mm: prepare to remove /proc/sys/vm/hugepages_treat_as_movable

Now hugepage migration is enabled, although restricted on pmd-based
hugepages for now (due to lack of testing.) So we should allocate
migratable hugepages from ZONE_MOVABLE if possible.

This patch makes GFP flags in hugepage allocation dependent on migration
support, not only the value of hugepages_treat_as_movable.  It provides no
change on the behavior for architectures which do not support hugepage
migration,

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Rik van Riel <riel@redhat.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Documentation/sysctl/vm.txt

@@ -200,17 +200,25 @@ fragmentation index is <= extfrag_threshold. The default value is 500.
 
 hugepages_treat_as_movable
 
-This parameter is only useful when kernelcore= is specified at boot time to
+This parameter controls whether we can allocate hugepages from ZONE_MOVABLE
-create ZONE_MOVABLE for pages that may be reclaimed or migrated. Huge pages
+or not. If set to non-zero, hugepages can be allocated from ZONE_MOVABLE.
-are not movable so are not normally allocated from ZONE_MOVABLE. A non-zero
+ZONE_MOVABLE is created when kernel boot parameter kernelcore= is specified,
-value written to hugepages_treat_as_movable allows huge pages to be allocated
+so this parameter has no effect if used without kernelcore=.
-from ZONE_MOVABLE.
 
-Once enabled, the ZONE_MOVABLE is treated as an area of memory the huge
+Hugepage migration is now available in some situations which depend on the
-pages pool can easily grow or shrink within. Assuming that applications are
+architecture and/or the hugepage size. If a hugepage supports migration,
-not running that mlock() a lot of memory, it is likely the huge pages pool
+allocation from ZONE_MOVABLE is always enabled for the hugepage regardless
-can grow to the size of ZONE_MOVABLE by repeatedly entering the desired value
+of the value of this parameter.
-into nr_hugepages and triggering page reclaim.
+IOW, this parameter affects only non-migratable hugepages.
+
+Assuming that hugepages are not migratable in your system, one usecase of
+this parameter is that users can make hugepage pool more extensible by
+enabling the allocation from ZONE_MOVABLE. This is because on ZONE_MOVABLE
+page reclaim/migration/compaction work more and you can get contiguous
+memory more likely. Note that using ZONE_MOVABLE for non-migratable
+hugepages can do harm to other features like memory hotremove (because
+memory hotremove expects that memory blocks on ZONE_MOVABLE are always
+removable,) so it's a trade-off responsible for the users.
 
 ==============================================================
 

kernel/sysctl.c

@@ -1225,7 +1225,7 @@ static struct ctl_table vm_table[] = {
 		.data		= &hugepages_treat_as_movable,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= hugetlb_treat_movable_handler,
+		.proc_handler	= proc_dointvec,
 	},
 	{
 		.procname	= "nr_overcommit_hugepages",

mm/hugetlb.c

@@ -34,7 +34,6 @@
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
 
 int hugetlb_max_hstate __read_mostly;
@@ -539,6 +538,15 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 	return page;
 }
 
+/* Movability of hugepages depends on migration support. */
+static inline gfp_t htlb_alloc_mask(struct hstate *h)
+{
+	if (hugepages_treat_as_movable || hugepage_migration_support(h))
+		return GFP_HIGHUSER_MOVABLE;
+	else
+		return GFP_HIGHUSER;
+}
+
 static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve,
@@ -568,11 +576,11 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 retry_cpuset:
 	cpuset_mems_cookie = get_mems_allowed();
 	zonelist = huge_zonelist(vma, address,
-					htlb_alloc_mask, &mpol, &nodemask);
+					htlb_alloc_mask(h), &mpol, &nodemask);
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						MAX_NR_ZONES - 1, nodemask) {
-		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
+		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask(h))) {
 			page = dequeue_huge_page_node(h, zone_to_nid(zone));
 			if (page) {
 				if (avoid_reserve)
@@ -738,7 +746,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 		return NULL;
 
 	page = alloc_pages_exact_node(nid,
-		htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
 						__GFP_REPEAT|__GFP_NOWARN,
 		huge_page_order(h));
 	if (page) {
@@ -965,12 +973,12 @@ static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 	spin_unlock(&hugetlb_lock);
 
 	if (nid == NUMA_NO_NODE)
-		page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+		page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP|
 				   __GFP_REPEAT|__GFP_NOWARN,
 				   huge_page_order(h));
 	else
 		page = alloc_pages_exact_node(nid,
-			htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+			htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
 			__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
 
 	if (page && arch_prepare_hugepage(page)) {
@@ -2117,18 +2125,6 @@ int hugetlb_mempolicy_sysctl_handler(struct ctl_table *table, int write,
 }
 #endif /* CONFIG_NUMA */
 
-int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
-			void __user *buffer,
-			size_t *length, loff_t *ppos)
-{
-	proc_dointvec(table, write, buffer, length, ppos);
-	if (hugepages_treat_as_movable)
-		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
-	else
-		htlb_alloc_mask = GFP_HIGHUSER;
-	return 0;
-}
-
 int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 			void __user *buffer,
 			size_t *length, loff_t *ppos)