[PATCH v4 2/9] platform/x86: hp-bioscfg: fix non-ASCII truncation in hp_get_string_from_buffer()

[Muhammad Bilal <meatuni001@gmail.com>]

utf16s_to_utf8s() writes into dst, but the loop that follows
overwrites dst from the raw UTF-16 code units with truncating casts,
so any character above U+007F is mangled. For example, U+00E9 is
stored as 0xe9 instead of 0xc3 0xa9.

Convert into a scratch buffer first, then escape '\\', '\r', '\n' and
'\t' into dst with string_escape_mem(). Quotes are not escaped, so the
existing strreplace() still handles them.

Tested on HP EliteBook 840 G2 (Fedora 44, Linux 7.2.7).

Fixes: a34fc329b189 ("platform/x86: hp-bioscfg: bioscfg")
Cc: stable@vger.kernel.org
Suggested-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Muhammad Bilal <meatuni001@gmail.com>
---
Changes in v3:
 - Drop Suggested-by: Andy Shevchenko
 - Use string_helpers.h instead of string.h, keep reverse xmas tree
   order of declarations (Andy)

Changes in v2:
 - Split out of the combined fix (Ilpo)
 - Use @only of string_escape_mem() instead of a new flag (Andy)

 drivers/platform/x86/hp/hp-bioscfg/bioscfg.c | 62 +++++---------------
 1 file changed, 14 insertions(+), 48 deletions(-)

diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
index 74a90867e..e468995f2 100644
--- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
+++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c
@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/printk.h>
-#include <linux/string.h>
+#include <linux/string_helpers.h>
 #include <linux/wmi.h>
 #include "bioscfg.h"
 #include "../../firmware_attributes_class.h"
@@ -53,12 +53,12 @@ int hp_get_integer_from_buffer(u8 **buffer, u32 *buffer_size, u32 *integer)
 
 int hp_get_string_from_buffer(u8 **buffer, u32 *buffer_size, char *dst, u32 dst_size)
 {
+	char utf8_buf[MAX_BUFF_SIZE];
 	u16 *src = (u16 *)*buffer;
+	int escaped_len;
 	u16 orig_size;
 	u16 src_size;
-	u16 size;
-	int i;
-	int conv_dst_size;
+	int utf8_len;
 
 	if (*buffer_size < sizeof(u16))
 		return -EINVAL;
@@ -74,56 +74,22 @@ int hp_get_string_from_buffer(u8 **buffer, u32 *buffer_size, char *dst, u32 dst_
 	src++;
 	/* size value in u16 chars */
 	orig_size = src_size / sizeof(u16);
-	size = orig_size;
-
-	for (i = 0; i < orig_size; i++)
-		if (src[i] == '\\' ||
-		    src[i] == '\r' ||
-		    src[i] == '\n' ||
-		    src[i] == '\t')
-			size++;
 
-	/*
-	 * Conversion is limited to destination string max number of
-	 * bytes.
-	 */
-	conv_dst_size = size;
-	if (size >= dst_size)
-		conv_dst_size = dst_size - 1;
+	utf8_len = utf16s_to_utf8s(src, orig_size, UTF16_HOST_ENDIAN,
+				   utf8_buf, sizeof(utf8_buf));
 
-	/*
-	 * convert from UTF-16 unicode to ASCII
-	 */
-	utf16s_to_utf8s(src, orig_size, UTF16_HOST_ENDIAN, dst, conv_dst_size);
-	dst[conv_dst_size] = 0;
-
-	for (i = 0; i < conv_dst_size; i++) {
-		if (*src == '\\' ||
-		    *src == '\r' ||
-		    *src == '\n' ||
-		    *src == '\t') {
-			dst[i++] = '\\';
-			if (i == conv_dst_size)
-				break;
-		}
-
-		if (*src == '\r')
-			dst[i] = 'r';
-		else if (*src == '\n')
-			dst[i] = 'n';
-		else if (*src == '\t')
-			dst[i] = 't';
-		else if (*src == '"')
-			dst[i] = '\'';
-		else
-			dst[i] = *src;
-		src++;
-	}
+	escaped_len = string_escape_mem(utf8_buf, utf8_len, dst, dst_size - 1,
+					ESCAPE_SPACE | ESCAPE_SPECIAL,
+					"\\\r\n\t");
+	if (escaped_len > dst_size - 1)
+		escaped_len = dst_size - 1;
+	dst[escaped_len] = '\0';
+	strreplace(dst, '"', '\'');
 
 	*buffer += sizeof(u16) + src_size;
 	*buffer_size -= sizeof(u16) + src_size;
 
-	return size;
+	return escaped_len;
 }
 
 int hp_get_common_data_from_buffer(u8 **buffer_ptr, u32 *buffer_size,
-- 
2.43.0