[RFC PATCH 5/8] hugetlb: change free_pool_huge_page to remove_pool_huge_page

[Mike Kravetz <mike.kravetz@oracle.com>]

free_pool_huge_page was called with hugetlb_lock held.  It would remove
a hugetlb page, and then free the corresponding pages to the lower level
allocators such as buddy.  free_pool_huge_page was called in a loop to
remove hugetlb pages and these loops could hold the hugetlb_lock for a
considerable time.

Create new routine remove_pool_huge_page to replace free_pool_huge_page.
remove_pool_huge_page will remove the hugetlb page, and it must be
called with the hugetlb_lock held.  It will return the removed page and
it is the responsibility of the caller to free the page to the lower
level allocators.  The hugetlb_lock is dropped before freeing to these
allocators which results in shorter lock hold times.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 mm/hugetlb.c | 53 +++++++++++++++++++++++++++++-----------------------
 1 file changed, 30 insertions(+), 23 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3028cf10d504..f60a24e326c2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1184,7 +1184,7 @@ static int hstate_next_node_to_alloc(struct hstate *h,
 }
 
 /*
- * helper for free_pool_huge_page() - return the previously saved
+ * helper for remove_pool_huge_page() - return the previously saved
  * node ["this node"] from which to free a huge page.  Advance the
  * next node id whether or not we find a free huge page to free so
  * that the next attempt to free addresses the next node.
@@ -1699,16 +1699,18 @@ static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 }
 
 /*
- * Free huge page from pool from next node to free.
- * Attempt to keep persistent huge pages more or less
- * balanced over allowed nodes.
+ * Remove huge page from pool from next node to free.  Attempt to keep
+ * persistent huge pages more or less balanced over allowed nodes.
+ * This routine only 'removes' the hugetlb page.  The caller must make
+ * an additional call to free the page to low level allocators.
  * Called with hugetlb_lock locked.
  */
-static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
-							 bool acct_surplus)
+static struct page *remove_pool_huge_page(struct hstate *h,
+						nodemask_t *nodes_allowed,
+						 bool acct_surplus)
 {
 	int nr_nodes, node;
-	int ret = 0;
+	struct page *page = NULL;
 
 	for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
 		/*
@@ -1717,23 +1719,14 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 		 */
 		if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
 		    !list_empty(&h->hugepage_freelists[node])) {
-			struct page *page =
-				list_entry(h->hugepage_freelists[node].next,
+			page = list_entry(h->hugepage_freelists[node].next,
 					  struct page, lru);
 			remove_hugetlb_page(h, page, acct_surplus);
-			/*
-			 * unlock/lock around update_and_free_page is temporary
-			 * and will be removed with subsequent patch.
-			 */
-			spin_unlock(&hugetlb_lock);
-			update_and_free_page(h, page);
-			spin_lock(&hugetlb_lock);
-			ret = 1;
 			break;
 		}
 	}
 
-	return ret;
+	return page;
 }
 
 /*
@@ -2064,6 +2057,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 					unsigned long unused_resv_pages)
 {
 	unsigned long nr_pages;
+	struct page *page;
 
 	/* Cannot return gigantic pages currently */
 	if (hstate_is_gigantic(h))
@@ -2080,7 +2074,7 @@ static void return_unused_surplus_pages(struct hstate *h,
 	 * evenly across all nodes with memory. Iterate across these nodes
 	 * until we can no longer free unreserved surplus pages. This occurs
 	 * when the nodes with surplus pages have no free pages.
-	 * free_pool_huge_page() will balance the freed pages across the
+	 * remove_pool_huge_page() will balance the freed pages across the
 	 * on-line nodes with memory and will handle the hstate accounting.
 	 *
 	 * Note that we decrement resv_huge_pages as we free the pages.  If
@@ -2090,9 +2084,15 @@ static void return_unused_surplus_pages(struct hstate *h,
 	while (nr_pages--) {
 		h->resv_huge_pages--;
 		unused_resv_pages--;
-		if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
+		page = remove_pool_huge_page(h, &node_states[N_MEMORY], 1);
+		if (!page)
 			goto out;
-		cond_resched_lock(&hugetlb_lock);
+
+		/* Drop lock and free page to buddy as it could sleep */
+		spin_unlock(&hugetlb_lock);
+		update_and_free_page(h, page);
+		cond_resched();
+		spin_lock(&hugetlb_lock);
 	}
 
 out:
@@ -2631,6 +2631,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 			      nodemask_t *nodes_allowed)
 {
 	unsigned long min_count, ret;
+	struct page *page;
 	NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL);
 
 	/*
@@ -2740,9 +2741,15 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 	min_count = min_hp_count(h, count);
 	try_to_free_low(h, count, nodes_allowed);
 	while (min_count < persistent_huge_pages(h)) {
-		if (!free_pool_huge_page(h, nodes_allowed, 0))
+		page = remove_pool_huge_page(h, nodes_allowed, 0);
+		if (!page)
 			break;
-		cond_resched_lock(&hugetlb_lock);
+
+		/* Drop lock as free routines may sleep */
+		spin_unlock(&hugetlb_lock);
+		update_and_free_page(h, page);
+		cond_resched();
+		spin_lock(&hugetlb_lock);
 
 		/* Recompute min_count in case hugetlb_lock was dropped */
 		min_count = min_hp_count(h, count);
-- 
2.30.2