Re: [PATCH 2/5] efi: Use ucs2_as_utf8 in efivarfs instead of open coding a bad version

[Matthew Garrett <mjg59-JW9irJGTvgXQT0dZR+AlfA@public.gmane.org>]

If we're worried about UTF-16, the appropriate thing for us to do is
error on seeing a surrogate pair.

On Wed, Feb 17, 2016 at 9:34 PM, H. Peter Anvin <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org> wrote:
> On February 12, 2016 3:27:09 AM PST, Matt Fleming <matt-mF/unelCI9GS6iBeEJttW/XRex20P6io@public.gmane.org> wrote:
>>From: Peter Jones <pjones-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>>
>>Translate EFI's UCS-2 variable names to UTF-8 instead of just assuming
>>all variable names fit in ASCII.
>>
>>Signed-off-by: Peter Jones <pjones-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
>>Acked-by: Matthew Garrett <mjg59-JW9irJGTvgXQT0dZR+AlfA@public.gmane.org>
>>Tested-by: "Lee, Chun-Yi" <jlee-IBi9RG/b67k@public.gmane.org>
>>Signed-off-by: Matt Fleming <matt-mF/unelCI9GS6iBeEJttW/XRex20P6io@public.gmane.org>
>>---
>> drivers/firmware/efi/efivars.c | 30 +++++++++++-------------------
>> fs/efivarfs/super.c            |  7 +++----
>> 2 files changed, 14 insertions(+), 23 deletions(-)
>>
>>diff --git a/drivers/firmware/efi/efivars.c
>>b/drivers/firmware/efi/efivars.c
>>index 756eca8c4cf8..f4ff8abc5f3e 100644
>>--- a/drivers/firmware/efi/efivars.c
>>+++ b/drivers/firmware/efi/efivars.c
>>@@ -540,38 +540,30 @@ static ssize_t efivar_delete(struct file *filp,
>>struct kobject *kobj,
>> static int
>> efivar_create_sysfs_entry(struct efivar_entry *new_var)
>> {
>>-      int i, short_name_size;
>>+      int short_name_size;
>>       char *short_name;
>>-      unsigned long variable_name_size;
>>-      efi_char16_t *variable_name;
>>+      unsigned long utf8_name_size;
>>+      efi_char16_t *variable_name = new_var->var.VariableName;
>>       int ret;
>>
>>-      variable_name = new_var->var.VariableName;
>>-      variable_name_size = ucs2_strlen(variable_name) *
>>sizeof(efi_char16_t);
>>-
>>       /*
>>-       * Length of the variable bytes in ASCII, plus the '-' separator,
>>+       * Length of the variable bytes in UTF8, plus the '-' separator,
>>        * plus the GUID, plus trailing NUL
>>        */
>>-      short_name_size = variable_name_size / sizeof(efi_char16_t)
>>-                              + 1 + EFI_VARIABLE_GUID_LEN + 1;
>>-
>>-      short_name = kzalloc(short_name_size, GFP_KERNEL);
>>+      utf8_name_size = ucs2_utf8size(variable_name);
>>+      short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1;
>>
>>+      short_name = kmalloc(short_name_size, GFP_KERNEL);
>>       if (!short_name)
>>               return -ENOMEM;
>>
>>-      /* Convert Unicode to normal chars (assume top bits are 0),
>>-         ala UTF-8 */
>>-      for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++)
>>{
>>-              short_name[i] = variable_name[i] & 0xFF;
>>-      }
>>+      ucs2_as_utf8(short_name, variable_name, short_name_size);
>>+
>>       /* This is ugly, but necessary to separate one vendor's
>>          private variables from another's.         */
>>-
>>-      *(short_name + strlen(short_name)) = '-';
>>+      short_name[utf8_name_size] = '-';
>>       efi_guid_to_str(&new_var->var.VendorGuid,
>>-                       short_name + strlen(short_name));
>>+                       short_name + utf8_name_size + 1);
>>
>>       new_var->kobj.kset = efivars_kset;
>>
>>diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
>>index b8a564f29107..8651ac28ec0d 100644
>>--- a/fs/efivarfs/super.c
>>+++ b/fs/efivarfs/super.c
>>@@ -118,7 +118,7 @@ static int efivarfs_callback(efi_char16_t *name16,
>>efi_guid_t vendor,
>>       struct dentry *dentry, *root = sb->s_root;
>>       unsigned long size = 0;
>>       char *name;
>>-      int len, i;
>>+      int len;
>>       int err = -ENOMEM;
>>
>>       entry = kzalloc(sizeof(*entry), GFP_KERNEL);
>>@@ -128,15 +128,14 @@ static int efivarfs_callback(efi_char16_t
>>*name16, efi_guid_t vendor,
>>       memcpy(entry->var.VariableName, name16, name_size);
>>       memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t));
>>
>>-      len = ucs2_strlen(entry->var.VariableName);
>>+      len = ucs2_utf8size(entry->var.VariableName);
>>
>>       /* name, plus '-', plus GUID, plus NUL*/
>>       name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL);
>>       if (!name)
>>               goto fail;
>>
>>-      for (i = 0; i < len; i++)
>>-              name[i] = entry->var.VariableName[i] & 0xFF;
>>+      ucs2_as_utf8(name, entry->var.VariableName, len);
>>
>>       name[len] = '-';
>>
>
> However, I think we should treat this "ucs2" as utf16, because sooner or later someone will enter utf16 characters.
> --
> Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.