1 files changed, 151 insertions, 58 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a876871f6be5..b8ce6f450956 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -53,6 +53,84 @@ static unsigned long __initdata default_hstate_size;
  */
 static DEFINE_SPINLOCK(hugetlb_lock);
 
+static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
+{
+	bool free = (spool->count == 0) && (spool->used_hpages == 0);
+
+	spin_unlock(&spool->lock);
+
+	/* If no pages are used, and no other handles to the subpool
+	 * remain, free the subpool the subpool remain */
+	if (free)
+		kfree(spool);
+}
+
+struct hugepage_subpool *hugepage_new_subpool(long nr_blocks)
+{
+	struct hugepage_subpool *spool;
+
+	spool = kmalloc(sizeof(*spool), GFP_KERNEL);
+	if (!spool)
+		return NULL;
+
+	spin_lock_init(&spool->lock);
+	spool->count = 1;
+	spool->max_hpages = nr_blocks;
+	spool->used_hpages = 0;
+
+	return spool;
+}
+
+void hugepage_put_subpool(struct hugepage_subpool *spool)
+{
+	spin_lock(&spool->lock);
+	BUG_ON(!spool->count);
+	spool->count--;
+	unlock_or_release_subpool(spool);
+}
+
+static int hugepage_subpool_get_pages(struct hugepage_subpool *spool,
+				      long delta)
+{
+	int ret = 0;
+
+	if (!spool)
+		return 0;
+
+	spin_lock(&spool->lock);
+	if ((spool->used_hpages + delta) <= spool->max_hpages) {
+		spool->used_hpages += delta;
+	} else {
+		ret = -ENOMEM;
+	}
+	spin_unlock(&spool->lock);
+
+	return ret;
+}
+
+static void hugepage_subpool_put_pages(struct hugepage_subpool *spool,
+				       long delta)
+{
+	if (!spool)
+		return;
+
+	spin_lock(&spool->lock);
+	spool->used_hpages -= delta;
+	/* If hugetlbfs_put_super couldn't free spool due to
+	* an outstanding quota reference, free it now. */
+	unlock_or_release_subpool(spool);
+}
+
+static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
+{
+	return HUGETLBFS_SB(inode->i_sb)->spool;
+}
+
+static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
+{
+	return subpool_inode(vma->vm_file->f_dentry->d_inode);
+}
+
 /*
  * Region tracking -- allows tracking of reservations and instantiated pages
  *                    across the pages in a mapping.
@@ -454,14 +532,16 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve)
 {
-	struct page *page = NULL;
+	struct page *page;
 	struct mempolicy *mpol;
 	nodemask_t *nodemask;
 	struct zonelist *zonelist;
 	struct zone *zone;
 	struct zoneref *z;
+	unsigned int cpuset_mems_cookie;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask, &mpol, &nodemask);
 	/*
@@ -488,10 +568,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 			}
 		}
 	}
-err:
+
 	mpol_cond_put(mpol);
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
+
+err:
+	mpol_cond_put(mpol);
+	return NULL;
 }
 
 static void update_and_free_page(struct hstate *h, struct page *page)
@@ -533,9 +618,9 @@ static void free_huge_page(struct page *page)
 	 */
 	struct hstate *h = page_hstate(page);
 	int nid = page_to_nid(page);
-	struct address_space *mapping;
+	struct hugepage_subpool *spool =
+		(struct hugepage_subpool *)page_private(page);
 
-	mapping = (struct address_space *) page_private(page);
 	set_page_private(page, 0);
 	page->mapping = NULL;
 	BUG_ON(page_count(page));
@@ -551,8 +636,7 @@ static void free_huge_page(struct page *page)
 		enqueue_huge_page(h, page);
 	}
 	spin_unlock(&hugetlb_lock);
-	if (mapping)
-		hugetlb_put_quota(mapping, 1);
+	hugepage_subpool_put_pages(spool, 1);
 }
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
@@ -852,6 +936,7 @@ static int gather_surplus_pages(struct hstate *h, int delta)
 	struct page *page, *tmp;
 	int ret, i;
 	int needed, allocated;
+	bool alloc_ok = true;
 
 	needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
 	if (needed <= 0) {
@@ -867,17 +952,13 @@ retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
-		if (!page)
-			/*
-			 * We were not able to allocate enough pages to
-			 * satisfy the entire reservation so we free what
-			 * we've allocated so far.
-			 */
-			goto free;
-
+		if (!page) {
+			alloc_ok = false;
+			break;
+		}
 		list_add(&page->lru, &surplus_list);
 	}
-	allocated += needed;
+	allocated += i;
 
 	/*
 	 * After retaking hugetlb_lock, we need to recalculate 'needed'
@@ -886,9 +967,16 @@ retry:
 	spin_lock(&hugetlb_lock);
 	needed = (h->resv_huge_pages + delta) -
 			(h->free_huge_pages + allocated);
-	if (needed > 0)
-		goto retry;
-
+	if (needed > 0) {
+		if (alloc_ok)
+			goto retry;
+		/*
+		 * We were not able to allocate enough pages to
+		 * satisfy the entire reservation so we free what
+		 * we've allocated so far.
+		 */
+		goto free;
+	}
 	/*
 	 * The surplus_list now contains _at_least_ the number of extra pages
 	 * needed to accommodate the reservation.  Add the appropriate number
@@ -914,10 +1002,10 @@ retry:
 		VM_BUG_ON(page_count(page));
 		enqueue_huge_page(h, page);
 	}
+free:
 	spin_unlock(&hugetlb_lock);
 
 	/* Free unnecessary surplus pages to the buddy allocator */
-free:
 	if (!list_empty(&surplus_list)) {
 		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
 			list_del(&page->lru);
@@ -966,11 +1054,12 @@ 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 quota 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 quota'd allocated
- * an instantiated the change should be committed via vma_commit_reservation.
- * No action is required on failure.
+ * 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)
@@ -1019,24 +1108,24 @@ static void vma_commit_reservation(struct hstate *h,
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr, int avoid_reserve)
 {
+	struct hugepage_subpool *spool = subpool_vma(vma);
 	struct hstate *h = hstate_vma(vma);
 	struct page *page;
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	struct inode *inode = mapping->host;
 	long chg;
 
 	/*
-	 * Processes that did not create the mapping will have no reserves and
-	 * will not have accounted against quota. Check that the quota can be
-	 * made before satisfying the allocation
-	 * MAP_NORESERVE mappings may also need pages and quota allocated
-	 * if no reserve mapping overlaps.
+	 * Processes that did not create the mapping will have no
+	 * reserves and will not have accounted against subpool
+	 * limit. Check that the subpool limit can be made before
+	 * satisfying the allocation MAP_NORESERVE mappings may also
+	 * need pages and subpool limit allocated allocated if no reserve
+	 * mapping overlaps.
 	 */
 	chg = vma_needs_reservation(h, vma, addr);
 	if (chg < 0)
 		return ERR_PTR(-VM_FAULT_OOM);
 	if (chg)
-		if (hugetlb_get_quota(inode->i_mapping, chg))
+		if (hugepage_subpool_get_pages(spool, chg))
 			return ERR_PTR(-VM_FAULT_SIGBUS);
 
 	spin_lock(&hugetlb_lock);
@@ -1046,12 +1135,12 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	if (!page) {
 		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
 		if (!page) {
-			hugetlb_put_quota(inode->i_mapping, chg);
+			hugepage_subpool_put_pages(spool, chg);
 			return ERR_PTR(-VM_FAULT_SIGBUS);
 		}
 	}
 
-	set_page_private(page, (unsigned long) mapping);
+	set_page_private(page, (unsigned long)spool);
 
 	vma_commit_reservation(h, vma, addr);
 
@@ -2072,6 +2161,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct resv_map *reservations = vma_resv_map(vma);
+	struct hugepage_subpool *spool = subpool_vma(vma);
 	unsigned long reserve;
 	unsigned long start;
 	unsigned long end;
@@ -2087,7 +2177,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 
 		if (reserve) {
 			hugetlb_acct_memory(h, -reserve);
-			hugetlb_put_quota(vma->vm_file->f_mapping, reserve);
+			hugepage_subpool_put_pages(spool, reserve);
 		}
 	}
 }
@@ -2241,16 +2331,23 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 		if (huge_pmd_unshare(mm, &address, ptep))
 			continue;
 
+		pte = huge_ptep_get(ptep);
+		if (huge_pte_none(pte))
+			continue;
+
+		/*
+		 * HWPoisoned hugepage is already unmapped and dropped reference
+		 */
+		if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
+			continue;
+
+		page = pte_page(pte);
 		/*
 		 * If a reference page is supplied, it is because a specific
 		 * page is being unmapped, not a range. Ensure the page we
 		 * are about to unmap is the actual page of interest.
 		 */
 		if (ref_page) {
-			pte = huge_ptep_get(ptep);
-			if (huge_pte_none(pte))
-				continue;
-			page = pte_page(pte);
 			if (page != ref_page)
 				continue;
 
@@ -2263,19 +2360,13 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 		}
 
 		pte = huge_ptep_get_and_clear(mm, address, ptep);
-		if (huge_pte_none(pte))
-			continue;
-
-		/*
-		 * HWPoisoned hugepage is already unmapped and dropped reference
-		 */
-		if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
-			continue;
-
-		page = pte_page(pte);
 		if (pte_dirty(pte))
 			set_page_dirty(page);
 		list_add(&page->lru, &page_list);
+
+		/* Bail out after unmapping reference page if supplied */
+		if (ref_page)
+			break;
 	}
 	flush_tlb_range(vma, start, end);
 	spin_unlock(&mm->page_table_lock);
@@ -2316,7 +2407,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 */
 	address = address & huge_page_mask(h);
 	pgoff = vma_hugecache_offset(h, vma, address);
-	mapping = (struct address_space *)page_private(page);
+	mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
 
 	/*
 	 * Take the mapping lock for the duration of the table walk. As
@@ -2869,11 +2960,12 @@ int hugetlb_reserve_pages(struct inode *inode,
 {
 	long ret, chg;
 	struct hstate *h = hstate_inode(inode);
+	struct hugepage_subpool *spool = subpool_inode(inode);
 
 	/*
 	 * Only apply hugepage reservation if asked. At fault time, an
 	 * attempt will be made for VM_NORESERVE to allocate a page
-	 * and filesystem quota without using reserves
+	 * without using reserves
 	 */
 	if (vm_flags & VM_NORESERVE)
 		return 0;
@@ -2900,17 +2992,17 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (chg < 0)
 		return chg;
 
-	/* There must be enough filesystem quota for the mapping */
-	if (hugetlb_get_quota(inode->i_mapping, chg))
+	/* There must be enough pages in the subpool for the mapping */
+	if (hugepage_subpool_get_pages(spool, chg))
 		return -ENOSPC;
 
 	/*
 	 * Check enough hugepages are available for the reservation.
-	 * Hand back the quota if there are not
+	 * Hand the pages back to the subpool if there are not
 	 */
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
-		hugetlb_put_quota(inode->i_mapping, chg);
+		hugepage_subpool_put_pages(spool, chg);
 		return ret;
 	}
 
@@ -2934,12 +3026,13 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
 	struct hstate *h = hstate_inode(inode);
 	long chg = region_truncate(&inode->i_mapping->private_list, offset);
+	struct hugepage_subpool *spool = subpool_inode(inode);
 
 	spin_lock(&inode->i_lock);
 	inode->i_blocks -= (blocks_per_huge_page(h) * freed);
 	spin_unlock(&inode->i_lock);
 
-	hugetlb_put_quota(inode->i_mapping, (chg - freed));
+	hugepage_subpool_put_pages(spool, (chg - freed));
 	hugetlb_acct_memory(h, -(chg - freed));
 }