summaryrefslogtreecommitdiff
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
authorNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>2010-09-08 10:19:33 +0900
committerAndi Kleen <ak@linux.intel.com>2010-10-08 09:32:44 +0200
commitbf50bab2b34483316162443587b8467952e07730 (patch)
treed142f7427c6b82e11ff9333bf507aa24b9525e3e /mm/hugetlb.c
parent998b4382c1d75a6fd3b0e334dae3ab33bd074d99 (diff)
hugetlb: add allocate function for hugepage migration
We can't use existing hugepage allocation functions to allocate hugepage for page migration, because page migration can happen asynchronously with the running processes and page migration users should call the allocation function with physical addresses (not virtual addresses) as arguments. ChangeLog since v3: - unify alloc_buddy_huge_page() and alloc_buddy_huge_page_node() ChangeLog since v2: - remove unnecessary get/put_mems_allowed() (thanks to David Rientjes) ChangeLog since v1: - add comment on top of alloc_huge_page_no_vma() Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Reviewed-by: Christoph Lameter <cl@linux.com> Signed-off-by: Andi Kleen <ak@linux.intel.com>
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c79
1 files changed, 54 insertions, 25 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bd031a4c738..83fa0c3b6e2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -466,11 +466,23 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
h->free_huge_pages_node[nid]++;
}
+static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+{
+ struct page *page;
+
+ if (list_empty(&h->hugepage_freelists[nid]))
+ return NULL;
+ page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
+ list_del(&page->lru);
+ h->free_huge_pages--;
+ h->free_huge_pages_node[nid]--;
+ return page;
+}
+
static struct page *dequeue_huge_page_vma(struct hstate *h,
struct vm_area_struct *vma,
unsigned long address, int avoid_reserve)
{
- int nid;
struct page *page = NULL;
struct mempolicy *mpol;
nodemask_t *nodemask;
@@ -496,19 +508,13 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
for_each_zone_zonelist_nodemask(zone, z, zonelist,
MAX_NR_ZONES - 1, nodemask) {
- nid = zone_to_nid(zone);
- if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
- !list_empty(&h->hugepage_freelists[nid])) {
- page = list_entry(h->hugepage_freelists[nid].next,
- struct page, lru);
- list_del(&page->lru);
- h->free_huge_pages--;
- h->free_huge_pages_node[nid]--;
-
- if (!avoid_reserve)
- decrement_hugepage_resv_vma(h, vma);
-
- break;
+ if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
+ page = dequeue_huge_page_node(h, zone_to_nid(zone));
+ if (page) {
+ if (!avoid_reserve)
+ decrement_hugepage_resv_vma(h, vma);
+ break;
+ }
}
}
err:
@@ -770,11 +776,10 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
return ret;
}
-static struct page *alloc_buddy_huge_page(struct hstate *h,
- struct vm_area_struct *vma, unsigned long address)
+static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
{
struct page *page;
- unsigned int nid;
+ unsigned int r_nid;
if (h->order >= MAX_ORDER)
return NULL;
@@ -812,9 +817,14 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
}
spin_unlock(&hugetlb_lock);
- page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
- __GFP_REPEAT|__GFP_NOWARN,
- huge_page_order(h));
+ if (nid == NUMA_NO_NODE)
+ page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+ __GFP_REPEAT|__GFP_NOWARN,
+ huge_page_order(h));
+ else
+ page = alloc_pages_exact_node(nid,
+ htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+ __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
if (page && arch_prepare_hugepage(page)) {
__free_pages(page, huge_page_order(h));
@@ -829,13 +839,13 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
*/
put_page_testzero(page);
VM_BUG_ON(page_count(page));
- nid = page_to_nid(page);
+ r_nid = page_to_nid(page);
set_compound_page_dtor(page, free_huge_page);
/*
* We incremented the global counters already
*/
- h->nr_huge_pages_node[nid]++;
- h->surplus_huge_pages_node[nid]++;
+ h->nr_huge_pages_node[r_nid]++;
+ h->surplus_huge_pages_node[r_nid]++;
__count_vm_event(HTLB_BUDDY_PGALLOC);
} else {
h->nr_huge_pages--;
@@ -848,6 +858,25 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
}
/*
+ * This allocation function is useful in the context where vma is irrelevant.
+ * E.g. soft-offlining uses this function because it only cares physical
+ * address of error page.
+ */
+struct page *alloc_huge_page_node(struct hstate *h, int nid)
+{
+ struct page *page;
+
+ spin_lock(&hugetlb_lock);
+ page = dequeue_huge_page_node(h, nid);
+ spin_unlock(&hugetlb_lock);
+
+ if (!page)
+ page = alloc_buddy_huge_page(h, nid);
+
+ return page;
+}
+
+/*
* Increase the hugetlb pool such that it can accomodate a reservation
* of size 'delta'.
*/
@@ -871,7 +900,7 @@ static int gather_surplus_pages(struct hstate *h, int delta)
retry:
spin_unlock(&hugetlb_lock);
for (i = 0; i < needed; i++) {
- page = alloc_buddy_huge_page(h, NULL, 0);
+ page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
if (!page) {
/*
* We were not able to allocate enough pages to
@@ -1052,7 +1081,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
spin_unlock(&hugetlb_lock);
if (!page) {
- page = alloc_buddy_huge_page(h, vma, addr);
+ page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
if (!page) {
hugetlb_put_quota(inode->i_mapping, chg);
return ERR_PTR(-VM_FAULT_SIGBUS);