#include <linux/hugetlb_cgroup.h>
#include <linux/node.h>
#include <linux/userfaultfd_k.h>
+#include <linux/page_owner.h>
#include "internal.h"
int hugetlb_max_hstate __read_mostly;
ClearPagePrivate(&page[1]);
}
+/*
+ * Internal hugetlb specific page flag. Do not use outside of the hugetlb
+ * code
+ */
+static inline bool PageHugeTemporary(struct page *page)
+{
+ if (!PageHuge(page))
+ return false;
+
+ return (unsigned long)page[2].mapping == -1U;
+}
+
+static inline void SetPageHugeTemporary(struct page *page)
+{
+ page[2].mapping = (void *)-1U;
+}
+
+static inline void ClearPageHugeTemporary(struct page *page)
+{
+ page[2].mapping = NULL;
+}
+
void free_huge_page(struct page *page)
{
/*
if (restore_reserve)
h->resv_huge_pages++;
- if (h->surplus_huge_pages_node[nid]) {
+ if (PageHugeTemporary(page)) {
+ list_del(&page->lru);
+ ClearPageHugeTemporary(page);
+ update_and_free_page(h, page);
+ } else if (h->surplus_huge_pages_node[nid]) {
/* remove the page from active list */
list_del(&page->lru);
update_and_free_page(h, page);
return rc;
}
-static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask,
+/*
+ * Allocates a fresh surplus page from the page allocator.
+ */
+static struct page *__alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nmask)
{
struct page *page;
return page;
}
+static struct page *__alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
+ int nid, nodemask_t *nmask)
+{
+ struct page *page;
+
+ if (hstate_is_gigantic(h))
+ return NULL;
+
+ page = __hugetlb_alloc_buddy_huge_page(h, gfp_mask, nid, nmask);
+ if (!page)
+ return NULL;
+
+ /*
+ * We do not account these pages as surplus because they are only
+ * temporary and will be released properly on the last reference
+ */
+ prep_new_huge_page(h, page, page_to_nid(page));
+ SetPageHugeTemporary(page);
+
+ return page;
+}
+
/*
* Use the VMA's mpolicy to allocate a huge page from the buddy.
*/
nodemask_t *nodemask;
nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
- page = __alloc_buddy_huge_page(h, gfp_mask, nid, nodemask);
+ page = __alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
mpol_cond_put(mpol);
return page;
}
-/*
- * 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.
- */
+/* page migration callback function */
struct page *alloc_huge_page_node(struct hstate *h, int nid)
{
gfp_t gfp_mask = htlb_alloc_mask(h);
spin_unlock(&hugetlb_lock);
if (!page)
- page = __alloc_buddy_huge_page(h, gfp_mask, nid, NULL);
+ page = __alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
return page;
}
-
+/* page migration callback function */
struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask)
{
}
spin_unlock(&hugetlb_lock);
- /* No reservations, try to overcommit */
-
- return __alloc_buddy_huge_page(h, gfp_mask, preferred_nid, nmask);
+ return __alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask);
}
/*
retry:
spin_unlock(&hugetlb_lock);
for (i = 0; i < needed; i++) {
- page = __alloc_buddy_huge_page(h, htlb_alloc_mask(h),
+ page = __alloc_surplus_huge_page(h, htlb_alloc_mask(h),
NUMA_NO_NODE, NULL);
if (!page) {
alloc_ok = false;
* First take pages out of surplus state. Then make up the
* remaining difference by allocating fresh huge pages.
*
- * We might race with __alloc_buddy_huge_page() here and be unable
+ * We might race with __alloc_surplus_huge_page() here and be unable
* to convert a surplus huge page to a normal huge page. That is
* not critical, though, it just means the overall size of the
* pool might be one hugepage larger than it needs to be, but
* By placing pages into the surplus state independent of the
* overcommit value, we are allowing the surplus pool size to
* exceed overcommit. There are few sane options here. Since
- * __alloc_buddy_huge_page() is checking the global counter,
+ * __alloc_surplus_huge_page() is checking the global counter,
* though, we'll note that we're not allowed to exceed surplus
* and won't grow the pool anywhere else. Not until one of the
* sysctls are changed, or the surplus pages go out of use.
spin_unlock(&hugetlb_lock);
put_page(page);
}
+
+void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason)
+{
+ struct hstate *h = page_hstate(oldpage);
+
+ hugetlb_cgroup_migrate(oldpage, newpage);
+ set_page_owner_migrate_reason(newpage, reason);
+
+ /*
+ * transfer temporary state of the new huge page. This is
+ * reverse to other transitions because the newpage is going to
+ * be final while the old one will be freed so it takes over
+ * the temporary status.
+ *
+ * Also note that we have to transfer the per-node surplus state
+ * here as well otherwise the global surplus count will not match
+ * the per-node's.
+ */
+ if (PageHugeTemporary(newpage)) {
+ int old_nid = page_to_nid(oldpage);
+ int new_nid = page_to_nid(newpage);
+
+ SetPageHugeTemporary(oldpage);
+ ClearPageHugeTemporary(newpage);
+
+ spin_lock(&hugetlb_lock);
+ if (h->surplus_huge_pages_node[old_nid]) {
+ h->surplus_huge_pages_node[old_nid]--;
+ h->surplus_huge_pages_node[new_nid]++;
+ }
+ spin_unlock(&hugetlb_lock);
+ }
+}
projects / users / jedix / linux-maple.git / commitdiff