hugetlb: fix pool shrinking while in restricted cpuset

From previous discussions on linux-mm, /proc/sys/vm/nr_hugepages is an

Adam Litke noticed that currently we grow the hugepage pool independent of any cpuset the running process may be in, but when shrinking the pool, the cpuset is checked. This leads to inconsistency when shrinking the pool in a restricted cpuset -- an administrator may have been able to grow the pool on a node restricted by a containing cpuset, but they cannot shrink it there. There are two options: either prevent growing of the pool outside of the cpuset or allow shrinking outside of the cpuset.

Quoted 1 line

From previous discussions on linux-mm, /proc/sys/vm/nr_hugepages is an

administrative interface that should not be restricted by cpusets. So allow shrinking the pool by removing pages from nodes outside of current's cpuset.

This is a bugfix and should go into 2.6.25.

Signed-off-by Nishanth Aravamudan <[email protected]>

Cc Adam Litke <[email protected]>

Cc William Irwin <[email protected]>

Cc Lee Schermerhorn <[email protected]>

Cc Christoph Lameter <[email protected]>

Cc Paul Jackson <[email protected]>

Cc Andrew Morton <[email protected]>

mm/hugetlb.c +22 -4

index 89e6286..61ac37f 100644
@@ -71,7 +71,25 @@ static void enqueue_huge_page(struct page *page)
 	free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page(struct vm_area_struct *vma,
+static struct page *dequeue_huge_page(void)
+{
+	int nid;
+	struct page *page = NULL;
+
+	for (nid = 0; nid < MAX_NUMNODES; ++nid) {
+		if (!list_empty(&hugepage_freelists[nid])) {
+			page = list_entry(hugepage_freelists[nid].next,
+					  struct page, lru);
+			list_del(&page->lru);
+			free_huge_pages--;
+			free_huge_pages_node[nid]--;
+			break;
+		}
+	}
+	return page;
+}
+
+static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
 				unsigned long address)
 {
 	int nid;

@@ -402,7 +420,7 @@ static struct page *alloc_huge_page_shared(struct vm_area_struct *vma,
 	struct page *page;
 
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page(vma, addr);
+	page = dequeue_huge_page_vma(vma, addr);
 	spin_unlock(&hugetlb_lock);
 	return page ? page : ERR_PTR(-VM_FAULT_OOM);
 }

@@ -417,7 +435,7 @@ static struct page *alloc_huge_page_private(struct vm_area_struct *vma,
 
 	spin_lock(&hugetlb_lock);
 	if (free_huge_pages > resv_huge_pages)
-		page = dequeue_huge_page(vma, addr);
+		page = dequeue_huge_page_vma(vma, addr);
 	spin_unlock(&hugetlb_lock);
 	if (!page) {
 		page = alloc_buddy_huge_page(vma, addr);

@@ -570,7 +588,7 @@ static unsigned long set_max_huge_pages(unsigned long count)
 	min_count = max(count, min_count);
 	try_to_free_low(min_count);
 	while (min_count < persistent_huge_pages) {
-		struct page *page = dequeue_huge_page(NULL, 0);
+		struct page *page = dequeue_huge_page();
 		if (!page)
 			break;
 		update_and_free_page(page);