[PATCH v3 3/5] hugetlb: be sure to free demoted CMA pages to CMA

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

When huge page demotion is fully implemented, gigantic pages can be
demoted to a smaller huge page size.  For example, on x86 a 1G page
can be demoted to 512 2M pages.  However, gigantic pages can potentially
be allocated from CMA.  If a gigantic page which was allocated from CMA
is demoted, the corresponding demoted pages needs to be returned to CMA.

Use the new interface cma_pages_valid() to determine if a non-gigantic
hugetlb page should be freed to CMA.  Also, clear mapping field of these
pages as expected by cma_release.

This also requires a change to CMA reservations for gigantic pages.
Currently, the 'order_per_bit' is set to the gigantic page size.
However, if gigantic pages can be demoted this needs to be set to the
order of the smallest huge page.  At CMA reservation time we do not know
the size of the smallest huge page size, so use HUGETLB_PAGE_ORDER.
Also, prohibit demotion to huge page sizes smaller than
HUGETLB_PAGE_ORDER.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 mm/hugetlb.c | 32 +++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f4dad1ab12d8..a15f6763e8f4 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -50,6 +50,16 @@ struct hstate hstates[HUGE_MAX_HSTATE];
 
 #ifdef CONFIG_CMA
 static struct cma *hugetlb_cma[MAX_NUMNODES];
+static bool hugetlb_cma_page(struct page *page, unsigned int order)
+{
+	return cma_pages_valid(hugetlb_cma[page_to_nid(page)], page,
+				1 << order);
+}
+#else
+static bool hugetlb_cma_page(struct page *page, unsigned int order)
+{
+	return false;
+}
 #endif
 static unsigned long hugetlb_cma_size __initdata;
 
@@ -1272,6 +1282,7 @@ static void destroy_compound_gigantic_page(struct page *page,
 	atomic_set(compound_pincount_ptr(page), 0);
 
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
+		p->mapping = NULL;
 		clear_compound_head(p);
 		set_page_refcounted(p);
 	}
@@ -1476,7 +1487,13 @@ static void __update_and_free_page(struct hstate *h, struct page *page)
 				1 << PG_active | 1 << PG_private |
 				1 << PG_writeback);
 	}
-	if (hstate_is_gigantic(h)) {
+
+	/*
+	 * Non-gigantic pages demoted from CMA allocated gigantic pages
+	 * need to be given back to CMA in free_gigantic_page.
+	 */
+	if (hstate_is_gigantic(h) ||
+	    hugetlb_cma_page(page, huge_page_order(h))) {
 		destroy_compound_gigantic_page(page, huge_page_order(h));
 		free_gigantic_page(page, huge_page_order(h));
 	} else {
@@ -3003,7 +3020,8 @@ static void __init hugetlb_init_hstates(void)
 		 *   is not supported.
 		 */
 		if (!hstate_is_gigantic(h) ||
-		    gigantic_page_runtime_supported()) {
+		    gigantic_page_runtime_supported() ||
+		    !hugetlb_cma_size || !(h->order <= HUGETLB_PAGE_ORDER)) {
 			for_each_hstate(h2) {
 				if (h2 == h)
 					continue;
@@ -3555,6 +3573,8 @@ static ssize_t demote_size_store(struct kobject *kobj,
 	if (!t_hstate)
 		return -EINVAL;
 	demote_order = t_hstate->order;
+	if (demote_order < HUGETLB_PAGE_ORDER)
+		return -EINVAL;
 
 	/* demote order must be smaller hstate order */
 	h = kobj_to_hstate(kobj, &nid);
@@ -6563,7 +6583,13 @@ void __init hugetlb_cma_reserve(int order)
 		size = round_up(size, PAGE_SIZE << order);
 
 		snprintf(name, sizeof(name), "hugetlb%d", nid);
-		res = cma_declare_contiguous_nid(0, size, 0, PAGE_SIZE << order,
+		/*
+		 * Note that 'order per bit' is based on smallest size that
+		 * may be returned to CMA allocator in the case of
+		 * huge page demotion.
+		 */
+		res = cma_declare_contiguous_nid(0, size, 0,
+						PAGE_SIZE << HUGETLB_PAGE_ORDER,
 						 0, false, name,
 						 &hugetlb_cma[nid], nid);
 		if (res) {
-- 
2.31.1