 0; i < chunk->nents; ++i) {
			if (umem->writable && dirty)
				set_page_dirty_lock(chunk->page_list[i].page);
			put_page(chunk->page_list[i].page);
		}

		kfree(chunk);
	}
}

int ib_umem_get(struct ib_device *dev, struct ib_umem *mem,
		void *addr, size_t size, int write)
{
	struct page **page_list;
	struct ib_umem_chunk *chunk;
	unsigned long locked;
	unsigned long lock_limit;
	unsigned long cur_base;
	unsigned long npages;
	int ret = 0;
	int off;
	int i;

	if (!can_do_mlock())
		return -EPERM;

	page_list = (struct page **) __get_free_page(GFP_KERNEL);
	if (!page_list)
		return -ENOMEM;

	mem->user_base = (unsigned long) addr;
	mem->length    = size;
	mem->offset    = (unsigned long) addr & ~PAGE_MASK;
	mem->page_size = PAGE_SIZE;
	mem->writable  = write;

	INIT_LIST_HEAD(&mem->chunk_list);

	npages = PAGE_ALIGN(size + mem->offset) >> PAGE_SHIFT;

	down_write(&current->mm->mmap_sem);

	locked     = npages + current->mm->locked_vm;
	lock_limit = current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur >> PAGE_SHIFT;

	if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
		ret = -ENOMEM;
		goto out;
	}

	cur_base = (unsigned long) addr & PAGE_MASK;

	while (npages) {
		ret = get_user_pages(current, current->mm, cur_base,
				     min_t(int, npages,
					   PAGE_SIZE / sizeof (struct page *)),
				     1, !write, page_list, NULL);

		if (ret < 0)
			goto out;

		cur_base += ret * PAGE_SIZE;
		npages   -= ret;

		off = 0;

		while (ret) {
			chunk = kmalloc(sizeof *chunk + sizeof (struct scatterlist) *
					min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK),
					GFP_KERNEL);
			if (!chunk) {
				ret = -ENOMEM;
				goto out;
			}

			chunk->nents = min_t(int, ret, IB_UMEM_MAX_PAGE_CHUNK);
			for (i = 0; i < chunk->nents; ++i) {
				chunk->page_list[i].page   = page_list[i + off];
				chunk->page_list[i].offset = 0;
				chunk->page_list[i].length = PAGE_SIZE;
			}

			chunk->nmap = dma_map_sg(dev->dma_device,
						 &chunk->page_list[0],
						 chunk->nents,
						 DMA_BIDIRECTIONAL);
			if (chunk->nmap <= 0) {
				for (i = 0; i < chunk->nents; ++i)
					put_page(chunk->page_list[i].page);
				kfree(chunk);

				ret = -ENOMEM;
				goto out;
			}

			ret -= chunk->nents;
			off += chunk->nents;
			list_add_tail(&chunk->list, &mem->chunk_list);
		}

		ret = 0;
	}

out:
	if (ret < 0)
		__ib_umem_release(dev, mem, 0);
	else
		current->mm->locked_vm = locked;

	up_write(&current->mm->mmap_sem);
	free_page((unsigned long) page_list);

	return ret;
}

void ib_umem_release(struct ib_device *dev, struct ib_umem *umem)
{
	__ib_umem_release(dev, umem, 1);

	down_write(&current->mm->mmap_sem);
	current->mm->locked_vm -=
		PAGE_ALIGN(umem->length + umem->offset) >> PAGE_SHIFT;
	up_write(&current->mm->mmap_sem);
}

static void ib_umem_account(struct work_struct *_work)
{
	struct ib_umem_account_work *work =
		container_of(_work, struct ib_umem_account_work, work);

	down_write(&work->mm->mmap_sem);
	work->mm->locked_vm -= work->diff;
	up_write(&work->mm->mmap_sem);
	mmput(work->mm);
	kfree(work);
}

void ib_umem_release_on_close(struct ib_device *dev, struct ib_umem *umem)
{
	struct ib_umem_account_work *work;
	struct mm_struct *mm;

	__ib_umem_release(dev, umem, 1);

	mm = get_task_mm(current);
	if (!mm)
		return;

	/*
	 * We may be called with the mm's mmap_sem already held.  This
	 * can happen when a userspace munmap() is the call that drops
	 * the last reference to our file and calls our release
	 * method.  If there are memory regions to destroy, we'll end
	 * up here and not be able to take the mmap_sem.  Therefore we
	 * defer the vm_locked accounting to the system workqueue.
	 */

	work = kmalloc(sizeof *work, GFP_KERNEL);
	if (!work) {
		mmput(mm);
		return;
	}

	INIT_WORK(&work->work, ib_umem_account);
	work->mm   = mm;
	work->diff = PAGE_ALIGN(umem->length + umem->offset) >> PAGE_SHIFT;

	schedule_work(&work->work);
}