lib/string_helpers: Add flags param to string_get_size()

The new flags parameter allows controlling
 - Whether or not the units suffix is separated by a space, for
   compatibility with sort -h
 - Whether or not to append a B suffix - we're not always printing
   bytes.

Co-developed-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Kent Overstreet <kent.overstreet@linux.dev>
Link: https://lore.kernel.org/r/20240229205345.93902-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Kees Cook <keescook@chromium.org>

Author: andy-shev

include/linux/string_helpers.h

@@ -17,14 +17,18 @@ static inline bool string_is_terminated(const char *s, int len)
 	return memchr(s, '\0', len) ? true : false;
 }
 
-/* Descriptions of the types of units to
- * print in */
+/* Descriptions of the types of units to print in */
 enum string_size_units {
 	STRING_UNITS_10,	/* use powers of 10^3 (standard SI) */
 	STRING_UNITS_2,		/* use binary powers of 2^10 */
+	STRING_UNITS_MASK	= BIT(0),
+
+	/* Modifiers */
+	STRING_UNITS_NO_SPACE	= BIT(30),
+	STRING_UNITS_NO_BYTES	= BIT(31),
 };
 
-int string_get_size(u64 size, u64 blk_size, enum string_size_units units,
+int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 		    char *buf, int len);
 
 int parse_int_array_user(const char __user *from, size_t count, int **array);

lib/string_helpers.c

@@ -25,7 +25,7 @@
  * string_get_size - get the size in the specified units
  * @size:	The size to be converted in blocks
  * @blk_size:	Size of the block (use 1 for size in bytes)
- * @units:	units to use (powers of 1000 or 1024)
+ * @units:	Units to use (powers of 1000 or 1024), whether to include space separator
  * @buf:	buffer to format to
  * @len:	length of buffer
  *
@@ -39,11 +39,12 @@
 int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 		    char *buf, int len)
 {
+	enum string_size_units units_base = units & STRING_UNITS_MASK;
 	static const char *const units_10[] = {
-		"B", "kB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB"
+		"", "k", "M", "G", "T", "P", "E", "Z", "Y",
 	};
 	static const char *const units_2[] = {
-		"B", "KiB", "MiB", "GiB", "TiB", "PiB", "EiB", "ZiB", "YiB"
+		"", "Ki", "Mi", "Gi", "Ti", "Pi", "Ei", "Zi", "Yi",
 	};
 	static const char *const *const units_str[] = {
 		[STRING_UNITS_10] = units_10,
@@ -68,7 +69,7 @@ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 
 	/* This is Napier's algorithm.  Reduce the original block size to
 	 *
-	 * coefficient * divisor[units]^i
+	 * coefficient * divisor[units_base]^i
 	 *
 	 * we do the reduction so both coefficients are just under 32 bits so
 	 * that multiplying them together won't overflow 64 bits and we keep
@@ -78,12 +79,12 @@ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 	 * precision is in the coefficients.
 	 */
 	while (blk_size >> 32) {
-		do_div(blk_size, divisor[units]);
+		do_div(blk_size, divisor[units_base]);
 		i++;
 	}
 
 	while (size >> 32) {
-		do_div(size, divisor[units]);
+		do_div(size, divisor[units_base]);
 		i++;
 	}
 
@@ -92,8 +93,8 @@ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 	size *= blk_size;
 
 	/* and logarithmically reduce it until it's just under the divisor */
-	while (size >= divisor[units]) {
-		remainder = do_div(size, divisor[units]);
+	while (size >= divisor[units_base]) {
+		remainder = do_div(size, divisor[units_base]);
 		i++;
 	}
 
@@ -103,10 +104,10 @@ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 	for (j = 0; sf_cap*10 < 1000; j++)
 		sf_cap *= 10;
 
-	if (units == STRING_UNITS_2) {
+	if (units_base == STRING_UNITS_2) {
 		/* express the remainder as a decimal.  It's currently the
 		 * numerator of a fraction whose denominator is
-		 * divisor[units], which is 1 << 10 for STRING_UNITS_2 */
+		 * divisor[units_base], which is 1 << 10 for STRING_UNITS_2 */
 		remainder *= 1000;
 		remainder >>= 10;
 	}
@@ -128,10 +129,12 @@ int string_get_size(u64 size, u64 blk_size, const enum string_size_units units,
 	if (i >= ARRAY_SIZE(units_2))
 		unit = "UNK";
 	else
-		unit = units_str[units][i];
+		unit = units_str[units_base][i];
 
-	return snprintf(buf, len, "%u%s %s", (u32)size,
-			tmp, unit);
+	return snprintf(buf, len, "%u%s%s%s%s", (u32)size, tmp,
+			(units & STRING_UNITS_NO_SPACE) ? "" : " ",
+			unit,
+			(units & STRING_UNITS_NO_BYTES) ? "" : "B");
 }
 EXPORT_SYMBOL(string_get_size);
 

lib/test-string_helpers.c

@@ -3,6 +3,7 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/array_size.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -500,21 +501,65 @@ static __init void test_string_get_size_check(const char *units,
 	pr_warn("expected: '%s', got '%s'\n", exp, res);
 }
 
-static __init void __test_string_get_size(const u64 size, const u64 blk_size,
-					  const char *exp_result10,
-					  const char *exp_result2)
+static __init void __strchrcut(char *dst, const char *src, const char *cut)
+{
+	const char *from = src;
+	size_t len;
+
+	do {
+		len = strcspn(from, cut);
+		memcpy(dst, from, len);
+		dst += len;
+		from += len;
+	} while (*from++);
+	*dst = '\0';
+}
+
+static __init void __test_string_get_size_one(const u64 size, const u64 blk_size,
+					      const char *exp_result10,
+					      const char *exp_result2,
+					      enum string_size_units units,
+					      const char *cut)
 {
 	char buf10[string_get_size_maxbuf];
 	char buf2[string_get_size_maxbuf];
+	char exp10[string_get_size_maxbuf];
+	char exp2[string_get_size_maxbuf];
+	char prefix10[64];
+	char prefix2[64];
+
+	sprintf(prefix10, "STRING_UNITS_10 [%s]", cut);
+	sprintf(prefix2, "STRING_UNITS_2 [%s]", cut);
+
+	__strchrcut(exp10, exp_result10, cut);
+	__strchrcut(exp2, exp_result2, cut);
 
-	string_get_size(size, blk_size, STRING_UNITS_10, buf10, sizeof(buf10));
-	string_get_size(size, blk_size, STRING_UNITS_2, buf2, sizeof(buf2));
+	string_get_size(size, blk_size, STRING_UNITS_10 | units, buf10, sizeof(buf10));
+	string_get_size(size, blk_size, STRING_UNITS_2 | units, buf2, sizeof(buf2));
 
-	test_string_get_size_check("STRING_UNITS_10", exp_result10, buf10,
-				   size, blk_size);
+	test_string_get_size_check(prefix10, exp10, buf10, size, blk_size);
+	test_string_get_size_check(prefix2, exp2, buf2, size, blk_size);
+}
+
+static __init void __test_string_get_size(const u64 size, const u64 blk_size,
+					  const char *exp_result10,
+					  const char *exp_result2)
+{
+	struct {
+		enum string_size_units units;
+		const char *cut;
+	} get_size_test_cases[] = {
+		{ 0, "" },
+		{ STRING_UNITS_NO_SPACE, " " },
+		{ STRING_UNITS_NO_SPACE | STRING_UNITS_NO_BYTES, " B" },
+		{ STRING_UNITS_NO_BYTES, "B" },
+	};
+	int i;
 
-	test_string_get_size_check("STRING_UNITS_2", exp_result2, buf2,
-				   size, blk_size);
+	for (i = 0; i < ARRAY_SIZE(get_size_test_cases); i++)
+		__test_string_get_size_one(size, blk_size, exp_result10, exp_result2,
+					   get_size_test_cases[i].units,
+					   get_size_test_cases[i].cut);
 }
 
 static __init void test_string_get_size(void)