[PATCH] Add NUMA policy support for huge pages.

The huge_zonelist() function in the memory policy layer provides an list of
zones ordered by NUMA distance.  The hugetlb layer will walk that list looking
for a zone that has available huge pages but is also in the nodeset of the
current cpuset.

This patch does not contain the folding of find_or_alloc_huge_page() that was
controversial in the earlier discussion.

Signed-off-by: Christoph Lameter <clameter@sgi.com>
Cc: Andi Kleen <ak@muc.de>
Acked-by: William Lee Irwin III <wli@holomorphy.com>
Cc: Adam Litke <agl@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 10 insertions, 2 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 1056717ee501..68d82ad6b17c 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -22,7 +22,7 @@ int hugetlb_report_meminfo(char *);
 int hugetlb_report_node_meminfo(int, char *);
 int is_hugepage_mem_enough(size_t);
 unsigned long hugetlb_total_pages(void);
-struct page *alloc_huge_page(void);
+struct page *alloc_huge_page(struct vm_area_struct *, unsigned long);
 void free_huge_page(struct page *);
 int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                         unsigned long address, int write_access);
@@ -97,7 +97,7 @@ static inline unsigned long hugetlb_total_pages(void)
 #define is_hugepage_only_range(mm, addr, len)   0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
                                                 do { } while (0)
-#define alloc_huge_page()                       ({ NULL; })
+#define alloc_huge_page(vma, addr)              ({ NULL; })
 #define free_huge_page(p)                       ({ (void)(p); BUG(); })
 #define hugetlb_fault(mm, vma, addr, write)     ({ BUG(); 0; })
 
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 8b67cf837ca9..817db6427113 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -156,6 +156,8 @@ extern void numa_default_policy(void);
 extern void numa_policy_init(void);
 extern void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new);
 extern struct mempolicy default_policy;
+extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
+                unsigned long addr);
 
 #else
 
@@ -232,6 +234,12 @@ static inline void numa_policy_rebind(const nodemask_t *old,
 {
 }
 
+static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
+                unsigned long addr)
+{
+        return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER);
+}
+
 #endif /* CONFIG_NUMA */
 #endif /* __KERNEL__ */