kstrto*: converting strings to integers done (hopefully) right

1. simple_strto*() do not contain overflow checks and crufty,
   libc way to indicate failure.
2. strict_strto*() also do not have overflow checks but the name and
   comments pretend they do.
3. Both families have only "long long" and "long" variants,
   but users want strtou8()
4. Both "simple" and "strict" prefixes are wrong:
   Simple doesn't exactly say what's so simple, strict should not exist
   because conversion should be strict by default.

The solution is to use "k" prefix and add convertors for more types.
Enter
	kstrtoull()
	kstrtoll()
	kstrtoul()
	kstrtol()
	kstrtouint()
	kstrtoint()

	kstrtou64()
	kstrtos64()
	kstrtou32()
	kstrtos32()
	kstrtou16()
	kstrtos16()
	kstrtou8()
	kstrtos8()

Include runtime testsuite (somewhat incomplete) as well.

strict_strto*() become deprecated, stubbed to kstrto*() and
eventually will be removed altogether.

Use kstrto*() in code today!

Note: on some archs _kstrtoul() and _kstrtol() are left in tree, even if
      they'll be unused at runtime. This is temporarily solution,
      because I don't want to hardcode list of archs where these
      functions aren't needed. Current solution with sizeof() and
      __alignof__ at least always works.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/video/via/viafbdev.h

@@ -94,9 +94,6 @@ extern int viafb_LCD_ON;
 extern int viafb_DVI_ON;
 extern int viafb_hotplug;
 
-extern int strict_strtoul(const char *cp, unsigned int base,
-	unsigned long *res);
-
 u8 viafb_gpio_i2c_read_lvds(struct lvds_setting_information
 	*plvds_setting_info, struct lvds_chip_information
 	*plvds_chip_info, u8 index);

include/linux/kernel.h

@@ -187,14 +187,76 @@ NORET_TYPE void do_exit(long error_code)
 	ATTRIB_NORET;
 NORET_TYPE void complete_and_exit(struct completion *, long)
 	ATTRIB_NORET;
+
+/* Internal, do not use. */
+int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
+int __must_check _kstrtol(const char *s, unsigned int base, long *res);
+
+int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res);
+int __must_check kstrtoll(const char *s, unsigned int base, long long *res);
+static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res)
+{
+	/*
+	 * We want to shortcut function call, but
+	 * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0.
+	 */
+	if (sizeof(unsigned long) == sizeof(unsigned long long) &&
+	    __alignof__(unsigned long) == __alignof__(unsigned long long))
+		return kstrtoull(s, base, (unsigned long long *)res);
+	else
+		return _kstrtoul(s, base, res);
+}
+
+static inline int __must_check kstrtol(const char *s, unsigned int base, long *res)
+{
+	/*
+	 * We want to shortcut function call, but
+	 * __builtin_types_compatible_p(long, long long) = 0.
+	 */
+	if (sizeof(long) == sizeof(long long) &&
+	    __alignof__(long) == __alignof__(long long))
+		return kstrtoll(s, base, (long long *)res);
+	else
+		return _kstrtol(s, base, res);
+}
+
+int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res);
+int __must_check kstrtoint(const char *s, unsigned int base, int *res);
+
+static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res)
+{
+	return kstrtoull(s, base, res);
+}
+
+static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res)
+{
+	return kstrtoll(s, base, res);
+}
+
+static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res)
+{
+	return kstrtouint(s, base, res);
+}
+
+static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res)
+{
+	return kstrtoint(s, base, res);
+}
+
+int __must_check kstrtou16(const char *s, unsigned int base, u16 *res);
+int __must_check kstrtos16(const char *s, unsigned int base, s16 *res);
+int __must_check kstrtou8(const char *s, unsigned int base, u8 *res);
+int __must_check kstrtos8(const char *s, unsigned int base, s8 *res);
+
 extern unsigned long simple_strtoul(const char *,char **,unsigned int);
 extern long simple_strtol(const char *,char **,unsigned int);
 extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
 extern long long simple_strtoll(const char *,char **,unsigned int);
-extern int __must_check strict_strtoul(const char *, unsigned int, unsigned long *);
-extern int __must_check strict_strtol(const char *, unsigned int, long *);
-extern int __must_check strict_strtoull(const char *, unsigned int, unsigned long long *);
-extern int __must_check strict_strtoll(const char *, unsigned int, long long *);
+#define strict_strtoul	kstrtoul
+#define strict_strtol	kstrtol
+#define strict_strtoull	kstrtoull
+#define strict_strtoll	kstrtoll
+
 extern int sprintf(char * buf, const char * fmt, ...)
 	__attribute__ ((format (printf, 2, 3)));
 extern int vsprintf(char *buf, const char *, va_list)

lib/Kconfig.debug

@@ -1250,3 +1250,6 @@ source "samples/Kconfig"
 source "lib/Kconfig.kgdb"
 
 source "lib/Kconfig.kmemcheck"
+
+config TEST_KSTRTOX
+	tristate "Test kstrto*() family of functions at runtime"

lib/Makefile

@@ -22,6 +22,8 @@ lib-y	+= kobject.o kref.o klist.o
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
 	 string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o
+obj-y += kstrtox.o
+obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG

lib/kstrtox.c

@@ -0,0 +1,227 @@
+/*
+ * Convert integer string representation to an integer.
+ * If an integer doesn't fit into specified type, -E is returned.
+ *
+ * Integer starts with optional sign.
+ * kstrtou*() functions do not accept sign "-".
+ *
+ * Radix 0 means autodetection: leading "0x" implies radix 16,
+ * leading "0" implies radix 8, otherwise radix is 10.
+ * Autodetection hints work after optional sign, but not before.
+ *
+ * If -E is returned, result is not touched.
+ */
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+static inline char _tolower(const char c)
+{
+	return c | 0x20;
+}
+
+static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
+{
+	unsigned long long acc;
+	int ok;
+
+	if (base == 0) {
+		if (s[0] == '0') {
+			if (_tolower(s[1]) == 'x' && isxdigit(s[2]))
+				base = 16;
+			else
+				base = 8;
+		} else
+			base = 10;
+	}
+	if (base == 16 && s[0] == '0' && _tolower(s[1]) == 'x')
+		s += 2;
+
+	acc = 0;
+	ok = 0;
+	while (*s) {
+		unsigned int val;
+
+		if ('0' <= *s && *s <= '9')
+			val = *s - '0';
+		else if ('a' <= _tolower(*s) && _tolower(*s) <= 'f')
+			val = _tolower(*s) - 'a' + 10;
+		else if (*s == '\n') {
+			if (*(s + 1) == '\0')
+				break;
+			else
+				return -EINVAL;
+		} else
+			return -EINVAL;
+
+		if (val >= base)
+			return -EINVAL;
+		if (acc > div_u64(ULLONG_MAX - val, base))
+			return -ERANGE;
+		acc = acc * base + val;
+		ok = 1;
+
+		s++;
+	}
+	if (!ok)
+		return -EINVAL;
+	*res = acc;
+	return 0;
+}
+
+int kstrtoull(const char *s, unsigned int base, unsigned long long *res)
+{
+	if (s[0] == '+')
+		s++;
+	return _kstrtoull(s, base, res);
+}
+EXPORT_SYMBOL(kstrtoull);
+
+int kstrtoll(const char *s, unsigned int base, long long *res)
+{
+	unsigned long long tmp;
+	int rv;
+
+	if (s[0] == '-') {
+		rv = _kstrtoull(s + 1, base, &tmp);
+		if (rv < 0)
+			return rv;
+		if ((long long)(-tmp) >= 0)
+			return -ERANGE;
+		*res = -tmp;
+	} else {
+		rv = kstrtoull(s, base, &tmp);
+		if (rv < 0)
+			return rv;
+		if ((long long)tmp < 0)
+			return -ERANGE;
+		*res = tmp;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(kstrtoll);
+
+/* Internal, do not use. */
+int _kstrtoul(const char *s, unsigned int base, unsigned long *res)
+{
+	unsigned long long tmp;
+	int rv;
+
+	rv = kstrtoull(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (unsigned long long)(unsigned long)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(_kstrtoul);
+
+/* Internal, do not use. */
+int _kstrtol(const char *s, unsigned int base, long *res)
+{
+	long long tmp;
+	int rv;
+
+	rv = kstrtoll(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (long long)(long)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(_kstrtol);
+
+int kstrtouint(const char *s, unsigned int base, unsigned int *res)
+{
+	unsigned long long tmp;
+	int rv;
+
+	rv = kstrtoull(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (unsigned long long)(unsigned int)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(kstrtouint);
+
+int kstrtoint(const char *s, unsigned int base, int *res)
+{
+	long long tmp;
+	int rv;
+
+	rv = kstrtoll(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (long long)(int)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(kstrtoint);
+
+int kstrtou16(const char *s, unsigned int base, u16 *res)
+{
+	unsigned long long tmp;
+	int rv;
+
+	rv = kstrtoull(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (unsigned long long)(u16)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(kstrtou16);
+
+int kstrtos16(const char *s, unsigned int base, s16 *res)
+{
+	long long tmp;
+	int rv;
+
+	rv = kstrtoll(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (long long)(s16)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(kstrtos16);
+
+int kstrtou8(const char *s, unsigned int base, u8 *res)
+{
+	unsigned long long tmp;
+	int rv;
+
+	rv = kstrtoull(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (unsigned long long)(u8)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(kstrtou8);
+
+int kstrtos8(const char *s, unsigned int base, s8 *res)
+{
+	long long tmp;
+	int rv;
+
+	rv = kstrtoll(s, base, &tmp);
+	if (rv < 0)
+		return rv;
+	if (tmp != (long long)(s8)tmp)
+		return -ERANGE;
+	*res = tmp;
+	return 0;
+}
+EXPORT_SYMBOL(kstrtos8);

lib/vsprintf.c

@@ -120,147 +120,6 @@ long long simple_strtoll(const char *cp, char **endp, unsigned int base)
 }
 EXPORT_SYMBOL(simple_strtoll);
 
-/**
- * strict_strtoul - convert a string to an unsigned long strictly
- * @cp: The string to be converted
- * @base: The number base to use
- * @res: The converted result value
- *
- * strict_strtoul converts a string to an unsigned long only if the
- * string is really an unsigned long string, any string containing
- * any invalid char at the tail will be rejected and -EINVAL is returned,
- * only a newline char at the tail is acceptible because people generally
- * change a module parameter in the following way:
- *
- * 	echo 1024 > /sys/module/e1000/parameters/copybreak
- *
- * echo will append a newline to the tail.
- *
- * It returns 0 if conversion is successful and *res is set to the converted
- * value, otherwise it returns -EINVAL and *res is set to 0.
- *
- * simple_strtoul just ignores the successive invalid characters and
- * return the converted value of prefix part of the string.
- */
-int strict_strtoul(const char *cp, unsigned int base, unsigned long *res)
-{
-	char *tail;
-	unsigned long val;
-
-	*res = 0;
-	if (!*cp)
-		return -EINVAL;
-
-	val = simple_strtoul(cp, &tail, base);
-	if (tail == cp)
-		return -EINVAL;
-
-	if ((tail[0] == '\0') || (tail[0] == '\n' && tail[1] == '\0')) {
-		*res = val;
-		return 0;
-	}
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL(strict_strtoul);
-
-/**
- * strict_strtol - convert a string to a long strictly
- * @cp: The string to be converted
- * @base: The number base to use
- * @res: The converted result value
- *
- * strict_strtol is similiar to strict_strtoul, but it allows the first
- * character of a string is '-'.
- *
- * It returns 0 if conversion is successful and *res is set to the converted
- * value, otherwise it returns -EINVAL and *res is set to 0.
- */
-int strict_strtol(const char *cp, unsigned int base, long *res)
-{
-	int ret;
-	if (*cp == '-') {
-		ret = strict_strtoul(cp + 1, base, (unsigned long *)res);
-		if (!ret)
-			*res = -(*res);
-	} else {
-		ret = strict_strtoul(cp, base, (unsigned long *)res);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(strict_strtol);
-
-/**
- * strict_strtoull - convert a string to an unsigned long long strictly
- * @cp: The string to be converted
- * @base: The number base to use
- * @res: The converted result value
- *
- * strict_strtoull converts a string to an unsigned long long only if the
- * string is really an unsigned long long string, any string containing
- * any invalid char at the tail will be rejected and -EINVAL is returned,
- * only a newline char at the tail is acceptible because people generally
- * change a module parameter in the following way:
- *
- * 	echo 1024 > /sys/module/e1000/parameters/copybreak
- *
- * echo will append a newline to the tail of the string.
- *
- * It returns 0 if conversion is successful and *res is set to the converted
- * value, otherwise it returns -EINVAL and *res is set to 0.
- *
- * simple_strtoull just ignores the successive invalid characters and
- * return the converted value of prefix part of the string.
- */
-int strict_strtoull(const char *cp, unsigned int base, unsigned long long *res)
-{
-	char *tail;
-	unsigned long long val;
-
-	*res = 0;
-	if (!*cp)
-		return -EINVAL;
-
-	val = simple_strtoull(cp, &tail, base);
-	if (tail == cp)
-		return -EINVAL;
-	if ((tail[0] == '\0') || (tail[0] == '\n' && tail[1] == '\0')) {
-		*res = val;
-		return 0;
-	}
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL(strict_strtoull);
-
-/**
- * strict_strtoll - convert a string to a long long strictly
- * @cp: The string to be converted
- * @base: The number base to use
- * @res: The converted result value
- *
- * strict_strtoll is similiar to strict_strtoull, but it allows the first
- * character of a string is '-'.
- *
- * It returns 0 if conversion is successful and *res is set to the converted
- * value, otherwise it returns -EINVAL and *res is set to 0.
- */
-int strict_strtoll(const char *cp, unsigned int base, long long *res)
-{
-	int ret;
-	if (*cp == '-') {
-		ret = strict_strtoull(cp + 1, base, (unsigned long long *)res);
-		if (!ret)
-			*res = -(*res);
-	} else {
-		ret = strict_strtoull(cp, base, (unsigned long long *)res);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL(strict_strtoll);
-
 static noinline_for_stack
 int skip_atoi(const char **s)
 {

scripts/checkpatch.pl

@@ -2804,9 +2804,9 @@ sub process {
 			WARN("consider using a completion\n" . $herecurr);
 
 		}
-# recommend strict_strto* over simple_strto*
+# recommend kstrto* over simple_strto*
 		if ($line =~ /\bsimple_(strto.*?)\s*\(/) {
-			WARN("consider using strict_$1 in preference to simple_$1\n" . $herecurr);
+			WARN("consider using kstrto* in preference to simple_$1\n" . $herecurr);
 		}
 # check for __initcall(), use device_initcall() explicitly please
 		if ($line =~ /^.\s*__initcall\s*\(/) {