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
|
/*
* Copyright (c) 2013-2015, 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.
*/
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/bitmap.h>
#include <linux/dma-mapping.h>
#include <linux/vmalloc.h>
#include <linux/mlx5/driver.h>
#include "mlx5_core.h"
struct mlx5_db_pgdir {
struct list_head list;
unsigned long *bitmap;
__be32 *db_page;
dma_addr_t db_dma;
};
/* Handling for queue buffers -- we allocate a bunch of memory and
* register it in a memory region at HCA virtual address 0.
*/
static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev,
size_t size, dma_addr_t *dma_handle,
int node)
{
struct mlx5_priv *priv = &dev->priv;
struct device *device = dev->device;
int original_node;
void *cpu_handle;
mutex_lock(&priv->alloc_mutex);
original_node = dev_to_node(device);
set_dev_node(device, node);
cpu_handle = dma_alloc_coherent(device, size, dma_handle,
GFP_KERNEL);
set_dev_node(device, original_node);
mutex_unlock(&priv->alloc_mutex);
return cpu_handle;
}
int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size,
struct mlx5_frag_buf *buf, int node)
{
dma_addr_t t;
buf->size = size;
buf->npages = 1;
buf->page_shift = (u8)get_order(size) + PAGE_SHIFT;
buf->frags = kzalloc(sizeof(*buf->frags), GFP_KERNEL);
if (!buf->frags)
return -ENOMEM;
buf->frags->buf = mlx5_dma_zalloc_coherent_node(dev, size,
&t, node);
if (!buf->frags->buf)
goto err_out;
buf->frags->map = t;
while (t & ((1 << buf->page_shift) - 1)) {
--buf->page_shift;
buf->npages *= 2;
}
return 0;
err_out:
kfree(buf->frags);
return -ENOMEM;
}
int mlx5_buf_alloc(struct mlx5_core_dev *dev,
int size, struct mlx5_frag_buf *buf)
{
return mlx5_buf_alloc_node(dev, size, buf, dev->priv.numa_node);
}
EXPORT_SYMBOL(mlx5_buf_alloc);
void mlx5_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
{
dma_free_coherent(dev->device, buf->size, buf->frags->buf,
buf->frags->map);
kfree(buf->frags);
}
EXPORT_SYMBOL_GPL(mlx5_buf_free);
int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
struct mlx5_frag_buf *buf, int node)
{
int i;
buf->size = size;
buf->npages = DIV_ROUND_UP(size, PAGE_SIZE);
buf->page_shift = PAGE_SHIFT;
buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list),
GFP_KERNEL);
if (!buf->frags)
goto err_out;
for (i = 0; i < buf->npages; i++) {
struct mlx5_buf_list *frag = &buf->frags[i];
int frag_sz = min_t(int, size, PAGE_SIZE);
frag->buf = mlx5_dma_zalloc_coherent_node(dev, frag_sz,
&frag->map, node);
if (!frag->buf)
goto err_free_buf;
if (frag->map & ((1 << buf->page_shift) - 1)) {
dma_free_coherent(dev->device, frag_sz,
buf->frags[i].buf, buf->frags[i].map);
mlx5_core_warn(dev, "unexpected map alignment: %pad, page_shift=%d\n",
&frag->map, buf->page_shift);
goto err_free_buf;
}
size -= frag_sz;
}
return 0;
err_free_buf:
while (i--)
dma_free_coherent(dev->device, PAGE_SIZE, buf->frags[i].buf,
buf->frags[i].map);
kfree(buf->frags);
err_out:
return -ENOMEM;
}
EXPORT_SYMBOL_GPL(mlx5_frag_buf_alloc_node);
void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf)
{
int size = buf->size;
int i;
for (i = 0; i < buf->npages; i++) {
int frag_sz = min_t(int, size, PAGE_SIZE);
dma_free_coherent(dev->device, frag_sz, buf->frags[i].buf,
buf->frags[i].map);
size -= frag_sz;
}
kfree(buf->frags);
}
EXPORT_SYMBOL_GPL(mlx5_frag_buf_free);
static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
int node)
{
u32 db_per_page = PAGE_SIZE / cache_line_size();
struct mlx5_db_pgdir *pgdir;
pgdir = kzalloc(sizeof(*pgdir), GFP_KERNEL);
if (!pgdir)
return NULL;
pgdir->bitmap = bitmap_zalloc(db_per_page, GFP_KERNEL);
if (!pgdir->bitmap) {
kfree(pgdir);
return NULL;
}
bitmap_fill(pgdir->bitmap, db_per_page);
pgdir->db_page = mlx5_dma_zalloc_coherent_node(dev, PAGE_SIZE,
&pgdir->db_dma, node);
if (!pgdir->db_page) {
bitmap_free(pgdir->bitmap);
kfree(pgdir);
return NULL;
}
return pgdir;
}
static int mlx5_alloc_db_from_pgdir(struct mlx5_db_pgdir *pgdir,
struct mlx5_db *db)
{
u32 db_per_page = PAGE_SIZE / cache_line_size();
int offset;
int i;
i = find_first_bit(pgdir->bitmap, db_per_page);
if (i >= db_per_page)
return -ENOMEM;
__clear_bit(i, pgdir->bitmap);
db->u.pgdir = pgdir;
db->index = i;
offset = db->index * cache_line_size();
db->db = pgdir->db_page + offset / sizeof(*pgdir->db_page);
db->dma = pgdir->db_dma + offset;
db->db[0] = 0;
db->db[1] = 0;
return 0;
}
int mlx5_db_alloc_node(struct mlx5_core_dev *dev, struct mlx5_db *db, int node)
{
struct mlx5_db_pgdir *pgdir;
int ret = 0;
mutex_lock(&dev->priv.pgdir_mutex);
list_for_each_entry(pgdir, &dev->priv.pgdir_list, list)
if (!mlx5_alloc_db_from_pgdir(pgdir, db))
goto out;
pgdir = mlx5_alloc_db_pgdir(dev, node);
if (!pgdir) {
ret = -ENOMEM;
goto out;
}
list_add(&pgdir->list, &dev->priv.pgdir_list);
/* This should never fail -- we just allocated an empty page: */
WARN_ON(mlx5_alloc_db_from_pgdir(pgdir, db));
out:
mutex_unlock(&dev->priv.pgdir_mutex);
return ret;
}
EXPORT_SYMBOL_GPL(mlx5_db_alloc_node);
int mlx5_db_alloc(struct mlx5_core_dev *dev, struct mlx5_db *db)
{
return mlx5_db_alloc_node(dev, db, dev->priv.numa_node);
}
EXPORT_SYMBOL_GPL(mlx5_db_alloc);
void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
{
u32 db_per_page = PAGE_SIZE / cache_line_size();
mutex_lock(&dev->priv.pgdir_mutex);
__set_bit(db->index,
|