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
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
|
/*
* Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
* Copyright (c) 2006, 2007 Cisco Systems, Inc. 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/mm.h>
#include <linux/scatterlist.h>
#include <linux/slab.h>
#include <linux/mlx4/cmd.h>
#include "mlx4.h"
#include "icm.h"
#include "fw.h"
/*
* We allocate in as big chunks as we can, up to a maximum of 256 KB
* per chunk. Note that the chunks are not necessarily in contiguous
* physical memory.
*/
enum {
MLX4_ICM_ALLOC_SIZE = 1 << 18,
MLX4_TABLE_CHUNK_SIZE = 1 << 18,
};
static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
{
int i;
if (chunk->nsg > 0)
pci_unmap_sg(dev->persist->pdev, chunk->mem, chunk->npages,
PCI_DMA_BIDIRECTIONAL);
for (i = 0; i < chunk->npages; ++i)
__free_pages(sg_page(&chunk->mem[i]),
get_order(chunk->mem[i].length));
}
static void mlx4_free_icm_coherent(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
{
int i;
for (i = 0; i < chunk->npages; ++i)
dma_free_coherent(&dev->persist->pdev->dev,
chunk->mem[i].length,
lowmem_page_address(sg_page(&chunk->mem[i])),
sg_dma_address(&chunk->mem[i]));
}
void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent)
{
struct mlx4_icm_chunk *chunk, *tmp;
if (!icm)
return;
list_for_each_entry_safe(chunk, tmp, &icm->chunk_list, list) {
if (coherent)
mlx4_free_icm_coherent(dev, chunk);
else
mlx4_free_icm_pages(dev, chunk);
kfree(chunk);
}
kfree(icm);
}
static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order,
gfp_t gfp_mask, int node)
{
struct page *page;
page = alloc_pages_node(node, gfp_mask, order);
if (!page) {
page = alloc_pages(gfp_mask, order);
if (!page)
return -ENOMEM;
}
sg_set_page(mem, page, PAGE_SIZE << order, 0);
return 0;
}
static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem,
int order, gfp_t gfp_mask)
{
void *buf = dma_alloc_coherent(dev, PAGE_SIZE << order,
&sg_dma_address(mem), gfp_mask);
if (!buf)
return -ENOMEM;
if (offset_in_page(buf)) {
dma_free_coherent(dev, PAGE_SIZE << order,
buf, sg_dma_address(mem));
return -ENOMEM;
}
sg_set_buf(mem, buf, PAGE_SIZE << order);
sg_dma_len(mem) = PAGE_SIZE << order;
return 0;
}
struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
gfp_t gfp_mask, int coherent)
{
struct mlx4_icm *icm;
struct mlx4_icm_chunk *chunk = NULL;
int cur_order;
gfp_t mask;
int ret;
/* We use sg_set_buf for coherent allocs, which assumes low memory */
BUG_ON(coherent && (gfp_mask & __GFP_HIGHMEM));
icm = kmalloc_node(sizeof(*icm),
gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN),
dev->numa_node);
if (!icm) {
icm = kmalloc(sizeof(*icm),
gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
if (!icm)
return NULL;
}
icm->refcount = 0;
INIT_LIST_HEAD(&icm->chunk_list);
cur_order = get_order(MLX4_ICM_ALLOC_SIZE);
while (npages > 0) {
if (!chunk) {
chunk = kmalloc_node(sizeof(*chunk),
gfp_mask & ~(__GFP_HIGHMEM |
__GFP_NOWARN),
dev->numa_node);
if (!chunk) {
chunk = kmalloc(sizeof(*chunk),
gfp_mask & ~(__GFP_HIGHMEM |
__GFP_NOWARN));
if (!chunk)
goto fail;
}
sg_init_table(chunk->mem, MLX4_ICM_CHUNK_LEN);
chunk->npages = 0;
chunk->nsg = 0;
list_add_tail(&chunk->list, &icm->chunk_list);
}
while (1 << cur_order > npages)
--cur_order;
mask = gfp_mask;
if (cur_order)
mask &= ~__GFP_DIRECT_RECLAIM;
if (coherent)
ret = mlx4_alloc_icm_coherent(&dev->persist->pdev->dev,
&chunk->mem[chunk->npages],
cur_order, mask);
else
ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages],
cur_order, mask,
dev->numa_node);
if (ret) {
if (--cur_order < 0)
goto fail;
else
continue;
}
++chunk->npages;
if (coherent)
++chunk->nsg;
else if (chunk->npages == MLX4_ICM_CHUNK_LEN) {
chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
chunk->npages,
PCI_DMA_BIDIRECTIONAL);
if (chunk->nsg <= 0)
goto fail;
}
if (chunk->npages == MLX4_ICM_CHUNK_LEN)
chunk = NULL;
npages -= 1 << cur_order;
}
if (!coherent && chunk) {
chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
chunk->npages,
PCI_DMA_BIDIRECTIONAL);
if (chunk->nsg <= 0)
goto fail;
}
return icm;
fail:
mlx4_free_icm(dev, icm, coherent);
return NULL;
}
static int mlx4_MAP_ICM(struct mlx4_dev *dev, struct mlx4_icm *icm, u64 virt)
{
return mlx4_map_cmd(dev, MLX4_CMD_MAP_ICM, icm, virt);
}
static int mlx4_UNMAP_ICM(struct mlx4_dev *dev, u64 virt, u32 page_count)
{
return mlx4_cmd(dev, virt, page_count, 0, MLX4_CMD_UNMAP_ICM,
MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}
int mlx4_MAP_ICM_AUX(struct mlx4_dev *dev, struct mlx4_icm *icm)
{
return mlx4_map_cmd(dev, MLX4_CMD_MAP_ICM_AUX, icm, -1);
}
int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev)
{
return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_ICM_AUX,
MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}
int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj)
{
u32 i = (obj & (table->num_obj - 1)) /
(MLX4_TABLE_CHUNK_SIZE / table->obj_size);
int ret = 0;
mutex_lock(&table->mutex);
if (table->icm[i]) {
++table->icm[i]->refcount;
goto out;
}
table->icm[i] = mlx4_alloc_icm(dev, MLX4_TABLE_CHUNK_SIZE >> PAGE_SHIFT,
(table->lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
__GFP_NOWARN, table->coherent);
if (!table->icm[i]) {
ret = -ENOMEM;
goto out;
}
if (mlx4_MAP_ICM(dev, table->icm[i], table->virt +
(u64) i * MLX4_TABLE_CHUNK_SIZE)) {
mlx4_free_icm(dev, table->icm[i], table->coherent);
table->icm[i] = NULL;
ret = -ENOMEM;
goto out;
}
++table->icm[i]->refcount;
out:
mutex_unlock(&table->mutex);
return ret;
}
void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, u32 obj)
{
u32 i;
u64 offset;
i = (obj & (table->num_obj - 1)) / (MLX4_TABLE_CHUNK_SIZE / table->obj_size);
mutex_lock(&table->mutex);
if (--table->icm[i]->refcount == 0) {
offset = (u64) i * MLX4_TABLE_CHUNK_SIZE;
mlx4_UNMAP_ICM(dev, table->virt + offset,
MLX4_TABLE_CHUNK_SIZE / MLX4_ICM_PAGE_SIZE);
mlx4_free_icm(dev, table->icm[i], table->coherent);
table->icm[i] = NULL;
}
mutex_unlock(&table->mutex);
}
void *mlx4_table_find(struct mlx4_icm_table *table, u32 obj,
dma_addr_t *dma_handle)
{
int offset, dma_offset, i;
u64 idx;
struct mlx4_icm_chunk *chunk;
struct mlx4_icm *icm;
struct page *page = NULL;
if (!table->lowmem)
return NULL;
mutex_lock(&table->mutex);
idx = (u64) (obj & (table->num_obj - 1)) * table->obj_size;
icm = table->icm[idx / MLX4_TABLE_CHUNK_SIZE];
dma_offset = offset = idx % MLX4_TABLE_CHUNK_SIZE;
if (!icm)
goto out;
list_for_each_entry(chunk, &icm->chunk_list, list) {
for (i = 0; i < chunk->npages; ++i) {
if (dma_handle && dma_offset >= 0) {
if (sg_dma_len(&chunk->mem[i]) > dma_offset)
*dma_handle = sg_dma_address(&chunk->mem[i]) +
dma_offset;
dma_offset -= sg_dma_len(&chunk->mem[i]);
}
/*
* DMA mapping can merge pages but not split them,
* so if we found the page, dma_handle has already
* been assigned to.
*/
if (chunk->mem[i].length > offset) {
page = sg_page(&chunk->mem[i]);
goto out;
}
offset -= chunk->mem[i].length;
}
}
out:
mutex_unlock(&table->mutex);
return page ? lowmem_page_address(page) + offset : NULL;
}
int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
u32 start, u32 end)
{
int inc = MLX4_TABLE_CHUNK_SIZE / table->obj_size;
int err;
u32 i;
for (i = start; i <= end; i += inc) {
err = mlx4_table_get(dev, table, i);
if (err)
goto fail;
}
return 0;
fail:
while (i > start) {
i -= inc;
mlx4_table_put(dev, table, i);
}
return err;
}
void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
u32 start, u32 end)
{
u32 i;
for (i = start; i <= end; i += MLX4_TABLE_CHUNK_SIZE / table->obj_size)
mlx4_table_put(dev, table, i);
}
int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
u64 virt, int obj_size, u32 nobj, int reserved,
int use_lowmem, int use_coherent)
{
int obj_per_chunk;
int num_icm;
unsigned chunk_size;
int i;
u64 size;
obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size;
if (WARN_ON(!obj_per_chunk))
return -EINVAL;
num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk;
table->icm = kvzalloc(num_icm * sizeof(*table->icm), GFP_KERNEL);
if (!table->icm)
return -ENOMEM;
table->virt = virt;
table->num_icm = num_icm;
table->num_obj = nobj;
table->obj_size = obj_size;
table->lowmem = use_lowmem;
table->coherent = use_coherent;
mutex_init(&table->mutex);
size = (u64) nobj * obj_size;
for (i = 0; i * MLX4_TABLE_CHUNK_SIZE < reserved * obj_size; ++i) {
chunk_size = MLX4_TABLE_CHUNK_SIZE;
if ((i + 1) * MLX4_TABLE_CHUNK_SIZE > size)
chunk_size = PAGE_ALIGN(size -
i * MLX4_TABLE_CHUNK_SIZE);
table->icm[i] = mlx4_alloc_icm(dev, chunk_size >> PAGE_SHIFT,
(use_lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
__GFP_NOWARN, use_coherent);
if (!table->icm[i])
goto err;
if (mlx4_MAP_ICM(dev, table->icm[i], virt + i * MLX4_TABLE_CHUNK_SIZE)) {
mlx4_free_icm(dev, table->icm[i], use_coherent);
table->icm[i] = NULL;
goto err;
}
/*
* Add a reference to this ICM chunk so that it never
* gets freed (since it contains reserved firmware objects).
*/
++table->icm[i]->refcount;
}
return 0;
err:
for (i = 0; i < num_icm; ++i)
if (table->icm[i]) {
mlx4_UNMAP_ICM(dev, virt + i * MLX4_TABLE_CHUNK_SIZE,
MLX4_TABLE_CHUNK_SIZE / MLX4_ICM_PAGE_SIZE);
mlx4_free_icm(dev, table->icm[i], use_coherent);
}
kvfree(table->icm);
return -ENOMEM;
}
void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table)
{
int i;
for (i = 0; i < table->num_icm; ++i)
if (table->icm[i]) {
mlx4_UNMAP_ICM(dev, table->virt + i * MLX4_TABLE_CHUNK_SIZE,
MLX4_TABLE_CHUNK_SIZE / MLX4_ICM_PAGE_SIZE);
mlx4_free_icm(dev, table->icm[i], table->coherent);
}
kvfree(table->icm);
}
|