Re: [PATCH v2 10/18] x86/asm: Remap the TSS into the cpu entry area

[Andy Lutomirski]

On Thu, Nov 23, 2017 at 11:55 AM, Borislav Petkov <bp@xxxxxxx> wrote:
> On Tue, Nov 21, 2017 at 08:44:05PM -0800, Andy Lutomirski wrote:
>> This has a secondary purpose: it puts the entry stack into a region
>> with a well-controlled layout.  A subsequent patch will take
>> advantage of this to streamline the SYSCALL entry code to be able to
>> find it more easily.
>>
>> Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
>> ---
>>  arch/x86/entry/entry_32.S     |  6 ++++--
>>  arch/x86/include/asm/fixmap.h |  7 +++++++
>>  arch/x86/kernel/asm-offsets.c |  3 +++
>>  arch/x86/kernel/cpu/common.c  | 40 ++++++++++++++++++++++++++++++++++------
>>  arch/x86/kernel/dumpstack.c   |  3 ++-
>>  arch/x86/power/cpu.c          | 11 ++++++-----
>>  6 files changed, 56 insertions(+), 14 deletions(-)
>>
>> diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
>> index 4838037f97f6..0ab316c46806 100644
>> --- a/arch/x86/entry/entry_32.S
>> +++ b/arch/x86/entry/entry_32.S
>> @@ -941,7 +941,8 @@ ENTRY(debug)
>>       movl    %esp, %eax                      # pt_regs pointer
>>
>>       /* Are we currently on the SYSENTER stack? */
>> -     PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
>> +     movl    PER_CPU_VAR(cpu_entry_area), %ecx
>> +     addl    $CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
>>       subl    %eax, %ecx      /* ecx = (end of SYSENTER_stack) - esp */
>
> Fixup that comment while you're at it to be either ontop or be of the
> #-type. The cool thing about the # comments is that gas puts them in the
> .s output too, so you can find them again.
>
>>       cmpl    $SIZEOF_SYSENTER_stack, %ecx
>>       jb      .Ldebug_from_sysenter_stack
>> @@ -984,7 +985,8 @@ ENTRY(nmi)
>>       movl    %esp, %eax                      # pt_regs pointer
>>
>>       /* Are we currently on the SYSENTER stack? */
>> -     PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
>> +     movl    PER_CPU_VAR(cpu_entry_area), %ecx
>> +     addl    $CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx
>>       subl    %eax, %ecx      /* ecx = (end of SYSENTER_stack) - esp */
>
> Ditto.

Nifty.  I didn't know about that.

>
>>       cmpl    $SIZEOF_SYSENTER_stack, %ecx
>>       jb      .Lnmi_from_sysenter_stack
>
> ...
>
>> diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
>> index b275863128eb..55858b277cf6 100644
>> --- a/arch/x86/kernel/asm-offsets.c
>> +++ b/arch/x86/kernel/asm-offsets.c
>> @@ -98,4 +98,7 @@ void common(void) {
>>       OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
>>       /* Size of SYSENTER_stack */
>>       DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
>> +
>> +     /* Layout info for cpu_entry_area */
>> +     OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
>
> The naming convention of those looks really strange. The beginning is in
> all caps and then small. Can we choose a convention pls.

This is actually consistent with the rest of the offsets.  The
convention is STRUCT_field.

>
> And the comments are not really needed - the variable names already say
> what they are.

Fair enough.

>
> ...
>
>> @@ -1281,7 +1304,8 @@ void enable_sep_cpu(void)
>>       wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
>>
>>       wrmsr(MSR_IA32_SYSENTER_ESP,
>> -           (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
>> +           (unsigned long)&get_cpu_entry_area(cpu)->tss +
>> +           offsetofend(struct tss_struct, SYSENTER_stack),
>>             0);
>
> Use a local var:
>
>         unsigned long se_esp;
>
>         ...
>
>         se_esp = (unsigned long)&get_cpu_entry_area(cpu)->tss + offsetofend(struct tss_struct, SYSENTER_stack);
>
>         wrmsr(MSR_IA32_SYSENTER_ESP, se_esp, 0);

Hmm.  I may just add a helper in a header for this.  It has plenty of users.

>
>>
>>       wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
>> @@ -1394,6 +1418,8 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
>>  /* May not be marked __init: used by software suspend */
>>  void syscall_init(void)
>>  {
>> +     int cpu = smp_processor_id();
>> +
>>       wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
>>       wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
>>
>> @@ -1407,7 +1433,7 @@ void syscall_init(void)
>>        */
>>       wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
>>       wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
>> -                 (unsigned long)this_cpu_ptr(&cpu_tss) +
>> +                 (unsigned long)&get_cpu_entry_area(cpu)->tss +
>>                   offsetofend(struct tss_struct, SYSENTER_stack));
>
> Ditto.
>
>>       wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
>>  #else
>
> --
> Regards/Gruss,
>     Boris.
>
> SUSE Linux GmbH, GF: Felix ImendÃrffer, Jane Smithard, Graham Norton, HRB 21284 (AG NÃrnberg)
> --