Allow huge page allocations to use GFP_HIGH_MOVABLE

Huge pages are not movable so are not allocated from ZONE_MOVABLE.  However,
as ZONE_MOVABLE will always have pages that can be migrated or reclaimed, it
can be used to satisfy hugepage allocations even when the system has been
running a long time.  This allows an administrator to resize the hugepage pool
at runtime depending on the size of ZONE_MOVABLE.

This patch adds a new sysctl called hugepages_treat_as_movable.  When a
non-zero value is written to it, future allocations for the huge page pool
will use ZONE_MOVABLE.  Despite huge pages being non-movable, we do not
introduce additional external fragmentation of note as huge pages are always
the largest contiguous block we care about.

[akpm@linux-foundation.org: various fixes]
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 36 insertions, 8 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2c13715e9dd..49b7053043a 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -15,6 +15,7 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 }
 
 int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
+int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
 int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int);
 void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
@@ -29,6 +30,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to);
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
 
 extern unsigned long max_huge_pages;
+extern unsigned long hugepages_treat_as_movable;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
 extern int sysctl_hugetlb_shm_group;
 
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index daabb3aa1ec..e147cf50529 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -159,7 +159,7 @@ extern void mpol_fix_fork_child_flag(struct task_struct *p);
 
 extern struct mempolicy default_policy;
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-		unsigned long addr);
+		unsigned long addr, gfp_t gfp_flags);
 extern unsigned slab_node(struct mempolicy *policy);
 
 extern enum zone_type policy_zone;
@@ -256,9 +256,9 @@ static inline void mpol_fix_fork_child_flag(struct task_struct *p)
 #define set_cpuset_being_rebound(x) do {} while (0)
 
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
-		unsigned long addr)
+		unsigned long addr, gfp_t gfp_flags)
 {
-	return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER);
+	return NODE_DATA(0)->node_zonelists + gfp_zone(gfp_flags);
 }
 
 static inline int do_migrate_pages(struct mm_struct *mm,
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2ce7acf841a..48dae075d5c 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -826,6 +826,14 @@ static ctl_table vm_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	 },
+	 {
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "hugepages_treat_as_movable",
+		.data		= &hugepages_treat_as_movable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &hugetlb_treat_movable_handler,
+	},
 #endif
 	{
 		.ctl_name	= VM_LOWMEM_RESERVE_RATIO,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index acc0fb3cf06..58980676b84 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,9 @@ unsigned long max_huge_pages;
 static struct list_head hugepage_freelists[MAX_NUMNODES];
 static unsigned int nr_huge_pages_node[MAX_NUMNODES];
 static unsigned int free_huge_pages_node[MAX_NUMNODES];
+static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
+unsigned long hugepages_treat_as_movable;
+
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
  */
@@ -68,12 +71,13 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
 {
 	int nid;
 	struct page *page = NULL;
-	struct zonelist *zonelist = huge_zonelist(vma, address);
+	struct zonelist *zonelist = huge_zonelist(vma, address,
+						htlb_alloc_mask);
 	struct zone **z;
 
 	for (z = zonelist->zones; *z; z++) {
 		nid = zone_to_nid(*z);
-		if (cpuset_zone_allowed_softwall(*z, GFP_HIGHUSER) &&
+		if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&
 		    !list_empty(&hugepage_freelists[nid]))
 			break;
 	}
@@ -113,7 +117,7 @@ static int alloc_fresh_huge_page(void)
 	prev_nid = nid;
 	spin_unlock(&nid_lock);
 
-	page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN,
+	page = alloc_pages_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
 					HUGETLB_PAGE_ORDER);
 	if (page) {
 		set_compound_page_dtor(page, free_huge_page);
@@ -263,6 +267,19 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 	max_huge_pages = set_max_huge_pages(max_huge_pages);
 	return 0;
 }
+
+int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
+			struct file *file, void __user *buffer,
+			size_t *length, loff_t *ppos)
+{
+	proc_dointvec(table, write, file, buffer, length, ppos);
+	if (hugepages_treat_as_movable)
+		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
+	else
+		htlb_alloc_mask = GFP_HIGHUSER;
+	return 0;
+}
+
 #endif /* CONFIG_SYSCTL */
 
 int hugetlb_report_meminfo(char *buf)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4c0f9999681..9f4e9b95e8f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1203,7 +1203,8 @@ static inline unsigned interleave_nid(struct mempolicy *pol,
 
 #ifdef CONFIG_HUGETLBFS
 /* Return a zonelist suitable for a huge page allocation. */
-struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr)
+struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
+							gfp_t gfp_flags)
 {
 	struct mempolicy *pol = get_vma_policy(current, vma, addr);
 
@@ -1211,7 +1212,7 @@ struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr)
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
-		return NODE_DATA(nid)->node_zonelists + gfp_zone(GFP_HIGHUSER);
+		return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags);
 	}
 	return zonelist_policy(GFP_HIGHUSER, pol);
 }