Re: [patch] mm, thp: avoid unlikely branches for split_huge_pmd

[Andrew Morton]

On Tue, 18 Oct 2016 16:04:06 -0700 (PDT) David Rientjes <rientjes@xxxxxxxxxx> wrote:

> While doing MADV_DONTNEED on a large area of thp memory, I noticed we 
> encountered many unlikely() branches in profiles for each backing 
> hugepage.  This is because zap_pmd_range() would call split_huge_pmd(), 
> which rechecked the conditions that were already validated, but as part of 
> an unlikely() branch.
> 
> Avoid the unlikely() branch when in a context where pmd is known to be 
> good for __split_huge_pmd() directly.

Before:

   text    data     bss     dec     hex filename
  38442      75      48   38565    96a5 mm/memory.o
  21755    2369   18464   42588    a65c mm/mempolicy.o
   4557    1816       0    6373    18e5 mm/mprotect.o

After:

  38362      75      48   38485    9655 mm/memory.o
  21714    2369   18464   42547    a633 mm/mempolicy.o
   4541    1816       0    6357    18d5 mm/mprotect.o


So there's a size improvment too.  gcc-4.4.4.