Re: [tip:x86/asm] x86: Introduce GDT_ENTRY_INIT()

[Akinobu Mita <akinobu.mita@gmail.com>]

2009/8/3 H. Peter Anvin <hpa@zytor.com>:
> Ingo Molnar wrote:
>>
>> * tip-bot for Akinobu Mita <akinobu.mita@gmail.com> wrote:
>>
>>> Commit-ID:  d520da1173abd1f918b7e690220e14ba0fc56cfc
>>> Gitweb:
>>> http://git.kernel.org/tip/d520da1173abd1f918b7e690220e14ba0fc56cfc
>>> Author:     Akinobu Mita <akinobu.mita@gmail.com>
>>> AuthorDate: Sun, 19 Jul 2009 00:12:20 +0900
>>> Committer:  Ingo Molnar <mingo@elte.hu>
>>> CommitDate: Sun, 19 Jul 2009 18:27:53 +0200
>>>
>>> x86: Introduce GDT_ENTRY_INIT()
>>>
>>> GDT_ENTRY_INIT is static initializer of desc_struct.
>>>
>>> We already have similar macro GDT_ENTRY() but it's static
>>> initializer for u64 and it cannot be used for desc_struct.
>>>
>>> Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
>>> LKML-Reference: <20090718151219.GD11294@localhost.localdomain>
>>> Signed-off-by: Ingo Molnar <mingo@elte.hu>
>>>
>
> OK, I spotted the following error, which certainly would explain a crash on
> an APM machine:
>
>        /* data */
> -       [GDT_ENTRY_APMBIOS_BASE+2]      = { { { 0x0000ffff, 0x00409200 } }
> },
> +       [GDT_ENTRY_APMBIOS_BASE+2]      = GDT_ENTRY_INIT(0x409a, 0, 0xffff),

Oops, I really should have checked the binary because the compiler should
generate same code with this patch.

> Also, we shouldn't be initializing the A bits to clear unless we actually
> plan to check the A (and D) bits... that's just a waste of CPU cycles.

I'll check it, too.