[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>
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e93bd63..eb40556 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -11,6 +11,8 @@
#include <linux/highmem.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
+#include <linux/mempolicy.h>
+
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -36,11 +38,12 @@
free_huge_pages_node[nid]++;
}
-static struct page *dequeue_huge_page(void)
+static struct page *dequeue_huge_page(struct vm_area_struct *vma,
+ unsigned long address)
{
int nid = numa_node_id();
struct page *page = NULL;
- struct zonelist *zonelist = NODE_DATA(nid)->node_zonelists;
+ struct zonelist *zonelist = huge_zonelist(vma, address);
struct zone **z;
for (z = zonelist->zones; *z; z++) {
@@ -87,13 +90,13 @@
spin_unlock(&hugetlb_lock);
}
-struct page *alloc_huge_page(void)
+struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
int i;
spin_lock(&hugetlb_lock);
- page = dequeue_huge_page();
+ page = dequeue_huge_page(vma, addr);
if (!page) {
spin_unlock(&hugetlb_lock);
return NULL;
@@ -196,7 +199,7 @@
spin_lock(&hugetlb_lock);
try_to_free_low(count);
while (count < nr_huge_pages) {
- struct page *page = dequeue_huge_page();
+ struct page *page = dequeue_huge_page(NULL, 0);
if (!page)
break;
update_and_free_page(page);
@@ -365,8 +368,9 @@
flush_tlb_range(vma, start, end);
}
-static struct page *find_or_alloc_huge_page(struct address_space *mapping,
- unsigned long idx, int shared)
+static struct page *find_or_alloc_huge_page(struct vm_area_struct *vma,
+ unsigned long addr, struct address_space *mapping,
+ unsigned long idx, int shared)
{
struct page *page;
int err;
@@ -378,7 +382,7 @@
if (hugetlb_get_quota(mapping))
goto out;
- page = alloc_huge_page();
+ page = alloc_huge_page(vma, addr);
if (!page) {
hugetlb_put_quota(mapping);
goto out;
@@ -418,7 +422,7 @@
}
page_cache_get(old_page);
- new_page = alloc_huge_page();
+ new_page = alloc_huge_page(vma, address);
if (!new_page) {
page_cache_release(old_page);
@@ -467,7 +471,7 @@
* Use page lock to guard against racing truncation
* before we get page_table_lock.
*/
- page = find_or_alloc_huge_page(mapping, idx,
+ page = find_or_alloc_huge_page(vma, address, mapping, idx,
vma->vm_flags & VM_SHARED);
if (!page)
goto out;