about summary refs log tree commit diff
path: root/sysdeps/s390/utf8-utf32-z9.c
blob: e39e0a73d9f32ddbcbbec622688beaa52eccbea9 (plain) (blame)
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
/* Conversion between UTF-8 and UTF-32 BE/internal.

   This module uses the Z9-109 variants of the Convert Unicode
   instructions.
   Copyright (C) 1997-2016 Free Software Foundation, Inc.

   Author: Andreas Krebbel  <Andreas.Krebbel@de.ibm.com>
   Based on the work by Ulrich Drepper  <drepper@cygnus.com>, 1997.

   Thanks to Daniel Appich who covered the relevant performance work
   in his diploma thesis.

   This is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   This is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <http://www.gnu.org/licenses/>.  */

#include <dlfcn.h>
#include <stdint.h>
#include <unistd.h>
#include <dl-procinfo.h>
#include <gconv.h>

#if defined HAVE_S390_VX_GCC_SUPPORT
# define ASM_CLOBBER_VR(NR) , NR
#else
# define ASM_CLOBBER_VR(NR)
#endif

#if defined __s390x__
# define CONVERT_32BIT_SIZE_T(REG)
#else
# define CONVERT_32BIT_SIZE_T(REG) "llgfr %" #REG ",%" #REG "\n\t"
#endif

/* Defines for skeleton.c.  */
#define DEFINE_INIT		0
#define DEFINE_FINI		0
#define MIN_NEEDED_FROM		1
#define MAX_NEEDED_FROM		6
#define MIN_NEEDED_TO		4
#define FROM_LOOP		__from_utf8_loop
#define TO_LOOP			__to_utf8_loop
#define FROM_DIRECTION		(dir == from_utf8)
#define ONE_DIRECTION           0

/* UTF-32 big endian byte order mark.  */
#define BOM			0x0000feffu

/* Direction of the transformation.  */
enum direction
{
  illegal_dir,
  to_utf8,
  from_utf8
};

struct utf8_data
{
  enum direction dir;
  int emit_bom;
};


extern int gconv_init (struct __gconv_step *step);
int
gconv_init (struct __gconv_step *step)
{
  /* Determine which direction.  */
  struct utf8_data *new_data;
  enum direction dir = illegal_dir;
  int emit_bom;
  int result;

  emit_bom = (__strcasecmp (step->__to_name, "UTF-32//") == 0);

  if (__strcasecmp (step->__from_name, "ISO-10646/UTF8/") == 0
      && (__strcasecmp (step->__to_name, "UTF-32//") == 0
	  || __strcasecmp (step->__to_name, "UTF-32BE//") == 0
	  || __strcasecmp (step->__to_name, "INTERNAL") == 0))
    {
      dir = from_utf8;
    }
  else if (__strcasecmp (step->__to_name, "ISO-10646/UTF8/") == 0
	   && (__strcasecmp (step->__from_name, "UTF-32BE//") == 0
	       || __strcasecmp (step->__from_name, "INTERNAL") == 0))
    {
      dir = to_utf8;
    }

  result = __GCONV_NOCONV;
  if (dir != illegal_dir)
    {
      new_data = (struct utf8_data *) malloc (sizeof (struct utf8_data));

      result = __GCONV_NOMEM;
      if (new_data != NULL)
	{
	  new_data->dir = dir;
	  new_data->emit_bom = emit_bom;
	  step->__data = new_data;

	  if (dir == from_utf8)
	    {
	      step->__min_needed_from = MIN_NEEDED_FROM;
	      step->__max_needed_from = MIN_NEEDED_FROM;
	      step->__min_needed_to = MIN_NEEDED_TO;
	      step->__max_needed_to = MIN_NEEDED_TO;
	    }
	  else
	    {
	      step->__min_needed_from = MIN_NEEDED_TO;
	      step->__max_needed_from = MIN_NEEDED_TO;
	      step->__min_needed_to = MIN_NEEDED_FROM;
	      step->__max_needed_to = MIN_NEEDED_FROM;
	    }

	  step->__stateful = 0;

	  result = __GCONV_OK;
	}
    }

  return result;
}


extern void gconv_end (struct __gconv_step *data);
void
gconv_end (struct __gconv_step *data)
{
  free (data->__data);
}

/* The macro for the hardware loop.  This is used for both
   directions.  */
#define HARDWARE_CONVERT(INSTRUCTION)					\
  {									\
    register const unsigned char* pInput __asm__ ("8") = inptr;		\
    register size_t inlen __asm__ ("9") = inend - inptr;		\
    register unsigned char* pOutput __asm__ ("10") = outptr;		\
    register size_t outlen __asm__("11") = outend - outptr;		\
    unsigned long cc = 0;						\
									\
    __asm__ __volatile__ (".machine push       \n\t"			\
			  ".machine \"z9-109\" \n\t"			\
			  ".machinemode \"zarch_nohighgprs\"\n\t"	\
			  "0: " INSTRUCTION "  \n\t"			\
			  ".machine pop        \n\t"			\
			  "   jo     0b        \n\t"			\
			  "   ipm    %2        \n"			\
			  : "+a" (pOutput), "+a" (pInput), "+d" (cc),	\
			    "+d" (outlen), "+d" (inlen)			\
			  :						\
			  : "cc", "memory");				\
									\
    inptr = pInput;							\
    outptr = pOutput;							\
    cc >>= 28;								\
									\
    if (cc == 1)							\
      {									\
	result = __GCONV_FULL_OUTPUT;					\
      }									\
    else if (cc == 2)							\
      {									\
	result = __GCONV_ILLEGAL_INPUT;					\
      }									\
  }

#define PREPARE_LOOP							\
  enum direction dir = ((struct utf8_data *) step->__data)->dir;	\
  int emit_bom = ((struct utf8_data *) step->__data)->emit_bom;		\
									\
  if (emit_bom && !data->__internal_use					\
      && data->__invocation_counter == 0)				\
    {									\
      /* Emit the Byte Order Mark.  */					\
      if (__glibc_unlikely (outbuf + 4 > outend))			\
	return __GCONV_FULL_OUTPUT;					\
									\
      put32u (outbuf, BOM);						\
      outbuf += 4;							\
    }

/* Conversion function from UTF-8 to UTF-32 internal/BE.  */

#define STORE_REST_COMMON						      \
  {									      \
    /* We store the remaining bytes while converting them into the UCS4	      \
       format.  We can assume that the first byte in the buffer is	      \
       correct and that it requires a larger number of bytes than there	      \
       are in the input buffer.  */					      \
    wint_t ch = **inptrp;						      \
    size_t cnt, r;							      \
									      \
    state->__count = inend - *inptrp;					      \
									      \
    assert (ch != 0xc0 && ch != 0xc1);					      \
    if (ch >= 0xc2 && ch < 0xe0)					      \
      {									      \
	/* We expect two bytes.  The first byte cannot be 0xc0 or	      \
	   0xc1, otherwise the wide character could have been		      \
	   represented using a single byte.  */				      \
	cnt = 2;							      \
	ch &= 0x1f;							      \
      }									      \
    else if (__glibc_likely ((ch & 0xf0) == 0xe0))			      \
      {									      \
	/* We expect three bytes.  */					      \
	cnt = 3;							      \
	ch &= 0x0f;							      \
      }									      \
    else if (__glibc_likely ((ch & 0xf8) == 0xf0))			      \
      {									      \
	/* We expect four bytes.  */					      \
	cnt = 4;							      \
	ch &= 0x07;							      \
      }									      \
    else if (__glibc_likely ((ch & 0xfc) == 0xf8))			      \
      {									      \
	/* We expect five bytes.  */					      \
	cnt = 5;							      \
	ch &= 0x03;							      \
      }									      \
    else								      \
      {									      \
	/* We expect six bytes.  */					      \
	cnt = 6;							      \
	ch &= 0x01;							      \
      }									      \
									      \
    /* The first byte is already consumed.  */				      \
    r = cnt - 1;							      \
    while (++(*inptrp) < inend)						      \
      {									      \
	ch <<= 6;							      \
	ch |= **inptrp & 0x3f;						      \
	--r;								      \
      }									      \
									      \
    /* Shift for the so far missing bytes.  */				      \
    ch <<= r * 6;							      \
									      \
    /* Store the number of bytes expected for the entire sequence.  */	      \
    state->__count |= cnt << 8;						      \
									      \
    /* Store the value.  */						      \
    state->__value.__wch = ch;						      \
  }

#define UNPACK_BYTES_COMMON \
  {									      \
    static const unsigned char inmask[5] = { 0xc0, 0xe0, 0xf0, 0xf8, 0xfc };  \
    wint_t wch = state->__value.__wch;					      \
    size_t ntotal = state->__count >> 8;				      \
									      \
    inlen = state->__count & 255;					      \
									      \
    bytebuf[0] = inmask[ntotal - 2];					      \
									      \
    do									      \
      {									      \
	if (--ntotal < inlen)						      \
	  bytebuf[ntotal] = 0x80 | (wch & 0x3f);			      \
	wch >>= 6;							      \
      }									      \
    while (ntotal > 1);							      \
									      \
    bytebuf[0] |= wch;							      \
  }

#define CLEAR_STATE_COMMON \
  state->__count = 0

#define BODY_FROM_HW(ASM)						\
  {									\
    ASM;								\
    if (__glibc_likely (inptr == inend)					\
	|| result == __GCONV_FULL_OUTPUT)				\
      break;								\
									\
    int i;								\
    for (i = 1; inptr + i < inend && i < 5; ++i)			\
      if ((inptr[i] & 0xc0) != 0x80)					\
	break;								\
									\
    if (__glibc_likely (inptr + i == inend				\
			&& result == __GCONV_EMPTY_INPUT))		\
      {									\
	result = __GCONV_INCOMPLETE_INPUT;				\
	break;								\
      }									\
    STANDARD_FROM_LOOP_ERR_HANDLER (i);					\
  }

/* This hardware routine uses the Convert UTF8 to UTF32 (cu14) instruction.  */
#define BODY_FROM_ETF3EH BODY_FROM_HW (HARDWARE_CONVERT ("cu14 %0, %1, 1"))


/* The software routine is copied from gconv_simple.c.  */
#define BODY_FROM_C							\
  {									\
    /* Next input byte.  */						\
    uint32_t ch = *inptr;						\
									\
    if (__glibc_likely (ch < 0x80))					\
      {									\
	/* One byte sequence.  */					\
	++inptr;							\
      }									\
    else								\
      {									\
	uint_fast32_t cnt;						\
	uint_fast32_t i;						\
									\
	if (ch >= 0xc2 && ch < 0xe0)					\
	  {								\
	    /* We expect two bytes.  The first byte cannot be 0xc0 or	\
	       0xc1, otherwise the wide character could have been	\
	       represented using a single byte.  */			\
	    cnt = 2;							\
	    ch &= 0x1f;							\
	  }								\
	else if (__glibc_likely ((ch & 0xf0) == 0xe0))			\
	  {								\
	    /* We expect three bytes.  */				\
	    cnt = 3;							\
	    ch &= 0x0f;							\
	  }								\
	else if (__glibc_likely ((ch & 0xf8) == 0xf0))			\
	  {								\
	    /* We expect four bytes.  */				\
	    cnt = 4;							\
	    ch &= 0x07;							\
	  }								\
	else								\
	  {								\
	    /* Search the end of this ill-formed UTF-8 character.  This	\
	       is the next byte with (x & 0xc0) != 0x80.  */		\
	    i = 0;							\
	    do								\
	      ++i;							\
	    while (inptr + i < inend					\
		   && (*(inptr + i) & 0xc0) == 0x80			\
		   && i < 5);						\
									\
	  errout:							\
	    STANDARD_FROM_LOOP_ERR_HANDLER (i);				\
	  }								\
									\
	if (__glibc_unlikely (inptr + cnt > inend))			\
	  {								\
	    /* We don't have enough input.  But before we report	\
	       that check that all the bytes are correct.  */		\
	    for (i = 1; inptr + i < inend; ++i)				\
	      if ((inptr[i] & 0xc0) != 0x80)				\
		break;							\
									\
	    if (__glibc_likely (inptr + i == inend))			\
	      {								\
		result = __GCONV_INCOMPLETE_INPUT;			\
		break;							\
	      }								\
									\
	    goto errout;						\
	  }								\
									\
	/* Read the possible remaining bytes.  */			\
	for (i = 1; i < cnt; ++i)					\
	  {								\
	    uint32_t byte = inptr[i];					\
									\
	    if ((byte & 0xc0) != 0x80)					\
	      /* This is an illegal encoding.  */			\
	      break;							\
									\
	    ch <<= 6;							\
	    ch |= byte & 0x3f;						\
	  }								\
									\
	/* If i < cnt, some trail byte was not >= 0x80, < 0xc0.		\
	   If cnt > 2 and ch < 2^(5*cnt-4), the wide character ch could	\
	   have been represented with fewer than cnt bytes.  */		\
	if (i < cnt || (cnt > 2 && (ch >> (5 * cnt - 4)) == 0)		\
	    /* Do not accept UTF-16 surrogates.  */			\
	    || (ch >= 0xd800 && ch <= 0xdfff)				\
	    || (ch > 0x10ffff))						\
	  {								\
	    /* This is an illegal encoding.  */				\
	    goto errout;						\
	  }								\
									\
	inptr += cnt;							\
      }									\
									\
    /* Now adjust the pointers and store the result.  */		\
    *((uint32_t *) outptr) = ch;					\
    outptr += sizeof (uint32_t);					\
  }

#define HW_FROM_VX							\
  {									\
    register const unsigned char* pInput asm ("8") = inptr;		\
    register size_t inlen asm ("9") = inend - inptr;			\
    register unsigned char* pOutput asm ("10") = outptr;		\
    register size_t outlen asm("11") = outend - outptr;			\
    unsigned long tmp, tmp2, tmp3;					\
    asm volatile (".machine push\n\t"					\
		  ".machine \"z13\"\n\t"				\
		  ".machinemode \"zarch_nohighgprs\"\n\t"		\
		  "    vrepib %%v30,0x7f\n\t" /* For compare > 0x7f.  */ \
		  "    vrepib %%v31,0x20\n\t"				\
		  CONVERT_32BIT_SIZE_T ([R_INLEN])			\
		  CONVERT_32BIT_SIZE_T ([R_OUTLEN])			\
		  /* Loop which handles UTF-8 chars <=0x7f.  */		\
		  "0:  clgijl %[R_INLEN],16,20f\n\t"			\
		  "    clgijl %[R_OUTLEN],64,20f\n\t"			\
		  "1: vl %%v16,0(%[R_IN])\n\t"				\
		  "    vstrcbs %%v17,%%v16,%%v30,%%v31\n\t"		\
		  "    jno 10f\n\t" /* Jump away if not all bytes are 1byte \
				   UTF8 chars.  */			\
		  /* Enlarge to UCS4.  */				\
		  "    vuplhb %%v18,%%v16\n\t"				\
		  "    vupllb %%v19,%%v16\n\t"				\
		  "    la %[R_IN],16(%[R_IN])\n\t"			\
		  "    vuplhh %%v20,%%v18\n\t"				\
		  "    aghi %[R_INLEN],-16\n\t"				\
		  "    vupllh %%v21,%%v18\n\t"				\
		  "    aghi %[R_OUTLEN],-64\n\t"			\
		  "    vuplhh %%v22,%%v19\n\t"				\
		  "    vupllh %%v23,%%v19\n\t"				\
		  /* Store 64 bytes to buf_out.  */			\
		  "    vstm %%v20,%%v23,0(%[R_OUT])\n\t"		\
		  "    la %[R_OUT],64(%[R_OUT])\n\t"			\
		  "    clgijl %[R_INLEN],16,20f\n\t"			\
		  "    clgijl %[R_OUTLEN],64,20f\n\t"			\
		  "    j 1b\n\t"					\
		  "10: \n\t"						\
		  /* At least one byte is > 0x7f.			\
		     Store the preceding 1-byte chars.  */		\
		  "    vlgvb %[R_TMP],%%v17,7\n\t"			\
		  "    sllk %[R_TMP2],%[R_TMP],2\n\t" /* Compute highest \
						     index to store. */ \
		  "    llgfr %[R_TMP3],%[R_TMP2]\n\t"			\
		  "    ahi %[R_TMP2],-1\n\t"				\
		  "    jl 20f\n\t"					\
		  "    vuplhb %%v18,%%v16\n\t"				\
		  "    vuplhh %%v20,%%v18\n\t"				\
		  "    vstl %%v20,%[R_TMP2],0(%[R_OUT])\n\t"		\
		  "    ahi %[R_TMP2],-16\n\t"				\
		  "    jl 11f\n\t"					\
		  "    vupllh %%v21,%%v18\n\t"				\
		  "    vstl %%v21,%[R_TMP2],16(%[R_OUT])\n\t"		\
		  "    ahi %[R_TMP2],-16\n\t"				\
		  "    jl 11f\n\t"					\
		  "    vupllb %%v19,%%v16\n\t"				\
		  "    vuplhh %%v22,%%v19\n\t"				\
		  "    vstl %%v22,%[R_TMP2],32(%[R_OUT])\n\t"		\
		  "    ahi %[R_TMP2],-16\n\t"				\
		  "    jl 11f\n\t"					\
		  "    vupllh %%v23,%%v19\n\t"				\
		  "    vstl %%v23,%[R_TMP2],48(%[R_OUT])\n\t"		\
		  "11: \n\t"						\
		  /* Update pointers.  */				\
		  "    la %[R_IN],0(%[R_TMP],%[R_IN])\n\t"		\
		  "    slgr %[R_INLEN],%[R_TMP]\n\t"			\
		  "    la %[R_OUT],0(%[R_TMP3],%[R_OUT])\n\t"		\
		  "    slgr %[R_OUTLEN],%[R_TMP3]\n\t"			\
		  /* Handle multibyte utf8-char with convert instruction. */ \
		  "20: cu14 %[R_OUT],%[R_IN],1\n\t"			\
		  "    jo 0b\n\t" /* Try vector implemenation again.  */ \
		  "    lochil %[R_RES],%[RES_OUT_FULL]\n\t" /* cc == 1.  */ \
		  "    lochih %[R_RES],%[RES_IN_ILL]\n\t" /* cc == 2.  */ \
		  ".machine pop"					\
		  : /* outputs */ [R_IN] "+a" (pInput)			\
		    , [R_INLEN] "+d" (inlen), [R_OUT] "+a" (pOutput)	\
		    , [R_OUTLEN] "+d" (outlen), [R_TMP] "=a" (tmp)	\
		    , [R_TMP2] "=d" (tmp2), [R_TMP3] "=a" (tmp3)	\
		    , [R_RES] "+d" (result)				\
		  : /* inputs */					\
		    [RES_OUT_FULL] "i" (__GCONV_FULL_OUTPUT)		\
		    , [RES_IN_ILL] "i" (__GCONV_ILLEGAL_INPUT)		\
		  : /* clobber list */ "memory", "cc"			\
		    ASM_CLOBBER_VR ("v16") ASM_CLOBBER_VR ("v17")	\
		    ASM_CLOBBER_VR ("v18") ASM_CLOBBER_VR ("v19")	\
		    ASM_CLOBBER_VR ("v20") ASM_CLOBBER_VR ("v21")	\
		    ASM_CLOBBER_VR ("v22") ASM_CLOBBER_VR ("v30")	\
		    ASM_CLOBBER_VR ("v31")				\
		  );							\
    inptr = pInput;							\
    outptr = pOutput;							\
  }
#define BODY_FROM_VX BODY_FROM_HW (HW_FROM_VX)

/* These definitions apply to the UTF-8 to UTF-32 direction.  The
   software implementation for UTF-8 still supports multibyte
   characters up to 6 bytes whereas the hardware variant does not.  */
#define MIN_NEEDED_INPUT	MIN_NEEDED_FROM
#define MAX_NEEDED_INPUT	MAX_NEEDED_FROM
#define MIN_NEEDED_OUTPUT	MIN_NEEDED_TO
#define LOOPFCT			__from_utf8_loop_c

#define LOOP_NEED_FLAGS

#define STORE_REST		STORE_REST_COMMON
#define UNPACK_BYTES		UNPACK_BYTES_COMMON
#define CLEAR_STATE		CLEAR_STATE_COMMON
#define BODY			BODY_FROM_C
#include <iconv/loop.c>


/* Generate loop-function with hardware utf-convert instruction.  */
#define MIN_NEEDED_INPUT	MIN_NEEDED_FROM
#define MAX_NEEDED_INPUT	MAX_NEEDED_FROM
#define MIN_NEEDED_OUTPUT	MIN_NEEDED_TO
#define LOOPFCT			__from_utf8_loop_etf3eh

#define LOOP_NEED_FLAGS

#define STORE_REST		STORE_REST_COMMON
#define UNPACK_BYTES		UNPACK_BYTES_COMMON
#define CLEAR_STATE		CLEAR_STATE_COMMON
#define BODY			BODY_FROM_ETF3EH
#include <iconv/loop.c>

#if defined HAVE_S390_VX_ASM_SUPPORT
/* Generate loop-function with hardware vector instructions.  */
# define MIN_NEEDED_INPUT	MIN_NEEDED_FROM
# define MAX_NEEDED_INPUT	MAX_NEEDED_FROM
# define MIN_NEEDED_OUTPUT	MIN_NEEDED_TO
# define LOOPFCT		__from_utf8_loop_vx

# define LOOP_NEED_FLAGS

# define STORE_REST		STORE_REST_COMMON
# define UNPACK_BYTES		UNPACK_BYTES_COMMON
# define CLEAR_STATE		CLEAR_STATE_COMMON
# define BODY			BODY_FROM_VX
# include <iconv/loop.c>
#endif


/* Generate ifunc'ed loop function.  */
__typeof(__from_utf8_loop_c)
__attribute__ ((ifunc ("__from_utf8_loop_resolver")))
__from_utf8_loop;

static void *
__from_utf8_loop_resolver (unsigned long int dl_hwcap)
{
#if defined HAVE_S390_VX_ASM_SUPPORT
  if (dl_hwcap & HWCAP_S390_VX)
    return __from_utf8_loop_vx;
  else
#endif
  if (dl_hwcap & HWCAP_S390_ZARCH && dl_hwcap & HWCAP_S390_HIGH_GPRS
      && dl_hwcap & HWCAP_S390_ETF3EH)
    return __from_utf8_loop_etf3eh;
  else
    return __from_utf8_loop_c;
}

strong_alias (__from_utf8_loop_c_single, __from_utf8_loop_single)


/* Conversion from UTF-32 internal/BE to UTF-8.  */
#define BODY_TO_HW(ASM)							\
  {									\
    ASM;								\
    if (__glibc_likely (inptr == inend)					\
	|| result == __GCONV_FULL_OUTPUT)				\
      break;								\
    if (inptr + 4 > inend)						\
      {									\
	result = __GCONV_INCOMPLETE_INPUT;				\
	break;								\
      }									\
    STANDARD_TO_LOOP_ERR_HANDLER (4);					\
  }

/* The hardware routine uses the S/390 cu41 instruction.  */
#define BODY_TO_ETF3EH BODY_TO_HW (HARDWARE_CONVERT ("cu41 %0, %1"))

/* The hardware routine uses the S/390 vector and cu41 instructions.  */
#define BODY_TO_VX BODY_TO_HW (HW_TO_VX)

/* The software routine mimics the S/390 cu41 instruction.  */
#define BODY_TO_C						\
  {								\
    uint32_t wc = *((const uint32_t *) inptr);			\
								\
    if (__glibc_likely (wc <= 0x7f))				\
      {								\
	/* Single UTF-8 char.  */				\
	*outptr = (uint8_t)wc;					\
	outptr++;						\
      }								\
    else if (wc <= 0x7ff)					\
      {								\
	/* Two UTF-8 chars.  */					\
	if (__glibc_unlikely (outptr + 2 > outend))		\
	  {							\
	    /* Overflow in the output buffer.  */		\
	    result = __GCONV_FULL_OUTPUT;			\
	    break;						\
	  }							\
								\
	outptr[0] = 0xc0;					\
	outptr[0] |= wc >> 6;					\
								\
	outptr[1] = 0x80;					\
	outptr[1] |= wc & 0x3f;					\
								\
	outptr += 2;						\
      }								\
    else if (wc <= 0xffff)					\
      {								\
	/* Three UTF-8 chars.  */				\
	if (__glibc_unlikely (outptr + 3 > outend))		\
	  {							\
	    /* Overflow in the output buffer.  */		\
	    result = __GCONV_FULL_OUTPUT;			\
	    break;						\
	  }							\
	if (wc >= 0xd800 && wc < 0xdc00)			\
	  {							\
	    /* Do not accept UTF-16 surrogates.   */		\
	    result = __GCONV_ILLEGAL_INPUT;			\
	    STANDARD_TO_LOOP_ERR_HANDLER (4);			\
	  }							\
	outptr[0] = 0xe0;					\
	outptr[0] |= wc >> 12;					\
								\
	outptr[1] = 0x80;					\
	outptr[1] |= (wc >> 6) & 0x3f;				\
								\
	outptr[2] = 0x80;					\
	outptr[2] |= wc & 0x3f;					\
								\
	outptr += 3;						\
      }								\
      else if (wc <= 0x10ffff)					\
	{							\
	  /* Four UTF-8 chars.  */				\
	  if (__glibc_unlikely (outptr + 4 > outend))		\
	    {							\
	      /* Overflow in the output buffer.  */		\
	      result = __GCONV_FULL_OUTPUT;			\
	      break;						\
	    }							\
	  outptr[0] = 0xf0;					\
	  outptr[0] |= wc >> 18;				\
								\
	  outptr[1] = 0x80;					\
	  outptr[1] |= (wc >> 12) & 0x3f;			\
								\
	  outptr[2] = 0x80;					\
	  outptr[2] |= (wc >> 6) & 0x3f;			\
								\
	  outptr[3] = 0x80;					\
	  outptr[3] |= wc & 0x3f;				\
								\
	  outptr += 4;						\
	}							\
      else							\
	{							\
	  STANDARD_TO_LOOP_ERR_HANDLER (4);			\
	}							\
    inptr += 4;							\
  }

#define HW_TO_VX							\
  {									\
    register const unsigned char* pInput asm ("8") = inptr;		\
    register size_t inlen asm ("9") = inend - inptr;			\
    register unsigned char* pOutput asm ("10") = outptr;		\
    register size_t outlen asm("11") = outend - outptr;			\
    unsigned long tmp, tmp2;						\
    asm volatile (".machine push\n\t"					\
		  ".machine \"z13\"\n\t"				\
		  ".machinemode \"zarch_nohighgprs\"\n\t"		\
		  "    vleif %%v20,127,0\n\t"   /* element 0: 127  */	\
		  "    vzero %%v21\n\t"					\
		  "    vleih %%v21,8192,0\n\t"  /* element 0:   >  */	\
		  "    vleih %%v21,-8192,2\n\t" /* element 1: =<>  */	\
		  CONVERT_32BIT_SIZE_T ([R_INLEN])			\
		  CONVERT_32BIT_SIZE_T ([R_OUTLEN])			\
		  /* Loop which handles UTF-32 chars <=0x7f.  */	\
		  "0:  clgijl %[R_INLEN],64,20f\n\t"			\
		  "    clgijl %[R_OUTLEN],16,20f\n\t"			\
		  "1:  vlm %%v16,%%v19,0(%[R_IN])\n\t"			\
		  "    lghi %[R_TMP],0\n\t"				\
		  /* Shorten to byte values.  */			\
		  "    vpkf %%v23,%%v16,%%v17\n\t"			\
		  "    vpkf %%v24,%%v18,%%v19\n\t"			\
		  "    vpkh %%v23,%%v23,%%v24\n\t"			\
		  /* Checking for values > 0x7f.  */			\
		  "    vstrcfs %%v22,%%v16,%%v20,%%v21\n\t"		\
		  "    jno 10f\n\t"					\
		  "    vstrcfs %%v22,%%v17,%%v20,%%v21\n\t"		\
		  "    jno 11f\n\t"					\
		  "    vstrcfs %%v22,%%v18,%%v20,%%v21\n\t"		\
		  "    jno 12f\n\t"					\
		  "    vstrcfs %%v22,%%v19,%%v20,%%v21\n\t"		\
		  "    jno 13f\n\t"					\
		  /* Store 16bytes to outptr.  */			\
		  "    vst %%v23,0(%[R_OUT])\n\t"			\
		  "    aghi %[R_INLEN],-64\n\t"				\
		  "    aghi %[R_OUTLEN],-16\n\t"			\
		  "    la %[R_IN],64(%[R_IN])\n\t"			\
		  "    la %[R_OUT],16(%[R_OUT])\n\t"			\
		  "    clgijl %[R_INLEN],64,20f\n\t"			\
		  "    clgijl %[R_OUTLEN],16,20f\n\t"			\
		  "    j 1b\n\t"					\
		  /* Found a value > 0x7f.  */				\
		  "13: ahi %[R_TMP],4\n\t"				\
		  "12: ahi %[R_TMP],4\n\t"				\
		  "11: ahi %[R_TMP],4\n\t"				\
		  "10: vlgvb %[R_I],%%v22,7\n\t"			\
		  "    srlg %[R_I],%[R_I],2\n\t"			\
		  "    agr %[R_I],%[R_TMP]\n\t"				\
		  "    je 20f\n\t"					\
		  /* Store characters before invalid one...  */		\
		  "    slgr %[R_OUTLEN],%[R_I]\n\t"			\
		  "15: aghi %[R_I],-1\n\t"				\
		  "    vstl %%v23,%[R_I],0(%[R_OUT])\n\t"		\
		  /* ... and update pointers.  */			\
		  "    aghi %[R_I],1\n\t"				\
		  "    la %[R_OUT],0(%[R_I],%[R_OUT])\n\t"		\
		  "    sllg %[R_I],%[R_I],2\n\t"			\
		  "    la %[R_IN],0(%[R_I],%[R_IN])\n\t"		\
		  "    slgr %[R_INLEN],%[R_I]\n\t"			\
		  /* Handle multibyte utf8-char with convert instruction. */ \
		  "20: cu41 %[R_OUT],%[R_IN]\n\t"			\
		  "    jo 0b\n\t" /* Try vector implemenation again.  */ \
		  "    lochil %[R_RES],%[RES_OUT_FULL]\n\t" /* cc == 1.  */ \
		  "    lochih %[R_RES],%[RES_IN_ILL]\n\t" /* cc == 2.  */ \
		  ".machine pop"					\
		  : /* outputs */ [R_IN] "+a" (pInput)			\
		    , [R_INLEN] "+d" (inlen), [R_OUT] "+a" (pOutput)	\
		    , [R_OUTLEN] "+d" (outlen), [R_TMP] "=d" (tmp)	\
		    , [R_I] "=a" (tmp2)					\
		    , [R_RES] "+d" (result)				\
		  : /* inputs */					\
		    [RES_OUT_FULL] "i" (__GCONV_FULL_OUTPUT)		\
		    , [RES_IN_ILL] "i" (__GCONV_ILLEGAL_INPUT)		\
		  : /* clobber list */ "memory", "cc"			\
		    ASM_CLOBBER_VR ("v16") ASM_CLOBBER_VR ("v17")	\
		    ASM_CLOBBER_VR ("v18") ASM_CLOBBER_VR ("v19")	\
		    ASM_CLOBBER_VR ("v20") ASM_CLOBBER_VR ("v21")	\
		    ASM_CLOBBER_VR ("v22") ASM_CLOBBER_VR ("v23")	\
		    ASM_CLOBBER_VR ("v24")				\
		  );							\
    inptr = pInput;							\
    outptr = pOutput;							\
  }

/* Generate loop-function with software routing.  */
#define MIN_NEEDED_INPUT	MIN_NEEDED_TO
#define MIN_NEEDED_OUTPUT	MIN_NEEDED_FROM
#define MAX_NEEDED_OUTPUT	MAX_NEEDED_FROM
#define LOOPFCT			__to_utf8_loop_c
#define BODY			BODY_TO_C
#define LOOP_NEED_FLAGS
#include <iconv/loop.c>

/* Generate loop-function with hardware utf-convert instruction.  */
#define MIN_NEEDED_INPUT	MIN_NEEDED_TO
#define MIN_NEEDED_OUTPUT	MIN_NEEDED_FROM
#define MAX_NEEDED_OUTPUT	MAX_NEEDED_FROM
#define LOOPFCT			__to_utf8_loop_etf3eh
#define LOOP_NEED_FLAGS
#define BODY			BODY_TO_ETF3EH
#include <iconv/loop.c>

#if defined HAVE_S390_VX_ASM_SUPPORT
/* Generate loop-function with hardware vector and utf-convert instructions.  */
# define MIN_NEEDED_INPUT	MIN_NEEDED_TO
# define MIN_NEEDED_OUTPUT	MIN_NEEDED_FROM
# define MAX_NEEDED_OUTPUT	MAX_NEEDED_FROM
# define LOOPFCT		__to_utf8_loop_vx
# define BODY			BODY_TO_VX
# define LOOP_NEED_FLAGS
# include <iconv/loop.c>
#endif

/* Generate ifunc'ed loop function.  */
__typeof(__to_utf8_loop_c)
__attribute__ ((ifunc ("__to_utf8_loop_resolver")))
__to_utf8_loop;

static void *
__to_utf8_loop_resolver (unsigned long int dl_hwcap)
{
#if defined HAVE_S390_VX_ASM_SUPPORT
  if (dl_hwcap & HWCAP_S390_VX)
    return __to_utf8_loop_vx;
  else
#endif
  if (dl_hwcap & HWCAP_S390_ZARCH && dl_hwcap & HWCAP_S390_HIGH_GPRS
      && dl_hwcap & HWCAP_S390_ETF3EH)
    return __to_utf8_loop_etf3eh;
  else
    return __to_utf8_loop_c;
}

strong_alias (__to_utf8_loop_c_single, __to_utf8_loop_single)


#include <iconv/skeleton.c>