Re: [PATCH 1/8] mm: Add optional support for PUD-sized transparent hugepages

[Kirill A. Shutemov]

On Sat, Jan 02, 2016 at 12:06:38PM -0500, Matthew Wilcox wrote:
> On Mon, Dec 28, 2015 at 12:05:51PM +0200, Kirill A. Shutemov wrote:
> > On Thu, Dec 24, 2015 at 11:20:30AM -0500, Matthew Wilcox wrote:
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > index 4bf3811..e14634f 100644
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -1958,6 +1977,17 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
> > >  	return ptl;
> > >  }
> > >  
> > > +/*
> > > + * No scalability reason to split PUD locks yet, but follow the same pattern
> > > + * as the PMD locks to make it easier if we have to.
> > > + */
> > 
> > I don't think it makes any good unless you convert all other places where
> > we use page_table_lock to protect pud table (like __pud_alloc()) to the
> > same API.
> > I think this would deserve separate patch.
> 
> Sure, a separate patch to convert existing users of the PTL.  But I
> don't think it does any harm to introduce the PUD version of the PMD API.
> Maybe with a comment indicating that tere is significant work to be done
> in converting existing users to this API?

I think that's fine with the fat comment around pud_lock() definition.
 
> > > diff --git a/mm/memory.c b/mm/memory.c
> > > index 416b129..7328df0 100644
> > > --- a/mm/memory.c
> > > +++ b/mm/memory.c
> > > @@ -1220,9 +1220,27 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
> > >  	pud = pud_offset(pgd, addr);
> > >  	do {
> > >  		next = pud_addr_end(addr, end);
> > > +		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
> > > +			if (next - addr != HPAGE_PUD_SIZE) {
> > > +#ifdef CONFIG_DEBUG_VM
> > 
> > IS_ENABLED(CONFIG_DEBUG_VM) ?
> > 
> > > +				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
> > > +					pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
> > > +						__func__, addr, end,
> > > +						vma->vm_start,
> > > +						vma->vm_end);
> > 
> > dump_vma(), I guess.
> 
> These two issues are copy-and-paste from the existing PMD code.  I'm happy
> to update the PMD code to the new-and-improved way of doing things;
> I'm just not keen to have the PMD and PUD code diverge unnecessarily.

Yes, please update PMD too. It looks ugly. VM_BUG_ON_VMA() is probably
right way to deal with this.

-- 
 Kirill A. Shutemov
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/