int nid;
struct page *page = NULL;
struct mempolicy *mpol;
+ nodemask_t *nodemask;
struct zonelist *zonelist = huge_zonelist(vma, address,
- htlb_alloc_mask, &mpol);
- struct zone **z;
-
- for (z = zonelist->zones; *z; z++) {
- nid = zone_to_nid(*z);
- if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&
+ htlb_alloc_mask, &mpol, &nodemask);
+ struct zone *zone;
+ struct zoneref *z;
+
+ 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(&hugepage_freelists[nid])) {
page = list_entry(hugepage_freelists[nid].next,
struct page, lru);
break;
}
}
- mpol_free(mpol); /* unref if mpol !NULL */
+ mpol_put(mpol); /* unref if mpol !NULL */
return page;
}
hugetlb_next_nid = next_nid;
} while (!page && hugetlb_next_nid != start_nid);
+ if (ret)
+ count_vm_event(HTLB_BUDDY_PGALLOC);
+ else
+ count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
+
return ret;
}
*/
nr_huge_pages_node[nid]++;
surplus_huge_pages_node[nid]++;
+ __count_vm_event(HTLB_BUDDY_PGALLOC);
} else {
nr_huge_pages--;
surplus_huge_pages--;
+ __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
}
spin_unlock(&hugetlb_lock);
resv_huge_pages += delta;
ret = 0;
free:
+ /* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+ if ((--needed) < 0)
+ break;
list_del(&page->lru);
- if ((--needed) >= 0)
- enqueue_huge_page(page);
- else {
+ enqueue_huge_page(page);
+ }
+
+ /* Free unnecessary surplus pages to the buddy allocator */
+ if (!list_empty(&surplus_list)) {
+ spin_unlock(&hugetlb_lock);
+ list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
+ list_del(&page->lru);
/*
* The page has a reference count of zero already, so
* call free_huge_page directly instead of using
* unlocked which is safe because free_huge_page takes
* hugetlb_lock before deciding how to free the page.
*/
- spin_unlock(&hugetlb_lock);
free_huge_page(page);
- spin_lock(&hugetlb_lock);
}
+ spin_lock(&hugetlb_lock);
}
return ret;
struct page *page;
unsigned long nr_pages;
+ /*
+ * We want to release as many surplus pages as possible, spread
+ * evenly across all nodes. Iterate across all nodes until we
+ * can no longer free unreserved surplus pages. This occurs when
+ * the nodes with surplus pages have no free pages.
+ */
+ unsigned long remaining_iterations = num_online_nodes();
+
/* Uncommit the reservation */
resv_huge_pages -= unused_resv_pages;
nr_pages = min(unused_resv_pages, surplus_huge_pages);
- while (nr_pages) {
+ while (remaining_iterations-- && nr_pages) {
nid = next_node(nid, node_online_map);
if (nid == MAX_NUMNODES)
nid = first_node(node_online_map);
surplus_huge_pages--;
surplus_huge_pages_node[nid]--;
nr_pages--;
+ remaining_iterations = num_online_nodes();
}
}
}
{
return sprintf(buf,
"Node %d HugePages_Total: %5u\n"
- "Node %d HugePages_Free: %5u\n",
+ "Node %d HugePages_Free: %5u\n"
+ "Node %d HugePages_Surp: %5u\n",
nid, nr_huge_pages_node[nid],
- nid, free_huge_pages_node[nid]);
+ nid, free_huge_pages_node[nid],
+ nid, surplus_huge_pages_node[nid]);
}
/* Return the number pages of memory we physically have, in PAGE_SIZE units. */