Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1468678

Re: [PATCH] x86: branchless clear_page()

Show all headers | View raw

On Tue, Aug 23, 2016 at 09:43:25AM -0400, Brian Gerst wrote:
> > -ENTRY(clear_page_c_e)
> > +ENTRY(clear_page_rep_stosb)
> >         movl $4096,%ecx
> >         xorl %eax,%eax
> >         rep stosb
> >         ret
> > -ENDPROC(clear_page_c_e)
> > +ENDPROC(clear_page_rep_stosb)
> 
> I like this idea, but does it make sense to take it a step further and
> inline the string instruction alternatives to avoid a call altogether?

It is easy but you can't do runtime patching then.

> Also, 32-bit should be converted to do the same thing as 64-bit.

I don't run 32-bit. :-)

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH] x86: branchless clear_page() Alexey Dobriyan <adobriyan@gmail.com> - 2016-08-22 23:00 +0200
  Re: [PATCH] x86: branchless clear_page() Borislav Petkov <bp@alien8.de> - 2016-08-22 23:10 +0200
    Re: [PATCH] x86: branchless clear_page() Alexey Dobriyan <adobriyan@gmail.com> - 2016-08-23 14:10 +0200
  Re: [PATCH] x86: branchless clear_page() Brian Gerst <brgerst@gmail.com> - 2016-08-23 15:50 +0200
    Re: [PATCH] x86: branchless clear_page() Alexey Dobriyan <adobriyan@gmail.com> - 2016-08-23 18:20 +0200
  [PATCH 1/3] x86: branchless clear_page() Alexey Dobriyan <adobriyan@gmail.com> - 2016-08-23 18:20 +0200
    [PATCH 2/3] x86: support REP MOVSB copy_page() Alexey Dobriyan <adobriyan@gmail.com> - 2016-08-23 18:30 +0200
      [PATCH 3/3] x86: branchless copy_page() Alexey Dobriyan <adobriyan@gmail.com> - 2016-08-23 18:30 +0200

csiph-web