[5/7] lib: rework bitmap_parse()
diff mbox series

Message ID 20190721212753.3287-6-yury.norov@gmail.com
State New
Headers show
Series
  • lib: rework bitmap_parse
Related show

Commit Message

Yury Norov July 21, 2019, 9:27 p.m. UTC
From Yury Norov <ynorov@marvell.com>

bitmap_parse() is ineffective and full of opaque variables and opencoded
parts. It leads to hard understanding and usage of it. This rework
includes:
 - remove bitmap_shift_left() call from the cycle. Now it makes the
   complexity of the algorithm as O(nbits^2). In the suggested approach
   the input string is parsed in reverse direction, so no shifts needed;
 - relax requirement on a single comma and no white spaces between chunks.
   It is considered useful in scripting, and it aligns with
   bitmap_parselist();
 - split bitmap_parse() to small readable helpers;
 - make an explicit calculation of the end of input line at the
   beginning, so users of the bitmap_parse() won't bother doing this.

Signed-off-by: Yury Norov <ynorov@marvell.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
---
 include/linux/bitmap.h |   8 +-
 lib/bitmap.c           | 178 ++++++++++++++++++++---------------------
 2 files changed, 87 insertions(+), 99 deletions(-)

Comments

Andy Shevchenko July 22, 2019, 1:37 p.m. UTC | #1
On Sun, Jul 21, 2019 at 02:27:51PM -0700, Yury Norov wrote:
> From Yury Norov <ynorov@marvell.com>
> 
> bitmap_parse() is ineffective and full of opaque variables and opencoded
> parts. It leads to hard understanding and usage of it. This rework
> includes:
>  - remove bitmap_shift_left() call from the cycle. Now it makes the
>    complexity of the algorithm as O(nbits^2). In the suggested approach
>    the input string is parsed in reverse direction, so no shifts needed;
>  - relax requirement on a single comma and no white spaces between chunks.
>    It is considered useful in scripting, and it aligns with
>    bitmap_parselist();
>  - split bitmap_parse() to small readable helpers;
>  - make an explicit calculation of the end of input line at the
>    beginning, so users of the bitmap_parse() won't bother doing this.

> Signed-off-by: Yury Norov <ynorov@marvell.com>
> Signed-off-by: Yury Norov <yury.norov@gmail.com>

I'm not sure this is good to have two SoB tags for one person.

> +	if (hex_to_bin(*end) < 0)

Isn't it simple isxdigit() check?

> +		return ERR_PTR(-EINVAL);
> +

> +	for (i = 0; i < 32; i += 4) {
> +		c = hex_to_bin(*end--);
> +		if (c < 0)
> +			return ERR_PTR(-EINVAL);
> +
> +		ret |= c << i;

Dunno if it's for this series, but perhaps we would like to have something like

	/* Convert hex representation of u32 value to binary format */
	static inline int hex2bin32(const char *buf, u32 *result)
	{
		u8 value[4];
		int ret;

		ret = hex2bin(value, buf, sizeof(u32));
		if (ret)
			return ret;

		*result = get_unaligned((u32 *)value);
		// I guess it's aligned and thus can be done with:
		//   *result = be32_to_cpup((__force __be32 *)value);
		// just don't like enforcing bitwise types
		return 0;
	}

// also can be your variant with for-loop.

At least here for now and then can be moved to the kernel.h / hexdump.c.

> +
> +		if (start > end || __end_of_region(*end))
> +			goto out;
> +	}
> +

> +	if (hex_to_bin(*end) >= 0)

Isn't it simple isxdigit() check?

> +		return ERR_PTR(-EOVERFLOW);

Patch
diff mbox series

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index f58e97446abcf..c3e84864cc335 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -172,7 +172,7 @@  bitmap_find_next_zero_area(unsigned long *map,
 					      align_mask, 0);
 }
 
-extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user,
+extern int bitmap_parse(const char *buf, unsigned int buflen,
 			unsigned long *dst, int nbits);
 extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen,
 			unsigned long *dst, int nbits);
@@ -408,12 +408,6 @@  static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr
 		__bitmap_shift_left(dst, src, shift, nbits);
 }
 
-static inline int bitmap_parse(const char *buf, unsigned int buflen,
-			unsigned long *maskp, int nmaskbits)
-{
-	return __bitmap_parse(buf, buflen, 0, maskp, nmaskbits);
-}
-
 /**
  * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap.
  * @n: u64 value
diff --git a/lib/bitmap.c b/lib/bitmap.c
index fbd4121c540b8..8fc918e74116d 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -333,97 +333,6 @@  EXPORT_SYMBOL(bitmap_find_next_zero_area_off);
  * second version by Paul Jackson, third by Joe Korty.
  */
 
-#define CHUNKSZ				32
-#define nbits_to_hold_value(val)	fls(val)
-#define BASEDEC 10		/* fancier cpuset lists input in decimal */
-
-/**
- * __bitmap_parse - convert an ASCII hex string into a bitmap.
- * @buf: pointer to buffer containing string.
- * @buflen: buffer size in bytes.  If string is smaller than this
- *    then it must be terminated with a \0.
- * @is_user: location of buffer, 0 indicates kernel space
- * @maskp: pointer to bitmap array that will contain result.
- * @nmaskbits: size of bitmap, in bits.
- *
- * Commas group hex digits into chunks.  Each chunk defines exactly 32
- * bits of the resultant bitmask.  No chunk may specify a value larger
- * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value
- * then leading 0-bits are prepended.  %-EINVAL is returned for illegal
- * characters and for grouping errors such as "1,,5", ",44", "," and "".
- * Leading and trailing whitespace accepted, but not embedded whitespace.
- */
-int __bitmap_parse(const char *buf, unsigned int buflen,
-		int is_user, unsigned long *maskp,
-		int nmaskbits)
-{
-	int c, old_c, totaldigits, ndigits, nchunks, nbits;
-	u32 chunk;
-	const char __user __force *ubuf = (const char __user __force *)buf;
-
-	bitmap_zero(maskp, nmaskbits);
-
-	nchunks = nbits = totaldigits = c = 0;
-	do {
-		chunk = 0;
-		ndigits = totaldigits;
-
-		/* Get the next chunk of the bitmap */
-		while (buflen) {
-			old_c = c;
-			if (is_user) {
-				if (__get_user(c, ubuf++))
-					return -EFAULT;
-			}
-			else
-				c = *buf++;
-			buflen--;
-			if (isspace(c))
-				continue;
-
-			/*
-			 * If the last character was a space and the current
-			 * character isn't '\0', we've got embedded whitespace.
-			 * This is a no-no, so throw an error.
-			 */
-			if (totaldigits && c && isspace(old_c))
-				return -EINVAL;
-
-			/* A '\0' or a ',' signal the end of the chunk */
-			if (c == '\0' || c == ',')
-				break;
-
-			if (!isxdigit(c))
-				return -EINVAL;
-
-			/*
-			 * Make sure there are at least 4 free bits in 'chunk'.
-			 * If not, this hexdigit will overflow 'chunk', so
-			 * throw an error.
-			 */
-			if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1))
-				return -EOVERFLOW;
-
-			chunk = (chunk << 4) | hex_to_bin(c);
-			totaldigits++;
-		}
-		if (ndigits == totaldigits)
-			return -EINVAL;
-		if (nchunks == 0 && chunk == 0)
-			continue;
-
-		__bitmap_shift_left(maskp, maskp, CHUNKSZ, nmaskbits);
-		*maskp |= chunk;
-		nchunks++;
-		nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ;
-		if (nbits > nmaskbits)
-			return -EOVERFLOW;
-	} while (buflen && c == ',');
-
-	return 0;
-}
-EXPORT_SYMBOL(__bitmap_parse);
-
 /**
  * bitmap_parse_user - convert an ASCII hex string in a user buffer into a bitmap
  *
@@ -444,7 +353,7 @@  int bitmap_parse_user(const char __user *ubuf,
 	if (IS_ERR(buf))
 		return PTR_ERR(buf);
 
-	ret = bitmap_parse(buf, ulen, maskp, nmaskbits);
+	ret = bitmap_parse(buf, UINT_MAX, maskp, nmaskbits);
 
 	kfree(buf);
 	return ret;
@@ -555,6 +464,14 @@  static const char *bitmap_find_region(const char *str)
 	return end_of_str(*str) ? NULL : str;
 }
 
+static const char *bitmap_find_region_reverse(const char *start, const char *end)
+{
+	while (start <= end && __end_of_region(*end))
+		end--;
+
+	return end;
+}
+
 static const char *bitmap_parse_region(const char *str, struct region *r)
 {
 	str = bitmap_getnum(str, &r->start);
@@ -678,6 +595,83 @@  int bitmap_parselist_user(const char __user *ubuf,
 }
 EXPORT_SYMBOL(bitmap_parselist_user);
 
+static const char *bitmap_get_x32_reverse(const char *start,
+					const char *end, u32 *num)
+{
+	u32 ret = 0;
+	int c, i;
+
+	if (hex_to_bin(*end) < 0)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 0; i < 32; i += 4) {
+		c = hex_to_bin(*end--);
+		if (c < 0)
+			return ERR_PTR(-EINVAL);
+
+		ret |= c << i;
+
+		if (start > end || __end_of_region(*end))
+			goto out;
+	}
+
+	if (hex_to_bin(*end) >= 0)
+		return ERR_PTR(-EOVERFLOW);
+out:
+	*num = ret;
+	return end;
+}
+
+/**
+ * bitmap_parse - convert an ASCII hex string into a bitmap.
+ * @start: pointer to buffer containing string.
+ * @buflen: buffer size in bytes.  If string is smaller than this
+ *    then it must be terminated with a \0 or \n. In that case,
+ *    UINT_MAX may be provided instead of string length.
+ * @maskp: pointer to bitmap array that will contain result.
+ * @nmaskbits: size of bitmap, in bits.
+ *
+ * Commas group hex digits into chunks.  Each chunk defines exactly 32
+ * bits of the resultant bitmask.  No chunk may specify a value larger
+ * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value
+ * then leading 0-bits are prepended.  %-EINVAL is returned for illegal
+ * characters. Grouping such as "1,,5", ",44", "," or "" is allowed.
+ * Leading, embedded and trailing whitespace accepted.
+ */
+int bitmap_parse(const char *start, unsigned int buflen,
+		unsigned long *maskp, int nmaskbits)
+{
+	const char *end = strnchrnul(start, buflen, '\n') - 1;
+	int chunks = BITS_TO_U32(nmaskbits);
+	u32 *bitmap = (u32 *)maskp;
+	int unset_bit;
+
+	while (1) {
+		end = bitmap_find_region_reverse(start, end);
+		if (start > end)
+			break;
+
+		if (!chunks--)
+			return -EOVERFLOW;
+
+		end = bitmap_get_x32_reverse(start, end, bitmap++);
+		if (IS_ERR(end))
+			return PTR_ERR(end);
+	}
+
+	unset_bit = (BITS_TO_U32(nmaskbits) - chunks) * 32;
+	if (unset_bit < nmaskbits) {
+		bitmap_clear(maskp, unset_bit, nmaskbits - unset_bit);
+		return 0;
+	}
+
+	if (find_next_bit(maskp, unset_bit, nmaskbits) != unset_bit)
+		return -EOVERFLOW;
+
+	return 0;
+}
+EXPORT_SYMBOL(bitmap_parse);
+
 
 #ifdef CONFIG_NUMA
 /**