[PATCH 20/22] Improve cmdline conversion

From: Leif Lindholm
Date: Wed Feb 05 2014 - 12:06:06 EST


From: "H. Peter Anvin" <hpa@xxxxxxxxx>

Improve the conversion of the UTF-16 EFI command line
to UTF-8 for passing to the kernel.

Signed-off-by: Roy Franz <roy.franz@xxxxxxxxxx>
Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxx>
Signed-off-by: Leif Lindholm <leif.lindholm@xxxxxxxxxx>
---
arch/x86/boot/compressed/eboot.c | 3 +-
drivers/firmware/efi/arm-stub.c | 3 +-
drivers/firmware/efi/efi-stub-helper.c | 89 ++++++++++++++++++++++++--------
3 files changed, 70 insertions(+), 25 deletions(-)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index a7677ba..feca05f 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -488,8 +488,7 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
hdr->type_of_loader = 0x21;

/* Convert unicode cmdline to ascii */
- cmdline_ptr = efi_convert_cmdline_to_ascii(sys_table, image,
- &options_size);
+ cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
if (!cmdline_ptr)
goto fail;
hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
diff --git a/drivers/firmware/efi/arm-stub.c b/drivers/firmware/efi/arm-stub.c
index aefe963..b505fde 100644
--- a/drivers/firmware/efi/arm-stub.c
+++ b/drivers/firmware/efi/arm-stub.c
@@ -87,8 +87,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
* protocol. We are going to copy the command line into the
* device tree, so this can be allocated anywhere.
*/
- cmdline_ptr = efi_convert_cmdline_to_ascii(sys_table, image,
- &cmdline_size);
+ cmdline_ptr = efi_convert_cmdline(sys_table, image, &cmdline_size);
if (!cmdline_ptr) {
pr_efi_err(sys_table, "getting command line via LOADED_IMAGE_PROTOCOL\n");
goto fail_free_image;
diff --git a/drivers/firmware/efi/efi-stub-helper.c b/drivers/firmware/efi/efi-stub-helper.c
index 8477a72..2ee69ea 100644
--- a/drivers/firmware/efi/efi-stub-helper.c
+++ b/drivers/firmware/efi/efi-stub-helper.c
@@ -625,52 +625,99 @@ static efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
}

/*
- * Convert the unicode UEFI command line to ASCII to pass to kernel.
+ * Get the number of UTF-8 bytes corresponding to an UTF-16 character.
+ * This overestimates for surrogates, but that is okay.
+ */
+static int efi_utf8_bytes(u16 c)
+{
+ return 1 + (c >= 0x80) + (c >= 0x800);
+}
+
+/*
+ * Convert an UTF-16 string, not necessarily null terminated, to UTF-8.
+ */
+static u8 *efi_utf16_to_utf8(u8 *dst, const u16 *src, int n)
+{
+ unsigned int c;
+
+ while (n--) {
+ c = *src++;
+ if (n && c >= 0xd800 && c <= 0xdbff &&
+ *src >= 0xdc00 && *src <= 0xdfff) {
+ c = 0x10000 + ((c & 0x3ff) << 10) + (*src & 0x3ff);
+ src++;
+ n--;
+ }
+ if (c >= 0xd800 && c <= 0xdfff)
+ c = 0xfffd; /* Unmatched surrogate */
+ if (c < 0x80) {
+ *dst++ = c;
+ continue;
+ }
+ if (c < 0x800) {
+ *dst++ = 0xc0 + (c >> 6);
+ goto t1;
+ }
+ if (c < 0x10000) {
+ *dst++ = 0xe0 + (c >> 12);
+ goto t2;
+ }
+ *dst++ = 0xf0 + (c >> 18);
+ *dst++ = 0x80 + ((c >> 12) & 0x3f);
+t2:
+ *dst++ = 0x80 + ((c >> 6) & 0x3f);
+t1:
+ *dst++ = 0x80 + (c & 0x3f);
+ }
+
+ return dst;
+}
+
+/*
+ * Do proper conversion from UTF-16 to UTF-8
* Size of memory allocated return in *cmd_line_len.
* Returns NULL on error.
*/
-static char *efi_convert_cmdline_to_ascii(efi_system_table_t *sys_table_arg,
- efi_loaded_image_t *image,
- int *cmd_line_len)
+static char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
+ efi_loaded_image_t *image,
+ int *cmd_line_len)
{
- u16 *s2;
+ const u16 *s2;
u8 *s1 = NULL;
unsigned long cmdline_addr = 0;
- int load_options_size = image->load_options_size / 2; /* ASCII */
- void *options = image->load_options;
- int options_size = 0;
+ int load_options_chars = image->load_options_size / 2; /* UTF-16 */
+ const u16 *options = image->load_options;
+ int options_bytes = 0; /* UTF-8 bytes */
+ int options_chars = 0; /* UTF-16 chars */
efi_status_t status;
- int i;
u16 zero = 0;

if (options) {
s2 = options;
- while (*s2 && *s2 != '\n' && options_size < load_options_size) {
- s2++;
- options_size++;
+ while (options_chars < load_options_chars
+ && *s2 && *s2 != '\n') {
+ options_bytes += efi_utf8_bytes(*s2++);
+ options_chars++;
}
}

- if (options_size == 0) {
- /* No command line options, so return empty string*/
- options_size = 1;
+ if (!options_chars) {
+ /* No command line options, so return empty string */
options = &zero;
}

- options_size++; /* NULL termination */
+ options_bytes++; /* NUL termination */

status = efi_low_alloc(sys_table_arg, options_bytes, 0, &cmdline_addr);
if (status != EFI_SUCCESS)
return NULL;

s1 = (u8 *)cmdline_addr;
- s2 = (u16 *)options;
-
- for (i = 0; i < options_size - 1; i++)
- *s1++ = *s2++;
+ s2 = (const u16 *)options;

+ s1 = efi_utf16_to_utf8(s1, s2, options_chars);
*s1 = '\0';

- *cmd_line_len = options_size;
+ *cmd_line_len = options_bytes;
return (char *)cmdline_addr;
}
--
1.7.10.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/