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
|
/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
/* Copyright (C) 2016-2018 Netronome Systems, Inc. */
#ifndef __NFP_BPF_H__
#define __NFP_BPF_H__ 1
#include <linux/bitfield.h>
#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/rhashtable.h>
#include <linux/skbuff.h>
#include <linux/types.h>
#include <linux/wait.h>
#include "../ccm.h"
#include "../nfp_asm.h"
#include "fw.h"
#define cmsg_warn(bpf, msg...) nn_dp_warn(&(bpf)->app->ctrl->dp, msg)
/* For relocation logic use up-most byte of branch instruction as scratch
* area. Remember to clear this before sending instructions to HW!
*/
#define OP_RELO_TYPE 0xff00000000000000ULL
enum nfp_relo_type {
RELO_NONE = 0,
/* standard internal jumps */
RELO_BR_REL,
/* internal jumps to parts of the outro */
RELO_BR_GO_OUT,
RELO_BR_GO_ABORT,
RELO_BR_GO_CALL_PUSH_REGS,
RELO_BR_GO_CALL_POP_REGS,
/* external jumps to fixed addresses */
RELO_BR_NEXT_PKT,
RELO_BR_HELPER,
/* immediate relocation against load address */
RELO_IMMED_REL,
};
/* To make absolute relocated branches (branches other than RELO_BR_REL)
* distinguishable in user space dumps from normal jumps, add a large offset
* to them.
*/
#define BR_OFF_RELO 15000
enum static_regs {
STATIC_REG_IMMA = 20, /* Bank AB */
STATIC_REG_IMM = 21, /* Bank AB */
STATIC_REG_STACK = 22, /* Bank A */
STATIC_REG_PKT_LEN = 22, /* Bank B */
};
enum pkt_vec {
PKT_VEC_PKT_LEN = 0,
PKT_VEC_PKT_PTR = 2,
PKT_VEC_QSEL_SET = 4,
PKT_VEC_QSEL_VAL = 6,
};
#define PKT_VEL_QSEL_SET_BIT 4
#define pv_len(np) reg_lm(1, PKT_VEC_PKT_LEN)
#define pv_ctm_ptr(np) reg_lm(1, PKT_VEC_PKT_PTR)
#define pv_qsel_set(np) reg_lm(1, PKT_VEC_QSEL_SET)
#define pv_qsel_val(np) reg_lm(1, PKT_VEC_QSEL_VAL)
#define stack_reg(np) reg_a(STATIC_REG_STACK)
#define stack_imm(np) imm_b(np)
#define plen_reg(np) reg_b(STATIC_REG_PKT_LEN)
#define pptr_reg(np) pv_ctm_ptr(np)
#define imm_a(np) reg_a(STATIC_REG_IMM)
#define imm_b(np) reg_b(STATIC_REG_IMM)
#define imma_a(np) reg_a(STATIC_REG_IMMA)
#define imma_b(np) reg_b(STATIC_REG_IMMA)
#define imm_both(np) reg_both(STATIC_REG_IMM)
#define ret_reg(np) imm_a(np)
#define NFP_BPF_ABI_FLAGS reg_imm(0)
#define NFP_BPF_ABI_FLAG_MARK 1
/**
* struct nfp_app_bpf - bpf app priv structure
* @app: backpointer to the app
* @ccm: common control message handler data
*
* @bpf_dev: BPF offload device handle
*
* @cmsg_key_sz: size of key in cmsg element array
* @cmsg_val_sz: size of value in cmsg element array
*
* @map_list: list of offloaded maps
* @maps_in_use: number of currently offloaded maps
* @map_elems_in_use: number of elements allocated to offloaded maps
*
* @maps_neutral: hash table of offload-neutral maps (on pointer)
*
* @abi_version: global BPF ABI version
* @cmsg_cache_cnt: number of entries to read for caching
*
* @adjust_head: adjust head capability
* @adjust_head.flags: extra flags for adjust head
* @adjust_head.off_min: minimal packet offset within buffer required
* @adjust_head.off_max: maximum packet offset within buffer required
* @adjust_head.guaranteed_sub: negative adjustment guaranteed possible
* @adjust_head.guaranteed_add: positive adjustment guaranteed possible
*
* @maps: map capability
* @maps.types: supported map types
* @maps.max_maps: max number of maps supported
* @maps.max_elems: max number of entries in each map
* @maps.max_key_sz: max size of map key
* @maps.max_val_sz: max size of map value
* @maps.max_elem_sz: max size of map entry (key + value)
*
* @helpers: helper addressess for various calls
* @helpers.map_lookup: map lookup helper address
* @helpers.map_update: map update helper address
* @helpers.map_delete: map delete helper address
* @helpers.perf_event_output: output perf event to a ring buffer
*
* @pseudo_random: FW initialized the pseudo-random machinery (CSRs)
* @queue_select: BPF can set the RX queue ID in packet vector
* @adjust_tail: BPF can simply trunc packet size for adjust tail
* @cmsg_multi_ent: FW can pack multiple map entries in a single cmsg
*/
struct nfp_app_bpf {
struct nfp_app *app;
struct nfp_ccm ccm;
struct bpf_offload_dev *bpf_dev;
unsigned int cmsg_key_sz;
unsigned int cmsg_val_sz;
unsigned int cmsg_cache_cnt;
struct list_head map_list;
unsigned int maps_in_use;
unsigned int map_elems_in_use;
struct rhashtable maps_neutral;
u32 abi_version;
struct nfp_bpf_cap_adjust_head {
u32 flags;
int off_min;
int off_max;
int guaranteed_sub;
int guaranteed_add;
} adjust_head;
struct {
u32 types;
u32 max_maps;
u32 max_elems;
u32 max_key_sz;
u32 max_val_sz;
u32 max_elem_sz;
} maps;
struct {
u32 map_lookup;
u32 map_update;
u32 map_delete;
u32 perf_event_output;
} helpers;
bool pseudo_random;
bool queue_select;
bool adjust_tail;
bool cmsg_multi_ent;
};
enum nfp_bpf_map_use {
NFP_MAP_UNUSED = 0,
NFP_MAP_USE_READ,
NFP_MAP_USE_WRITE,
NFP_MAP_USE_ATOMIC_CNT,
};
struct nfp_bpf_map_word {
unsigned char type :4;
unsigned char non_zero_update :1;
};
#define NFP_BPF_MAP_CACHE_CNT 4U
#define NFP_BPF_MAP_CACHE_TIME_NS (250 * 1000)
/**
* struct nfp_bpf_map - private per-map data attached to BPF maps for offload
* @offmap: pointer to the offloaded BPF map
* @bpf: back pointer to bpf app private structure
* @tid: table id identifying map on datapath
*
* @cache_lock: protects @cache_blockers, @cache_to, @cache
* @cache_blockers: number of ops in flight which block caching
* @cache_gen: counter incremented by every blocker on exit
* @cache_to: time when cache will no longer be valid (ns)
* @cache: skb with cached response
*
* @l: link on the nfp_app_bpf->map_list list
* @use_map: map of how the value is used (in 4B chunks)
*/
struct nfp_bpf_map {
struct bpf_offloaded_map *offmap;
struct nfp_app_bpf *bpf;
u32 tid;
spinlock_t cache_lock;
u32 cache_blockers;
u32 cache_gen;
u64 cache_to;
struct sk_buff *cache;
struct list_head l;
struct nfp_bpf_map_word use_map[];
};
struct nfp_bpf_neutral_map {
struct rhash_head l;
struct bpf_map *ptr;
u32 map_id;
u32 count;
};
extern const struct rhashtable_params nfp_bpf_maps_neutral_params;
struct nfp_prog;
struct nfp_insn_meta;
typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *);
#define nfp_prog_first_meta(nfp_prog) \
list_first_entry(&(nfp_prog)->insns, struct nfp_insn_meta, l)
#define nfp_prog_last_meta(nfp_prog) \
list_last_entry(&(nfp_prog)->insns, struct nfp_insn_meta, l)
#define nfp_meta_next(meta) list_next_entry(meta, l)
#define nfp_meta_prev(meta) list_prev_entry(meta, l)
/**
* struct nfp_bpf_reg_state - register state for calls
* @reg: BPF register state from latest path
* @var_off: for stack arg - changes stack offset on different paths
*/
struct nfp_bpf_reg_state {
struct bpf_reg_state reg;
bool var_off;
};
#define FLAG_INSN_IS_JUMP_DST BIT(0)
#define FLAG_INSN_IS_SUBPROG_START BIT(1)
#define FLAG_INSN_PTR_CALLER_STACK_FRAME BIT(2)
/* Instruction is pointless, noop even on its own */
#define FLAG_INSN_SKIP_NOOP BIT(3)
/* Instruction is optimized out based on preceding instructions */
#define FLAG_INSN_SKIP_PREC_DEPENDENT BIT(4)
/* Instruction is optimized by the verifier */
#define FLAG_INSN_SKIP_VERIFIER_OPT BIT(5)
/* Instruction needs to zero extend to high 32-bit */
#define FLAG_INSN_DO_ZEXT BIT(6)
#define FLAG_INSN_SKIP_MASK (FLAG_INSN_SKIP_NOOP | \
FLAG_INSN_SKIP_PREC_DEPENDENT | \
FLAG_INSN_SKIP_VERIFIER_OPT)
/**
* struct nfp_insn_meta - BPF instruction wrapper
* @insn: BPF instruction
* @ptr: pointer type for memory operations
* @ldst_gather_len: memcpy length gathered from load/store sequence
* @paired_st: the paired store insn at the head of the sequence
* @ptr_not_const: pointer is not always constant
* @pkt_cache: packet data cache information
* @pkt_cache.range_start: start offset for associated packet data cache
* @pkt_cache.range_end: end offset for associated packet data cache
* @pkt_cache.do_init: this read needs to initialize packet data cache
* @xadd_over_16bit: 16bit immediate is not guaranteed
* @xadd_maybe_16bit: 16bit immediate is possible
* @jmp_dst: destination info for jump instructions
* @jump_neg_op: jump instruction has inverted immediate, use ADD instead of SUB
* @num_insns_after_br: number of insns following a branch jump, used for fixup
* @func_id: function id for call instructions
* @arg1: arg1 for call instructions
* @arg2: arg2 for call instructions
* @umin_src: copy of core verifier umin_value for src opearnd.
* @umax_src: copy of core verifier umax_value for src operand.
* @umin_dst: copy of core verifier umin_value for dst opearnd.
* @umax_dst: copy of core verifier umax_value for dst operand.
* @off: index of first generated machine instruction (in nfp_prog.prog)
* @n: eBPF instruction number
* @flags: eBPF instruction extra optimization flags
* @subprog_idx: index of subprogram to which the instruction belongs
* @double_cb: callback for second part of the instruction
* @l: link on nfp_prog->insns list
*/
struct nfp_insn_meta {
struct bpf_insn insn;
union {
/* pointer ops (ld/st/xadd) */
struct {
struct bpf_reg_state ptr;
struct bpf_insn *paired_st;
s16 ldst_gather_len;
bool ptr_not_const;
struct {
s16 range_start;
s16 range_end;
bool do_init;
} pkt_cache;
bool xadd_over_16bit;
bool xadd_maybe_16bit;
};
/* jump */
struct {
struct nfp_insn_meta *jmp_dst;
bool jump_neg_op;
u32 num_insns_after_br; /* only for BPF-to-BPF calls */
};
/* function calls */
struct {
u32 func_id;
struct bpf_reg_state arg1;
struct nfp_bpf_reg_state arg2;
};
/* We are interested in range info for operands of ALU
* operations. For example, shift amount, multiplicand and
* multiplier etc.
*/
struct {
u64 umin_src;
u64 umax_src;
u64 umin_dst;
u64 umax_dst;
};
};
unsigned int off;
unsigned short n;
unsigned short flags;
unsigned short subprog_idx;
instr_cb_t double_cb;
struct list_head l;
};
#define BPF_SIZE_MASK 0x18
static inline u8 mbpf_class(const struct nfp_insn_meta *meta)
{
return BPF_CLASS(meta->insn.code);
}
static inline u8 mbpf_src(const struct nfp_insn_meta *meta)
{
return BPF_SRC(meta->insn.code);
}
static inline u8 mbpf_op(const struct nfp_insn_meta *meta)
{
return BPF_OP(meta->insn.code);
}
static inline u8 mbpf_mode(const struct nfp_insn_meta *meta)
{
return BPF_MODE(meta->insn.code);
}
static inline bool is_mbpf_alu(const struct nfp_insn_meta *meta
|