MAP_NORESERVE for hugetlb mappings V3

index 0ffed95..c2be4c3 100644
@@ -100,6 +100,7 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
 #define VM_RESERVED	0x00080000	/* Count as reserved_vm like IO */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
+#define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
 #define VM_MAPPED_COPY	0x01000000	/* T if mapped copy of data (nommu mmap) */

index fac6633..98ab014 100644
@@ -1101,6 +1101,9 @@ munmap_back:
 	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
 		return -ENOMEM;
 
+	if (flags & MAP_NORESERVE)
+		vm_flags |= VM_NORESERVE;
+
 	if (accountable && (!(flags & MAP_NORESERVE) ||
 			    sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
 		if (vm_flags & VM_SHARED) {

index a5bf31c..e0d0a6d 100644
@@ -155,12 +155,10 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
 	 * make it unwritable again.
-	 *
-	 * FIXME? We haven't defined a VM_NORESERVE flag, so mprotecting
-	 * a MAP_NORESERVE private mapping to writable will now reserve.
 	 */
 	if (newflags & VM_WRITE) {
-		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED))) {
+		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|
+						VM_SHARED|VM_NORESERVE))) {
 			charged = nrpages;
 			if (security_vm_enough_memory(charged))
 				return -ENOMEM;

index cd18d11..90a7f5f 100644
@@ -561,6 +561,127 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages)
 	}
 }
 
+struct file_region {
+	struct list_head link;
+	long from;
+	long to;
+};
+
+static long region_add(struct list_head *head, long f, long t)
+{
+	struct file_region *rg, *nrg, *trg;
+
+	/* Locate the region we are either in or before. */
+	list_for_each_entry(rg, head, link)
+		if (f <= rg->to)
+			break;
+
+	/* Round our left edge to the current segment if it encloses us. */
+	if (f > rg->from)
+		f = rg->from;
+
+	/* Check for and consume any regions we now overlap with. */
+	nrg = rg;
+	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		if (rg->from > t)
+			break;
+
+		/* If this area reaches higher then extend our area to
+		 * include it completely.  If this is not the first area
+		 * which we intend to reuse, free it. */
+		if (rg->to > t)
+			t = rg->to;
+		if (rg != nrg) {
+			list_del(&rg->link);
+			kfree(rg);
+		}
+	}
+	nrg->from = f;
+	nrg->to = t;
+	return 0;
+}
+
+static long region_chg(struct list_head *head, long f, long t)
+{
+	struct file_region *rg, *nrg;
+	long chg = 0;
+
+	/* Locate the region we are before or in. */
+	list_for_each_entry(rg, head, link)
+		if (f <= rg->to)
+			break;
+
+	/* If we are below the current region then a new region is required.
+	 * Subtle, allocate a new region at the position but make it zero
+	 * size such that we can guarantee to record the reservation. */
+	if (&rg->link == head || t < rg->from) {
+		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+		if (!nrg)
+			return -ENOMEM;
+		nrg->from = f;
+		nrg->to   = f;
+		INIT_LIST_HEAD(&nrg->link);
+		list_add(&nrg->link, rg->link.prev);
+
+		return t - f;
+	}
+
+	/* Round our left edge to the current segment if it encloses us. */
+	if (f > rg->from)
+		f = rg->from;
+	chg = t - f;
+
+	/* Check for and consume any regions we now overlap with. */
+	list_for_each_entry(rg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		if (rg->from > t)
+			return chg;
+
+		/* We overlap with this area, if it extends futher than
+		 * us then we must extend ourselves.  Account for its
+		 * existing reservation. */
+		if (rg->to > t) {
+			chg += rg->to - t;
+			t = rg->to;
+		}
+		chg -= rg->to - rg->from;
+	}
+	return chg;
+}
+
+static long region_truncate(struct list_head *head, long end)
+{
+	struct file_region *rg, *trg;
+	long chg = 0;
+
+	/* Locate the region we are either in or before. */
+	list_for_each_entry(rg, head, link)
+		if (end <= rg->to)
+			break;
+	if (&rg->link == head)
+		return 0;
+
+	/* If we are in the middle of a region then adjust it. */
+	if (end > rg->from) {
+		chg = rg->to - end;
+		rg->to = end;
+		rg = list_entry(rg->link.next, typeof(*rg), link);
+	}
+
+	/* Drop any remaining regions. */
+	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+		if (&rg->link == head)
+			break;
+		chg += rg->to - rg->from;
+		list_del(&rg->link);
+		kfree(rg);
+	}
+	return chg;
+}
+
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr, int avoid_reserve)
 {

@@ -1392,127 +1513,6 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_tlb_range(vma, start, end);
 }
 
-struct file_region {
-	struct list_head link;
-	long from;
-	long to;
-};
-
-static long region_add(struct list_head *head, long f, long t)
-{
-	struct file_region *rg, *nrg, *trg;
-
-	/* Locate the region we are either in or before. */
-	list_for_each_entry(rg, head, link)
-		if (f <= rg->to)
-			break;
-
-	/* Round our left edge to the current segment if it encloses us. */
-	if (f > rg->from)
-		f = rg->from;
-
-	/* Check for and consume any regions we now overlap with. */
-	nrg = rg;
-	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
-		if (&rg->link == head)
-			break;
-		if (rg->from > t)
-			break;
-
-		/* If this area reaches higher then extend our area to
-		 * include it completely.  If this is not the first area
-		 * which we intend to reuse, free it. */
-		if (rg->to > t)
-			t = rg->to;
-		if (rg != nrg) {
-			list_del(&rg->link);
-			kfree(rg);
-		}
-	}
-	nrg->from = f;
-	nrg->to = t;
-	return 0;
-}
-
-static long region_chg(struct list_head *head, long f, long t)
-{
-	struct file_region *rg, *nrg;
-	long chg = 0;
-
-	/* Locate the region we are before or in. */
-	list_for_each_entry(rg, head, link)
-		if (f <= rg->to)
-			break;
-
-	/* If we are below the current region then a new region is required.
-	 * Subtle, allocate a new region at the position but make it zero
-	 * size such that we can guarantee to record the reservation. */
-	if (&rg->link == head || t < rg->from) {
-		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
-		if (!nrg)
-			return -ENOMEM;
-		nrg->from = f;
-		nrg->to   = f;
-		INIT_LIST_HEAD(&nrg->link);
-		list_add(&nrg->link, rg->link.prev);
-
-		return t - f;
-	}
-
-	/* Round our left edge to the current segment if it encloses us. */
-	if (f > rg->from)
-		f = rg->from;
-	chg = t - f;
-
-	/* Check for and consume any regions we now overlap with. */
-	list_for_each_entry(rg, rg->link.prev, link) {
-		if (&rg->link == head)
-			break;
-		if (rg->from > t)
-			return chg;
-
-		/* We overlap with this area, if it extends futher than
-		 * us then we must extend ourselves.  Account for its
-		 * existing reservation. */
-		if (rg->to > t) {
-			chg += rg->to - t;
-			t = rg->to;
-		}
-		chg -= rg->to - rg->from;
-	}
-	return chg;
-}
-
-static long region_truncate(struct list_head *head, long end)
-{
-	struct file_region *rg, *trg;
-	long chg = 0;
-
-	/* Locate the region we are either in or before. */
-	list_for_each_entry(rg, head, link)
-		if (end <= rg->to)
-			break;
-	if (&rg->link == head)
-		return 0;
-
-	/* If we are in the middle of a region then adjust it. */
-	if (end > rg->from) {
-		chg = rg->to - end;
-		rg->to = end;
-		rg = list_entry(rg->link.next, typeof(*rg), link);
-	}
-
-	/* Drop any remaining regions. */
-	list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
-		if (&rg->link == head)
-			break;
-		chg += rg->to - rg->from;
-		list_del(&rg->link);
-		kfree(rg);
-	}
-	return chg;
-}
-
 int hugetlb_reserve_pages(struct inode *inode,
 					long from, long to,
 					struct vm_area_struct *vma)

index 90a7f5f..118dc54 100644
@@ -88,6 +88,9 @@ static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
 /* Decrement the reserved pages in the hugepage pool by one */
 static void decrement_hugepage_resv_vma(struct vm_area_struct *vma)
 {
+	if (vma->vm_flags & VM_NORESERVE)
+		return;
+
 	if (vma->vm_flags & VM_SHARED) {
 		/* Shared mappings always use reserves */
 		resv_huge_pages--;

@@ -682,25 +685,67 @@ static long region_truncate(struct list_head *head, long end)
 	return 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 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.
+ */
+static int vma_needs_reservation(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_SHARED) {
+		unsigned long idx = ((addr - vma->vm_start) >> HPAGE_SHIFT) +
+				(vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+		return region_chg(&inode->i_mapping->private_list,
+							idx, idx + 1);
+
+	} else {
+		if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+			return 1;
+	}
+
+	return 0;
+}
+static void vma_commit_reservation(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_SHARED) {
+		unsigned long idx = ((addr - vma->vm_start) >> HPAGE_SHIFT) +
+				(vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+		region_add(&inode->i_mapping->private_list, idx, idx + 1);
+	}
+}
+
 static struct page *alloc_huge_page(struct vm_area_struct *vma,
 				    unsigned long addr, int avoid_reserve)
 {
 	struct page *page;
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct inode *inode = mapping->host;
-	unsigned int chg = 0;
+	unsigned int 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.
 	 */
-	if (!(vma->vm_flags & VM_SHARED) &&
-			!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
-		chg = 1;
+	chg = vma_needs_reservation(vma, addr);
+	if (chg < 0)
+		return ERR_PTR(chg);
+	if (chg)
 		if (hugetlb_get_quota(inode->i_mapping, chg))
 			return ERR_PTR(-ENOSPC);
-	}
 
 	spin_lock(&hugetlb_lock);
 	page = dequeue_huge_page_vma(vma, addr, avoid_reserve);

@@ -717,6 +762,8 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	set_page_refcounted(page);
 	set_page_private(page, (unsigned long) mapping);
 
+	vma_commit_reservation(vma, addr);
+
 	return page;
 }
 

@@ -1519,6 +1566,9 @@ int hugetlb_reserve_pages(struct inode *inode,
 {
 	long ret, chg;
 
+	if (vma && vma->vm_flags & VM_NORESERVE)
+		return 0;
+
 	/*
 	 * Shared mappings base their reservation on the number of pages that
 	 * are already allocated on behalf of the file. Private mappings need