mm/hugetlb: make hugetlb migration callback CMA aware

new_non_cma_page() in gup.c requires to allocate the new page that is not
on the CMA area.  new_non_cma_page() implements it by using allocation
scope APIs.

However, there is a work-around for hugetlb.  Normal hugetlb page
allocation API for migration is alloc_huge_page_nodemask().  It consists
of two steps.  First is dequeing from the pool.  Second is, if there is no
available page on the queue, allocating by using the page allocator.

new_non_cma_page() can't use this API since first step (deque) isn't aware
of scope API to exclude CMA area.  So, new_non_cma_page() exports hugetlb
internal function for the second step, alloc_migrate_huge_page(), to
global scope and uses it directly.  This is suboptimal since hugetlb pages
on the queue cannot be utilized.

This patch tries to fix this situation by making the deque function on
hugetlb CMA aware.  In the deque function, CMA memory is skipped if
PF_MEMALLOC_NOCMA flag is found.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Roman Gushchin <guro@fb.com>
Link: http://lkml.kernel.org/r/1596180906-8442-2-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 10 insertions, 7 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 6c20c6e37635..c55427beeb26 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1635,11 +1635,7 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 		struct hstate *h = page_hstate(page);
 
 		gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
-		/*
-		 * We don't want to dequeue from the pool because pool pages will
-		 * mostly be from the CMA region.
-		 */
-		return alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
+		return alloc_huge_page_nodemask(h, nid, NULL, gfp_mask);
 	}
 #endif
 	if (PageTransHuge(page)) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eaab9ef88e9d..a301c2d672bf 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -19,6 +19,7 @@
 #include <linux/memblock.h>
 #include <linux/sysfs.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include <linux/mmdebug.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
@@ -1040,10 +1041,16 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 {
 	struct page *page;
+	bool nocma = !!(current->flags & PF_MEMALLOC_NOCMA);
+
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
+		if (nocma && is_migrate_cma_page(page))
+			continue;
 
-	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
 		if (!PageHWPoison(page))
 			break;
+	}
+
 	/*
 	 * if 'non-isolated free hugepage' not found on the list,
 	 * the allocation fails.
@@ -1935,7 +1942,7 @@ out_unlock:
 	return page;
 }
 
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
 				     int nid, nodemask_t *nmask)
 {
 	struct page *page;