Re: [PATCH 15/31] mm/mpol: Add MPOL_MF_LAZY

[Mel Gorman]

On Thu, Oct 25, 2012 at 02:16:32PM +0200, Peter Zijlstra wrote:
> From: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
> 
> This patch adds another mbind() flag to request "lazy migration".  The
> flag, MPOL_MF_LAZY, modifies MPOL_MF_MOVE* such that the selected
> pages are marked PROT_NONE. The pages will be migrated in the fault
> path on "first touch", if the policy dictates at that time.
> 
> "Lazy Migration" will allow testing of migrate-on-fault via mbind().
> Also allows applications to specify that only subsequently touched
> pages be migrated to obey new policy, instead of all pages in range.
> This can be useful for multi-threaded applications working on a
> large shared data area that is initialized by an initial thread
> resulting in all pages on one [or a few, if overflowed] nodes.
> After PROT_NONE, the pages in regions assigned to the worker threads
> will be automatically migrated local to the threads on 1st touch.
> 

I like the idea. Applications will need some way of progamatically detecting
if MPOL_MF_LAZY is available. I guess they could always try the flag and if
it fails, do nothing. When/if the manual page for it happens it probably
will be a lot more obvious. The changelog does not actually describe what
this patch does though

This patch is a preparation step for "lazy migration". When the flag is
used, the range is marked prot_none. In a later patch it will be
detected at fault time that the page is misplaced and migrate it at that
point.

> Signed-off-by: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
> Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>
> Cc: Lee Schermerhorn <Lee.Schermerhorn@xxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
> [ nearly complete rewrite.. ]
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
> Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>

> ---
>  include/uapi/linux/mempolicy.h |   13 ++++++++--
>  mm/mempolicy.c                 |   49 ++++++++++++++++++++++++++---------------
>  2 files changed, 42 insertions(+), 20 deletions(-)
> 
> Index: tip/include/uapi/linux/mempolicy.h
> ===================================================================
> --- tip.orig/include/uapi/linux/mempolicy.h
> +++ tip/include/uapi/linux/mempolicy.h
> @@ -49,9 +49,16 @@ enum mpol_rebind_step {
>  
>  /* Flags for mbind */
>  #define MPOL_MF_STRICT	(1<<0)	/* Verify existing pages in the mapping */
> -#define MPOL_MF_MOVE	(1<<1)	/* Move pages owned by this process to conform to mapping */
> -#define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to mapping */
> -#define MPOL_MF_INTERNAL (1<<3)	/* Internal flags start here */
> +#define MPOL_MF_MOVE	 (1<<1)	/* Move pages owned by this process to conform
> +				   to policy */
> +#define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to policy */
> +#define MPOL_MF_LAZY	 (1<<3)	/* Modifies '_MOVE:  lazy migrate on fault */
> +#define MPOL_MF_INTERNAL (1<<4)	/* Internal flags start here */
> +
> +#define MPOL_MF_VALID	(MPOL_MF_STRICT   | 	\
> +			 MPOL_MF_MOVE     | 	\
> +			 MPOL_MF_MOVE_ALL |	\
> +			 MPOL_MF_LAZY)
>  
>  /*
>   * Internal flags that share the struct mempolicy flags word with
> Index: tip/mm/mempolicy.c
> ===================================================================
> --- tip.orig/mm/mempolicy.c
> +++ tip/mm/mempolicy.c
> @@ -583,22 +583,32 @@ check_range(struct mm_struct *mm, unsign
>  		return ERR_PTR(-EFAULT);
>  	prev = NULL;
>  	for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
> +		unsigned long endvma = vma->vm_end;
> +
> +		if (endvma > end)
> +			endvma = end;
> +		if (vma->vm_start > start)
> +			start = vma->vm_start;
> +
>  		if (!(flags & MPOL_MF_DISCONTIG_OK)) {
>  			if (!vma->vm_next && vma->vm_end < end)
>  				return ERR_PTR(-EFAULT);
>  			if (prev && prev->vm_end < vma->vm_start)
>  				return ERR_PTR(-EFAULT);
>  		}
> -		if (!is_vm_hugetlb_page(vma) &&
> -		    ((flags & MPOL_MF_STRICT) ||
> +
> +		if (is_vm_hugetlb_page(vma))
> +			goto next;
> +
> +		if (flags & MPOL_MF_LAZY) {
> +			change_prot_none(vma, start, endvma);
> +			goto next;
> +		}
> +

More hard-coding of prot_none.

> +		if ((flags & MPOL_MF_STRICT) ||
>  		     ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
> -				vma_migratable(vma)))) {
> -			unsigned long endvma = vma->vm_end;
> +		      vma_migratable(vma))) {
>  
> -			if (endvma > end)
> -				endvma = end;
> -			if (vma->vm_start > start)
> -				start = vma->vm_start;
>  			err = check_pgd_range(vma, start, endvma, nodes,
>  						flags, private);
>  			if (err) {
> @@ -606,6 +616,7 @@ check_range(struct mm_struct *mm, unsign
>  				break;
>  			}
>  		}
> +next:
>  		prev = vma;
>  	}
>  	return first;
> @@ -1137,8 +1148,7 @@ static long do_mbind(unsigned long start
>  	int err;
>  	LIST_HEAD(pagelist);
>  
> -	if (flags & ~(unsigned long)(MPOL_MF_STRICT |
> -				     MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
> +  	if (flags & ~(unsigned long)MPOL_MF_VALID)
>  		return -EINVAL;
>  	if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
>  		return -EPERM;
> @@ -1161,6 +1171,9 @@ static long do_mbind(unsigned long start
>  	if (IS_ERR(new))
>  		return PTR_ERR(new);
>  
> +	if (flags & MPOL_MF_LAZY)
> +		new->flags |= MPOL_F_MOF;
> +
>  	/*
>  	 * If we are using the default policy then operation
>  	 * on discontinuous address spaces is okay after all
> @@ -1197,21 +1210,23 @@ static long do_mbind(unsigned long start
>  	vma = check_range(mm, start, end, nmask,
>  			  flags | MPOL_MF_INVERT, &pagelist);
>  
> -	err = PTR_ERR(vma);
> -	if (!IS_ERR(vma)) {
> -		int nr_failed = 0;
> -
> +	err = PTR_ERR(vma);	/* maybe ... */
> +	if (!IS_ERR(vma) && mode != MPOL_NOOP)
>  		err = mbind_range(mm, start, end, new);
>  
> +	if (!err) {
> +		int nr_failed = 0;
> +
>  		if (!list_empty(&pagelist)) {
> +			WARN_ON_ONCE(flags & MPOL_MF_LAZY);
>  			nr_failed = migrate_pages(&pagelist, new_vma_page,
> -						(unsigned long)vma,
> -						false, MIGRATE_SYNC);
> +						  (unsigned long)vma,
> +						  false, MIGRATE_SYNC);
>  			if (nr_failed)
>  				putback_lru_pages(&pagelist);
>  		}
>  
> -		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
> +		if (nr_failed && (flags & MPOL_MF_STRICT))
>  			err = -EIO;
>  	} else
>  		putback_lru_pages(&pagelist);
> 
> 

-- 
Mel Gorman
SUSE Labs
--
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/