[v2,1/3] newlib: riscv: Add memchr() and memrchr() implementations

Message ID 4d1db27470f8833edb05693f286c63cfd001c01f.1746628687.git.ericsalem@gmail.com
State New
Headers
Series newlib: riscv: Add and optimize memchr() and memrchr() functions |

Commit Message

Eric Salem May 7, 2025, 2:46 p.m. UTC
  Copy stock implementations of memchr() and memrchr() to the RISC-V port.

Reviewed-by: Christian Herber <christian.herber@oss.nxp.com>
Signed-off-by: Eric Salem <ericsalem@gmail.com>
---
 newlib/libc/machine/riscv/Makefile.inc |  2 +-
 newlib/libc/machine/riscv/memchr.c     | 99 ++++++++++++++++++++++++++
 newlib/libc/machine/riscv/memrchr.c    | 99 ++++++++++++++++++++++++++
 3 files changed, 199 insertions(+), 1 deletion(-)
 create mode 100644 newlib/libc/machine/riscv/memchr.c
 create mode 100644 newlib/libc/machine/riscv/memrchr.c
  

Patch

diff --git a/newlib/libc/machine/riscv/Makefile.inc b/newlib/libc/machine/riscv/Makefile.inc
index 4d6c0469abb3..85bed91772cf 100644
--- a/newlib/libc/machine/riscv/Makefile.inc
+++ b/newlib/libc/machine/riscv/Makefile.inc
@@ -1,3 +1,3 @@ 
 libc_a_SOURCES += \
 	%D%/memmove.S %D%/memmove-stub.c %D%/memset.S %D%/memcpy-asm.S %D%/memcpy.c %D%/strlen.c \
-	%D%/strcpy.c %D%/stpcpy.c %D%/strcmp.S %D%/setjmp.S %D%/ieeefp.c %D%/ffs.c
+	%D%/strcpy.c %D%/stpcpy.c %D%/strcmp.S %D%/memchr.c %D%/memrchr.c %D%/setjmp.S %D%/ieeefp.c %D%/ffs.c
diff --git a/newlib/libc/machine/riscv/memchr.c b/newlib/libc/machine/riscv/memchr.c
new file mode 100644
index 000000000000..5c08c12813fe
--- /dev/null
+++ b/newlib/libc/machine/riscv/memchr.c
@@ -0,0 +1,99 @@ 
+/*
+FUNCTION
+	<<memchr>>---find character in memory
+
+INDEX
+	memchr
+
+SYNOPSIS
+	#include <string.h>
+	void *memchr(const void *<[src]>, int <[c]>, size_t <[length]>);
+
+DESCRIPTION
+	This function searches memory starting at <<*<[src]>>> for the
+	character <[c]>.  The search only ends with the first
+	occurrence of <[c]>, or after <[length]> characters; in
+	particular, <<NUL>> does not terminate the search.
+
+RETURNS
+	If the character <[c]> is found within <[length]> characters
+	of <<*<[src]>>>, a pointer to the character is returned. If
+	<[c]> is not found, then <<NULL>> is returned.
+
+PORTABILITY
+<<memchr>> is ANSI C.
+
+<<memchr>> requires no supporting OS subroutines.
+
+QUICKREF
+	memchr ansi pure
+*/
+
+#include <_ansi.h>
+#include <string.h>
+#include <limits.h>
+#include "../../string/local.h"
+
+void *
+memchr (const void *src_void,
+	int c,
+	size_t length)
+{
+  const unsigned char *src = (const unsigned char *) src_void;
+  unsigned char d = c;
+
+#if !defined(PREFER_SIZE_OVER_SPEED) && !defined(__OPTIMIZE_SIZE__)
+  unsigned long *asrc;
+  unsigned long  mask;
+  unsigned int i;
+
+  while (UNALIGNED_X(src))
+    {
+      if (!length--)
+        return NULL;
+      if (*src == d)
+        return (void *) src;
+      src++;
+    }
+
+  if (!TOO_SMALL_LITTLE_BLOCK(length))
+    {
+      /* If we get this far, we know that length is large and src is
+         word-aligned. */
+      /* The fast code reads the source one word at a time and only
+         performs the bytewise search on word-sized segments if they
+         contain the search character, which is detected by XORing
+         the word-sized segment with a word-sized block of the search
+         character and then detecting for the presence of NUL in the
+         result.  */
+      asrc = (unsigned long *) src;
+      mask = d << 8 | d;
+      mask = mask << 16 | mask;
+      for (i = 32; i < sizeof(mask) * 8; i <<= 1)
+        mask = (mask << i) | mask;
+
+      while (!TOO_SMALL_LITTLE_BLOCK(length))
+        {
+          if (DETECT_CHAR(*asrc, mask))
+            break;
+          length -= LITTLE_BLOCK_SIZE;
+          asrc++;
+        }
+
+      /* If there are fewer than LITTLE_BLOCK_SIZE characters left,
+         then we resort to the bytewise loop.  */
+
+      src = (unsigned char *) asrc;
+    }
+
+#endif /* not PREFER_SIZE_OVER_SPEED */
+
+  while (length--)
+    {
+      if (*src == d)
+        return (void *) src;
+      src++;
+    }
+
+  return NULL;
+}
diff --git a/newlib/libc/machine/riscv/memrchr.c b/newlib/libc/machine/riscv/memrchr.c
new file mode 100644
index 000000000000..8d15ccb780ec
--- /dev/null
+++ b/newlib/libc/machine/riscv/memrchr.c
@@ -0,0 +1,99 @@ 
+/*
+FUNCTION
+	<<memrchr>>---reverse search for character in memory
+
+INDEX
+	memrchr
+
+SYNOPSIS
+	#include <string.h>
+	void *memrchr(const void *<[src]>, int <[c]>, size_t <[length]>);
+
+DESCRIPTION
+	This function searches memory starting at <[length]> bytes
+	beyond <<*<[src]>>> backwards for the character <[c]>.
+	The search only ends with the first occurrence of <[c]>; in
+	particular, <<NUL>> does not terminate the search.
+
+RETURNS
+	If the character <[c]> is found within <[length]> characters
+	of <<*<[src]>>>, a pointer to the character is returned. If
+	<[c]> is not found, then <<NULL>> is returned.
+
+PORTABILITY
+<<memrchr>> is a GNU extension.
+
+<<memrchr>> requires no supporting OS subroutines.
+
+QUICKREF
+	memrchr
+*/
+
+#include <_ansi.h>
+#include <string.h>
+#include <limits.h>
+#include "../../string/local.h"
+
+void *
+memrchr (const void *src_void,
+	int c,
+	size_t length)
+{
+  const unsigned char *src = (const unsigned char *) src_void + length - 1;
+  unsigned char d = c;
+
+#if !defined(PREFER_SIZE_OVER_SPEED) && !defined(__OPTIMIZE_SIZE__)
+  unsigned long *asrc;
+  unsigned long  mask;
+  unsigned int i;
+
+  while (UNALIGNED_X(src))
+    {
+      if (!length--)
+        return NULL;
+      if (*src == d)
+        return (void *) src;
+      src--;
+    }
+
+  if (!TOO_SMALL_LITTLE_BLOCK(length))
+    {
+      /* If we get this far, we know that length is large and src is
+         word-aligned. */
+      /* The fast code reads the source one word at a time and only
+         performs the bytewise search on word-sized segments if they
+         contain the search character, which is detected by XORing
+         the word-sized segment with a word-sized block of the search
+         character and then detecting for the presence of NUL in the
+         result.  */
+      asrc = (unsigned long *) (src - LITTLE_BLOCK_SIZE + 1);
+      mask = d << 8 | d;
+      mask = mask << 16 | mask;
+      for (i = 32; i < sizeof(mask) * 8; i <<= 1)
+        mask = (mask << i) | mask;
+
+      while (!TOO_SMALL_LITTLE_BLOCK(length))
+        {
+          if (DETECT_CHAR(*asrc, mask))
+            break;
+          length -= LITTLE_BLOCK_SIZE;
+          asrc--;
+        }
+
+      /* If there are fewer than LITTLE_BLOCK_SIZE characters left,
+         then we resort to the bytewise loop.  */
+
+      src = (unsigned char *) asrc + LITTLE_BLOCK_SIZE - 1;
+    }
+
+#endif /* not PREFER_SIZE_OVER_SPEED */
+
+  while (length--)
+    {
+      if (*src == d)
+        return (void *) src;
+      src--;
+    }
+
+  return NULL;
+}