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
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
|
/* bpf/cpumap.c
*
* Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
* Released under terms in GPL version 2. See COPYING.
*/
/* The 'cpumap' is primarily used as a backend map for XDP BPF helper
* call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
*
* Unlike devmap which redirects XDP frames out another NIC device,
* this map type redirects raw XDP frames to another CPU. The remote
* CPU will do SKB-allocation and call the normal network stack.
*
* This is a scalability and isolation mechanism, that allow
* separating the early driver network XDP layer, from the rest of the
* netstack, and assigning dedicated CPUs for this stage. This
* basically allows for 10G wirespeed pre-filtering via bpf.
*/
#include <linux/bpf.h>
#include <linux/filter.h>
#include <linux/ptr_ring.h>
#include <net/xdp.h>
#include <linux/sched.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/capability.h>
#include <trace/events/xdp.h>
#include <linux/netdevice.h> /* netif_receive_skb_core */
#include <linux/etherdevice.h> /* eth_type_trans */
/* General idea: XDP packets getting XDP redirected to another CPU,
* will maximum be stored/queued for one driver ->poll() call. It is
* guaranteed that setting flush bit and flush operation happen on
* same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
* which queue in bpf_cpu_map_entry contains packets.
*/
#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */
struct xdp_bulk_queue {
void *q[CPU_MAP_BULK_SIZE];
unsigned int count;
};
/* Struct for every remote "destination" CPU in map */
struct bpf_cpu_map_entry {
u32 cpu; /* kthread CPU and map index */
int map_id; /* Back reference to map */
u32 qsize; /* Queue size placeholder for map lookup */
/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
struct xdp_bulk_queue __percpu *bulkq;
/* Queue with potential multi-producers, and single-consumer kthread */
struct ptr_ring *queue;
struct task_struct *kthread;
struct work_struct kthread_stop_wq;
atomic_t refcnt; /* Control when this struct can be free'ed */
struct rcu_head rcu;
};
struct bpf_cpu_map {
struct bpf_map map;
/* Below members specific for map type */
struct bpf_cpu_map_entry **cpu_map;
unsigned long __percpu *flush_needed;
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
struct xdp_bulk_queue *bq, bool in_napi_ctx);
static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
{
return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
}
static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
{
struct bpf_cpu_map *cmap;
int err = -ENOMEM;
u64 cost;
int ret;
if (!capable(CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
return ERR_PTR(-EINVAL);
cmap = kzalloc(sizeof(*cmap), GFP_USER);
if (!cmap)
return ERR_PTR(-ENOMEM);
bpf_map_init_from_attr(&cmap->map, attr);
/* Pre-limit array size based on NR_CPUS, not final CPU check */
if (cmap->map.max_entries > NR_CPUS) {
err = -E2BIG;
goto free_cmap;
}
/* make sure page count doesn't overflow */
cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
if (cost >= U32_MAX - PAGE_SIZE)
goto free_cmap;
cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
/* Notice returns -EPERM on if map size is larger than memlock limit */
ret = bpf_map_precharge_memlock(cmap->map.pages);
if (ret) {
err = ret;
goto free_cmap;
}
/* A per cpu bitfield with a bit per possible CPU in map */
cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr),
__alignof__(unsigned long));
if (!cmap->flush_needed)
goto free_cmap;
/* Alloc array for possible remote "destination" CPUs */
cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
sizeof(struct bpf_cpu_map_entry *),
cmap->map.numa_node);
if (!cmap->cpu_map)
goto free_percpu;
return &cmap->map;
free_percpu:
free_percpu(cmap->flush_needed);
free_cmap:
kfree(cmap);
return ERR_PTR(err);
}
static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
{
atomic_inc(&rcpu->refcnt);
}
/* called from workqueue, to workaround syscall using preempt_disable */
static void cpu_map_kthread_stop(struct work_struct *work)
{
struct bpf_cpu_map_entry *rcpu;
rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
* as it waits until all in-flight call_rcu() callbacks complete.
*/
rcu_barrier();
/* kthread_stop will wake_up_process and wait for it to complete */
kthread_stop(rcpu->kthread);
}
static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
struct xdp_frame *xdpf)
{
unsigned int frame_size;
void *pkt_data_start;
struct sk_buff *skb;
/* build_skb need to place skb_shared_info after SKB end, and
* also want to know the memory "truesize". Thus, need to
* know the memory frame size backing xdp_buff.
*
* XDP was designed to have PAGE_SIZE frames, but this
* assumption is not longer true with ixgbe and i40e. It
* would be preferred to set frame_size to 2048 or 4096
* depending on the driver.
* frame_size = 2048;
* frame_len = frame_size - sizeof(*xdp_frame);
*
* Instead, with info avail, skb_shared_info in placed after
* packet len. This, unfortunately fakes the truesize.
* Another disadvantage of this approach, the skb_shared_info
* is not at a fixed memory location, with mixed length
* packets, which is bad for cache-line hotness.
*/
frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
pkt_data_start = xdpf->data - xdpf->headroom;
skb = build_skb(pkt_data_start, frame_size);
if (!skb)
return NULL;
skb_reserve(skb, xdpf->headroom);
__skb_put(skb, xdpf->len);
if (xdpf->metasize)
skb_metadata_set(skb, xdpf->metasize);
/* Essential SKB info: protocol and skb->dev */
skb->protocol = eth_type_trans(skb, xdpf->dev_rx);
/* Optional SKB info, currently missing:
* - HW checksum info (skb->ip_summed)
* - HW RX hash (skb_set_hash)
* - RX ring dev queue index (skb_record_rx_queue)
*/
return skb;
}
static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
{
/* The tear-down procedure should have made sure that queue is
* empty. See __cpu_map_entry_replace() and work-queue
* invoked cpu_map_kthread_stop(). Catch any broken behaviour
* gracefully and warn once.
*/
struct xdp_frame *xdpf;
while ((xdpf = ptr_ring_consume(ring)))
if (WARN_ON_ONCE(xdpf))
xdp_return_frame(xdpf);
}
static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
{
if (atomic_dec_and_test(&rcpu->refcnt)) {
/* The queue should be empty at this point */
__cpu_map_ring_cleanup(rcpu->queue);
ptr_ring_cleanup(rcpu->queue, NULL);
kfree(rcpu->queue);
kfree(rcpu);
}
}
static int cpu_map_kthread_run(void *data)
{
struct bpf_cpu_map_entry *rcpu = data;
set_current_state(TASK_INTERRUPTIBLE);
/* When kthread gives stop order, then rcpu have been disconnected
* from map, thus no new packets can enter. Remaining in-flight
* per CPU stored packets are flushed to this queue. Wait honoring
* kthread_stop signal until queue is empty.
*/
while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue))
|