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

[Kirill A. Shutemov]

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.

> +static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
> +{
> +	spinlock_t *ptl = &mm->page_table_lock;
> +	spin_lock(ptl);
> +	return ptl;
> +}
> +
>  extern void free_area_init(unsigned long * zones_size);
>  extern void free_area_init_node(int nid, unsigned long * zones_size,
>  		unsigned long zone_start_pfn, unsigned long *zholes_size);

...

> 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.

> +					BUG();
> +				}
> +#endif
> +				split_huge_pud(vma, pud, addr);
> +			} else if (zap_huge_pud(tlb, vma, pud, addr))
> +				goto next;
> +			/* fall through */
> +		}
>  		if (pud_none_or_clear_bad(pud))
>  			continue;
>  		next = zap_pmd_range(tlb, vma, pud, addr, next, details);
> +next:
> +		cond_resched();
>  	} while (pud++, addr = next, addr != end);
>  
>  	return addr;
-- 
 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/