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>

2 files changed, 5 insertions, 3 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2c13715e9dde..49b7053043ad 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 daabb3aa1ec6..e147cf50529f 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,