Re: [PATCH v2 10/12] mm: mempolicy: mbind and migrate_pages support thp migration

[Anshuman Khandual]

On 11/08/2016 05:01 AM, Naoya Horiguchi wrote:
> This patch enables thp migration for mbind(2) and migrate_pages(2).
> 
> Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> ---
> ChangeLog v1 -> v2:
> - support pte-mapped and doubly-mapped thp
> ---
>  mm/mempolicy.c | 108 +++++++++++++++++++++++++++++++++++++++++----------------
>  1 file changed, 79 insertions(+), 29 deletions(-)
> 
> diff --git v4.9-rc2-mmotm-2016-10-27-18-27/mm/mempolicy.c v4.9-rc2-mmotm-2016-10-27-18-27_patched/mm/mempolicy.c
> index 77d0668..96507ee 100644
> --- v4.9-rc2-mmotm-2016-10-27-18-27/mm/mempolicy.c
> +++ v4.9-rc2-mmotm-2016-10-27-18-27_patched/mm/mempolicy.c
> @@ -94,6 +94,7 @@
>  #include <linux/mm_inline.h>
>  #include <linux/mmu_notifier.h>
>  #include <linux/printk.h>
> +#include <linux/swapops.h>
>  
>  #include <asm/tlbflush.h>
>  #include <asm/uaccess.h>
> @@ -486,6 +487,49 @@ static inline bool queue_pages_node_check(struct page *page,
>  	return node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT);
>  }
>  
> +static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
> +				unsigned long end, struct mm_walk *walk)
> +{
> +	int ret = 0;
> +	struct page *page;
> +	struct queue_pages *qp = walk->private;
> +	unsigned long flags;
> +
> +	if (unlikely(is_pmd_migration_entry(*pmd))) {
> +		ret = 1;
> +		goto unlock;
> +	}
> +	page = pmd_page(*pmd);
> +	if (is_huge_zero_page(page)) {
> +		spin_unlock(ptl);
> +		__split_huge_pmd(walk->vma, pmd, addr, false, NULL);
> +		goto out;
> +	}
> +	if (!thp_migration_supported()) {
> +		get_page(page);
> +		spin_unlock(ptl);
> +		lock_page(page);
> +		ret = split_huge_page(page);
> +		unlock_page(page);
> +		put_page(page);
> +		goto out;
> +	}
> +	if (queue_pages_node_check(page, qp)) {
> +		ret = 1;
> +		goto unlock;
> +	}
> +
> +	ret = 1;
> +	flags = qp->flags;
> +	/* go to thp migration */
> +	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
> +		migrate_page_add(page, qp->pagelist, flags);
> +unlock:
> +	spin_unlock(ptl);
> +out:
> +	return ret;
> +}
> +
>  /*
>   * Scan through pages checking if pages follow certain conditions,
>   * and move them to the pagelist if they do.
> @@ -497,30 +541,15 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
>  	struct page *page;
>  	struct queue_pages *qp = walk->private;
>  	unsigned long flags = qp->flags;
> -	int nid, ret;
> +	int ret;
>  	pte_t *pte;
>  	spinlock_t *ptl;
>  
> -	if (pmd_trans_huge(*pmd)) {
> -		ptl = pmd_lock(walk->mm, pmd);
> -		if (pmd_trans_huge(*pmd)) {
> -			page = pmd_page(*pmd);
> -			if (is_huge_zero_page(page)) {
> -				spin_unlock(ptl);
> -				__split_huge_pmd(vma, pmd, addr, false, NULL);
> -			} else {
> -				get_page(page);
> -				spin_unlock(ptl);
> -				lock_page(page);
> -				ret = split_huge_page(page);
> -				unlock_page(page);
> -				put_page(page);
> -				if (ret)
> -					return 0;
> -			}
> -		} else {
> -			spin_unlock(ptl);
> -		}
> +	ptl = pmd_trans_huge_lock(pmd, vma);
> +	if (ptl) {
> +		ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
> +		if (ret)
> +			return 0;
>  	}

I wonder if we should introduce pte_entry function along with pmd_entry
function as we are first looking for trans huge PMDs either for direct
addition into the migration list or splitting it before looking for PTEs.