[PATCH 21/24] efi/libstub: Add UTF-8 decoding to efi_puts

From: Arvind Sankar <nivedita@alum.mit.edu>
To: Ard Biesheuvel <ardb@kernel.org>
Cc: linux-efi@vger.kernel.org
Subject: [PATCH 21/24] efi/libstub: Add UTF-8 decoding to efi_puts
Date: Mon, 18 May 2020 15:07:13 -0400	[thread overview]
Message-ID: <20200518190716.751506-22-nivedita@alum.mit.edu> (raw)
In-Reply-To: <20200518190716.751506-1-nivedita@alum.mit.edu>

In order to be able to use the UTF-16 support added to vsprintf in the
previous commit, enhance efi_puts to decode UTF-8 into UTF-16. Invalid
UTF-8 encodings are passed through unchanged.

Signed-off-by: Arvind Sankar <nivedita@alum.mit.edu>
---
 .../firmware/efi/libstub/efi-stub-helper.c    | 67 +++++++++++++++++--
 1 file changed, 62 insertions(+), 5 deletions(-)

diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index a36f3af6e130..48242bc982a3 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -36,17 +36,74 @@ void efi_char16_puts(efi_char16_t *str)
 		       output_string, str);
 }
 
+static
+u32 utf8_to_utf32(const u8 **s8)
+{
+	u32 c32;
+	u8 c0, cx;
+	size_t clen, i;
+
+	c0 = cx = *(*s8)++;
+	/*
+	 * The position of the most-significant 0 bit gives us the length of
+	 * a multi-octet encoding.
+	 */
+	for (clen = 0; cx & 0x80; ++clen)
+		cx <<= 1;
+	/*
+	 * If the 0 bit is in position 8, this is a valid single-octet
+	 * encoding. If the 0 bit is in position 7 or positions 1-3, the
+	 * encoding is invalid.
+	 * In either case, we just return the first octet.
+	 */
+	if (clen < 2 || clen > 4)
+		return c0;
+	/* Get the bits from the first octet. */
+	c32 = cx >> clen--;
+	for (i = 0; i < clen; ++i) {
+		/* Trailing octets must have 10 in most significant bits. */
+		cx = (*s8)[i] ^ 0x80;
+		if (cx & 0xc0)
+			return c0;
+		c32 = (c32 << 6) | cx;
+	}
+	/*
+	 * Check for validity:
+	 * - The character must be in the Unicode range.
+	 * - It must not be a surrogate.
+	 * - It must be encoded using the correct number of octets.
+	 */
+	if (c32 > 0x10ffff ||
+	    (c32 & 0xf800) == 0xd800 ||
+	    clen != (c32 >= 0x80) + (c32 >= 0x800) + (c32 >= 0x10000))
+		return c0;
+	*s8 += clen;
+	return c32;
+}
+
 void efi_puts(const char *str)
 {
 	efi_char16_t buf[128];
 	size_t pos = 0, lim = ARRAY_SIZE(buf);
+	const u8 *s8 = (const u8 *)str;
+	u32 c32;
 
-	while (*str) {
-		if (*str == '\n')
+	while (*s8) {
+		if (*s8 == '\n')
 			buf[pos++] = L'\r';
-		/* Cast to unsigned char to avoid sign-extension */
-		buf[pos++] = (unsigned char)(*str++);
-		if (*str == '\0' || pos >= lim - 2) {
+		c32 = utf8_to_utf32(&s8);
+		if (c32 < 0x10000)
+			/* Characters in plane 0 use a single word. */
+			buf[pos++] = c32;
+		else {
+			/*
+			 * Characters in other planes encode into a surrogate
+			 * pair.
+			 */
+			buf[pos++] = (0xd800 - (0x10000 >> 10)) + (c32 >> 10);
+			buf[pos++] = 0xdc00 + (c32 & 0x3ff);
+		}
+		if (*s8 == '\0' || pos >= lim - 2) {
 			buf[pos] = L'\0';
 			efi_char16_puts(buf);
 			pos = 0;
-- 
2.26.2

