[PATCH v4 04/11] mm/hugetlb: make hugetlb migration callback CMA aware

[js1304]

From: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>

new_non_cma_page() in gup.c which try to allocate migration target page
requires to allocate the new page that is not on the CMA area.
new_non_cma_page() implements it by removing __GFP_MOVABLE flag.  This way
works well for THP page or normal page but not for hugetlb page.

hugetlb page allocation process consists of two steps.  First is dequeing
from the pool.  Second is, if there is no available page on the queue,
allocating from the page allocator.

new_non_cma_page() can control allocation from the page allocator by
specifying correct gfp flag.  However, dequeing cannot be controlled until
now, so, new_non_cma_page() skips dequeing completely.  It is a suboptimal
since new_non_cma_page() cannot utilize hugetlb pages on the queue so this
patch tries to fix this situation.

This patch makes the deque function on hugetlb CMA aware and skip CMA
pages if newly added skip_cma argument is passed as true.

Acked-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
---
 include/linux/hugetlb.h |  6 ++----
 mm/gup.c                |  3 ++-
 mm/hugetlb.c            | 46 ++++++++++++++++++++++++++++++----------------
 mm/mempolicy.c          |  2 +-
 mm/migrate.c            |  2 +-
 5 files changed, 36 insertions(+), 23 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index bb93e95..5a9ddf1 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -506,11 +506,9 @@ struct huge_bootmem_page {
 struct page *alloc_huge_page(struct vm_area_struct *vma,
 				unsigned long addr, int avoid_reserve);
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-				nodemask_t *nmask, gfp_t gfp_mask);
+				nodemask_t *nmask, gfp_t gfp_mask, bool skip_cma);
 struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
-struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
-				     int nid, nodemask_t *nmask);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
 
@@ -770,7 +768,7 @@ static inline struct page *alloc_huge_page(struct vm_area_struct *vma,
 
 static inline struct page *
 alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-			nodemask_t *nmask, gfp_t gfp_mask)
+			nodemask_t *nmask, gfp_t gfp_mask, bool skip_cma)
 {
 	return NULL;
 }
diff --git a/mm/gup.c b/mm/gup.c
index 5daadae..2c3dab4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1630,11 +1630,12 @@ static struct page *new_non_cma_page(struct page *page, unsigned long private)
 #ifdef CONFIG_HUGETLB_PAGE
 	if (PageHuge(page)) {
 		struct hstate *h = page_hstate(page);
+
 		/*
 		 * 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, true);
 	}
 #endif
 	if (PageTransHuge(page)) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3245aa0..bcf4abe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -29,6 +29,7 @@
 #include <linux/numa.h>
 #include <linux/llist.h>
 #include <linux/cma.h>
+#include <linux/sched/mm.h>
 
 #include <asm/page.h>
 #include <asm/tlb.h>
@@ -1033,13 +1034,18 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	h->free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
+static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid, bool skip_cma)
 {
 	struct page *page;
 
-	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
+	list_for_each_entry(page, &h->hugepage_freelists[nid], lru) {
+		if (skip_cma && is_migrate_cma_page(page))
+			continue;
+
 		if (!PageHWPoison(page))
 			break;
+	}
+
 	/*
 	 * if 'non-isolated free hugepage' not found on the list,
 	 * the allocation fails.
@@ -1054,7 +1060,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 }
 
 static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
-		nodemask_t *nmask)
+		nodemask_t *nmask, bool skip_cma)
 {
 	unsigned int cpuset_mems_cookie;
 	struct zonelist *zonelist;
@@ -1079,7 +1085,7 @@ static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask,
 			continue;
 		node = zone_to_nid(zone);
 
-		page = dequeue_huge_page_node_exact(h, node);
+		page = dequeue_huge_page_node_exact(h, node, skip_cma);
 		if (page)
 			return page;
 	}
@@ -1115,7 +1121,7 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask, false);
 	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
 		SetPagePrivate(page);
 		h->resv_huge_pages--;
@@ -1928,7 +1934,7 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 	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;
@@ -1971,21 +1977,29 @@ struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
 
 /* page migration callback function */
 struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
-		nodemask_t *nmask, gfp_t gfp_mask)
+		nodemask_t *nmask, gfp_t gfp_mask, bool skip_cma)
 {
+	unsigned int flags = 0;
+	struct page *page = NULL;
+
+	if (skip_cma)
+		flags = memalloc_nocma_save();
+
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0) {
-		struct page *page;
-
-		page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask);
-		if (page) {
-			spin_unlock(&hugetlb_lock);
-			return page;
-		}
+		page = dequeue_huge_page_nodemask(h, gfp_mask,
+					preferred_nid, nmask, skip_cma);
 	}
 	spin_unlock(&hugetlb_lock);
 
-	return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask);
+	if (!page)
+		page = alloc_migrate_huge_page(h, gfp_mask,
+					preferred_nid, nmask);
+
+	if (skip_cma)
+		memalloc_nocma_restore(flags);
+
+	return page;
 }
 
 /* mempolicy aware migration callback */
@@ -2000,7 +2014,7 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 
 	gfp_mask = htlb_alloc_mask(h);
 	node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask);
+	page = alloc_huge_page_nodemask(h, node, nodemask, gfp_mask, false);
 	mpol_cond_put(mpol);
 
 	return page;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9034a53..667b453 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1072,7 +1072,7 @@ struct page *alloc_new_node_page(struct page *page, unsigned long node)
 		struct hstate *h = page_hstate(compound_head(page));
 		gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 
-		return alloc_huge_page_nodemask(h, node, NULL, gfp_mask);
+		return alloc_huge_page_nodemask(h, node, NULL, gfp_mask, false);
 	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 3b3d918..02b31fe 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1543,7 +1543,7 @@ struct page *new_page_nodemask(struct page *page,
 
 		gfp_mask = htlb_alloc_mask(h);
 		return alloc_huge_page_nodemask(h, preferred_nid,
-						nodemask, gfp_mask);
+						nodemask, gfp_mask, false);
 	}
 
 	if (PageTransHuge(page)) {
-- 
2.7.4