Extract initrd free logic from arch-specific code.

Message ID 20180328152714.6103-1-shea@shealevy.com
State New
Headers show
Series
  • Extract initrd free logic from arch-specific code.
Related show

Commit Message

Shea Levy March 28, 2018, 3:26 p.m.
Now only those architectures that have custom initrd free requirements
need to define free_initrd_mem.

Signed-off-by: Shea Levy <shea@shealevy.com>
---
 arch/alpha/mm/init.c      |  8 --------
 arch/arc/mm/init.c        |  7 -------
 arch/arm/Kconfig          |  1 +
 arch/arm64/Kconfig        |  1 +
 arch/blackfin/Kconfig     |  1 +
 arch/c6x/mm/init.c        |  7 -------
 arch/cris/Kconfig         |  1 +
 arch/frv/mm/init.c        | 11 -----------
 arch/h8300/mm/init.c      |  7 -------
 arch/hexagon/Kconfig      |  1 +
 arch/ia64/Kconfig         |  1 +
 arch/m32r/Kconfig         |  1 +
 arch/m32r/mm/init.c       | 11 -----------
 arch/m68k/mm/init.c       |  7 -------
 arch/metag/Kconfig        |  1 +
 arch/microblaze/mm/init.c |  7 -------
 arch/mips/Kconfig         |  1 +
 arch/mn10300/Kconfig      |  1 +
 arch/nios2/mm/init.c      |  7 -------
 arch/openrisc/mm/init.c   |  7 -------
 arch/parisc/mm/init.c     |  7 -------
 arch/powerpc/mm/mem.c     |  7 -------
 arch/riscv/mm/init.c      |  6 ------
 arch/s390/Kconfig         |  1 +
 arch/score/Kconfig        |  1 +
 arch/sh/mm/init.c         |  7 -------
 arch/sparc/Kconfig        |  1 +
 arch/tile/Kconfig         |  1 +
 arch/um/kernel/mem.c      |  7 -------
 arch/unicore32/Kconfig    |  1 +
 arch/x86/Kconfig          |  1 +
 arch/xtensa/Kconfig       |  1 +
 init/initramfs.c          |  7 +++++++
 usr/Kconfig               |  4 ++++
 34 files changed, 28 insertions(+), 113 deletions(-)

Comments

Rob Landley March 28, 2018, 3:58 p.m. | #1
On 03/28/2018 10:26 AM, Shea Levy wrote:
> Now only those architectures that have custom initrd free requirements
> need to define free_initrd_mem.
...
> --- a/arch/arc/mm/init.c
> +++ b/arch/arc/mm/init.c
> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
>  {
>  	free_initmem_default(-1);
>  }
> -
> -#ifdef CONFIG_BLK_DEV_INITRD
> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> -{
> -	free_reserved_area((void *)start, (void *)end, -1, "initrd");
> -}
> -#endif
> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> index 3f972e83909b..19d1c5594e2d 100644
> --- a/arch/arm/Kconfig
> +++ b/arch/arm/Kconfig
> @@ -47,6 +47,7 @@ config ARM
>  	select HARDIRQS_SW_RESEND
>  	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
>  	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> +	select HAVE_ARCH_FREE_INITRD_MEM
>  	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
>  	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
>  	select HAVE_ARCH_MMAP_RND_BITS if MMU

Isn't this why weak symbols were invented?

Confused,

Rob
Shea Levy March 28, 2018, 4:04 p.m. | #2
Hi Rob,

Rob Landley <rob@landley.net> writes:

> On 03/28/2018 10:26 AM, Shea Levy wrote:
>> Now only those architectures that have custom initrd free requirements
>> need to define free_initrd_mem.
> ...
>> --- a/arch/arc/mm/init.c
>> +++ b/arch/arc/mm/init.c
>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
>>  {
>>  	free_initmem_default(-1);
>>  }
>> -
>> -#ifdef CONFIG_BLK_DEV_INITRD
>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
>> -{
>> -	free_reserved_area((void *)start, (void *)end, -1, "initrd");
>> -}
>> -#endif
>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
>> index 3f972e83909b..19d1c5594e2d 100644
>> --- a/arch/arm/Kconfig
>> +++ b/arch/arm/Kconfig
>> @@ -47,6 +47,7 @@ config ARM
>>  	select HARDIRQS_SW_RESEND
>>  	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
>>  	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
>> +	select HAVE_ARCH_FREE_INITRD_MEM
>>  	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
>>  	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
>>  	select HAVE_ARCH_MMAP_RND_BITS if MMU
>
> Isn't this why weak symbols were invented?
>

This approach was suggested by Christoph Hellwig upthread, and seems to
have some precedent elsewhere (e.g. strncasecmp), but I agree weak
symbols seem appropriate here. I'm happy to implement either approach!

>
> Confused,
>
> Rob

Thanks,
Shea
Russell King - ARM Linux March 28, 2018, 4:48 p.m. | #3
On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
> On 03/28/2018 10:26 AM, Shea Levy wrote:
> > Now only those architectures that have custom initrd free requirements
> > need to define free_initrd_mem.
> ...
> > --- a/arch/arc/mm/init.c
> > +++ b/arch/arc/mm/init.c
> > @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> >  {
> >  	free_initmem_default(-1);
> >  }
> > -
> > -#ifdef CONFIG_BLK_DEV_INITRD
> > -void __init free_initrd_mem(unsigned long start, unsigned long end)
> > -{
> > -	free_reserved_area((void *)start, (void *)end, -1, "initrd");
> > -}
> > -#endif
> > diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> > index 3f972e83909b..19d1c5594e2d 100644
> > --- a/arch/arm/Kconfig
> > +++ b/arch/arm/Kconfig
> > @@ -47,6 +47,7 @@ config ARM
> >  	select HARDIRQS_SW_RESEND
> >  	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> >  	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> > +	select HAVE_ARCH_FREE_INITRD_MEM
> >  	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> >  	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> >  	select HAVE_ARCH_MMAP_RND_BITS if MMU
> 
> Isn't this why weak symbols were invented?

Weak symbols means that we end up with both the weakly-referenced code
and the arch code in the kernel image.  That's fine if the weak code
is small.
Kees Cook March 28, 2018, 4:55 p.m. | #4
On Wed, Mar 28, 2018 at 8:26 AM, Shea Levy <shea@shealevy.com> wrote:
> Now only those architectures that have custom initrd free requirements
> need to define free_initrd_mem.
>
> Signed-off-by: Shea Levy <shea@shealevy.com>

Yay consolidation! :)

> --- a/usr/Kconfig
> +++ b/usr/Kconfig
> @@ -233,3 +233,7 @@ config INITRAMFS_COMPRESSION
>         default ".lzma" if RD_LZMA
>         default ".bz2"  if RD_BZIP2
>         default ""
> +
> +config HAVE_ARCH_FREE_INITRD_MEM
> +       bool
> +       default n

If you keep the Kconfig, you can leave off "default n", and I'd
suggest adding a help section just to describe what the per-arch
responsibilities are when select-ing the config. (See
HAVE_ARCH_SECCOMP_FILTER for an example.)

-Kees
Rob Landley March 28, 2018, 7:04 p.m. | #5
On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
> On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
>> On 03/28/2018 10:26 AM, Shea Levy wrote:
>>> Now only those architectures that have custom initrd free requirements
>>> need to define free_initrd_mem.
>> ...
>>> --- a/arch/arc/mm/init.c
>>> +++ b/arch/arc/mm/init.c
>>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
>>>  {
>>>  	free_initmem_default(-1);
>>>  }
>>> -
>>> -#ifdef CONFIG_BLK_DEV_INITRD
>>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
>>> -{
>>> -	free_reserved_area((void *)start, (void *)end, -1, "initrd");
>>> -}
>>> -#endif
>>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
>>> index 3f972e83909b..19d1c5594e2d 100644
>>> --- a/arch/arm/Kconfig
>>> +++ b/arch/arm/Kconfig
>>> @@ -47,6 +47,7 @@ config ARM
>>>  	select HARDIRQS_SW_RESEND
>>>  	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
>>>  	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
>>> +	select HAVE_ARCH_FREE_INITRD_MEM
>>>  	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
>>>  	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
>>>  	select HAVE_ARCH_MMAP_RND_BITS if MMU
>>
>> Isn't this why weak symbols were invented?
> 
> Weak symbols means that we end up with both the weakly-referenced code
> and the arch code in the kernel image.  That's fine if the weak code
> is small.

The kernel's been able to build with link time garbage collection since 2016:

https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d

Wouldn't that remove the unused one?

Rob
Russell King - ARM Linux March 28, 2018, 10:14 p.m. | #6
On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
> 
> 
> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
> >> On 03/28/2018 10:26 AM, Shea Levy wrote:
> >>> Now only those architectures that have custom initrd free requirements
> >>> need to define free_initrd_mem.
> >> ...
> >>> --- a/arch/arc/mm/init.c
> >>> +++ b/arch/arc/mm/init.c
> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> >>>  {
> >>>  	free_initmem_default(-1);
> >>>  }
> >>> -
> >>> -#ifdef CONFIG_BLK_DEV_INITRD
> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> >>> -{
> >>> -	free_reserved_area((void *)start, (void *)end, -1, "initrd");
> >>> -}
> >>> -#endif
> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> >>> index 3f972e83909b..19d1c5594e2d 100644
> >>> --- a/arch/arm/Kconfig
> >>> +++ b/arch/arm/Kconfig
> >>> @@ -47,6 +47,7 @@ config ARM
> >>>  	select HARDIRQS_SW_RESEND
> >>>  	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> >>>  	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> >>> +	select HAVE_ARCH_FREE_INITRD_MEM
> >>>  	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> >>>  	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> >>>  	select HAVE_ARCH_MMAP_RND_BITS if MMU
> >>
> >> Isn't this why weak symbols were invented?
> > 
> > Weak symbols means that we end up with both the weakly-referenced code
> > and the arch code in the kernel image.  That's fine if the weak code
> > is small.
> 
> The kernel's been able to build with link time garbage collection since 2016:
> 
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
> 
> Wouldn't that remove the unused one?

Probably, if anyone bothered to use that, which they don't.

LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
what I can see, nothing selects it.  Therefore, the symbol is always
disabled, and so the feature never gets used in mainline kernels.

Brings up the obvious question - why is it there if it's completely
unused?  (Maybe to cause confusion, and allowing a justification
for __weak ?)
Oliver O'Halloran March 28, 2018, 10:37 p.m. | #7
On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
<linux@armlinux.org.uk> wrote:
> On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
>>
>>
>> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
>> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
>> >> On 03/28/2018 10:26 AM, Shea Levy wrote:
>> >>> Now only those architectures that have custom initrd free requirements
>> >>> need to define free_initrd_mem.
>> >> ...
>> >>> --- a/arch/arc/mm/init.c
>> >>> +++ b/arch/arc/mm/init.c
>> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
>> >>>  {
>> >>>   free_initmem_default(-1);
>> >>>  }
>> >>> -
>> >>> -#ifdef CONFIG_BLK_DEV_INITRD
>> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
>> >>> -{
>> >>> - free_reserved_area((void *)start, (void *)end, -1, "initrd");
>> >>> -}
>> >>> -#endif
>> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
>> >>> index 3f972e83909b..19d1c5594e2d 100644
>> >>> --- a/arch/arm/Kconfig
>> >>> +++ b/arch/arm/Kconfig
>> >>> @@ -47,6 +47,7 @@ config ARM
>> >>>   select HARDIRQS_SW_RESEND
>> >>>   select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
>> >>>   select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
>> >>> + select HAVE_ARCH_FREE_INITRD_MEM
>> >>>   select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
>> >>>   select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
>> >>>   select HAVE_ARCH_MMAP_RND_BITS if MMU
>> >>
>> >> Isn't this why weak symbols were invented?
>> >
>> > Weak symbols means that we end up with both the weakly-referenced code
>> > and the arch code in the kernel image.  That's fine if the weak code
>> > is small.
>>
>> The kernel's been able to build with link time garbage collection since 2016:
>>
>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
>>
>> Wouldn't that remove the unused one?
>
> Probably, if anyone bothered to use that, which they don't.
>
> LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> what I can see, nothing selects it.  Therefore, the symbol is always
> disabled, and so the feature never gets used in mainline kernels.
>
> Brings up the obvious question - why is it there if it's completely
> unused?  (Maybe to cause confusion, and allowing a justification
> for __weak ?)

IIRC Nick had some patches to do the arch enablement for powerpc, but
I'm not sure what happened to them though. I suspect it just fell down
Nick's ever growing TODO list.
Nicholas Piggin March 29, 2018, 12:23 a.m. | #8
On Thu, 29 Mar 2018 09:37:52 +1100
Oliver <oohall@gmail.com> wrote:

> On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
> <linux@armlinux.org.uk> wrote:
> > On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:  
> >>
> >>
> >> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:  
> >> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:  
> >> >> On 03/28/2018 10:26 AM, Shea Levy wrote:  
> >> >>> Now only those architectures that have custom initrd free requirements
> >> >>> need to define free_initrd_mem.  
> >> >> ...  
> >> >>> --- a/arch/arc/mm/init.c
> >> >>> +++ b/arch/arc/mm/init.c
> >> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> >> >>>  {
> >> >>>   free_initmem_default(-1);
> >> >>>  }
> >> >>> -
> >> >>> -#ifdef CONFIG_BLK_DEV_INITRD
> >> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> >> >>> -{
> >> >>> - free_reserved_area((void *)start, (void *)end, -1, "initrd");
> >> >>> -}
> >> >>> -#endif
> >> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> >> >>> index 3f972e83909b..19d1c5594e2d 100644
> >> >>> --- a/arch/arm/Kconfig
> >> >>> +++ b/arch/arm/Kconfig
> >> >>> @@ -47,6 +47,7 @@ config ARM
> >> >>>   select HARDIRQS_SW_RESEND
> >> >>>   select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> >> >>>   select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> >> >>> + select HAVE_ARCH_FREE_INITRD_MEM
> >> >>>   select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> >> >>>   select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> >> >>>   select HAVE_ARCH_MMAP_RND_BITS if MMU  
> >> >>
> >> >> Isn't this why weak symbols were invented?  
> >> >
> >> > Weak symbols means that we end up with both the weakly-referenced code
> >> > and the arch code in the kernel image.  That's fine if the weak code
> >> > is small.  
> >>
> >> The kernel's been able to build with link time garbage collection since 2016:
> >>
> >> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
> >>
> >> Wouldn't that remove the unused one?  
> >
> > Probably, if anyone bothered to use that, which they don't.
> >
> > LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> > what I can see, nothing selects it.  Therefore, the symbol is always
> > disabled, and so the feature never gets used in mainline kernels.
> >
> > Brings up the obvious question - why is it there if it's completely
> > unused?  (Maybe to cause confusion, and allowing a justification
> > for __weak ?)  

Well weak symbols have been used long before it was added.

> IIRC Nick had some patches to do the arch enablement for powerpc, but
> I'm not sure what happened to them though. I suspect it just fell down
> Nick's ever growing TODO list.

Yeah I had started some patches for powerpc and x86 that have ended up
on the back burner. There's been some MIPS people playing with it too.

For the kernel, LD_DEAD_CODE_DATA_ELIMINATION is not great. It can save
a little, but you get issues like any exception table entry or bug table
entry in a function will create a reference back to the function, so the
linker can't trim it away even if nothing else references it.

I'll try to take another look at it within the next few months and
remove it if I can't make progress.

Nicolas Pitre has been doing some much better work on dead code using
real LTO.

Thanks,
Nick
Wei Yang March 29, 2018, 1:12 a.m. | #9
On Wed, Mar 28, 2018 at 09:55:07AM -0700, Kees Cook wrote:
>On Wed, Mar 28, 2018 at 8:26 AM, Shea Levy <shea@shealevy.com> wrote:
>> Now only those architectures that have custom initrd free requirements
>> need to define free_initrd_mem.
>>
>> Signed-off-by: Shea Levy <shea@shealevy.com>
>
>Yay consolidation! :)
>
>> --- a/usr/Kconfig
>> +++ b/usr/Kconfig
>> @@ -233,3 +233,7 @@ config INITRAMFS_COMPRESSION
>>         default ".lzma" if RD_LZMA
>>         default ".bz2"  if RD_BZIP2
>>         default ""
>> +
>> +config HAVE_ARCH_FREE_INITRD_MEM
>> +       bool
>> +       default n
>
>If you keep the Kconfig, you can leave off "default n", and I'd
>suggest adding a help section just to describe what the per-arch
>responsibilities are when select-ing the config. (See
>HAVE_ARCH_SECCOMP_FILTER for an example.)
>

One question about this change.

The original code would "select" HAVE_ARCH_FREE_INITRD_MEM on those arch.
After this change, we need to manually "select" this?

>-Kees
>
>-- 
>Kees Cook
>Pixel Security
Russell King - ARM Linux March 29, 2018, 3:27 p.m. | #10
On Thu, Mar 29, 2018 at 09:37:52AM +1100, Oliver wrote:
> On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
> <linux@armlinux.org.uk> wrote:
> > On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
> >>
> >>
> >> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
> >> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
> >> >> On 03/28/2018 10:26 AM, Shea Levy wrote:
> >> >>> Now only those architectures that have custom initrd free requirements
> >> >>> need to define free_initrd_mem.
> >> >> ...
> >> >>> --- a/arch/arc/mm/init.c
> >> >>> +++ b/arch/arc/mm/init.c
> >> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> >> >>>  {
> >> >>>   free_initmem_default(-1);
> >> >>>  }
> >> >>> -
> >> >>> -#ifdef CONFIG_BLK_DEV_INITRD
> >> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> >> >>> -{
> >> >>> - free_reserved_area((void *)start, (void *)end, -1, "initrd");
> >> >>> -}
> >> >>> -#endif
> >> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> >> >>> index 3f972e83909b..19d1c5594e2d 100644
> >> >>> --- a/arch/arm/Kconfig
> >> >>> +++ b/arch/arm/Kconfig
> >> >>> @@ -47,6 +47,7 @@ config ARM
> >> >>>   select HARDIRQS_SW_RESEND
> >> >>>   select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> >> >>>   select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> >> >>> + select HAVE_ARCH_FREE_INITRD_MEM
> >> >>>   select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> >> >>>   select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> >> >>>   select HAVE_ARCH_MMAP_RND_BITS if MMU
> >> >>
> >> >> Isn't this why weak symbols were invented?
> >> >
> >> > Weak symbols means that we end up with both the weakly-referenced code
> >> > and the arch code in the kernel image.  That's fine if the weak code
> >> > is small.
> >>
> >> The kernel's been able to build with link time garbage collection since 2016:
> >>
> >> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
> >>
> >> Wouldn't that remove the unused one?
> >
> > Probably, if anyone bothered to use that, which they don't.
> >
> > LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> > what I can see, nothing selects it.  Therefore, the symbol is always
> > disabled, and so the feature never gets used in mainline kernels.
> >
> > Brings up the obvious question - why is it there if it's completely
> > unused?  (Maybe to cause confusion, and allowing a justification
> > for __weak ?)
> 
> IIRC Nick had some patches to do the arch enablement for powerpc, but
> I'm not sure what happened to them though. I suspect it just fell down
> Nick's ever growing TODO list.

I've given it a go on ARM, marking every linker-built table with KEEP()
and comparing the System.map files.  The resulting kernel is around
150k smaller, which seems good.

However, it doesn't boot - and I don't know why.  Booting the kernel
under kvmtool in a VM using virtio-console, I can find no way to get
any kernel messages out of it.  Using lkvm debug, I can see that the
PC is stuck inside die(), and that's the only information I have.
It dies before bringing up the other CPUs, so it's a very early death.

I don't think other console types are available under ARM64.
Geert Uytterhoeven March 29, 2018, 3:43 p.m. | #11
On Thu, Mar 29, 2018 at 5:27 PM, Russell King - ARM Linux
<linux@armlinux.org.uk> wrote:
> On Thu, Mar 29, 2018 at 09:37:52AM +1100, Oliver wrote:
>> On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
>> <linux@armlinux.org.uk> wrote:
>> > On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
>> >> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
>> >> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
>> >> >> On 03/28/2018 10:26 AM, Shea Levy wrote:
>> >> >>> Now only those architectures that have custom initrd free requirements
>> >> >>> need to define free_initrd_mem.
>> >> >> ...
>> >> >>> --- a/arch/arc/mm/init.c
>> >> >>> +++ b/arch/arc/mm/init.c
>> >> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
>> >> >>>  {
>> >> >>>   free_initmem_default(-1);
>> >> >>>  }
>> >> >>> -
>> >> >>> -#ifdef CONFIG_BLK_DEV_INITRD
>> >> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
>> >> >>> -{
>> >> >>> - free_reserved_area((void *)start, (void *)end, -1, "initrd");
>> >> >>> -}
>> >> >>> -#endif
>> >> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
>> >> >>> index 3f972e83909b..19d1c5594e2d 100644
>> >> >>> --- a/arch/arm/Kconfig
>> >> >>> +++ b/arch/arm/Kconfig
>> >> >>> @@ -47,6 +47,7 @@ config ARM
>> >> >>>   select HARDIRQS_SW_RESEND
>> >> >>>   select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
>> >> >>>   select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
>> >> >>> + select HAVE_ARCH_FREE_INITRD_MEM
>> >> >>>   select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
>> >> >>>   select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
>> >> >>>   select HAVE_ARCH_MMAP_RND_BITS if MMU
>> >> >>
>> >> >> Isn't this why weak symbols were invented?
>> >> >
>> >> > Weak symbols means that we end up with both the weakly-referenced code
>> >> > and the arch code in the kernel image.  That's fine if the weak code
>> >> > is small.
>> >>
>> >> The kernel's been able to build with link time garbage collection since 2016:
>> >>
>> >> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
>> >>
>> >> Wouldn't that remove the unused one?
>> >
>> > Probably, if anyone bothered to use that, which they don't.
>> >
>> > LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
>> > what I can see, nothing selects it.  Therefore, the symbol is always
>> > disabled, and so the feature never gets used in mainline kernels.
>> >
>> > Brings up the obvious question - why is it there if it's completely
>> > unused?  (Maybe to cause confusion, and allowing a justification
>> > for __weak ?)
>>
>> IIRC Nick had some patches to do the arch enablement for powerpc, but
>> I'm not sure what happened to them though. I suspect it just fell down
>> Nick's ever growing TODO list.
>
> I've given it a go on ARM, marking every linker-built table with KEEP()
> and comparing the System.map files.  The resulting kernel is around
> 150k smaller, which seems good.
>
> However, it doesn't boot - and I don't know why.  Booting the kernel
> under kvmtool in a VM using virtio-console, I can find no way to get
> any kernel messages out of it.  Using lkvm debug, I can see that the
> PC is stuck inside die(), and that's the only information I have.
> It dies before bringing up the other CPUs, so it's a very early death.
>
> I don't think other console types are available under ARM64.

earlycon?

Gr{oetje,eeting}s,

                        Geert
Russell King - ARM Linux March 29, 2018, 3:58 p.m. | #12
On Thu, Mar 29, 2018 at 05:43:47PM +0200, Geert Uytterhoeven wrote:
> On Thu, Mar 29, 2018 at 5:27 PM, Russell King - ARM Linux
> <linux@armlinux.org.uk> wrote:
> > On Thu, Mar 29, 2018 at 09:37:52AM +1100, Oliver wrote:
> >> On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
> >> <linux@armlinux.org.uk> wrote:
> >> > On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
> >> >> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
> >> >> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
> >> >> >> On 03/28/2018 10:26 AM, Shea Levy wrote:
> >> >> >>> Now only those architectures that have custom initrd free requirements
> >> >> >>> need to define free_initrd_mem.
> >> >> >> ...
> >> >> >>> --- a/arch/arc/mm/init.c
> >> >> >>> +++ b/arch/arc/mm/init.c
> >> >> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> >> >> >>>  {
> >> >> >>>   free_initmem_default(-1);
> >> >> >>>  }
> >> >> >>> -
> >> >> >>> -#ifdef CONFIG_BLK_DEV_INITRD
> >> >> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> >> >> >>> -{
> >> >> >>> - free_reserved_area((void *)start, (void *)end, -1, "initrd");
> >> >> >>> -}
> >> >> >>> -#endif
> >> >> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> >> >> >>> index 3f972e83909b..19d1c5594e2d 100644
> >> >> >>> --- a/arch/arm/Kconfig
> >> >> >>> +++ b/arch/arm/Kconfig
> >> >> >>> @@ -47,6 +47,7 @@ config ARM
> >> >> >>>   select HARDIRQS_SW_RESEND
> >> >> >>>   select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> >> >> >>>   select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> >> >> >>> + select HAVE_ARCH_FREE_INITRD_MEM
> >> >> >>>   select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> >> >> >>>   select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> >> >> >>>   select HAVE_ARCH_MMAP_RND_BITS if MMU
> >> >> >>
> >> >> >> Isn't this why weak symbols were invented?
> >> >> >
> >> >> > Weak symbols means that we end up with both the weakly-referenced code
> >> >> > and the arch code in the kernel image.  That's fine if the weak code
> >> >> > is small.
> >> >>
> >> >> The kernel's been able to build with link time garbage collection since 2016:
> >> >>
> >> >> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
> >> >>
> >> >> Wouldn't that remove the unused one?
> >> >
> >> > Probably, if anyone bothered to use that, which they don't.
> >> >
> >> > LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> >> > what I can see, nothing selects it.  Therefore, the symbol is always
> >> > disabled, and so the feature never gets used in mainline kernels.
> >> >
> >> > Brings up the obvious question - why is it there if it's completely
> >> > unused?  (Maybe to cause confusion, and allowing a justification
> >> > for __weak ?)
> >>
> >> IIRC Nick had some patches to do the arch enablement for powerpc, but
> >> I'm not sure what happened to them though. I suspect it just fell down
> >> Nick's ever growing TODO list.
> >
> > I've given it a go on ARM, marking every linker-built table with KEEP()
> > and comparing the System.map files.  The resulting kernel is around
> > 150k smaller, which seems good.
> >
> > However, it doesn't boot - and I don't know why.  Booting the kernel
> > under kvmtool in a VM using virtio-console, I can find no way to get
> > any kernel messages out of it.  Using lkvm debug, I can see that the
> > PC is stuck inside die(), and that's the only information I have.
> > It dies before bringing up the other CPUs, so it's a very early death.
> >
> > I don't think other console types are available under ARM64.
> 
> earlycon?

Through what - as I say above, I think the only thing that's present is
virtio-console, and the virtio stack only get initialised much later in
boot.

Eg, there's the memory-based virtio driver which interfaces any virtio
driver to a memory-based ring structures for communication with the host
(drivers/virtio/virtio_mmio.c) which is initialised at module_init()
time, and so isn't available for earlycon.

I don't think merely changing the module_init() calls in the appropriate
virtio bits will suffice - it's why I pointed out that it dies before
SMP initialisation, which also means that it dies before we start
running the initcalls for subsystems and drivers.

I'm not aware of there being an emulated UART in the guest's address
space, so serial based stuff doesn't work.
Rob Landley March 29, 2018, 4:39 p.m. | #13
On 03/28/2018 05:14 PM, Russell King - ARM Linux wrote:
> On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
>>
>>
>> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
>>> On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
>>>> On 03/28/2018 10:26 AM, Shea Levy wrote:
>>>>> Now only those architectures that have custom initrd free requirements
>>>>> need to define free_initrd_mem.
>>>> ...
>>>>> --- a/arch/arc/mm/init.c
>>>>> +++ b/arch/arc/mm/init.c
>>>>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
>>>>>  {
>>>>>  	free_initmem_default(-1);
>>>>>  }
>>>>> -
>>>>> -#ifdef CONFIG_BLK_DEV_INITRD
>>>>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
>>>>> -{
>>>>> -	free_reserved_area((void *)start, (void *)end, -1, "initrd");
>>>>> -}
>>>>> -#endif
>>>>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
>>>>> index 3f972e83909b..19d1c5594e2d 100644
>>>>> --- a/arch/arm/Kconfig
>>>>> +++ b/arch/arm/Kconfig
>>>>> @@ -47,6 +47,7 @@ config ARM
>>>>>  	select HARDIRQS_SW_RESEND
>>>>>  	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
>>>>>  	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
>>>>> +	select HAVE_ARCH_FREE_INITRD_MEM
>>>>>  	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
>>>>>  	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
>>>>>  	select HAVE_ARCH_MMAP_RND_BITS if MMU
>>>>
>>>> Isn't this why weak symbols were invented?
>>>
>>> Weak symbols means that we end up with both the weakly-referenced code
>>> and the arch code in the kernel image.  That's fine if the weak code
>>> is small.
>>
>> The kernel's been able to build with link time garbage collection since 2016:
>>
>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
>>
>> Wouldn't that remove the unused one?
> 
> Probably, if anyone bothered to use that, which they don't.
> 
> LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> what I can see, nothing selects it.  Therefore, the symbol is always
> disabled, and so the feature never gets used in mainline kernels.

It looks like there are per-architecture linker scripts that need to be updated?
So if an architecture supports it, it's always done (well, it probes for the
toolchain supporting the flag). And if the architecture doesn't support it, the
linker script needs to be updated to mark sections with "I know nothing seems to
reference this at the ELF level but keep it anyway, we're pulling an assembly
trick".

> Brings up the obvious question - why is it there if it's completely
> unused?  (Maybe to cause confusion, and allowing a justification
> for __weak ?)

Presumably it will become the default on architectures as their linker scripts
are converted. Once they're all converted the config symbol can go away. (Given
the move to requiring gcc 4.7 or whatever it is, there can't be an architecture
depending on a toolchain that _doesn't_ support it after that point. I doubt you
can pair gcc 4.7 with a >12 year old binutils and expect good things...)

Rob
Marc Zyngier March 29, 2018, 4:53 p.m. | #14
On Thu, 29 Mar 2018 16:58:27 +0100,
Russell King - ARM Linux wrote:
> 
> On Thu, Mar 29, 2018 at 05:43:47PM +0200, Geert Uytterhoeven wrote:
> > On Thu, Mar 29, 2018 at 5:27 PM, Russell King - ARM Linux
> > <linux@armlinux.org.uk> wrote:
> > > On Thu, Mar 29, 2018 at 09:37:52AM +1100, Oliver wrote:
> > >> On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
> > >> <linux@armlinux.org.uk> wrote:
> > >> > On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
> > >> >> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
> > >> >> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
> > >> >> >> On 03/28/2018 10:26 AM, Shea Levy wrote:
> > >> >> >>> Now only those architectures that have custom initrd free requirements
> > >> >> >>> need to define free_initrd_mem.
> > >> >> >> ...
> > >> >> >>> --- a/arch/arc/mm/init.c
> > >> >> >>> +++ b/arch/arc/mm/init.c
> > >> >> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> > >> >> >>>  {
> > >> >> >>>   free_initmem_default(-1);
> > >> >> >>>  }
> > >> >> >>> -
> > >> >> >>> -#ifdef CONFIG_BLK_DEV_INITRD
> > >> >> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> > >> >> >>> -{
> > >> >> >>> - free_reserved_area((void *)start, (void *)end, -1, "initrd");
> > >> >> >>> -}
> > >> >> >>> -#endif
> > >> >> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> > >> >> >>> index 3f972e83909b..19d1c5594e2d 100644
> > >> >> >>> --- a/arch/arm/Kconfig
> > >> >> >>> +++ b/arch/arm/Kconfig
> > >> >> >>> @@ -47,6 +47,7 @@ config ARM
> > >> >> >>>   select HARDIRQS_SW_RESEND
> > >> >> >>>   select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> > >> >> >>>   select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> > >> >> >>> + select HAVE_ARCH_FREE_INITRD_MEM
> > >> >> >>>   select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> > >> >> >>>   select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> > >> >> >>>   select HAVE_ARCH_MMAP_RND_BITS if MMU
> > >> >> >>
> > >> >> >> Isn't this why weak symbols were invented?
> > >> >> >
> > >> >> > Weak symbols means that we end up with both the weakly-referenced code
> > >> >> > and the arch code in the kernel image.  That's fine if the weak code
> > >> >> > is small.
> > >> >>
> > >> >> The kernel's been able to build with link time garbage collection since 2016:
> > >> >>
> > >> >> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
> > >> >>
> > >> >> Wouldn't that remove the unused one?
> > >> >
> > >> > Probably, if anyone bothered to use that, which they don't.
> > >> >
> > >> > LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> > >> > what I can see, nothing selects it.  Therefore, the symbol is always
> > >> > disabled, and so the feature never gets used in mainline kernels.
> > >> >
> > >> > Brings up the obvious question - why is it there if it's completely
> > >> > unused?  (Maybe to cause confusion, and allowing a justification
> > >> > for __weak ?)
> > >>
> > >> IIRC Nick had some patches to do the arch enablement for powerpc, but
> > >> I'm not sure what happened to them though. I suspect it just fell down
> > >> Nick's ever growing TODO list.
> > >
> > > I've given it a go on ARM, marking every linker-built table with KEEP()
> > > and comparing the System.map files.  The resulting kernel is around
> > > 150k smaller, which seems good.
> > >
> > > However, it doesn't boot - and I don't know why.  Booting the kernel
> > > under kvmtool in a VM using virtio-console, I can find no way to get
> > > any kernel messages out of it.  Using lkvm debug, I can see that the
> > > PC is stuck inside die(), and that's the only information I have.
> > > It dies before bringing up the other CPUs, so it's a very early death.
> > >
> > > I don't think other console types are available under ARM64.
> > 
> > earlycon?
> 
> Through what - as I say above, I think the only thing that's present is
> virtio-console, and the virtio stack only get initialised much later in
> boot.
> 
> Eg, there's the memory-based virtio driver which interfaces any virtio
> driver to a memory-based ring structures for communication with the host
> (drivers/virtio/virtio_mmio.c) which is initialised at module_init()
> time, and so isn't available for earlycon.
> 
> I don't think merely changing the module_init() calls in the appropriate
> virtio bits will suffice - it's why I pointed out that it dies before
> SMP initialisation, which also means that it dies before we start
> running the initcalls for subsystems and drivers.
> 
> I'm not aware of there being an emulated UART in the guest's address
> space, so serial based stuff doesn't work.

"earlycon=uart,mmio,0x3f8" is what you're looking for:

$ Work/kvmtool/lkvm run -c2 -k zImage -p "earlycon=uart,mmio,0x3f8" --console virtio --aarch32
  # lkvm run -k zImage -m 320 -c 2 --name guest-3856
  Info: Loaded kernel to 0x80008000 (6767104 bytes)
  Info: Placing fdt at 0x8fe00000 - 0x8fffffff
  Info: virtio-mmio.devices=0x200@0x10000:36

  Info: virtio-mmio.devices=0x200@0x10200:37

  Info: virtio-mmio.devices=0x200@0x10400:38

[    0.000000] Booting Linux on physical CPU 0x0
[    0.000000] Linux version 4.16.0-rc6+ (maz@approximate) (gcc version 6.3.0 20170516 (Debian 6.3.0-18)) #8407 SMP PREEMPT Tue Mar 20 15:01:43 GMT 2018
[    0.000000] CPU: ARMv7 Processor [410fd082] revision 2 (ARMv7), cr=30c5383d
[    0.000000] CPU: div instructions available: patching division code
[    0.000000] CPU: PIPT / VIPT nonaliasing data cache, PIPT instruction cache
[    0.000000] OF: fdt: Machine model: linux,dummy-virt
[    0.000000] earlycon: uart0 at MMIO 0x00000000000003f8 (options '')
[    0.000000] bootconsole [uart0] enabled
[    0.000000] Memory policy: Data cache writealloc
[    0.000000] efi: Getting EFI parameters from FDT:
[    0.000000] efi: UEFI not found.

[...]

	M.
Russell King - ARM Linux March 29, 2018, 5:31 p.m. | #15
On Thu, Mar 29, 2018 at 11:39:24AM -0500, Rob Landley wrote:
> 
> 
> On 03/28/2018 05:14 PM, Russell King - ARM Linux wrote:
> > On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
> >>
> >>
> >> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
> >>> On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
> >>>> On 03/28/2018 10:26 AM, Shea Levy wrote:
> >>>>> Now only those architectures that have custom initrd free requirements
> >>>>> need to define free_initrd_mem.
> >>>> ...
> >>>>> --- a/arch/arc/mm/init.c
> >>>>> +++ b/arch/arc/mm/init.c
> >>>>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> >>>>>  {
> >>>>>  	free_initmem_default(-1);
> >>>>>  }
> >>>>> -
> >>>>> -#ifdef CONFIG_BLK_DEV_INITRD
> >>>>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> >>>>> -{
> >>>>> -	free_reserved_area((void *)start, (void *)end, -1, "initrd");
> >>>>> -}
> >>>>> -#endif
> >>>>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> >>>>> index 3f972e83909b..19d1c5594e2d 100644
> >>>>> --- a/arch/arm/Kconfig
> >>>>> +++ b/arch/arm/Kconfig
> >>>>> @@ -47,6 +47,7 @@ config ARM
> >>>>>  	select HARDIRQS_SW_RESEND
> >>>>>  	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> >>>>>  	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> >>>>> +	select HAVE_ARCH_FREE_INITRD_MEM
> >>>>>  	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> >>>>>  	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> >>>>>  	select HAVE_ARCH_MMAP_RND_BITS if MMU
> >>>>
> >>>> Isn't this why weak symbols were invented?
> >>>
> >>> Weak symbols means that we end up with both the weakly-referenced code
> >>> and the arch code in the kernel image.  That's fine if the weak code
> >>> is small.
> >>
> >> The kernel's been able to build with link time garbage collection since 2016:
> >>
> >> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
> >>
> >> Wouldn't that remove the unused one?
> > 
> > Probably, if anyone bothered to use that, which they don't.
> > 
> > LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> > what I can see, nothing selects it.  Therefore, the symbol is always
> > disabled, and so the feature never gets used in mainline kernels.
> 
> It looks like there are per-architecture linker scripts that need to be updated?
> So if an architecture supports it, it's always done (well, it probes for the
> toolchain supporting the flag). And if the architecture doesn't support it, the
> linker script needs to be updated to mark sections with "I know nothing seems to
> reference this at the ELF level but keep it anyway, we're pulling an assembly
> trick".

It looks like it needs much more than just architecture changes as the
reason it fails on ARM is because the init thread structure is missing
due to missing KEEP()s in INIT_TASK_DATA().  Probably means it doesn't
work anywhere.

8<===
From: Russell King <rmk+kernel@armlinux.org.uk>
Subject: [PATCH] Fix LD_DEAD_CODE_DATA_ELIMINATION

LD_DEAD_CODE_DATA_ELIMINATION fails to boot on ARM because the linker
eliminates the init thread data from the bottom of the init threads
stack.  This causes recursive faults that end up overwriting parts
of the kernel before they can print any message.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 include/asm-generic/vmlinux.lds.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 1ab0e520d6fc..41af8a74aae4 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -279,8 +279,8 @@
 	VMLINUX_SYMBOL(__start_init_task) = .;				\
 	VMLINUX_SYMBOL(init_thread_union) = .;				\
 	VMLINUX_SYMBOL(init_stack) = .;					\
-	*(.data..init_task)						\
-	*(.data..init_thread_info)					\
+	KEEP(*(.data..init_task))					\
+	KEEP(*(.data..init_thread_info))				\
 	. = VMLINUX_SYMBOL(__start_init_task) + THREAD_SIZE;		\
 	VMLINUX_SYMBOL(__end_init_task) = .;
Russell King - ARM Linux March 29, 2018, 5:32 p.m. | #16
On Thu, Mar 29, 2018 at 05:53:14PM +0100, Marc Zyngier wrote:
> On Thu, 29 Mar 2018 16:58:27 +0100,
> Russell King - ARM Linux wrote:
> > 
> > On Thu, Mar 29, 2018 at 05:43:47PM +0200, Geert Uytterhoeven wrote:
> > > On Thu, Mar 29, 2018 at 5:27 PM, Russell King - ARM Linux
> > > <linux@armlinux.org.uk> wrote:
> > > > On Thu, Mar 29, 2018 at 09:37:52AM +1100, Oliver wrote:
> > > >> On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
> > > >> <linux@armlinux.org.uk> wrote:
> > > >> > On Wed, Mar 28, 2018 at 02:04:22PM -0500, Rob Landley wrote:
> > > >> >> On 03/28/2018 11:48 AM, Russell King - ARM Linux wrote:
> > > >> >> > On Wed, Mar 28, 2018 at 10:58:51AM -0500, Rob Landley wrote:
> > > >> >> >> On 03/28/2018 10:26 AM, Shea Levy wrote:
> > > >> >> >>> Now only those architectures that have custom initrd free requirements
> > > >> >> >>> need to define free_initrd_mem.
> > > >> >> >> ...
> > > >> >> >>> --- a/arch/arc/mm/init.c
> > > >> >> >>> +++ b/arch/arc/mm/init.c
> > > >> >> >>> @@ -229,10 +229,3 @@ void __ref free_initmem(void)
> > > >> >> >>>  {
> > > >> >> >>>   free_initmem_default(-1);
> > > >> >> >>>  }
> > > >> >> >>> -
> > > >> >> >>> -#ifdef CONFIG_BLK_DEV_INITRD
> > > >> >> >>> -void __init free_initrd_mem(unsigned long start, unsigned long end)
> > > >> >> >>> -{
> > > >> >> >>> - free_reserved_area((void *)start, (void *)end, -1, "initrd");
> > > >> >> >>> -}
> > > >> >> >>> -#endif
> > > >> >> >>> diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
> > > >> >> >>> index 3f972e83909b..19d1c5594e2d 100644
> > > >> >> >>> --- a/arch/arm/Kconfig
> > > >> >> >>> +++ b/arch/arm/Kconfig
> > > >> >> >>> @@ -47,6 +47,7 @@ config ARM
> > > >> >> >>>   select HARDIRQS_SW_RESEND
> > > >> >> >>>   select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
> > > >> >> >>>   select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
> > > >> >> >>> + select HAVE_ARCH_FREE_INITRD_MEM
> > > >> >> >>>   select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
> > > >> >> >>>   select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
> > > >> >> >>>   select HAVE_ARCH_MMAP_RND_BITS if MMU
> > > >> >> >>
> > > >> >> >> Isn't this why weak symbols were invented?
> > > >> >> >
> > > >> >> > Weak symbols means that we end up with both the weakly-referenced code
> > > >> >> > and the arch code in the kernel image.  That's fine if the weak code
> > > >> >> > is small.
> > > >> >>
> > > >> >> The kernel's been able to build with link time garbage collection since 2016:
> > > >> >>
> > > >> >> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b67067f1176d
> > > >> >>
> > > >> >> Wouldn't that remove the unused one?
> > > >> >
> > > >> > Probably, if anyone bothered to use that, which they don't.
> > > >> >
> > > >> > LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
> > > >> > what I can see, nothing selects it.  Therefore, the symbol is always
> > > >> > disabled, and so the feature never gets used in mainline kernels.
> > > >> >
> > > >> > Brings up the obvious question - why is it there if it's completely
> > > >> > unused?  (Maybe to cause confusion, and allowing a justification
> > > >> > for __weak ?)
> > > >>
> > > >> IIRC Nick had some patches to do the arch enablement for powerpc, but
> > > >> I'm not sure what happened to them though. I suspect it just fell down
> > > >> Nick's ever growing TODO list.
> > > >
> > > > I've given it a go on ARM, marking every linker-built table with KEEP()
> > > > and comparing the System.map files.  The resulting kernel is around
> > > > 150k smaller, which seems good.
> > > >
> > > > However, it doesn't boot - and I don't know why.  Booting the kernel
> > > > under kvmtool in a VM using virtio-console, I can find no way to get
> > > > any kernel messages out of it.  Using lkvm debug, I can see that the
> > > > PC is stuck inside die(), and that's the only information I have.
> > > > It dies before bringing up the other CPUs, so it's a very early death.
> > > >
> > > > I don't think other console types are available under ARM64.
> > > 
> > > earlycon?
> > 
> > Through what - as I say above, I think the only thing that's present is
> > virtio-console, and the virtio stack only get initialised much later in
> > boot.
> > 
> > Eg, there's the memory-based virtio driver which interfaces any virtio
> > driver to a memory-based ring structures for communication with the host
> > (drivers/virtio/virtio_mmio.c) which is initialised at module_init()
> > time, and so isn't available for earlycon.
> > 
> > I don't think merely changing the module_init() calls in the appropriate
> > virtio bits will suffice - it's why I pointed out that it dies before
> > SMP initialisation, which also means that it dies before we start
> > running the initcalls for subsystems and drivers.
> > 
> > I'm not aware of there being an emulated UART in the guest's address
> > space, so serial based stuff doesn't work.
> 
> "earlycon=uart,mmio,0x3f8" is what you're looking for:

Does that also mean that we have a RTC at the standard PC IO addresses
as well, but in mmio space?
Rob Landley March 29, 2018, 5:43 p.m. | #17
On 03/29/2018 10:27 AM, Russell King - ARM Linux wrote:
> On Thu, Mar 29, 2018 at 09:37:52AM +1100, Oliver wrote:
>> On Thu, Mar 29, 2018 at 9:14 AM, Russell King - ARM Linux
>>> LD_DEAD_CODE_DATA_ELIMINATION is a symbol without a prompt, and from
>>> what I can see, nothing selects it.  Therefore, the symbol is always
>>> disabled, and so the feature never gets used in mainline kernels.
>>>
>>> Brings up the obvious question - why is it there if it's completely
>>> unused?  (Maybe to cause confusion, and allowing a justification
>>> for __weak ?)
>>
>> IIRC Nick had some patches to do the arch enablement for powerpc, but
>> I'm not sure what happened to them though. I suspect it just fell down
>> Nick's ever growing TODO list.
> 
> I've given it a go on ARM, marking every linker-built table with KEEP()
> and comparing the System.map files.  The resulting kernel is around
> 150k smaller, which seems good.
> 
> However, it doesn't boot - and I don't know why.  Booting the kernel
> under kvmtool in a VM using virtio-console, I can find no way to get
> any kernel messages out of it.  Using lkvm debug, I can see that the
> PC is stuck inside die(), and that's the only information I have.

qemu-system-arm's "-s" option lets you hook to the hardware with gdb, as if
using one of those jtags that speaks gdbserver protocol. It stops waiting for
you to attach with 'target remote' it, then 'file vmlinux' to load the symbols...

The miniconfig and qemu invocation I use for arm64 are attached, tested with
2.11.0 on a 4.14 kernel. You should be able to just "qemu-aarch64.sh -s" and
then probably "target remote 127.0.0.1:1234"? (Been a while since I've used it,
don't have a cross-gdb for arm64 lying around...)

Sigh, I just tried -s and qemu 2.11.0 is _not_ waiting for gdb to attach on
arm64, despite what the docs say:

$ qemu-system-aarch64 --help | grep gdb
-gdb dev        wait for gdb connection on 'dev'
-s              shorthand for -gdb tcp::1234

Another random regression in qemu, gee what a surprise.

> It dies before bringing up the other CPUs, so it's a very early death.
> 
> I don't think other console types are available under ARM64.

I've often found useful the two line version of:

https://balau82.wordpress.com/2010/02/28/hello-world-for-bare-metal-arm-using-qemu/

Which is generally some variant of:

{char *XX = "blah"; while (*XX) {while (*SERIAL_STATUS_REGISTER & OUT_READY);
*SERIAL_OUT = *XX++;}}

(I.E. balu cheated not spinning checking the ready-for-next-byte bit, because
qemu's always angry.)

That trick lets you cut and paste a print statement into all sorts of early
hardware nonsense, on most architectures. You just have to look up
SERIAL_STATUS_REGISTER, OUT_OK_BIT, and SERIAL_OUT values for the serial port du
jour.

That said I've mostly used it in things like u-boot. I dunno at what point the
kernel's done enough setup that direct banging on registers would stop working.
(Works in the decompresion code, anyway.) And it assumes the port's set to the
right speed (usually left there by the bootloader)...

Rob
# make ARCH=arm64 allnoconfig KCONFIG_ALLCONFIG=aarch64.miniconf
# make ARCH=arm64 -j $(nproc)
# boot arch/arm64/boot/Image


CONFIG_MMU=y
CONFIG_ARCH_MULTI_V7=y
CONFIG_ARCH_VIRT=y
CONFIG_SOC_DRA7XX=y
CONFIG_ARCH_OMAP2PLUS_TYPICAL=y
CONFIG_ARCH_ALPINE=y
CONFIG_ARM_THUMB=y
CONFIG_VDSO=y
CONFIG_CPU_IDLE=y
CONFIG_ARM_CPUIDLE=y
CONFIG_KERNEL_MODE_NEON=y

CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y

CONFIG_RTC_CLASS=y
CONFIG_RTC_HCTOSYS=y
CONFIG_RTC_DRV_PL031=y

CONFIG_NET_CORE=y
CONFIG_VIRTIO_NET=y

CONFIG_PCI=y
CONFIG_PCI_HOST_GENERIC=y
CONFIG_VIRTIO_BLK=y
CONFIG_VIRTIO_PCI=y
CONFIG_VIRTIO_MMIO=y

CONFIG_ATA=y
CONFIG_ATA_SFF=y
CONFIG_ATA_BMDMA=y
CONFIG_ATA_PIIX=y

CONFIG_PATA_PLATFORM=y
CONFIG_PATA_OF_PLATFORM=y
CONFIG_ATA_GENERIC=y


# CONFIG_EMBEDDED is not set
CONFIG_EARLY_PRINTK=y
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_SCRIPT=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y

CONFIG_BLK_DEV=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_RD_GZIP=y

CONFIG_BLK_DEV_LOOP=y
CONFIG_EXT4_FS=y
CONFIG_EXT4_USE_FOR_EXT2=y
CONFIG_VFAT_FS=y
CONFIG_FAT_DEFAULT_UTF8=y
CONFIG_MISC_FILESYSTEMS=y
CONFIG_SQUASHFS=y
CONFIG_SQUASHFS_XATTR=y
CONFIG_SQUASHFS_ZLIB=y
CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y

CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_INET=y
CONFIG_IPV6=y
CONFIG_NETDEVICES=y
#CONFIG_NET_CORE=y
#CONFIG_NETCONSOLE=y
CONFIG_ETHERNET=y
Marc Zyngier March 29, 2018, 5:53 p.m. | #18
On Thu, 29 Mar 2018 18:32:47 +0100,
Russell King - ARM Linux wrote:
> 
> On Thu, Mar 29, 2018 at 05:53:14PM +0100, Marc Zyngier wrote:
> > On Thu, 29 Mar 2018 16:58:27 +0100,
> > Russell King - ARM Linux wrote:

[...]

> > > I'm not aware of there being an emulated UART in the guest's address
> > > space, so serial based stuff doesn't work.
> > 
> > "earlycon=uart,mmio,0x3f8" is what you're looking for:
> 
> Does that also mean that we have a RTC at the standard PC IO addresses
> as well, but in mmio space?

There is one, together with an i8042. Not exposed in the DT though.

	M.
kbuild test robot March 30, 2018, 1:43 a.m. | #19
Hi Shea,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linus/master]
[also build test WARNING on v4.16-rc7]
[cannot apply to next-20180329]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Shea-Levy/Extract-initrd-free-logic-from-arch-specific-code/20180330-085507
config: ia64-allnoconfig (attached as .config)
compiler: ia64-linux-gcc (GCC) 7.2.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=ia64 

All warnings (new ones prefixed by >>):

warning: (IA64) selects HAVE_ARCH_FREE_INITRD_MEM which has unmet direct dependencies (BLK_DEV_INITRD)

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
kbuild test robot March 30, 2018, 3:16 a.m. | #20
Hi Shea,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linus/master]
[also build test WARNING on v4.16-rc7]
[cannot apply to next-20180329]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Shea-Levy/Extract-initrd-free-logic-from-arch-specific-code/20180330-085507
config: m32r-m32104ut_defconfig (attached as .config)
compiler: m32r-linux-gcc (GCC) 7.2.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=m32r 

All warnings (new ones prefixed by >>):

warning: (M32R) selects HAVE_ARCH_FREE_INITRD_MEM which has unmet direct dependencies (BLK_DEV_INITRD)

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
Ingo Molnar March 30, 2018, 11:15 a.m. | #21
* Shea Levy <shea@shealevy.com> wrote:

> Now only those architectures that have custom initrd free requirements
> need to define free_initrd_mem.
> 
> Signed-off-by: Shea Levy <shea@shealevy.com>

Please put the Kconfig symbol name this patch introduces both into the title, so 
that people know what to grep for.

> ---
>  arch/alpha/mm/init.c      |  8 --------
>  arch/arc/mm/init.c        |  7 -------
>  arch/arm/Kconfig          |  1 +
>  arch/arm64/Kconfig        |  1 +
>  arch/blackfin/Kconfig     |  1 +
>  arch/c6x/mm/init.c        |  7 -------
>  arch/cris/Kconfig         |  1 +
>  arch/frv/mm/init.c        | 11 -----------
>  arch/h8300/mm/init.c      |  7 -------
>  arch/hexagon/Kconfig      |  1 +
>  arch/ia64/Kconfig         |  1 +
>  arch/m32r/Kconfig         |  1 +
>  arch/m32r/mm/init.c       | 11 -----------
>  arch/m68k/mm/init.c       |  7 -------
>  arch/metag/Kconfig        |  1 +
>  arch/microblaze/mm/init.c |  7 -------
>  arch/mips/Kconfig         |  1 +
>  arch/mn10300/Kconfig      |  1 +
>  arch/nios2/mm/init.c      |  7 -------
>  arch/openrisc/mm/init.c   |  7 -------
>  arch/parisc/mm/init.c     |  7 -------
>  arch/powerpc/mm/mem.c     |  7 -------
>  arch/riscv/mm/init.c      |  6 ------
>  arch/s390/Kconfig         |  1 +
>  arch/score/Kconfig        |  1 +
>  arch/sh/mm/init.c         |  7 -------
>  arch/sparc/Kconfig        |  1 +
>  arch/tile/Kconfig         |  1 +
>  arch/um/kernel/mem.c      |  7 -------
>  arch/unicore32/Kconfig    |  1 +
>  arch/x86/Kconfig          |  1 +
>  arch/xtensa/Kconfig       |  1 +
>  init/initramfs.c          |  7 +++++++
>  usr/Kconfig               |  4 ++++
>  34 files changed, 28 insertions(+), 113 deletions(-)

Please also put it into Documentation/features/.

> diff --git a/usr/Kconfig b/usr/Kconfig
> index 43658b8a975e..7a94f6df39bf 100644
> --- a/usr/Kconfig
> +++ b/usr/Kconfig
> @@ -233,3 +233,7 @@ config INITRAMFS_COMPRESSION
>  	default ".lzma" if RD_LZMA
>  	default ".bz2"  if RD_BZIP2
>  	default ""
> +
> +config HAVE_ARCH_FREE_INITRD_MEM
> +	bool
> +	default n

Help text would be nice, to tell arch maintainers what the purpose of this switch 
is.

Also, a nit, I think this should be named "ARCH_HAS_FREE_INITRD_MEM", which is the 
dominant pattern:

triton:~/tip> git grep 'select.*ARCH' arch/x86/Kconfig* | cut -f2 | cut -d_ -f1-2 | sort | uniq -c | sort -n
    ...
      2 select ARCH_USES
      2 select ARCH_WANTS
      3 select ARCH_MIGHT
      3 select ARCH_WANT
      4 select ARCH_SUPPORTS
      4 select ARCH_USE
     16 select HAVE_ARCH
     23 select ARCH_HAS

It also reads nicely in English:

  "arch has free_initrd_mem()"

While the other makes little sense:

  "have arch free_initrd_mem()"

?

Thanks,

	Ingo
Shea Levy April 1, 2018, 3:05 p.m. | #22
Hi Ingo,

Ingo Molnar <mingo@kernel.org> writes:

> * Shea Levy <shea@shealevy.com> wrote:
>
>> Now only those architectures that have custom initrd free requirements
>> need to define free_initrd_mem.
>> 
>> Signed-off-by: Shea Levy <shea@shealevy.com>
>
> Please put the Kconfig symbol name this patch introduces both into the title, so 
> that people know what to grep for.
>
>> ---
>>  arch/alpha/mm/init.c      |  8 --------
>>  arch/arc/mm/init.c        |  7 -------
>>  arch/arm/Kconfig          |  1 +
>>  arch/arm64/Kconfig        |  1 +
>>  arch/blackfin/Kconfig     |  1 +
>>  arch/c6x/mm/init.c        |  7 -------
>>  arch/cris/Kconfig         |  1 +
>>  arch/frv/mm/init.c        | 11 -----------
>>  arch/h8300/mm/init.c      |  7 -------
>>  arch/hexagon/Kconfig      |  1 +
>>  arch/ia64/Kconfig         |  1 +
>>  arch/m32r/Kconfig         |  1 +
>>  arch/m32r/mm/init.c       | 11 -----------
>>  arch/m68k/mm/init.c       |  7 -------
>>  arch/metag/Kconfig        |  1 +
>>  arch/microblaze/mm/init.c |  7 -------
>>  arch/mips/Kconfig         |  1 +
>>  arch/mn10300/Kconfig      |  1 +
>>  arch/nios2/mm/init.c      |  7 -------
>>  arch/openrisc/mm/init.c   |  7 -------
>>  arch/parisc/mm/init.c     |  7 -------
>>  arch/powerpc/mm/mem.c     |  7 -------
>>  arch/riscv/mm/init.c      |  6 ------
>>  arch/s390/Kconfig         |  1 +
>>  arch/score/Kconfig        |  1 +
>>  arch/sh/mm/init.c         |  7 -------
>>  arch/sparc/Kconfig        |  1 +
>>  arch/tile/Kconfig         |  1 +
>>  arch/um/kernel/mem.c      |  7 -------
>>  arch/unicore32/Kconfig    |  1 +
>>  arch/x86/Kconfig          |  1 +
>>  arch/xtensa/Kconfig       |  1 +
>>  init/initramfs.c          |  7 +++++++
>>  usr/Kconfig               |  4 ++++
>>  34 files changed, 28 insertions(+), 113 deletions(-)
>
> Please also put it into Documentation/features/.
>

I switched this patch series (the latest revision v6 was just posted) to
using weak symbols instead of Kconfig. Does it still warrant documentation?

>
>> diff --git a/usr/Kconfig b/usr/Kconfig
>> index 43658b8a975e..7a94f6df39bf 100644
>> --- a/usr/Kconfig
>> +++ b/usr/Kconfig
>> @@ -233,3 +233,7 @@ config INITRAMFS_COMPRESSION
>>  	default ".lzma" if RD_LZMA
>>  	default ".bz2"  if RD_BZIP2
>>  	default ""
>> +
>> +config HAVE_ARCH_FREE_INITRD_MEM
>> +	bool
>> +	default n
>
> Help text would be nice, to tell arch maintainers what the purpose of this switch 
> is.
>
> Also, a nit, I think this should be named "ARCH_HAS_FREE_INITRD_MEM", which is the 
> dominant pattern:
>
> triton:~/tip> git grep 'select.*ARCH' arch/x86/Kconfig* | cut -f2 | cut -d_ -f1-2 | sort | uniq -c | sort -n
>     ...
>       2 select ARCH_USES
>       2 select ARCH_WANTS
>       3 select ARCH_MIGHT
>       3 select ARCH_WANT
>       4 select ARCH_SUPPORTS
>       4 select ARCH_USE
>      16 select HAVE_ARCH
>      23 select ARCH_HAS
>
> It also reads nicely in English:
>
>   "arch has free_initrd_mem()"
>
> While the other makes little sense:
>
>   "have arch free_initrd_mem()"
>
> ?
>
> Thanks,
>
> 	Ingo

Thanks,
Shea
Ingo Molnar April 2, 2018, 5:59 a.m. | #23
* Shea Levy <shea@shealevy.com> wrote:

> > Please also put it into Documentation/features/.
> 
> I switched this patch series (the latest revision v6 was just posted) to
> using weak symbols instead of Kconfig. Does it still warrant documentation?

Probably not.

Thanks,

	Ingo

Patch

diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c
index 9d74520298ab..55f7c8efa962 100644
--- a/arch/alpha/mm/init.c
+++ b/arch/alpha/mm/init.c
@@ -291,11 +291,3 @@  free_initmem(void)
 {
 	free_initmem_default(-1);
 }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void
-free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index ba145065c579..7bcf23ab1756 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -229,10 +229,3 @@  void __ref free_initmem(void)
 {
 	free_initmem_default(-1);
 }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3f972e83909b..19d1c5594e2d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -47,6 +47,7 @@  config ARM
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cb03e93f03cf..de93620870af 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -85,6 +85,7 @@  config ARM64
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_BITREVERSE
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index d9c2866ba618..6c6dae9fe894 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -15,6 +15,7 @@  config BLACKFIN
 	def_bool y
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c
index 4cc72b0d1c1d..a11cb657182a 100644
--- a/arch/c6x/mm/init.c
+++ b/arch/c6x/mm/init.c
@@ -66,13 +66,6 @@  void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 void __init free_initmem(void)
 {
 	free_initmem_default(-1);
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index cd5a0865c97f..5425f77e5664 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -76,6 +76,7 @@  config CRIS
 	select HAVE_DEBUG_BUGVERBOSE if ETRAX_ARCH_V32
 	select HAVE_NMI
 	select DMA_DIRECT_OPS if PCI
+	select HAVE_ARCH_FREE_INITRD_MEM
 
 config HZ
 	int
diff --git a/arch/frv/mm/init.c b/arch/frv/mm/init.c
index cf464100e838..345edc4dc462 100644
--- a/arch/frv/mm/init.c
+++ b/arch/frv/mm/init.c
@@ -131,14 +131,3 @@  void free_initmem(void)
 	free_initmem_default(-1);
 #endif
 } /* end free_initmem() */
-
-/*****************************************************************************/
-/*
- * free the initial ramdisk memory
- */
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-} /* end free_initrd_mem() */
-#endif
diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c
index 015287ac8ce8..37574332b202 100644
--- a/arch/h8300/mm/init.c
+++ b/arch/h8300/mm/init.c
@@ -102,13 +102,6 @@  void __init mem_init(void)
 }
 
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 void
 free_initmem(void)
 {
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 76d2f20d525e..69a16cd2e253 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -17,6 +17,7 @@  config HEXAGON
 	# GENERIC_ALLOCATOR is used by dma_alloc_coherent()
 	select GENERIC_ALLOCATOR
 	select GENERIC_IRQ_SHOW
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
 	select NO_IOPORT_MAP
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index bbe12a038d21..366ef1dd3cd4 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -28,6 +28,7 @@  config IA64
 	select HAVE_DYNAMIC_FTRACE if (!ITANIUM)
 	select HAVE_FUNCTION_TRACER
 	select TTY
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_MEMBLOCK
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index dd84ee194579..9e41bdff45c3 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -21,6 +21,7 @@  config M32R
 	select CPU_NO_EFFICIENT_FFS
 	select DMA_DIRECT_OPS
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
+	select HAVE_ARCH_FREE_INITRD_MEM
 
 config SBUS
 	bool
diff --git a/arch/m32r/mm/init.c b/arch/m32r/mm/init.c
index 93abc8c3a46e..e2b5f09209ee 100644
--- a/arch/m32r/mm/init.c
+++ b/arch/m32r/mm/init.c
@@ -139,14 +139,3 @@  void free_initmem(void)
 {
 	free_initmem_default(-1);
 }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-/*======================================================================*
- * free_initrd_mem() :
- * orig : arch/sh/mm/init.c
- *======================================================================*/
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index e85acd131fa8..e20bef09258c 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -172,10 +172,3 @@  void __init mem_init(void)
 	mem_init_print_info(NULL);
 	print_memmap();
 }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
diff --git a/arch/metag/Kconfig b/arch/metag/Kconfig
index c7b62a339539..5be7f1693b1b 100644
--- a/arch/metag/Kconfig
+++ b/arch/metag/Kconfig
@@ -7,6 +7,7 @@  config METAG
 	select GENERIC_IRQ_SHOW
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_64BIT_ALIGNED_ACCESS
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index df6de7ccdc2e..ea058dfda222 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -187,13 +187,6 @@  void __init setup_memory(void)
 	paging_init();
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 void free_initmem(void)
 {
 	free_initmem_default(-1);
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 8128c3b68d6b..c033cd1e0c52 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -27,6 +27,7 @@  config MIPS
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select HANDLE_DOMAIN_IRQ
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index e9d8d60bd28b..5aa4f1aa309f 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -6,6 +6,7 @@  config MN10300
 	select HAVE_UID16
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_IPC_PARSE_VERSION
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_KGDB
 	select GENERIC_ATOMIC64
diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c
index c92fe4234009..3df75ff8c768 100644
--- a/arch/nios2/mm/init.c
+++ b/arch/nios2/mm/init.c
@@ -82,13 +82,6 @@  void __init mmu_init(void)
 	flush_tlb_all();
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 void __ref free_initmem(void)
 {
 	free_initmem_default(-1);
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index 6972d5d6f23f..c1a3dcf9ad40 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -222,13 +222,6 @@  void __init mem_init(void)
 	return;
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 void free_initmem(void)
 {
 	free_initmem_default(-1);
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index cab32ee824d2..3643399230f3 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -932,10 +932,3 @@  void flush_tlb_all(void)
 	spin_unlock(&sid_lock);
 }
 #endif
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index fe8c61149fb8..e85b2a3cd264 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -404,13 +404,6 @@  void free_initmem(void)
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void __init free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 /*
  * This is called when a page has been modified by the kernel.
  * It just marks the page as not i-cache clean.  We do the i-cache
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index c77df8142be2..36f83fe8a726 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -62,9 +62,3 @@  void free_initmem(void)
 {
 	free_initmem_default(0);
 }
-
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-}
-#endif /* CONFIG_BLK_DEV_INITRD */
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index eaee7087886f..94a9879f1ea8 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -125,6 +125,7 @@  config S390
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ALIGNED_STRUCT_PAGE if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_JUMP_LABEL
 	select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
 	select HAVE_ARCH_SECCOMP_FILTER
diff --git a/arch/score/Kconfig b/arch/score/Kconfig
index d881f99c9ddd..2beff03b2429 100644
--- a/arch/score/Kconfig
+++ b/arch/score/Kconfig
@@ -16,6 +16,7 @@  config SCORE
 	select MODULES_USE_ELF_REL
 	select CLONE_BACKWARDS
 	select CPU_NO_EFFICIENT_FFS
+	select HAVE_ARCH_FREE_INITRD_MEM
 
 choice
 	prompt "System type"
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index ce0bbaa7e404..7451459d0725 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -477,13 +477,6 @@  void free_initmem(void)
 	free_initmem_default(-1);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 		bool want_memblock)
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 8767e45f1b2b..06d543e35caf 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -18,6 +18,7 @@  config SPARC
 	select OF_PROMTREE
 	select HAVE_IDE
 	select HAVE_OPROFILE
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_KGDB if !SMP || SPARC64
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_EXIT_THREAD
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index ef9d403cbbe4..7fb36c15762c 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -16,6 +16,7 @@  config TILE
 	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_CONTEXT_TRACKING
diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c
index 3c0e470ea646..2d26eec92126 100644
--- a/arch/um/kernel/mem.c
+++ b/arch/um/kernel/mem.c
@@ -170,13 +170,6 @@  void free_initmem(void)
 {
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	free_reserved_area((void *)start, (void *)end, -1, "initrd");
-}
-#endif
-
 /* Allocate and free page tables. */
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 462e59a7ae78..4da24cf467de 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -4,6 +4,7 @@  config UNICORE32
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_MEMBLOCK
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0fa71a78ec99..51ce64e6d848 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -111,6 +111,7 @@  config X86
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if X86_64
 	select HAVE_ARCH_KGDB
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index c921e8bccdc8..01a4a0e42118 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -16,6 +16,7 @@  config XTENSA
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_STRNCPY_FROM_USER if KASAN
+	select HAVE_ARCH_FREE_INITRD_MEM
 	select HAVE_ARCH_KASAN if MMU
 	select HAVE_CC_STACKPROTECTOR
 	select HAVE_DEBUG_KMEMLEAK
diff --git a/init/initramfs.c b/init/initramfs.c
index 7e99a0038942..d319058eb464 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -526,6 +526,13 @@  extern unsigned long __initramfs_size;
 #include <linux/initrd.h>
 #include <linux/kexec.h>
 
+#ifndef CONFIG_HAVE_ARCH_FREE_INITRD_MEM
+void __init free_initrd_mem(unsigned long start, unsigned long end)
+{
+       free_reserved_area((void *)start, (void *)end, -1, "initrd");
+}
+#endif
+
 static void __init free_initrd(void)
 {
 #ifdef CONFIG_KEXEC_CORE
diff --git a/usr/Kconfig b/usr/Kconfig
index 43658b8a975e..7a94f6df39bf 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -233,3 +233,7 @@  config INITRAMFS_COMPRESSION
 	default ".lzma" if RD_LZMA
 	default ".bz2"  if RD_BZIP2
 	default ""
+
+config HAVE_ARCH_FREE_INITRD_MEM
+	bool
+	default n