summaryrefslogtreecommitdiff
path: root/kernel/bpf/cpumap.c
blob: 480e936c54d0f996a7ffa93837fbc761aebea005 (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
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
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
// SPDX-License-Identifier: GPL-2.0-only
/* bpf/cpumap.c
 *
 * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
 */

/* 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_list */
#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 queueing the frame and the 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 bpf_cpu_map_entry;
struct bpf_cpu_map;

struct xdp_bulk_queue {
	void *q[CPU_MAP_BULK_SIZE];
	struct list_head flush_node;
	struct bpf_cpu_map_entry *obj;
	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 */

	/* XDP can run multiple RX-ring queues, need __percpu enqueue store */
	struct xdp_bulk_queue __percpu *bulkq;

	struct bpf_cpu_map *cmap;

	/* Queue with potential multi-producers, and single-consumer kthread */
	struct ptr_ring *queue;
	struct task_struct *kthread;

	struct bpf_cpumap_val value;
	struct bpf_prog *prog;

	atomic_t refcnt; /* Control when this struct can be free'ed */
	struct rcu_head rcu;

	struct work_struct kthread_stop_wq;
};

struct bpf_cpu_map {
	struct bpf_map map;
	/* Below members specific for map type */
	struct bpf_cpu_map_entry __rcu **cpu_map;
};

static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list);

static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
{
	u32 value_size = attr->value_size;
	struct bpf_cpu_map *cmap;
	int err = -ENOMEM;

	if (!bpf_capable())
		return ERR_PTR(-EPERM);

	/* check sanity of attributes */
	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    (value_size != offsetofend(struct bpf_cpumap_val, qsize) &&
	     value_size != offsetofend(struct bpf_cpumap_val, bpf_prog.fd)) ||
	    attr->map_flags & ~BPF_F_NUMA_NODE)
		return ERR_PTR(-EINVAL);

	cmap = kzalloc(sizeof(*cmap), GFP_USER | __GFP_ACCOUNT);
	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;
	}

	/* 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_cmap;

	return &cmap->map;
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 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)) {
		if (rcpu->prog)
			bpf_prog_put(rcpu->prog);
		/* 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_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
				    void **frames, int n,
				    struct xdp_cpumap_stats *stats)
{
	struct xdp_rxq_info rxq;
	struct xdp_buff xdp;
	int i, nframes = 0;

	if (!rcpu->prog)
		return n;

	rcu_read_lock_bh();

	xdp_set_return_frame_no_direct();
	xdp.rxq = &rxq;

	for (i = 0; i < n; i++) {
		struct xdp_frame *xdpf = frames[i];
		u32 act;
		int err;

		rxq.dev = xdpf->dev_rx;
		rxq.mem = xdpf->mem;
		/* TODO: report queue_index to xdp_rxq_info */

		xdp_convert_frame_to_buff(xdpf, &xdp);

		act = bpf_prog_run_xdp(rcpu->prog, &xdp);
		switch (act) {
		case XDP_PASS:
			err = xdp_update_frame_from_buff(&xdp, xdpf);
			if (err < 0) {
				xdp_return_frame(xdpf);
				stats->drop++;
			} else {
				frames[nframes++] = xdpf;
				stats->pass++;
			}
			break;
		case XDP_REDIRECT:
			err = xdp_do_redirect(xdpf->dev_rx, &xdp,
					      rcpu->prog);
			if (unlikely(err)) {
				xdp_return_frame(xdpf);
				stats->drop++;
			} else {
				stats->redirect++;
			}
			break;
		default:
			bpf_warn_invalid_xdp_action(act);
			fallthrough;
		case XDP_DROP:
			xdp_return_frame(xdpf);
			stats->drop++;
			break;
		}
	}

	if (stats->redirect)
		xdp_do_flush_map();

	xdp_clear_return_frame_no_direct();

	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */

	return nframes;
}

#define CPUMAP_BATCH 8

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)) {
		struct xdp_cpumap_stats stats = {}; /* zero stats */
		unsigned int kmem_alloc_drops = 0, sched = 0;
		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
		void *frames[CPUMAP_BATCH];
		void *skbs[CPUMAP_BATCH];
		int i, n, m, nframes;
		LIST_HEAD(list);

		/* Release CPU reschedule checks */
		if (__ptr_ring_empty(rcpu->queue)) {
			set_current_state(TASK_INTERRUPTIBLE);
			/* Recheck to avoid lost wake-up */
			if (__ptr_ring_empty(rcpu->queue)) {
				schedule();
				sched = 1;
			} else {
				__set_current_state(TASK_RUNNING);
			}
		} else {
			sched = cond_resched();
		}

		/*
		 * The bpf_cpu_map_entry is single consumer, with this
		 * kthread CPU pinned. Lockless access to ptr_ring
		 * consume side valid as no-resize allowed of queue.
		 */
		n = __ptr_ring_consume_batched(rcpu->queue, frames,
					       CPUMAP_BATCH);
		for (i = 0; i < n; i++) {
			void *f = frames[i];
			struct page *page = virt_to_page(f);

			/* Bring struct page memory area to curr CPU. Read by
			 * build_skb_around via page_is_pfmemalloc(), and when
			 * freed written by page_frag_free call.
			 */
			prefetchw(page);
		}

		/* Support running another XDP prog on this CPU */
		nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, n, &stats);
		if (nframes) {
			m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs);
			if (unlikely(m == 0)) {
				for (i = 0; i < nframes; i++)
					skbs[i] = NULL; /* effect: xdp_return_frame */
				kmem_alloc_drops += nframes;
			}
		}

		local_bh_disable();
		for (i = 0; i < nframes; i++) {
			struct xdp_frame *xdpf = frames[i];
			struct sk_buff *skb = skbs[i];

			skb = __xdp_build_skb_from_frame(xdpf, skb,
							 xdpf->dev_rx);
			if (!skb) {
				xdp_return_frame(xdpf);
				continue;
			}

			list_add_tail(&skb->list, &list);
		}
		netif_receive_skb_list(&list);

		/* Feedback loop via tracepoint */
		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
					 sched, &stats);

		local_bh_enable(); /* resched point, may call do_softirq() */
	}
	__set_current_state(TASK_RUNNING);

	put_cpu_map_entry(rcpu);
	return 0;
}

bool cpu_map_prog_allowed(struct bpf_map *map)
{
	return map->map_type == BPF_MAP_TYPE_CPUMAP &&
	       map->value_size != offsetofend(struct bpf_cpumap_val, qsize);
}

static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd)
{
	struct bpf_prog *prog;

	prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
	if (IS_ERR(prog))
		return PTR_ERR(prog);

	if (prog->expected_attach_type != BPF_XDP_CPUMAP) {
		bpf_prog_put(prog);
		return -EINVAL;
	}

	rcpu->value.bpf_prog.id = prog->aux->id;
	rcpu->prog = prog;

	return 0;
}

static struct bpf_cpu_map_entry *
__cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
		      u32 cpu)
{
	int numa, err, i, fd = value->bpf_prog.fd;
	gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
	struct bpf_cpu_map_entry *rcpu;
	struct xdp_bulk_queue *bq;

	/* Have map->numa_node, but choose node of redirect target CPU */
	numa = cpu_to_node(cpu);

	rcpu = bpf_map_kmalloc_node(map, sizeof(*rcpu), gfp | __GFP_ZERO, numa);
	if (!rcpu)
		return NULL;

	/* Alloc percpu bulkq */
	rcpu->bulkq = bpf_map_alloc_percpu(map, sizeof(*rcpu->bulkq),
					   sizeof(void *), gfp);
	if (!rcpu->bulkq)
		goto free_rcu;

	for_each_possible_cpu(i) {
		bq = per_cpu_ptr(rcpu->bulkq, i);
		bq->obj = rcpu;
	}

	/* Alloc queue */
	rcpu->queue = bpf_map_kmalloc_node(map, sizeof(*rcpu->queue), gfp,
					   numa);
	if (!rcpu->queue)
		goto free_bulkq;

	err = ptr_ring_init(rcpu->queue, value->qsize, gfp);
	if (err)
		goto free_queue;

	rcpu->cpu    = cpu;
	rcpu->map_id = map->id;
	rcpu->value.qsize  = value->qsize;

	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd))
		goto free_ptr_ring;

	/* Setup kthread */
	rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
					       "cpumap/%d/map:%d", cpu,
					       map->id);
	if (IS_ERR(rcpu->kthread))
		goto free_prog;

	get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
	get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */

	/* Make sure kthread runs on a single CPU */
	kthread_bind(rcpu->kthread, cpu);
	wake_up_process(rcpu->kthread);

	return rcpu;

free_prog:
	if (rcpu->prog)
		bpf_prog_put(rcpu->prog);
free_ptr_ring:
	ptr_ring_cleanup(rcpu->queue, NULL);
free_queue:
	kfree(rcpu->queue);
free_bulkq:
	free_percpu(rcpu->bulkq);
free_rcu:
	kfree(rcpu);
	return NULL;
}

static void __cpu_map_entry_free(struct rcu_head *rcu)
{
	struct bpf_cpu_map_entry *rcpu;

	/* This cpu_map_entry have been disconnected from map and one
	 * RCU grace-period have elapsed.  Thus, XDP cannot queue any
	 * new packets and cannot change/set flush_needed that can
	 * find this entry.
	 */
	rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);

	free_percpu(rcpu->bulkq);
	/* Cannot kthread_stop() here, last put free rcpu resources */
	put_cpu_map_entry(rcpu);
}

/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
 * ensure any driver rcu critical sections have completed, but this
 * does not guarantee a flush has happened yet. Because driver side
 * rcu_read_lock/unlock only protects the running XDP program.  The
 * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
 * pending flush op doesn't fail.
 *
 * The bpf_cpu_map_entry is still used by the kthread, and there can
 * still be pending packets (in queue and percpu bulkq).  A refcnt
 * makes sure to last user (kthread_stop vs. call_rcu) free memory
 * resources.
 *
 * The rcu callback __cpu_map_entry_free flush remaining packets in
 * percpu bulkq to queue.  Due to caller map_delete_elem() disable
 * preemption, cannot call kthread_stop() to make sure queue is empty.
 * Instead a work_queue is started for stopping kthread,
 * cpu_map_kthread_stop, which waits for an RCU grace period before
 * stopping kthread, emptying the queue.
 */
static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
				    u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
{
	struct bpf_cpu_map_entry *old_rcpu;

	old_rcpu = unrcu_pointer(xchg(&cmap->cpu_map[key_cpu], RCU_INITIALIZER(rcpu)));
	if (old_rcpu) {
		call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
		INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
		schedule_work(&old_rcpu->kthread_stop_wq);
	}
}

static int cpu_map_delete_elem(struct bpf_map *map, void *key)
{
	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
	u32 key_cpu = *(u32 *)key;

	if (key_cpu >= map->max_entries)
		return -EINVAL;

	/* notice caller map_delete_elem() use preempt_disable() */
	__cpu_map_entry_replace(cmap, key_cpu, NULL);
	return 0;
}

static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
			       u64 map_flags)
{
	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
	struct bpf_cpumap_val cpumap_value = {};
	struct bpf_cpu_map_entry *rcpu;
	/* Array index key correspond to CPU number */
	u32 key_cpu = *(u32 *)key;

	memcpy(&cpumap_value, value, map->value_size);

	if (unlikely(map_flags > BPF_EXIST))
		return -EINVAL;
	if (unlikely(key_cpu >= cmap->map.max_entries))
		return -E2BIG;
	if (unlikely(map_flags == BPF_NOEXIST))
		return -EEXIST;
	if (unlikely(cpumap_value.qsize > 16384)) /* sanity limit on qsize */
		return -EOVERFLOW;

	/* Make sure CPU is a valid possible cpu */
	if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
		return -ENODEV;

	if (cpumap_value.qsize == 0) {
		rcpu = NULL; /* Same as deleting */
	} else {
		/* Updating qsize cause re-allocation of bpf_cpu_map_entry */
		rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu);
		if (!rcpu)
			return -ENOMEM;
		rcpu->cmap = cmap;
	}
	rcu_read_lock();
	__cpu_map_entry_replace(cmap, key_cpu, rcpu);
	rcu_read_unlock();
	return 0;
}

static void cpu_map_free(struct bpf_map *map)
{
	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
	u32 i;

	/* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
	 * so the bpf programs (can be more than one that used this map) were
	 * disconnected from events. Wait for outstanding critical sections in
	 * these programs to complete. The rcu critical section only guarantees
	 * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
	 * It does __not__ ensure pending flush operations (if any) are
	 * complete.
	 */

	synchronize_rcu();

	/* For cpu_map the remote CPUs can still be using the entries
	 * (struct bpf_cpu_map_entry).
	 */
	for (i = 0; i < cmap->map.max_entries; i++) {
		struct bpf_cpu_map_entry *rcpu;

		rcpu = rcu_dereference_raw(cmap->cpu_map[i]);
		if (!rcpu)
			continue;

		/* bq flush and cleanup happens after RCU grace-period */
		__cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
	}
	bpf_map_area_free(cmap->cpu_map);
	kfree(cmap);
}

/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or
 * by local_bh_disable() (from XDP calls inside NAPI). The
 * rcu_read_lock_bh_held() below makes lockdep accept both.
 */
static void *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
	struct bpf_cpu_map_entry *rcpu;

	if (key >= map->max_entries)
		return NULL;

	rcpu = rcu_dereference_check(cmap->cpu_map[key],
				     rcu_read_lock_bh_held());
	return rcpu;
}

static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_cpu_map_entry *rcpu =
		__cpu_map_lookup_elem(map, *(u32 *)key);

	return rcpu ? &rcpu->value : NULL;
}

static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
	u32 index = key ? *(u32 *)key : U32_MAX;
	u32 *next = next_key;

	if (index >= cmap->map.max_entries) {
		*next = 0;
		return 0;
	}

	if (index == cmap->map.max_entries - 1)
		return -ENOENT;
	*next = index + 1;
	return 0;
}

static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags)
{
	return __bpf_xdp_redirect_map(map, ifindex, flags, 0,
				      __cpu_map_lookup_elem);
}

static int cpu_map_btf_id;
const struct bpf_map_ops cpu_map_ops = {
	.map_meta_equal		= bpf_map_meta_equal,
	.map_alloc		= cpu_map_alloc,
	.map_free		= cpu_map_free,
	.map_delete_elem	= cpu_map_delete_elem,
	.map_update_elem	= cpu_map_update_elem,
	.map_lookup_elem	= cpu_map_lookup_elem,
	.map_get_next_key	= cpu_map_get_next_key,
	.map_check_btf		= map_check_no_btf,
	.map_btf_name		= "bpf_cpu_map",
	.map_btf_id		= &cpu_map_btf_id,
	.map_redirect		= cpu_map_redirect,
};

static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
{
	struct bpf_cpu_map_entry *rcpu = bq->obj;
	unsigned int processed = 0, drops = 0;
	const int to_cpu = rcpu->cpu;
	struct ptr_ring *q;
	int i;

	if (unlikely(!bq->count))
		return;

	q = rcpu->queue;
	spin_lock(&q->producer_lock);

	for (i = 0; i < bq->count; i++) {
		struct xdp_frame *xdpf = bq->q[i];
		int err;

		err = __ptr_ring_produce(q, xdpf);
		if (err) {
			drops++;
			xdp_return_frame_rx_napi(xdpf);
		}
		processed++;
	}
	bq->count = 0;
	spin_unlock(&q->producer_lock);

	__list_del_clearprev(&bq->flush_node);

	/* Feedback loop via tracepoints */
	trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
}

/* Runs under RCU-read-side, plus in softirq under NAPI protection.
 * Thus, safe percpu variable access.
 */
static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
{
	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);

	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
		bq_flush_to_queue(bq);

	/* Notice, xdp_buff/page MUST be queued here, long enough for
	 * driver to code invoking us to finished, due to driver
	 * (e.g. ixgbe) recycle tricks based on page-refcnt.
	 *
	 * Thus, incoming xdp_frame is always queued here (else we race
	 * with another CPU on page-refcnt and remaining driver code).
	 * Queue time is very short, as driver will invoke flush
	 * operation, when completing napi->poll call.
	 */
	bq->q[bq->count++] = xdpf;

	if (!bq->flush_node.prev)
		list_add(&bq->flush_node, flush_list);
}

int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
		    struct net_device *dev_rx)
{
	struct xdp_frame *xdpf;

	xdpf = xdp_convert_buff_to_frame(xdp);
	if (unlikely(!xdpf))
		return -EOVERFLOW;

	/* Info needed when constructing SKB on remote CPU */
	xdpf->dev_rx = dev_rx;

	bq_enqueue(rcpu, xdpf);
	return 0;
}

void __cpu_map_flush(void)
{
	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
	struct xdp_bulk_queue *bq, *tmp;

	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
		bq_flush_to_queue(bq);

		/* If already running, costs spin_lock_irqsave + smb_mb */
		wake_up_process(bq->obj->kthread);
	}
}

static int __init cpu_map_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu));
	return 0;
}

subsys_initcall(cpu_map_init);