[08/14] S390: Optimize utf8-utf16 module.

Message ID 1456219278-5258-9-git-send-email-stli@linux.vnet.ibm.com
State Superseded
Headers

Commit Message

Stefan Liebler Feb. 23, 2016, 9:21 a.m. UTC
  This patch reworks the s390 specific module to convert between utf8 and utf16.
Now ifunc is used to choose either the c or etf3eh (with convert utf instruction)
variants at runtime. Furthermore a new vector variant for z13 is introduced
which will be build and chosen if vector support is available at build / runtime.

In case of converting utf 8 to utf16, the vector variant optimizes input of
1byte utf8 characters. The convert utf instruction is used if a multibyte utf8
character is found.

For the other direction utf16 to utf8, the cu21 instruction can't be re-enabled,
because it does not report an error, if the input-stream consists of a single
low surrogate utf16 char (e.g. 0xdc00). This applies to the newest z13, too.
Thus there is only the c or the new vector variant, which can handle 1..4 byte
utf8 characters.

The c variant from utf16 to utf8 has beed fixed. If a high surrogate was at the
end of the input-buffer, then errno was set to EINVAL and the input-pointer
pointed just after the high surrogate. Now it points to the beginning of the
high surrogate.

This patch also fixes some whitespace errors. The c variant from utf8 to utf16
is now checking that tail-bytes starts with 0b10... and the value is not in
range of an utf16 surrogate.

Furthermore, the etf3eh variants are handling the "UTF-xx//IGNORE" case now.
Before they ignored the ignore-case and always stopped at an error.

ChangeLog:

	* sysdeps/s390/s390-64/utf8-utf16-z9.c: Use ifunc to select c,
	etf3eh or new vector loop-variant.
---
 sysdeps/s390/s390-64/utf8-utf16-z9.c | 547 ++++++++++++++++++++++++++++-------
 1 file changed, 441 insertions(+), 106 deletions(-)
  

Patch

diff --git a/sysdeps/s390/s390-64/utf8-utf16-z9.c b/sysdeps/s390/s390-64/utf8-utf16-z9.c
index 4148ed7..76625d0 100644
--- a/sysdeps/s390/s390-64/utf8-utf16-z9.c
+++ b/sysdeps/s390/s390-64/utf8-utf16-z9.c
@@ -30,33 +30,27 @@ 
 #include <dl-procinfo.h>
 #include <gconv.h>
 
-/* UTF-16 big endian byte order mark.  */
-#define BOM_UTF16	0xfeff
+#if defined HAVE_S390_VX_GCC_SUPPORT
+# define ASM_CLOBBER_VR(NR) , NR
+#else
+# define ASM_CLOBBER_VR(NR)
+#endif
 
+/* Defines for skeleton.c.  */
 #define DEFINE_INIT		0
 #define DEFINE_FINI		0
 #define MIN_NEEDED_FROM		1
 #define MAX_NEEDED_FROM		4
 #define MIN_NEEDED_TO		2
 #define MAX_NEEDED_TO		4
-#define FROM_LOOP		from_utf8_loop
-#define TO_LOOP			to_utf8_loop
+#define FROM_LOOP		__from_utf8_loop
+#define TO_LOOP			__to_utf8_loop
 #define FROM_DIRECTION		(dir == from_utf8)
 #define ONE_DIRECTION           0
-#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 UTF-16 Byte Order Mark.  */				\
-      if (__glibc_unlikely (outbuf + 2 > outend))			      \
-	return __GCONV_FULL_OUTPUT;					\
-									\
-      put16u (outbuf, BOM_UTF16);					\
-      outbuf += 2;							\
-    }
+
+
+/* UTF-16 big endian byte order mark.  */
+#define BOM_UTF16	0xfeff
 
 /* Direction of the transformation.  */
 enum direction
@@ -151,16 +145,16 @@  gconv_end (struct __gconv_step *data)
     register unsigned long long outlen __asm__("11") = outend - outptr;	\
     uint64_t cc = 0;							\
 									\
-    __asm__ volatile (".machine push       \n\t"			\
-		      ".machine \"z9-109\" \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");				\
+    __asm__ __volatile__ (".machine push       \n\t"			\
+			  ".machine \"z9-109\" \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;							\
@@ -169,50 +163,135 @@  gconv_end (struct __gconv_step *data)
     if (cc == 1)							\
       {									\
 	result = __GCONV_FULL_OUTPUT;					\
-	break;								\
       }									\
     else if (cc == 2)							\
       {									\
 	result = __GCONV_ILLEGAL_INPUT;					\
-	break;								\
       }									\
   }
 
+#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 UTF-16 Byte Order Mark.  */				\
+      if (__glibc_unlikely (outbuf + 2 > outend))			\
+	return __GCONV_FULL_OUTPUT;					\
+									\
+      put16u (outbuf, BOM_UTF16);					\
+      outbuf += 2;							\
+    }
+
 /* Conversion function from UTF-8 to UTF-16.  */
+#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);					\
+  }
+
+#define BODY_FROM_ETF3EH BODY_FROM_HW (HARDWARE_CONVERT ("cu12 %0, %1, 1"))
+
+#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"				\
+		  /* Loop which handles UTF-8 chars <=0x7f.  */		\
+		  "0: clgijl %[R_INLEN],16,20f\n\t"			\
+		  "clgijl %[R_OUTLEN],32,20f\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 UTF-16.  */				\
+		  "vuplhb %%v18,%%v16\n\t"				\
+		  "la %[R_IN],16(%[R_IN])\n\t"				\
+		  "vupllb %%v19,%%v16\n\t"				\
+		  "aghi %[R_INLEN],-16\n\t"				\
+		  /* Store 32 bytes to buf_out.  */			\
+		  "vstm %%v18,%%v19,0(%[R_OUT])\n\t"			\
+		  "aghi %[R_OUTLEN],-32\n\t"				\
+		  "la %[R_OUT],32(%[R_OUT])\n\t"			\
+		  "clgijl %[R_INLEN],16,20f\n\t"			\
+		  "clgijl %[R_OUTLEN],32,20f\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],1\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"				\
+		  "vstl %%v18,%[R_TMP2],0(%[R_OUT])\n\t"		\
+		  "ahi %[R_TMP2],-16\n\t"				\
+		  "jl 11f\n\t"						\
+		  "vupllb %%v19,%%v16\n\t"				\
+		  "vstl %%v19,%[R_TMP2],16(%[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: cu12 %[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 ("v30") ASM_CLOBBER_VR ("v31")	\
+		  );							\
+    inptr = pInput;							\
+    outptr = pOutput;							\
+  }
+#define BODY_FROM_VX BODY_FROM_HW (HW_FROM_VX)
+
 
-#define MIN_NEEDED_INPUT	MIN_NEEDED_FROM
-#define MAX_NEEDED_INPUT	MAX_NEEDED_FROM
-#define MIN_NEEDED_OUTPUT	MIN_NEEDED_TO
-#define MAX_NEEDED_OUTPUT	MAX_NEEDED_TO
-#define LOOPFCT			FROM_LOOP
 /* The software implementation is based on the code in gconv_simple.c.  */
-#define BODY								\
+#define BODY_FROM_C							\
   {									\
-    if (GLRO (dl_hwcap) & HWCAP_S390_ETF3EH)				\
-      {									\
-	HARDWARE_CONVERT ("cu12 %0, %1, 1");				\
-									\
-	if (inptr != inend)						\
-	  {								\
-	    int i;							\
-	    for (i = 1; inptr + i < inend; ++i)				\
-	      if ((inptr[i] & 0xc0) != 0x80)				\
-		break;							\
-								\
-	    if (__glibc_likely (inptr + i == inend))			      \
-	      {								\
-		result = __GCONV_INCOMPLETE_INPUT;			\
-		break;							\
-	      }								\
-	    STANDARD_FROM_LOOP_ERR_HANDLER (i);				\
-	  }								\
-	continue;							\
-    }									\
-									\
     /* Next input byte.  */						\
     uint16_t ch = *inptr;						\
 									\
-    if (__glibc_likely (ch < 0x80))					      \
+    if (__glibc_likely (ch < 0x80))					\
       {									\
 	/* One byte sequence.  */					\
 	++inptr;							\
@@ -230,13 +309,13 @@  gconv_end (struct __gconv_step *data)
 	    cnt = 2;							\
 	    ch &= 0x1f;							\
 	  }								\
-        else if (__glibc_likely ((ch & 0xf0) == 0xe0))			      \
+	else if (__glibc_likely ((ch & 0xf0) == 0xe0))			\
 	  {								\
 	    /* We expect three bytes.  */				\
 	    cnt = 3;							\
 	    ch &= 0x0f;							\
 	  }								\
-	else if (__glibc_likely ((ch & 0xf8) == 0xf0))			      \
+	else if (__glibc_likely ((ch & 0xf8) == 0xf0))			\
 	  {								\
 	    /* We expect four bytes.  */				\
 	    cnt = 4;							\
@@ -257,7 +336,7 @@  gconv_end (struct __gconv_step *data)
 	    STANDARD_FROM_LOOP_ERR_HANDLER (i);				\
 	  }								\
 									\
-	if (__glibc_unlikely (inptr + cnt > inend))			      \
+	if (__glibc_unlikely (inptr + cnt > inend))			\
 	  {								\
 	    /* We don't have enough input.  But before we report	\
 	       that check that all the bytes are correct.  */		\
@@ -265,7 +344,7 @@  gconv_end (struct __gconv_step *data)
 	      if ((inptr[i] & 0xc0) != 0x80)				\
 		break;							\
 									\
-	    if (__glibc_likely (inptr + i == inend))			      \
+	    if (__glibc_likely (inptr + i == inend))			\
 	      {								\
 		result = __GCONV_INCOMPLETE_INPUT;			\
 		break;							\
@@ -280,23 +359,31 @@  gconv_end (struct __gconv_step *data)
 	       low) are needed.  */					\
 	    uint16_t zabcd, high, low;					\
 									\
-	    if (__glibc_unlikely (outptr + 4 > outend))			      \
+	    if (__glibc_unlikely (outptr + 4 > outend))			\
 	      {								\
 		/* Overflow in the output buffer.  */			\
 		result = __GCONV_FULL_OUTPUT;				\
 		break;							\
 	      }								\
 									\
+	    /* Check if tail-bytes >= 0x80, < 0xc0.  */			\
+	    for (i = 1; i < cnt; ++i)					\
+	      {								\
+		if ((inptr[i] & 0xc0) != 0x80)				\
+		  /* This is an illegal encoding.  */			\
+		  goto errout;						\
+	      }								\
+									\
 	    /* See Principles of Operations cu12.  */			\
 	    zabcd = (((inptr[0] & 0x7) << 2) |				\
-                     ((inptr[1] & 0x30) >> 4)) - 1;			\
+		     ((inptr[1] & 0x30) >> 4)) - 1;			\
 									\
 	    /* z-bit must be zero after subtracting 1.  */		\
 	    if (zabcd & 0x10)						\
 	      STANDARD_FROM_LOOP_ERR_HANDLER (4)			\
 									\
 	    high = (uint16_t)(0xd8 << 8);       /* high surrogate id */ \
-	    high |= zabcd << 6;	                        /* abcd bits */	\
+	    high |= zabcd << 6;                         /* abcd bits */	\
 	    high |= (inptr[1] & 0xf) << 2;              /* efgh bits */	\
 	    high |= (inptr[2] & 0x30) >> 4;               /* ij bits */	\
 									\
@@ -326,8 +413,19 @@  gconv_end (struct __gconv_step *data)
 		ch <<= 6;						\
 		ch |= byte & 0x3f;					\
 	      }								\
-	    inptr += cnt;						\
 									\
+	    /* 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))			\
+	      {								\
+		/* This is an illegal encoding.  */			\
+		goto errout;						\
+	      }								\
+									\
+	    inptr += cnt;						\
 	  }								\
       }									\
     /* Now adjust the pointers and store the result.  */		\
@@ -335,43 +433,70 @@  gconv_end (struct __gconv_step *data)
     outptr += sizeof (uint16_t);					\
   }
 
+/* Generate loop-function with software implementation.  */
+#define MIN_NEEDED_INPUT	MIN_NEEDED_FROM
+#define MAX_NEEDED_INPUT	MAX_NEEDED_FROM
+#define MIN_NEEDED_OUTPUT	MIN_NEEDED_TO
+#define MAX_NEEDED_OUTPUT	MAX_NEEDED_TO
+#define LOOPFCT			__from_utf8_loop_c
+#define LOOP_NEED_FLAGS
+#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 MAX_NEEDED_OUTPUT	MAX_NEEDED_TO
+#define LOOPFCT			__from_utf8_loop_etf3eh
 #define LOOP_NEED_FLAGS
+#define BODY			BODY_FROM_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_FROM
+# define MAX_NEEDED_INPUT	MAX_NEEDED_FROM
+# define MIN_NEEDED_OUTPUT	MIN_NEEDED_TO
+# define MAX_NEEDED_OUTPUT	MAX_NEEDED_TO
+# define LOOPFCT		__from_utf8_loop_vx
+# define LOOP_NEED_FLAGS
+# 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_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-16 to UTF-8.  */
 
-#define MIN_NEEDED_INPUT	MIN_NEEDED_TO
-#define MAX_NEEDED_INPUT	MAX_NEEDED_TO
-#define MIN_NEEDED_OUTPUT	MIN_NEEDED_FROM
-#define MAX_NEEDED_OUTPUT	MAX_NEEDED_FROM
-#define LOOPFCT			TO_LOOP
 /* The software routine is based on the functionality of the S/390
    hardware instruction (cu21) as described in the Principles of
    Operation.  */
-#define BODY								\
+#define BODY_TO_C							\
   {									\
-    /* The hardware instruction currently fails to report an error for	\
-       isolated low surrogates so we have to disable the instruction	\
-       until this gets resolved.  */					\
-    if (0) /* (GLRO (dl_hwcap) & HWCAP_S390_ETF3EH) */			\
-      {									\
-	HARDWARE_CONVERT ("cu21 %0, %1, 1");				\
-	if (inptr != inend)						\
-	  {								\
-	    /* Check if the third byte is				\
-	       a valid start of a UTF-16 surrogate.  */			\
-	    if (inend - inptr == 3 && (inptr[3] & 0xfc) != 0xdc)	\
-	      STANDARD_TO_LOOP_ERR_HANDLER (3);				\
-									\
-	    result = __GCONV_INCOMPLETE_INPUT;				\
-	    break;							\
-	  }								\
-	continue;							\
-      }									\
-									\
     uint16_t c = get16 (inptr);						\
 									\
-    if (__glibc_likely (c <= 0x007f))					      \
+    if (__glibc_likely (c <= 0x007f))					\
       {									\
 	/* Single byte UTF-8 char.  */					\
 	*outptr = c & 0xff;						\
@@ -379,20 +504,20 @@  gconv_end (struct __gconv_step *data)
       }									\
     else if (c >= 0x0080 && c <= 0x07ff)				\
       {									\
-        /* Two byte UTF-8 char.  */					\
+	/* Two byte UTF-8 char.  */					\
 									\
-	if (__glibc_unlikely (outptr + 2 > outend))			      \
+	if (__glibc_unlikely (outptr + 2 > outend))			\
 	  {								\
 	    /* Overflow in the output buffer.  */			\
 	    result = __GCONV_FULL_OUTPUT;				\
 	    break;							\
 	  }								\
 									\
-        outptr[0] = 0xc0;						\
-        outptr[0] |= c >> 6;						\
+	outptr[0] = 0xc0;						\
+	outptr[0] |= c >> 6;						\
 									\
-        outptr[1] = 0x80;						\
-        outptr[1] |= c & 0x3f;						\
+	outptr[1] = 0x80;						\
+	outptr[1] |= c & 0x3f;						\
 									\
 	outptr += 2;							\
       }									\
@@ -400,7 +525,7 @@  gconv_end (struct __gconv_step *data)
       {									\
 	/* Three byte UTF-8 char.  */					\
 									\
-	if (__glibc_unlikely (outptr + 3 > outend))			      \
+	if (__glibc_unlikely (outptr + 3 > outend))			\
 	  {								\
 	    /* Overflow in the output buffer.  */			\
 	    result = __GCONV_FULL_OUTPUT;				\
@@ -419,22 +544,22 @@  gconv_end (struct __gconv_step *data)
       }									\
     else if (c >= 0xd800 && c <= 0xdbff)				\
       {									\
-        /* Four byte UTF-8 char.  */					\
+	/* Four byte UTF-8 char.  */					\
 	uint16_t low, uvwxy;						\
 									\
-	if (__glibc_unlikely (outptr + 4 > outend))			      \
+	if (__glibc_unlikely (outptr + 4 > outend))			\
 	  {								\
 	    /* Overflow in the output buffer.  */			\
 	    result = __GCONV_FULL_OUTPUT;				\
 	    break;							\
 	  }								\
-	inptr += 2;							\
-	if (__glibc_unlikely (inptr + 2 > inend))			      \
+	if (__glibc_unlikely (inptr + 4 > inend))			\
 	  {								\
 	    result = __GCONV_INCOMPLETE_INPUT;				\
 	    break;							\
 	  }								\
 									\
+	inptr += 2;							\
 	low = get16 (inptr);						\
 									\
 	if ((low & 0xfc00) != 0xdc00)					\
@@ -461,11 +586,221 @@  gconv_end (struct __gconv_step *data)
       }									\
     else								\
       {									\
-        STANDARD_TO_LOOP_ERR_HANDLER (2);				\
+	STANDARD_TO_LOOP_ERR_HANDLER (2);				\
       }									\
     inptr += 2;								\
   }
-#define LOOP_NEED_FLAGS
-#include <iconv/loop.c>
+
+#define BODY_TO_VX							\
+  {									\
+    size_t inlen  = inend - inptr;					\
+    size_t outlen  = outend - outptr;					\
+    unsigned long tmp, tmp2, tmp3;					\
+    asm volatile (".machine push\n\t"					\
+		  ".machine \"z13\"\n\t"				\
+		  ".machinemode \"zarch_nohighgprs\"\n\t"		\
+		  /* Setup to check for values <= 0x7f.  */		\
+		  "larl %[R_TMP],9f\n\t"				\
+		  "vlm %%v30,%%v31,0(%[R_TMP])\n\t"			\
+		  /* Loop which handles UTF-16 chars <=0x7f.  */	\
+		  "0: clgijl %[R_INLEN],32,2f\n\t"			\
+		  "clgijl %[R_OUTLEN],16,2f\n\t"			\
+		  "1: vlm %%v16,%%v17,0(%[R_IN])\n\t"			\
+		  "lghi %[R_TMP2],0\n\t"				\
+		  /* Check for > 1byte UTF-8 chars.  */			\
+		  "vstrchs %%v19,%%v16,%%v30,%%v31\n\t"			\
+		  "jno 10f\n\t" /* Jump away if not all bytes are 1byte	\
+				   UTF8 chars.  */			\
+		  "vstrchs %%v19,%%v17,%%v30,%%v31\n\t"			\
+		  "jno 11f\n\t" /* Jump away if not all bytes are 1byte	\
+				   UTF8 chars.  */			\
+		  /* Shorten to UTF-8.  */				\
+		  "vpkh %%v18,%%v16,%%v17\n\t"				\
+		  "la %[R_IN],32(%[R_IN])\n\t"				\
+		  "aghi %[R_INLEN],-32\n\t"				\
+		  /* Store 16 bytes to buf_out.  */			\
+		  "vst %%v18,0(%[R_OUT])\n\t"				\
+		  "aghi %[R_OUTLEN],-16\n\t"				\
+		  "la %[R_OUT],16(%[R_OUT])\n\t"			\
+		  "clgijl %[R_INLEN],32,2f\n\t"				\
+		  "clgijl %[R_OUTLEN],16,2f\n\t"			\
+		  "j 1b\n\t"						\
+		  /* Setup to check for ch > 0x7f. (v30, v31)  */	\
+		  "9: .short 0x7f,0x7f,0x0,0x0,0x0,0x0,0x0,0x0\n\t"	\
+		  ".short 0x2000,0x2000,0x0,0x0,0x0,0x0,0x0,0x0\n\t"	\
+		  /* At least one byte is > 0x7f.			\
+		     Store the preceding 1-byte chars.  */		\
+		  "11: lghi %[R_TMP2],16\n\t" /* match was found in v17.  */ \
+		  "10:\n\t"						\
+		  "vlgvb %[R_TMP],%%v19,7\n\t"				\
+		  /* Shorten to UTF-8.  */				\
+		  "vpkh %%v18,%%v16,%%v17\n\t"				\
+		  "ar %[R_TMP],%[R_TMP2]\n\t" /* Number of in bytes.  */ \
+		  "srlg %[R_TMP3],%[R_TMP],1\n\t" /* Number of out bytes.  */ \
+		  "ahik %[R_TMP2],%[R_TMP3],-1\n\t" /* Highest index to store.  */ \
+		  "jl 13f\n\t"						\
+		  "vstl %%v18,%[R_TMP2],0(%[R_OUT])\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"			\
+		  "13:\n\t"						\
+		  /* Calculate remaining uint16_t values in loaded vrs.  */ \
+		  "lghi %[R_TMP2],16\n\t"				\
+		  "slgr %[R_TMP2],%[R_TMP3]\n\t"			\
+		  "llh %[R_TMP],0(%[R_IN])\n\t"				\
+		  "aghi %[R_INLEN],-2\n\t"				\
+		  "j 22f\n\t"						\
+		  /* Handle remaining bytes.  */			\
+		  "2:\n\t"						\
+		  /* Zero, one or more bytes available?  */		\
+		  "clgfi %[R_INLEN],1\n\t"				\
+		  "locghie %[R_RES],%[RES_IN_FULL]\n\t" /* Only one byte.  */ \
+		  "jle 99f\n\t" /* End if less than two bytes.  */	\
+		  /* Calculate remaining uint16_t values in inptr.  */	\
+		  "srlg %[R_TMP2],%[R_INLEN],1\n\t"			\
+		  /* Handle multibyte utf8-char. */			\
+		  "20: llh %[R_TMP],0(%[R_IN])\n\t"			\
+		  "aghi %[R_INLEN],-2\n\t"				\
+		  /* Test if ch is 1-byte UTF-8 char.  */		\
+		  "21: clijh %[R_TMP],0x7f,22f\n\t"			\
+		  /* Handle 1-byte UTF-8 char.  */			\
+		  "31: slgfi %[R_OUTLEN],1\n\t"				\
+		  "jl 90f \n\t"						\
+		  "stc %[R_TMP],0(%[R_OUT])\n\t"			\
+		  "la %[R_IN],2(%[R_IN])\n\t"				\
+		  "la %[R_OUT],1(%[R_OUT])\n\t"				\
+		  "brctg %[R_TMP2],20b\n\t"				\
+		  "j 0b\n\t" /* Switch to vx-loop.  */			\
+		  /* Test if ch is 2-byte UTF-8 char.  */		\
+		  "22: clfi %[R_TMP],0x7ff\n\t"				\
+		  "jh 23f\n\t"						\
+		  /* Handle 2-byte UTF-8 char.  */			\
+		  "32: slgfi %[R_OUTLEN],2\n\t"				\
+		  "jl 90f \n\t"						\
+		  "llill %[R_TMP3],0xc080\n\t"				\
+		  "la %[R_IN],2(%[R_IN])\n\t"				\
+		  "risbgn %[R_TMP3],%[R_TMP],51,55,2\n\t" /* 1. byte.   */ \
+		  "risbgn %[R_TMP3],%[R_TMP],58,63,0\n\t" /* 2. byte.   */ \
+		  "sth %[R_TMP3],0(%[R_OUT])\n\t"			\
+		  "la %[R_OUT],2(%[R_OUT])\n\t"				\
+		  "brctg %[R_TMP2],20b\n\t"				\
+		  "j 0b\n\t" /* Switch to vx-loop.  */			\
+		  /* Test if ch is 3-byte UTF-8 char.  */		\
+		  "23: clfi %[R_TMP],0xd7ff\n\t"			\
+		  "jh 24f\n\t"						\
+		  /* Handle 3-byte UTF-8 char.  */			\
+		  "33: slgfi %[R_OUTLEN],3\n\t"				\
+		  "jl 90f \n\t"						\
+		  "llilf %[R_TMP3],0xe08080\n\t"			\
+		  "la %[R_IN],2(%[R_IN])\n\t"				\
+		  "risbgn %[R_TMP3],%[R_TMP],44,47,4\n\t" /* 1. byte.  */ \
+		  "risbgn %[R_TMP3],%[R_TMP],50,55,2\n\t" /* 2. byte.  */ \
+		  "risbgn %[R_TMP3],%[R_TMP],58,63,0\n\t" /* 3. byte.  */ \
+		  "stcm %[R_TMP3],7,0(%[R_OUT])\n\t"			\
+		  "la %[R_OUT],3(%[R_OUT])\n\t"				\
+		  "brctg %[R_TMP2],20b\n\t"				\
+		  "j 0b\n\t" /* Switch to vx-loop.  */			\
+		  /* Test if ch is 4-byte UTF-8 char.  */		\
+		  "24: clfi %[R_TMP],0xdfff\n\t"			\
+		  "jh 33b\n\t" /* Handle this 3-byte UTF-8 char.  */	\
+		  "clfi %[R_TMP],0xdbff\n\t"				\
+		  "locghih %[R_RES],%[RES_IN_ILL]\n\t"			\
+		  "jh 99f\n\t" /* Jump away if this is a low surrogate	\
+				  without a preceding high surrogate.  */ \
+		  /* Handle 4-byte UTF-8 char.  */			\
+		  "34: slgfi %[R_OUTLEN],4\n\t"				\
+		  "jl 90f \n\t"						\
+		  "slgfi %[R_INLEN],2\n\t"				\
+		  "locghil %[R_RES],%[RES_IN_FULL]\n\t"			\
+		  "jl 99f\n\t" /* Jump away if low surrogate is missing.  */ \
+		  "llilf %[R_TMP3],0xf0808080\n\t"			\
+		  "aghi %[R_TMP],0x40\n\t"				\
+		  "risbgn %[R_TMP3],%[R_TMP],37,39,16\n\t" /* 1. byte: uvw  */ \
+		  "risbgn %[R_TMP3],%[R_TMP],42,43,14\n\t" /* 2. byte: xy  */ \
+		  "risbgn %[R_TMP3],%[R_TMP],44,47,14\n\t" /* 2. byte: efgh  */	\
+		  "risbgn %[R_TMP3],%[R_TMP],50,51,12\n\t" /* 3. byte: ij */ \
+		  "llh %[R_TMP],2(%[R_IN])\n\t" /* Load low surrogate.  */ \
+		  "risbgn %[R_TMP3],%[R_TMP],52,55,2\n\t" /* 3. byte: klmn  */ \
+		  "risbgn %[R_TMP3],%[R_TMP],58,63,0\n\t" /* 4. byte: opqrst  */ \
+		  "nilf %[R_TMP],0xfc00\n\t"				\
+		  "clfi %[R_TMP],0xdc00\n\t" /* Check if it starts with 0xdc00.  */ \
+		  "locghine %[R_RES],%[RES_IN_ILL]\n\t"			\
+		  "jne 99f\n\t" /* Jump away if low surrogate is invalid.  */ \
+		  "st %[R_TMP3],0(%[R_OUT])\n\t"			\
+		  "la %[R_IN],4(%[R_IN])\n\t"				\
+		  "la %[R_OUT],4(%[R_OUT])\n\t"				\
+		  "aghi %[R_TMP2],-2\n\t"				\
+		  "jh 20b\n\t"						\
+		  "j 0b\n\t" /* Switch to vx-loop.  */			\
+		  /* Exit with __GCONV_FULL_OUTPUT.  */			\
+		  "90: lghi %[R_RES],%[RES_OUT_FULL]\n\t"		\
+		  "99:\n\t"						\
+		  ".machine pop"					\
+		  : /* outputs */ [R_IN] "+a" (inptr)			\
+		    , [R_INLEN] "+d" (inlen), [R_OUT] "+a" (outptr)	\
+		    , [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)		\
+		    , [RES_IN_FULL] "i" (__GCONV_INCOMPLETE_INPUT)	\
+		  : /* clobber list */ "memory", "cc"			\
+		    ASM_CLOBBER_VR ("v16") ASM_CLOBBER_VR ("v17")	\
+		    ASM_CLOBBER_VR ("v18") ASM_CLOBBER_VR ("v19")	\
+		    ASM_CLOBBER_VR ("v30") ASM_CLOBBER_VR ("v31")	\
+		  );							\
+    if (__glibc_likely (inptr == inend)					\
+	|| result != __GCONV_ILLEGAL_INPUT)				\
+      break;								\
+									\
+    STANDARD_TO_LOOP_ERR_HANDLER (2);					\
+  }
+
+/* Generate loop-function with software implementation.  */
+#define MIN_NEEDED_INPUT	MIN_NEEDED_TO
+#define MAX_NEEDED_INPUT	MAX_NEEDED_TO
+#define MIN_NEEDED_OUTPUT	MIN_NEEDED_FROM
+#define MAX_NEEDED_OUTPUT	MAX_NEEDED_FROM
+#if defined HAVE_S390_VX_ASM_SUPPORT
+# define LOOPFCT		__to_utf8_loop_c
+# define BODY                   BODY_TO_C
+# define LOOP_NEED_FLAGS
+# include <iconv/loop.c>
+
+/* Generate loop-function with software implementation.  */
+# define MIN_NEEDED_INPUT	MIN_NEEDED_TO
+# define MAX_NEEDED_INPUT	MAX_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>
+
+/* 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 (dl_hwcap & HWCAP_S390_VX)
+    return __to_utf8_loop_vx;
+  else
+    return __to_utf8_loop_c;
+}
+
+strong_alias (__to_utf8_loop_c_single, __to_utf8_loop_single)
+
+#else
+# define LOOPFCT		TO_LOOP
+# define BODY                   BODY_TO_C
+# define LOOP_NEED_FLAGS
+# include <iconv/loop.c>
+#endif /* !HAVE_S390_VX_ASM_SUPPORT  */
 
 #include <iconv/skeleton.c>