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
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
|
/* SPDX-License-Identifier: GPL-2.0
*
* page_pool.c
* Author: Jesper Dangaard Brouer <netoptimizer@brouer.com>
* Copyright (C) 2016 Red Hat, Inc.
*/
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/device.h>
#include <net/page_pool.h>
#include <linux/dma-direction.h>
#include <linux/dma-mapping.h>
#include <linux/page-flags.h>
#include <linux/mm.h> /* for __put_page() */
#include <trace/events/page_pool.h>
#define DEFER_TIME (msecs_to_jiffies(1000))
#define DEFER_WARN_INTERVAL (60 * HZ)
static int page_pool_init(struct page_pool *pool,
const struct page_pool_params *params)
{
unsigned int ring_qsize = 1024; /* Default */
memcpy(&pool->p, params, sizeof(pool->p));
/* Validate only known flags were used */
if (pool->p.flags & ~(PP_FLAG_ALL))
return -EINVAL;
if (pool->p.pool_size)
ring_qsize = pool->p.pool_size;
/* Sanity limit mem that can be pinned down */
if (ring_qsize > 32768)
return -E2BIG;
/* DMA direction is either DMA_FROM_DEVICE or DMA_BIDIRECTIONAL.
* DMA_BIDIRECTIONAL is for allowing page used for DMA sending,
* which is the XDP_TX use-case.
*/
if ((pool->p.dma_dir != DMA_FROM_DEVICE) &&
(pool->p.dma_dir != DMA_BIDIRECTIONAL))
return -EINVAL;
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) {
/* In order to request DMA-sync-for-device the page
* needs to be mapped
*/
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
return -EINVAL;
if (!pool->p.max_len)
return -EINVAL;
/* pool->p.offset has to be set according to the address
* offset used by the DMA engine to start copying rx data
*/
}
if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0)
return -ENOMEM;
atomic_set(&pool->pages_state_release_cnt, 0);
/* Driver calling page_pool_create() also call page_pool_destroy() */
refcount_set(&pool->user_cnt, 1);
if (pool->p.flags & PP_FLAG_DMA_MAP)
get_device(pool->p.dev);
return 0;
}
struct page_pool *page_pool_create(const struct page_pool_params *params)
{
struct page_pool *pool;
int err;
pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, params->nid);
if (!pool)
return ERR_PTR(-ENOMEM);
err = page_pool_init(pool, params);
if (err < 0) {
pr_warn("%s() gave up with errno %d\n", __func__, err);
kfree(pool);
return ERR_PTR(err);
}
return pool;
}
EXPORT_SYMBOL(page_pool_create);
/* fast path */
static struct page *__page_pool_get_cached(struct page_pool *pool)
{
struct ptr_ring *r = &pool->ring;
bool refill = false;
struct page *page;
/* Test for safe-context, caller should provide this guarantee */
if (likely(in_serving_softirq())) {
if (likely(pool->alloc.count)) {
/* Fast-path */
page = pool->alloc.cache[--pool->alloc.count];
return page;
}
refill = true;
}
/* Quicker fallback, avoid locks when ring is empty */
if (__ptr_ring_empty(r))
return NULL;
/* Slow-path: Get page from locked ring queue,
* refill alloc array if requested.
*/
spin_lock(&r->consumer_lock);
page = __ptr_ring_consume(r);
if (refill)
pool->alloc.count = __ptr_ring_consume_batched(r,
pool->alloc.cache,
PP_ALLOC_CACHE_REFILL);
spin_unlock(&r->consumer_lock);
return page;
}
static void page_pool_dma_sync_for_device(struct page_pool *pool,
struct page *page,
unsigned int dma_sync_size)
{
dma_sync_size = min(dma_sync_size, pool->p.max_len);
dma_sync_single_range_for_device(pool->p.dev, page->dma_addr,
pool->p.offset, dma_sync_size,
pool->p.dma_dir);
}
/* slow path */
noinline
static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool,
gfp_t _gfp)
{
struct page *page;
gfp_t gfp = _gfp;
dma_addr_t dma;
/* We could always set __GFP_COMP, and avoid this branch, as
* prep_new_page() can handle order-0 with __GFP_COMP.
*/
if (pool->p.order)
gfp |= __GFP_COMP;
/* FUTURE development:
*
* Current slow-path essentially falls back to single page
* allocations, which doesn't improve performance. This code
* need bulk allocation support from the page allocator code.
*/
/* Cache was empty, do real allocation */
page = alloc_pages_node(pool->p.nid, gfp, pool->p.order);
if (!page)
return NULL;
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
goto skip_dma_map;
/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
* since dma_addr_t can be either 32 or 64 bits and does not always fit
* into page private data (i.e 32bit cpu with 64bit DMA caps)
* This mapping is kept for lifetime of page, until leaving pool.
*/
dma = dma_map_page_attrs(pool->p.dev, page, 0,
(PAGE_SIZE << pool->p.order),
pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC);
if (dma_mapping_error(pool->p.dev, dma)) {
put_page(page);
return NULL;
}
page->dma_addr = dma;
if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
page_pool_dma_sync_for_device(pool, page, pool->p.max_len);
skip_dma_map:
/* Track how many pages are held 'in-flight' */
pool->pages_state_hold_cnt++;
trace_page_pool_state_hold(pool, page, pool->pages_state_hold_cnt);
/* When page just alloc'ed is should/must have refcnt 1. */
return page;
}
/* For using page_pool replace: alloc_pages() API calls, but provide
* synchronization guarantee for allocation side.
*/
struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp)
{
struct page *page;
/* Fast-path: Get a page from cache */
page = __page_pool_get_cached(pool);
if (page)
return page;
/* Slow-path: cache empty, do real allocation */
page = __page_pool_alloc_pages_slow(pool, gfp);
return page;
}
EXPORT_SYMBOL(page_pool_alloc_pages);
/* Calculate distance between two u32 values, valid if distance is below 2^(31)
* https://en.wikipedia.org/wiki/Serial_number_arithmetic#General_Solution
*/
#define _distance(a, b) (s32)((a) - (b))
static s32 page_pool_inflight(struct page_pool *pool)
{
u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
s32 inflight;
inflight = _distance(hold_cnt, release_cnt);
trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
return inflight;
}
/* Cleanup page_pool state from page */
static void __page_pool_clean_page(struct page_pool *pool,
struct page *page)
{
dma_addr_t dma;
int count;
if (!(pool->p.flags & PP_FLAG_DMA_MAP))
goto skip_dma_unmap;
dma = page->dma_addr;
/* DMA unmap */
dma_unmap_page_attrs(pool->p.dev, dma,
PAGE_SIZE << pool->p.order, pool->p.dma_dir,
DMA_ATTR_SKIP_CPU_SYNC);
page->dma_addr = 0;
skip_dma_unmap:
/* This may be the last page returned, releasing the pool, so
* it is not safe to reference pool afterwards.
*/
count = atomic_inc_return(&pool->pages_state_release_cnt);
trace_page_pool_state_release(pool, page, count);
}
/* unmap the page and clean our state */
void page_pool_unmap_page(struct page_pool *pool, struct page *page)
{
/* When page is unmapped, this implies page will not be
* returned to page_pool.
*/
__page_pool_clean_page(pool, page);
}
EXPORT_SYMBOL(page_pool_unmap_page);
/* Return a page to the page allocator, cleaning up our state */
static void __page_pool_return_page(struct page_pool *pool, struct page *page)
{
__page_pool_clean_page(pool, page);
put_page(page);
/* An optimization would be to call __free_pages(page, pool->p.order)
* knowing page is not part of page-cache (thus avoiding a
* __page_cache_release() call).
*/
}
static bool __page_pool_recycle_into_
|