Re: [PATCH 06/18] mm, hugetlb: remove vma_need_reservation()

[Joonsoo Kim]

On Tue, Jul 30, 2013 at 11:19:58PM +0530, Aneesh Kumar K.V wrote:
> Joonsoo Kim <iamjoonsoo.kim@xxxxxxx> writes:
> 
> > vma_need_reservation() can be substituted by vma_has_reserves()
> > with minor change. These function do almost same thing,
> > so unifying them is better to maintain.
> 
> I found the resulting code confusing and complex. I am sure there is
> more that what is explained in the commit message. If you are just doing
> this for cleanup, may be we should avoid doing this  ?

I may need this cleanup, because I want to decide whether this page comes
from reserved page pool or not, more clearly. Without this, this decision
can be harder.
Anyway, I should describe the purpose of this patch in detail.

Thanks.

> 
> 
> >
> > Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
> >
> > diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> > index bf2ee11..ff46a2c 100644
> > --- a/mm/hugetlb.c
> > +++ b/mm/hugetlb.c
> > @@ -451,8 +451,18 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
> >  		vma->vm_private_data = (void *)0;
> >  }
> >
> > -/* Returns true if the VMA has associated reserve pages */
> > -static int vma_has_reserves(struct vm_area_struct *vma, long chg)
> > +/*
> > + * Determine if the huge page at addr within the vma has an associated
> > + * reservation.  Where it does not we will need to logically increase
> > + * reservation and actually increase subpool usage before an allocation
> > + * can occur.  Where any new reservation would be required the
> > + * reservation change is prepared, but not committed.  Once the page
> > + * has been allocated from the subpool and instantiated the change should
> > + * be committed via vma_commit_reservation.  No action is required on
> > + * failure.
> > + */
> > +static int vma_has_reserves(struct hstate *h,
> > +			struct vm_area_struct *vma, unsigned long addr)
> >  {
> >  	if (vma->vm_flags & VM_NORESERVE) {
> >  		/*
> > @@ -464,10 +474,22 @@ static int vma_has_reserves(struct vm_area_struct *vma, long chg)
> >  		 * step. Currently, we don't have any other solution to deal
> >  		 * with this situation properly, so add work-around here.
> >  		 */
> > -		if (vma->vm_flags & VM_MAYSHARE && chg == 0)
> > -			return 1;
> > -		else
> > -			return 0;
> > +		if (vma->vm_flags & VM_MAYSHARE) {
> > +			struct address_space *mapping = vma->vm_file->f_mapping;
> > +			struct inode *inode = mapping->host;
> > +			pgoff_t idx = vma_hugecache_offset(h, vma, addr);
> > +			struct resv_map *resv = inode->i_mapping->private_data;
> > +			long chg;
> > +
> > +			chg = region_chg(resv, idx, idx + 1);
> > +			if (chg < 0)
> > +				return -ENOMEM;
> > +
> > +			if (chg == 0)
> > +				return 1;
> > +		}
> > +
> > +		return 0;
> >  	}
> >
> >  	/* Shared mappings always use reserves */
> > @@ -478,8 +500,16 @@ static int vma_has_reserves(struct vm_area_struct *vma, long chg)
> >  	 * Only the process that called mmap() has reserves for
> >  	 * private mappings.
> >  	 */
> > -	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
> > +	if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
> > +		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
> > +		struct resv_map *resv = vma_resv_map(vma);
> > +
> > +		/* Just for allocating region structure */
> > +		if (region_chg(resv, idx, idx + 1) < 0)
> > +			return -ENOMEM;
> > +
> >  		return 1;
> > +	}
> >
> >  	return 0;
> >  }
> > @@ -542,8 +572,7 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
> >
> >  static struct page *dequeue_huge_page_vma(struct hstate *h,
> >  				struct vm_area_struct *vma,
> > -				unsigned long address, int avoid_reserve,
> > -				long chg)
> > +				unsigned long address, int avoid_reserve)
> >  {
> >  	struct page *page = NULL;
> >  	struct mempolicy *mpol;
> > @@ -558,7 +587,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
> >  	 * have no page reserves. This check ensures that reservations are
> >  	 * not "stolen". The child may still get SIGKILLed
> >  	 */
> > -	if (!vma_has_reserves(vma, chg) &&
> > +	if (!vma_has_reserves(h, vma, address) &&
> >  			h->free_huge_pages - h->resv_huge_pages == 0)
> >  		return NULL;
> >
> > @@ -578,7 +607,7 @@ retry_cpuset:
> >  			if (page) {
> >  				if (avoid_reserve)
> >  					break;
> > -				if (!vma_has_reserves(vma, chg))
> > +				if (!vma_has_reserves(h, vma, address))
> >  					break;
> >
> >  				h->resv_huge_pages--;
> > @@ -1077,42 +1106,6 @@ static void return_unused_surplus_pages(struct hstate *h,
> >  	}
> >  }
> >
> > -/*
> > - * Determine if the huge page at addr within the vma has an associated
> > - * reservation.  Where it does not we will need to logically increase
> > - * reservation and actually increase subpool usage before an allocation
> > - * can occur.  Where any new reservation would be required the
> > - * reservation change is prepared, but not committed.  Once the page
> > - * has been allocated from the subpool and instantiated the change should
> > - * be committed via vma_commit_reservation.  No action is required on
> > - * failure.
> > - */
> > -static long vma_needs_reservation(struct hstate *h,
> > -			struct vm_area_struct *vma, unsigned long addr)
> > -{
> > -	struct address_space *mapping = vma->vm_file->f_mapping;
> > -	struct inode *inode = mapping->host;
> > -
> > -	if (vma->vm_flags & VM_MAYSHARE) {
> > -		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
> > -		struct resv_map *resv = inode->i_mapping->private_data;
> > -
> > -		return region_chg(resv, idx, idx + 1);
> > -
> > -	} else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
> > -		return 1;
> > -
> > -	} else  {
> > -		long err;
> > -		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
> > -		struct resv_map *resv = vma_resv_map(vma);
> > -
> > -		err = region_chg(resv, idx, idx + 1);
> > -		if (err < 0)
> > -			return err;
> > -		return 0;
> > -	}
> > -}
> >  static void vma_commit_reservation(struct hstate *h,
> >  			struct vm_area_struct *vma, unsigned long addr)
> >  {
> > @@ -1140,8 +1133,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
> >  	struct hugepage_subpool *spool = subpool_vma(vma);
> >  	struct hstate *h = hstate_vma(vma);
> >  	struct page *page;
> > -	long chg;
> > -	int ret, idx;
> > +	int ret, idx, has_reserve;
> >  	struct hugetlb_cgroup *h_cg;
> >
> >  	idx = hstate_index(h);
> > @@ -1153,20 +1145,21 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
> >  	 * need pages and subpool limit allocated allocated if no reserve
> >  	 * mapping overlaps.
> >  	 */
> > -	chg = vma_needs_reservation(h, vma, addr);
> > -	if (chg < 0)
> > +	has_reserve = vma_has_reserves(h, vma, addr);
> > +	if (has_reserve < 0)
> >  		return ERR_PTR(-ENOMEM);
> > -	if (chg)
> > -		if (hugepage_subpool_get_pages(spool, chg))
> > +
> > +	if (!has_reserve && (hugepage_subpool_get_pages(spool, 1) < 0))
> >  			return ERR_PTR(-ENOSPC);
> >
> >  	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
> >  	if (ret) {
> > -		hugepage_subpool_put_pages(spool, chg);
> > +		if (!has_reserve)
> > +			hugepage_subpool_put_pages(spool, 1);
> >  		return ERR_PTR(-ENOSPC);
> >  	}
> >  	spin_lock(&hugetlb_lock);
> > -	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, chg);
> > +	page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
> >  	if (!page) {
> >  		spin_unlock(&hugetlb_lock);
> >  		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
> > @@ -1174,7 +1167,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
> >  			hugetlb_cgroup_uncharge_cgroup(idx,
> >  						       pages_per_huge_page(h),
> >  						       h_cg);
> > -			hugepage_subpool_put_pages(spool, chg);
> > +			if (!has_reserve)
> > +				hugepage_subpool_put_pages(spool, 1);
> >  			return ERR_PTR(-ENOSPC);
> >  		}
> >  		spin_lock(&hugetlb_lock);
> > @@ -2769,7 +2763,7 @@ retry:
> >  	 * the spinlock.
> >  	 */
> >  	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED))
> > -		if (vma_needs_reservation(h, vma, address) < 0) {
> > +		if (vma_has_reserves(h, vma, address) < 0) {
> >  			ret = VM_FAULT_OOM;
> >  			goto backout_unlocked;
> >  		}
> > @@ -2860,7 +2854,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
> >  	 * consumed.
> >  	 */
> >  	if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
> > -		if (vma_needs_reservation(h, vma, address) < 0) {
> > +		if (vma_has_reserves(h, vma, address) < 0) {
> >  			ret = VM_FAULT_OOM;
> >  			goto out_mutex;
> >  		}
> > -- 
> > 1.7.9.5
> 
> --
> To unsubscribe, send a message with 'unsubscribe linux-mm' in
> the body to majordomo@xxxxxxxxxx  For more info on Linux MM,
> see: http://www.linux-mm.org/ .
> Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
--
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/