summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/net/bpf_jit_comp64.c
blob: 6073b78516f69348b7e80ed3680224c67a026e2c (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
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
/*
 * bpf_jit_comp64.c: eBPF JIT compiler
 *
 * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
 *		  IBM Corporation
 *
 * Based on the powerpc classic BPF JIT compiler by Matt Evans
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; version 2
 * of the License.
 */
#include <linux/moduleloader.h>
#include <asm/cacheflush.h>
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <asm/kprobes.h>

#include "bpf_jit64.h"

int bpf_jit_enable __read_mostly;

static void bpf_jit_fill_ill_insns(void *area, unsigned int size)
{
	int *p = area;

	/* Fill whole space with trap instructions */
	while (p < (int *)((char *)area + size))
		*p++ = BREAKPOINT_INSTRUCTION;
}

static inline void bpf_flush_icache(void *start, void *end)
{
	smp_wmb();
	flush_icache_range((unsigned long)start, (unsigned long)end);
}

static inline bool bpf_is_seen_register(struct codegen_context *ctx, int i)
{
	return (ctx->seen & (1 << (31 - b2p[i])));
}

static inline void bpf_set_seen_register(struct codegen_context *ctx, int i)
{
	ctx->seen |= (1 << (31 - b2p[i]));
}

static inline bool bpf_has_stack_frame(struct codegen_context *ctx)
{
	/*
	 * We only need a stack frame if:
	 * - we call other functions (kernel helpers), or
	 * - the bpf program uses its stack area
	 * The latter condition is deduced from the usage of BPF_REG_FP
	 */
	return ctx->seen & SEEN_FUNC || bpf_is_seen_register(ctx, BPF_REG_FP);
}

static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx)
{
	/*
	 * Load skb->len and skb->data_len
	 * r3 points to skb
	 */
	PPC_LWZ(b2p[SKB_HLEN_REG], 3, offsetof(struct sk_buff, len));
	PPC_LWZ(b2p[TMP_REG_1], 3, offsetof(struct sk_buff, data_len));
	/* header_len = len - data_len */
	PPC_SUB(b2p[SKB_HLEN_REG], b2p[SKB_HLEN_REG], b2p[TMP_REG_1]);

	/* skb->data pointer */
	PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data));
}

static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func)
{
#ifdef PPC64_ELF_ABI_v1
	/* func points to the function descriptor */
	PPC_LI64(b2p[TMP_REG_2], func);
	/* Load actual entry point from function descriptor */
	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0);
	/* ... and move it to LR */
	PPC_MTLR(b2p[TMP_REG_1]);
	/*
	 * Load TOC from function descriptor at offset 8.
	 * We can clobber r2 since we get called through a
	 * function pointer (so caller will save/restore r2)
	 * and since we don't use a TOC ourself.
	 */
	PPC_BPF_LL(2, b2p[TMP_REG_2], 8);
#else
	/* We can clobber r12 */
	PPC_FUNC_ADDR(12, func);
	PPC_MTLR(12);
#endif
	PPC_BLRL();
}

static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx)
{
	int i;
	bool new_stack_frame = bpf_has_stack_frame(ctx);

	if (new_stack_frame) {
		/*
		 * We need a stack frame, but we don't necessarily need to
		 * save/restore LR unless we call other functions
		 */
		if (ctx->seen & SEEN_FUNC) {
			EMIT(PPC_INST_MFLR | __PPC_RT(R0));
			PPC_BPF_STL(0, 1, PPC_LR_STKOFF);
		}

		PPC_BPF_STLU(1, 1, -BPF_PPC_STACKFRAME);
	}

	/*
	 * Back up non-volatile regs -- BPF registers 6-10
	 * If we haven't created our own stack frame, we save these
	 * in the protected zone below the previous stack frame
	 */
	for (i = BPF_REG_6; i <= BPF_REG_10; i++)
		if (bpf_is_seen_register(ctx, i))
			PPC_BPF_STL(b2p[i], 1,
				(new_stack_frame ? BPF_PPC_STACKFRAME : 0) -
					(8 * (32 - b2p[i])));

	/*
	 * Save additional non-volatile regs if we cache skb
	 * Also, setup skb data
	 */
	if (ctx->seen & SEEN_SKB) {
		PPC_BPF_STL(b2p[SKB_HLEN_REG], 1,
			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_HLEN_REG])));
		PPC_BPF_STL(b2p[SKB_DATA_REG], 1,
			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_DATA_REG])));
		bpf_jit_emit_skb_loads(image, ctx);
	}

	/* Setup frame pointer to point to the bpf stack area */
	if (bpf_is_seen_register(ctx, BPF_REG_FP))
		PPC_ADDI(b2p[BPF_REG_FP], 1,
				BPF_PPC_STACKFRAME - BPF_PPC_STACK_SAVE);
}

static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx)
{
	int i;
	bool new_stack_frame = bpf_has_stack_frame(ctx);

	/* Move result to r3 */
	PPC_MR(3, b2p[BPF_REG_0]);

	/* Restore NVRs */
	for (i = BPF_REG_6; i <= BPF_REG_10; i++)
		if (bpf_is_seen_register(ctx, i))
			PPC_BPF_LL(b2p[i], 1,
				(new_stack_frame ? BPF_PPC_STACKFRAME : 0) -
					(8 * (32 - b2p[i])));

	/* Restore non-volatile registers used for skb cache */
	if (ctx->seen & SEEN_SKB) {
		PPC_BPF_LL(b2p[SKB_HLEN_REG], 1,
			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_HLEN_REG])));
		PPC_BPF_LL(b2p[SKB_DATA_REG], 1,
			BPF_PPC_STACKFRAME - (8 * (32 - b2p[SKB_DATA_REG])));
	}

	/* Tear down our stack frame */
	if (new_stack_frame) {
		PPC_ADDI(1, 1, BPF_PPC_STACKFRAME);
		if (ctx->seen & SEEN_FUNC) {
			PPC_BPF_LL(0, 1, PPC_LR_STKOFF);
			PPC_MTLR(0);
		}
	}

	PPC_BLR();
}

/* Assemble the body code between the prologue & epilogue */
static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
			      struct codegen_context *ctx,
			      u32 *addrs)
{
	const struct bpf_insn *insn = fp->insnsi;
	int flen = fp->len;
	int i;

	/* Start of epilogue code - will only be valid 2nd pass onwards */
	u32 exit_addr = addrs[flen];

	for (i = 0; i < flen; i++) {
		u32 code = insn[i].code;
		u32 dst_reg = b2p[insn[i].dst_reg];
		u32 src_reg = b2p[insn[i].src_reg];
		s16 off = insn[i].off;
		s32 imm = insn[i].imm;
		u64 imm64;
		u8 *func;
		u32 true_cond;
		int stack_local_off;

		/*
		 * addrs[] maps a BPF bytecode address into a real offset from
		 * the start of the body code.
		 */
		addrs[i] = ctx->idx * 4;

		/*
		 * As an optimization, we note down which non-volatile registers
		 * are used so that we can only save/restore those in our
		 * prologue and epilogue. We do this here regardless of whether
		 * the actual BPF instruction uses src/dst registers or not
		 * (for instance, BPF_CALL does not use them). The expectation
		 * is that those instructions will have src_reg/dst_reg set to
		 * 0. Even otherwise, we just lose some prologue/epilogue
		 * optimization but everything else should work without
		 * any issues.
		 */
		if (dst_reg >= 24 && dst_reg <= 31)
			bpf_set_seen_register(ctx, insn[i].dst_reg);
		if (src_reg >= 24 && src_reg <= 31)
			bpf_set_seen_register(ctx, insn[i].src_reg);

		switch (code) {
		/*
		 * Arithmetic operations: ADD/SUB/MUL/DIV/MOD/NEG
		 */
		case BPF_ALU | BPF_ADD | BPF_X: /* (u32) dst += (u32) src */
		case BPF_ALU64 | BPF_ADD | BPF_X: /* dst += src */
			PPC_ADD(dst_reg, dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_SUB | BPF_X: /* (u32) dst -= (u32) src */
		case BPF_ALU64 | BPF_SUB | BPF_X: /* dst -= src */
			PPC_SUB(dst_reg, dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */
		case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */
		case BPF_ALU64 | BPF_ADD | BPF_K: /* dst += imm */
		case BPF_ALU64 | BPF_SUB | BPF_K: /* dst -= imm */
			if (BPF_OP(code) == BPF_SUB)
				imm = -imm;
			if (imm) {
				if (imm >= -32768 && imm < 32768)
					PPC_ADDI(dst_reg, dst_reg, IMM_L(imm));
				else {
					PPC_LI32(b2p[TMP_REG_1], imm);
					PPC_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]);
				}
			}
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */
		case BPF_ALU64 | BPF_MUL | BPF_X: /* dst *= src */
			if (BPF_CLASS(code) == BPF_ALU)
				PPC_MULW(dst_reg, dst_reg, src_reg);
			else
				PPC_MULD(dst_reg, dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_MUL | BPF_K: /* (u32) dst *= (u32) imm */
		case BPF_ALU64 | BPF_MUL | BPF_K: /* dst *= imm */
			if (imm >= -32768 && imm < 32768)
				PPC_MULI(dst_reg, dst_reg, IMM_L(imm));
			else {
				PPC_LI32(b2p[TMP_REG_1], imm);
				if (BPF_CLASS(code) == BPF_ALU)
					PPC_MULW(dst_reg, dst_reg,
							b2p[TMP_REG_1]);
				else
					PPC_MULD(dst_reg, dst_reg,
							b2p[TMP_REG_1]);
			}
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */
		case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */
			PPC_CMPWI(src_reg, 0);
			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
			PPC_LI(b2p[BPF_REG_0], 0);
			PPC_JMP(exit_addr);
			if (BPF_OP(code) == BPF_MOD) {
				PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg);
				PPC_MULW(b2p[TMP_REG_1], src_reg,
						b2p[TMP_REG_1]);
				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
			} else
				PPC_DIVWU(dst_reg, dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */
		case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */
			PPC_CMPDI(src_reg, 0);
			PPC_BCC_SHORT(COND_NE, (ctx->idx * 4) + 12);
			PPC_LI(b2p[BPF_REG_0], 0);
			PPC_JMP(exit_addr);
			if (BPF_OP(code) == BPF_MOD) {
				PPC_DIVD(b2p[TMP_REG_1], dst_reg, src_reg);
				PPC_MULD(b2p[TMP_REG_1], src_reg,
						b2p[TMP_REG_1]);
				PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]);
			} else
				PPC_DIVD(dst_reg, dst_reg, src_reg);
			break;
		case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */
		case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */
		case BPF_ALU64 | BPF_MOD | BPF_K: /* dst %= imm */
		case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */
			if (imm == 0)
				return -EINVAL;
			else if (imm == 1)
				goto bpf_alu32_trunc;

			PPC_LI32(b2p[TMP_REG_1], imm);
			switch (BPF_CLASS(code)) {
			case BPF_ALU:
				if (BPF_OP(code) == BPF_MOD) {
					PPC_DIVWU(b2p[TMP_REG_2], dst_reg,
							b2p[TMP_REG_1]);
					PPC_MULW(b2p[TMP_REG_1],
							b2p[TMP_REG_1],
							b2p[TMP_REG_2]);
					PPC_SUB(dst_reg, dst_reg,
							b2p[TMP_REG_1]);
				} else
					PPC_DIVWU(dst_reg, dst_reg,
							b2p[TMP_REG_1]);
				break;
			case BPF_ALU64:
				if (BPF_OP(code) == BPF_MOD) {
					PPC_DIVD(b2p[TMP_REG_2], dst_reg,
							b2p[TMP_REG_1]);
					PPC_MULD(b2p[TMP_REG_1],
							b2p[TMP_REG_1],
							b2p[TMP_REG_2]);
					PPC_SUB(dst_reg, dst_reg,
							b2p[TMP_REG_1]);
				} else
					PPC_DIVD(dst_reg, dst_reg,
							b2p[TMP_REG_1]);
				break;
			}
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_NEG: /* (u32) dst = -dst */
		case BPF_ALU64 | BPF_NEG: /* dst = -dst */
			PPC_NEG(dst_reg, dst_reg);
			goto bpf_alu32_trunc;

		/*
		 * Logical operations: AND/OR/XOR/[A]LSH/[A]RSH
		 */
		case BPF_ALU | BPF_AND | BPF_X: /* (u32) dst = dst & src */
		case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */
			PPC_AND(dst_reg, dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_AND | BPF_K: /* (u32) dst = dst & imm */
		case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */
			if (!IMM_H(imm))
				PPC_ANDI(dst_reg, dst_reg, IMM_L(imm));
			else {
				/* Sign-extended */
				PPC_LI32(b2p[TMP_REG_1], imm);
				PPC_AND(dst_reg, dst_reg, b2p[TMP_REG_1]);
			}
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */
		case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */
			PPC_OR(dst_reg, dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_OR | BPF_K:/* dst = (u32) dst | (u32) imm */
		case BPF_ALU64 | BPF_OR | BPF_K:/* dst = dst | imm */
			if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
				/* Sign-extended */
				PPC_LI32(b2p[TMP_REG_1], imm);
				PPC_OR(dst_reg, dst_reg, b2p[TMP_REG_1]);
			} else {
				if (IMM_L(imm))
					PPC_ORI(dst_reg, dst_reg, IMM_L(imm));
				if (IMM_H(imm))
					PPC_ORIS(dst_reg, dst_reg, IMM_H(imm));
			}
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_XOR | BPF_X: /* (u32) dst ^= src */
		case BPF_ALU64 | BPF_XOR | BPF_X: /* dst ^= src */
			PPC_XOR(dst_reg, dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_XOR | BPF_K: /* (u32) dst ^= (u32) imm */
		case BPF_ALU64 | BPF_XOR | BPF_K: /* dst ^= imm */
			if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) {
				/* Sign-extended */
				PPC_LI32(b2p[TMP_REG_1], imm);
				PPC_XOR(dst_reg, dst_reg, b2p[TMP_REG_1]);
			} else {
				if (IMM_L(imm))
					PPC_XORI(dst_reg, dst_reg, IMM_L(imm));
				if (IMM_H(imm))
					PPC_XORIS(dst_reg, dst_reg, IMM_H(imm));
			}
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */
			/* slw clears top 32 bits */
			PPC_SLW(dst_reg, dst_reg, src_reg);
			break;
		case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */
			PPC_SLD(dst_reg, dst_reg, src_reg);
			break;
		case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */
			/* with imm 0, we still need to clear top 32 bits */
			PPC_SLWI(dst_reg, dst_reg, imm);
			break;
		case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */
			if (imm != 0)
				PPC_SLDI(dst_reg, dst_reg, imm);
			break;
		case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */
			PPC_SRW(dst_reg, dst_reg, src_reg);
			break;
		case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */
			PPC_SRD(dst_reg, dst_reg, src_reg);
			break;
		case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */
			PPC_SRWI(dst_reg, dst_reg, imm);
			break;
		case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */
			if (imm != 0)
				PPC_SRDI(dst_reg, dst_reg, imm);
			break;
		case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */
			PPC_SRAD(dst_reg, dst_reg, src_reg);
			break;
		case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */
			if (imm != 0)
				PPC_SRADI(dst_reg, dst_reg, imm);
			break;

		/*
		 * MOV
		 */
		case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */
		case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
			PPC_MR(dst_reg, src_reg);
			goto bpf_alu32_trunc;
		case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */
		case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */
			PPC_LI32(dst_reg, imm);
			if (imm < 0)
				goto bpf_alu32_trunc;
			break;

bpf_alu32_trunc:
		/* Truncate to 32-bits */
		if (BPF_CLASS(code) == BPF_ALU)
			PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31);
		break;

		/*
		 * BPF_FROM_BE/LE
		 */
		case BPF_ALU | BPF_END | BPF_FROM_LE:
		case BPF_ALU | BPF_END | BPF_FROM_BE:
#ifdef __BIG_ENDIAN__
			if (BPF_SRC(code) == BPF_FROM_BE)
				goto emit_clear;
#else /* !__BIG_ENDIAN__ */
			if (BPF_SRC(code) == BPF_FROM_LE)
				goto emit_clear;
#endif
			switch (imm) {
			case 16:
				/* Rotate 8 bits left & mask with 0x0000ff00 */
				PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23);
				/* Rotate 8 bits right & insert LSB to reg */
				PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31);
				/* Move result back to dst_reg */
				PPC_MR(dst_reg, b2p[TMP_REG_1]);
				break;
			case 32:
				/*
				 * Rotate word left by 8 bits:
				 * 2 bytes are already in their final position
				 * -- byte 2 and 4 (of bytes 1, 2, 3 and 4)
				 */
				PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31);
				/* Rotate 24 bits and insert byte 1 */
				PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7);
				/* Rotate 24 bits and insert byte 3 */
				PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23);
				PPC_MR(dst_reg, b2p[TMP_REG_1]);
				break;
			case 64:
				/*
				 * Way easier and faster(?) to store the value
				 * into stack and then use ldbrx
				 *
				 * First, determine where in stack we can store
				 * this:
				 * - if we have allotted a stack frame, then we
				 *   will utilize the area set aside by
				 *   BPF_PPC_STACK_LOCALS
				 * - else, we use the area beneath the NV GPR
				 *   save area
				 *
				 * ctx->seen will be reliable in pass2, but
				 * the instructions generated will remain the
				 * same across all passes
				 */
				if (bpf_has_stack_frame(ctx))
					stack_local_off = STACK_FRAME_MIN_SIZE;
				else
					stack_local_off = -(BPF_PPC_STACK_SAVE + 8);

				PPC_STD(dst_reg, 1, stack_local_off);
				PPC_ADDI(b2p[TMP_REG_1], 1, stack_local_off);
				PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
				break;
			}
			break;

emit_clear:
			switch (imm) {
			case 16:
				/* zero-extend 16 bits into 64 bits */
				PPC_RLDICL(dst_reg, dst_reg, 0, 48);
				break;
			case 32:
				/* zero-extend 32 bits into 64 bits */
				PPC_RLDICL(dst_reg, dst_reg, 0, 32);
				break;
			case 64:
				/* nop */
				break;
			}
			break;

		/*
		 * BPF_ST(X)
		 */
		case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
		case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */
			if (BPF_CLASS(code) == BPF_ST) {
				PPC_LI(b2p[TMP_REG_1], imm);
				src_reg = b2p[TMP_REG_1];
			}
			PPC_STB(src_reg, dst_reg, off);
			break;
		case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */
		case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */
			if (BPF_CLASS(code) == BPF_ST) {
				PPC_LI(b2p[TMP_REG_1], imm);
				src_reg = b2p[TMP_REG_1];
			}
			PPC_STH(src_reg, dst_reg, off);
			break;
		case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */
		case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */
			if (BPF_CLASS(code) == BPF_ST) {
				PPC_LI32(b2p[TMP_REG_1], imm);
				src_reg = b2p[TMP_REG_1];
			}
			PPC_STW(src_reg, dst_reg, off);
			break;
		case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */
		case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */
			if (BPF_CLASS(code) == BPF_ST) {
				PPC_LI32(b2p[TMP_REG_1], imm);
				src_reg = b2p[TMP_REG_1];
			}
			PPC_STD(src_reg, dst_reg, off);
			break;

		/*
		 * BPF_STX XADD (atomic_add)
		 */
		/* *(u32 *)(dst + off) += src */
		case BPF_STX | BPF_XADD | BPF_W:
			/* Get EA into TMP_REG_1 */
			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
			/* error if EA is not word-aligned */
			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03);
			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12);
			PPC_LI(b2p[BPF_REG_0], 0);
			PPC_JMP(exit_addr);
			/* load value from memory into TMP_REG_2 */
			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
			/* add value from src_reg into this */
			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
			/* store result back */
			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
			/* we're done if this succeeded */
			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
			/* otherwise, let's try once more */
			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
			/* exit if the store was not successful */
			PPC_LI(b2p[BPF_REG_0], 0);
			PPC_BCC(COND_NE, exit_addr);
			break;
		/* *(u64 *)(dst + off) += src */
		case BPF_STX | BPF_XADD | BPF_DW:
			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
			/* error if EA is not doubleword-aligned */
			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07);
			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4));
			PPC_LI(b2p[BPF_REG_0], 0);
			PPC_JMP(exit_addr);
			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
			PPC_LI(b2p[BPF_REG_0], 0);
			PPC_BCC(COND_NE, exit_addr);
			break;

		/*
		 * BPF_LDX
		 */
		/* dst = *(u8 *)(ul) (src + off) */
		case BPF_LDX | BPF_MEM | BPF_B:
			PPC_LBZ(dst_reg, src_reg, off);
			break;
		/* dst = *(u16 *)(ul) (src + off) */
		case BPF_LDX | BPF_MEM | BPF_H:
			PPC_LHZ(dst_reg, src_reg, off);
			break;
		/* dst = *(u32 *)(ul) (src + off) */
		case BPF_LDX | BPF_MEM | BPF_W:
			PPC_LWZ(dst_reg, src_reg, off);
			break;
		/* dst = *(u64 *)(ul) (src + off) */
		case BPF_LDX | BPF_MEM | BPF_DW:
			PPC_LD(dst_reg, src_reg, off);
			break;

		/*
		 * Doubleword load
		 * 16 byte instruction that uses two 'struct bpf_insn'
		 */
		case BPF_LD | BPF_IMM | BPF_DW: /* dst = (u64) imm */
			imm64 = ((u64)(u32) insn[i].imm) |
				    (((u64)(u32) insn[i+1].imm) << 32);
			/* Adjust for two bpf instructions */
			addrs[++i] = ctx->idx * 4;
			PPC_LI64(dst_reg, imm64);
			break;

		/*
		 * Return/Exit
		 */
		case BPF_JMP | BPF_EXIT:
			/*
			 * If this isn't the very last instruction, branch to
			 * the epilogue. If we _are_ the last instruction,
			 * we'll just fall through to the epilogue.
			 */
			if (i != flen - 1)
				PPC_JMP(exit_addr);
			/* else fall through to the epilogue */
			break;

		/*
		 * Call kernel helper
		 */
		case BPF_JMP | BPF_CALL:
			ctx->seen |= SEEN_FUNC;
			func = (u8 *) __bpf_call_base + imm;

			/* Save skb pointer if we need to re-cache skb data */
			if (bpf_helper_changes_skb_data(func))
				PPC_BPF_STL(3, 1, STACK_FRAME_MIN_SIZE);

			bpf_jit_emit_func_call(image, ctx, (u64)func);

			/* move return value from r3 to BPF_REG_0 */
			PPC_MR(b2p[BPF_REG_0], 3);

			/* refresh skb cache */
			if (bpf_helper_changes_skb_data(func)) {
				/* reload skb pointer to r3 */
				PPC_BPF_LL(3, 1, STACK_FRAME_MIN_SIZE);
				bpf_jit_emit_skb_loads(image, ctx);
			}
			break;

		/*
		 * Jumps and branches
		 */
		case BPF_JMP | BPF_JA:
			PPC_JMP(addrs[i + 1 + off]);
			break;

		case BPF_JMP | BPF_JGT | BPF_K:
		case BPF_JMP | BPF_JGT | BPF_X:
		case BPF_JMP | BPF_JSGT | BPF_K:
		case BPF_JMP | BPF_JSGT | BPF_X:
			true_cond = COND_GT;
			goto cond_branch;
		case BPF_JMP | BPF_JGE | BPF_K:
		case BPF_JMP | BPF_JGE | BPF_X:
		case BPF_JMP | BPF_JSGE | BPF_K:
		case BPF_JMP | BPF_JSGE | BPF_X:
			true_cond = COND_GE;
			goto cond_branch;
		case BPF_JMP | BPF_JEQ | BPF_K:
		case BPF_JMP | BPF_JEQ | BPF_X:
			true_cond = COND_EQ;
			goto cond_branch;
		case BPF_JMP | BPF_JNE | BPF_K:
		case BPF_JMP | BPF_JNE | BPF_X:
			true_cond = COND_NE;
			goto cond_branch;
		case BPF_JMP | BPF_JSET | BPF_K:
		case BPF_JMP | BPF_JSET | BPF_X:
			true_cond = COND_NE;
			/* Fall through */

cond_branch:
			switch (code) {
			case BPF_JMP | BPF_JGT | BPF_X:
			case BPF_JMP | BPF_JGE | BPF_X:
			case BPF_JMP | BPF_JEQ | BPF_X:
			case BPF_JMP | BPF_JNE | BPF_X:
				/* unsigned comparison */
				PPC_CMPLD(dst_reg, src_reg);
				break;
			case BPF_JMP | BPF_JSGT | BPF_X:
			case BPF_JMP | BPF_JSGE | BPF_X:
				/* signed comparison */
				PPC_CMPD(dst_reg, src_reg);
				break;
			case BPF_JMP | BPF_JSET | BPF_X:
				PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, src_reg);
				break;
			case BPF_JMP | BPF_JNE | BPF_K:
			case BPF_JMP | BPF_JEQ | BPF_K:
			case BPF_JMP | BPF_JGT | BPF_K:
			case BPF_JMP | BPF_JGE | BPF_K:
				/*
				 * Need sign-extended load, so only positive
				 * values can be used as imm in cmpldi
				 */
				if (imm >= 0 && imm < 32768)
					PPC_CMPLDI(dst_reg, imm);
				else {
					/* sign-extending load */
					PPC_LI32(b2p[TMP_REG_1], imm);
					/* ... but unsigned comparison */
					PPC_CMPLD(dst_reg, b2p[TMP_REG_1]);
				}
				break;
			case BPF_JMP | BPF_JSGT | BPF_K:
			case BPF_JMP | BPF_JSGE | BPF_K:
				/*
				 * signed comparison, so any 16-bit value
				 * can be used in cmpdi
				 */
				if (imm >= -32768 && imm < 32768)
					PPC_CMPDI(dst_reg, imm);
				else {
					PPC_LI32(b2p[TMP_REG_1], imm);
					PPC_CMPD(dst_reg, b2p[TMP_REG_1]);
				}
				break;
			case BPF_JMP | BPF_JSET | BPF_K:
				/* andi does not sign-extend the immediate */
				if (imm >= 0 && imm < 32768)
					/* PPC_ANDI is _only/always_ dot-form */
					PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm);
				else {
					PPC_LI32(b2p[TMP_REG_1], imm);
					PPC_AND_DOT(b2p[TMP_REG_1], dst_reg,
						    b2p[TMP_REG_1]);
				}
				break;
			}
			PPC_BCC(true_cond, addrs[i + 1 + off]);
			break;

		/*
		 * Loads from packet header/data
		 * Assume 32-bit input value in imm and X (src_reg)
		 */

		/* Absolute loads */
		case BPF_LD | BPF_W | BPF_ABS:
			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_word);
			goto common_load_abs;
		case BPF_LD | BPF_H | BPF_ABS:
			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_half);
			goto common_load_abs;
		case BPF_LD | BPF_B | BPF_ABS:
			func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_byte);
common_load_abs:
			/*
			 * Load from [imm]
			 * Load into r4, which can just be passed onto
			 *  skb load helpers as the second parameter
			 */
			PPC_LI32(4, imm);
			goto common_load;

		/* Indirect loads */
		case BPF_LD | BPF_W | BPF_IND:
			func = (u8 *)sk_load_word;
			goto common_load_ind;
		case BPF_LD | BPF_H | BPF_IND:
			func = (u8 *)sk_load_half;
			goto common_load_ind;
		case BPF_LD | BPF_B | BPF_IND:
			func = (u8 *)sk_load_byte;
common_load_ind:
			/*
			 * Load from [src_reg + imm]
			 * Treat src_reg as a 32-bit value
			 */
			PPC_EXTSW(4, src_reg);
			if (imm) {
				if (imm >= -32768 && imm < 32768)
					PPC_ADDI(4, 4, IMM_L(imm));
				else {
					PPC_LI32(b2p[TMP_REG_1], imm);
					PPC_ADD(4, 4, b2p[TMP_REG_1]);
				}
			}

common_load:
			ctx->seen |= SEEN_SKB;
			ctx->seen |= SEEN_FUNC;
			bpf_jit_emit_func_call(image, ctx, (u64)func);

			/*
			 * Helper returns 'lt' condition on error, and an
			 * appropriate return value in BPF_REG_0
			 */
			PPC_BCC(COND_LT, exit_addr);
			break;

		/*
		 * TODO: Tail call
		 */
		case BPF_JMP | BPF_CALL | BPF_X:

		default:
			/*
			 * The filter contains something cruel & unusual.
			 * We don't handle it, but also there shouldn't be
			 * anything missing from our list.
			 */
			pr_err_ratelimited("eBPF filter opcode %04x (@%d) unsupported\n",
					code, i);
			return -ENOTSUPP;
		}
	}

	/* Set end-of-body-code address for exit. */
	addrs[i] = ctx->idx * 4;

	return 0;
}

void bpf_jit_compile(struct bpf_prog *fp) { }

struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
{
	u32 proglen;
	u32 alloclen;
	u8 *image = NULL;
	u32 *code_base;
	u32 *addrs;
	struct codegen_context cgctx;
	int pass;
	int flen;
	struct bpf_binary_header *bpf_hdr;

	if (!bpf_jit_enable)
		return fp;

	flen = fp->len;
	addrs = kzalloc((flen+1) * sizeof(*addrs), GFP_KERNEL);
	if (addrs == NULL)
		return fp;

	cgctx.idx = 0;
	cgctx.seen = 0;
	/* Scouting faux-generate pass 0 */
	if (bpf_jit_build_body(fp, 0, &cgctx, addrs))
		/* We hit something illegal or unsupported. */
		goto out;

	/*
	 * Pretend to build prologue, given the features we've seen.  This will
	 * update ctgtx.idx as it pretends to output instructions, then we can
	 * calculate total size from idx.
	 */
	bpf_jit_build_prologue(0, &cgctx);
	bpf_jit_build_epilogue(0, &cgctx);

	proglen = cgctx.idx * 4;
	alloclen = proglen + FUNCTION_DESCR_SIZE;

	bpf_hdr = bpf_jit_binary_alloc(alloclen, &image, 4,
			bpf_jit_fill_ill_insns);
	if (!bpf_hdr)
		goto out;

	code_base = (u32 *)(image + FUNCTION_DESCR_SIZE);

	/* Code generation passes 1-2 */
	for (pass = 1; pass < 3; pass++) {
		/* Now build the prologue, body code & epilogue for real. */
		cgctx.idx = 0;
		bpf_jit_build_prologue(code_base, &cgctx);
		bpf_jit_build_body(fp, code_base, &cgctx, addrs);
		bpf_jit_build_epilogue(code_base, &cgctx);

		if (bpf_jit_enable > 1)
			pr_info("Pass %d: shrink = %d, seen = 0x%x\n", pass,
				proglen - (cgctx.idx * 4), cgctx.seen);
	}

	if (bpf_jit_enable > 1)
		/*
		 * Note that we output the base address of the code_base
		 * rather than image, since opcodes are in code_base.
		 */
		bpf_jit_dump(flen, proglen, pass, code_base);

	if (image) {
		bpf_flush_icache(bpf_hdr, image + alloclen);
#ifdef PPC64_ELF_ABI_v1
		/* Function descriptor nastiness: Address + TOC */
		((u64 *)image)[0] = (u64)code_base;
		((u64 *)image)[1] = local_paca->kernel_toc;
#endif
		fp->bpf_func = (void *)image;
		fp->jited = 1;
	}

out:
	kfree(addrs);
	return fp;
}

void bpf_jit_free(struct bpf_prog *fp)
{
	unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
	struct bpf_binary_header *bpf_hdr = (void *)addr;

	if (fp->jited)
		bpf_jit_binary_free(bpf_hdr);

	bpf_prog_unlock_free(fp);
}
OpenPOWER on IntegriCloud