[libc] add strtoll function and backend

This change adds the stroll function, but most of the implementation is
in the new file str_conv_utils.h since many of the other integer
conversion functions are implemented through what are effectively calls
to strtoll.

Reviewed By: sivachandra

Differential Revision: https://reviews.llvm.org/D107792

Author: michaelrj-google

libc/config/linux/x86_64/entrypoints.txt

@@ -158,6 +158,7 @@ if(LLVM_LIBC_FULL_BUILD)
     libc.src.stdlib.abs
     libc.src.stdlib.labs
     libc.src.stdlib.llabs
+    libc.src.stdlib.strtoll
 
     # signal.h entrypoints
     libc.src.signal.raise

libc/spec/spec.td

@@ -62,6 +62,7 @@ def ConstVoidRestrictedPtr : ConstType<VoidRestrictedPtr>;
 def CharPtr : PtrType<CharType>;
 def ConstCharPtr : ConstType<CharPtr>;
 def CharRestrictedPtr : RestrictedPtrType<CharType>;
+def CharRestrictedPtrPtr : RestrictedPtrType<CharPtr>;
 def ConstCharRestrictedPtr : ConstType<CharRestrictedPtr>;
 
 def OnceFlagType : NamedType<"once_flag">;

libc/spec/stdc.td

@@ -478,6 +478,7 @@ def StdC : StandardSpec<"stdc"> {
           FunctionSpec<"abs", RetValSpec<IntType>, [ArgSpec<IntType>]>,
           FunctionSpec<"labs", RetValSpec<LongType>, [ArgSpec<LongType>]>,
           FunctionSpec<"llabs", RetValSpec<LongLongType>, [ArgSpec<LongLongType>]>,
+          FunctionSpec<"strtoll", RetValSpec<LongLongType>, [ArgSpec<ConstCharRestrictedPtr>, ArgSpec<CharRestrictedPtrPtr>, ArgSpec<IntType>]>,
           FunctionSpec<"_Exit", RetValSpec<NoReturn>, [ArgSpec<IntType>]>,
       ]
   >;

libc/src/__support/CMakeLists.txt

@@ -12,6 +12,16 @@ add_header_library(
     ctype_utils.h
 )
 
+add_header_library(
+  str_conv_utils
+  HDRS
+    str_conv_utils.h
+  DEPENDS
+    .ctype_utils
+    libc.include.errno
+    libc.src.errno.__errno_location
+)
+
 add_header_library(
   integer_operations
   HDRS

libc/src/__support/str_conv_utils.h

@@ -0,0 +1,111 @@
+//===-- Stdlib utils --------------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LIBC_SRC_STDLIB_STDLIB_UTILS_H
+#define LIBC_SRC_STDLIB_STDLIB_UTILS_H
+
+#include "src/__support/ctype_utils.h"
+#include <errno.h>
+#include <limits.h>
+
+namespace __llvm_libc {
+namespace internal {
+
+// Returns a pointer to the first character in src that is not a whitespace
+// character (as determined by isspace())
+static inline const char *first_non_whitespace(const char *__restrict src) {
+  while (internal::isspace(*src)) {
+    ++src;
+  }
+  return src;
+}
+
+static inline int b36_char_to_int(char input) {
+  if (isdigit(input))
+    return input - '0';
+  if (isalpha(input))
+    return (input | 32) + 10 - 'a';
+  return 0;
+}
+
+// Takes the address of the string pointer and parses the base from the start of
+// it. This will advance the string pointer.
+static inline int infer_base(const char *__restrict *__restrict src) {
+  if (**src == '0') {
+    ++(*src);
+    if ((**src | 32) == 'x') {
+      ++(*src);
+      return 16;
+    }
+    return 8;
+  }
+  return 10;
+}
+
+// Takes a pointer to a string, a pointer to a string pointer, and the base to
+// convert to. This function is used as the backend for all of the string to int
+// functions.
+static inline long long strtoll(const char *__restrict src,
+                                char **__restrict str_end, int base) {
+  unsigned long long result = 0;
+
+  if (base < 0 || base == 1 || base > 36) {
+    errno = EINVAL; // NOLINT
+    return 0;
+  }
+
+  src = first_non_whitespace(src);
+
+  char result_sign = '+';
+  if (*src == '+' || *src == '-') {
+    result_sign = *src;
+    ++src;
+  }
+
+  if (base == 0) {
+    base = infer_base(&src);
+  } else if (base == 16 && *src == '0' && (*(src + 1) | 32) == 'x') {
+    src = src + 2;
+  }
+
+  unsigned long long const ABS_MAX =
+      (result_sign == '+' ? LLONG_MAX
+                          : static_cast<unsigned long long>(LLONG_MAX) + 1);
+  unsigned long long const ABS_MAX_DIV_BY_BASE = ABS_MAX / base;
+  while (isalnum(*src)) {
+    int cur_digit = b36_char_to_int(*src);
+    if (cur_digit >= base)
+      break;
+    if (result > ABS_MAX_DIV_BY_BASE) {
+      result = ABS_MAX;
+      errno = ERANGE; // NOLINT
+      break;
+    }
+    result = result * base;
+    if (result > ABS_MAX - cur_digit) {
+      result = ABS_MAX;
+      errno = ERANGE; // NOLINT
+      break;
+    }
+    result = result + cur_digit;
+
+    ++src;
+  }
+
+  if (str_end != nullptr)
+    *str_end = const_cast<char *>(src);
+  if (result_sign == '+')
+    return result;
+  else
+    return -result;
+}
+
+} // namespace internal
+} // namespace __llvm_libc
+
+#endif // LIBC_SRC_STDLIB_STDLIB_UTILS_H

libc/src/stdlib/CMakeLists.txt

@@ -50,3 +50,13 @@ add_entrypoint_object(
   DEPENDS
     libc.src.__support.integer_operations
 )
+
+add_entrypoint_object(
+  strtoll
+  SRCS
+    strtoll.cpp
+  HDRS
+    strtoll.h
+  DEPENDS
+    libc.src.__support.str_conv_utils
+)

libc/src/stdlib/strtoll.cpp

@@ -0,0 +1,21 @@
+//===-- Implementation of strtoll -----------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "src/stdlib/strtoll.h"
+#include "src/__support/common.h"
+#include "src/__support/str_conv_utils.h"
+
+namespace __llvm_libc {
+
+LLVM_LIBC_FUNCTION(long long, strtoll,
+                   (const char *__restrict str, char **__restrict str_end,
+                    int base)) {
+  return internal::strtoll(str, str_end, base);
+}
+
+} // namespace __llvm_libc

libc/src/stdlib/strtoll.h

@@ -0,0 +1,19 @@
+//===-- Implementation header for strtoll -----------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_LIBC_SRC_STDLIB_STRTOLL_H
+#define LLVM_LIBC_SRC_STDLIB_STRTOLL_H
+
+namespace __llvm_libc {
+
+long long strtoll(const char *__restrict str, char **__restrict str_end,
+                  int base);
+
+} // namespace __llvm_libc
+
+#endif // LLVM_LIBC_SRC_STDLIB_STRTOLL_H

libc/test/src/stdlib/CMakeLists.txt

@@ -54,3 +54,15 @@ add_libc_unittest(
   DEPENDS
     libc.src.stdlib.llabs
 )
+
+add_libc_unittest(
+  strtoll_test
+  SUITE
+    libc_stdlib_unittests
+  SRCS
+    strtoll_test.cpp
+  DEPENDS
+    libc.src.stdlib.strtoll
+    libc.include.errno
+    libc.test.errno_setter_matcher
+)