Support MAP_NORESERVE accounting as part of the new counter.
For each hugepage allocation, at allocation time we check if there is
a reservation for this allocation or not. If there is a reservation for
this allocation, then this allocation was charged at reservation time,
and we don't re-account it. If there is no reserevation for this
allocation, we charge the appropriate hugetlb_cgroup.
The hugetlb_cgroup to uncharge for this allocation is stored in
page[3].private. We use new APIs added in an earlier patch to set this
pointer.
Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
---
mm/hugetlb.c | 26 +++++++++++++++++++++++++-
1 file changed, 25 insertions(+), 1 deletion(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 39eb2fa53a420..3e94f5c2d7cd4 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1367,6 +1367,9 @@ void free_huge_page(struct page *page)
clear_page_huge_active(page);
hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h),
page, false);
+ hugetlb_cgroup_uncharge_page(hstate_index(h), pages_per_huge_page(h),
+ page, true);
+
if (restore_reserve)
h->resv_huge_pages++;
@@ -2189,10 +2192,19 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
gbl_chg = 1;
}
+ /* If this allocation is not consuming a reservation, charge it now.
+ */
+ if (map_chg || avoid_reserve || !vma_resv_map(vma)) {
+ ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h),
+ &h_cg, true);
+ if (ret)
+ goto out_subpool_put;
+ }
+
ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg,
false);
if (ret)
- goto out_subpool_put;
+ goto out_uncharge_cgroup_reservation;
spin_lock(&hugetlb_lock);
/*
@@ -2216,6 +2228,14 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
}
hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page,
false);
+ /* If allocation is not consuming a reservation, also store the
+ * hugetlb_cgroup pointer on the page.
+ */
+ if (!vma_resv_map(vma) || map_chg || avoid_reserve) {
+ hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg,
+ page, true);
+ }
+
spin_unlock(&hugetlb_lock);
set_page_private(page, (unsigned long)spool);
@@ -2241,6 +2261,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
out_uncharge_cgroup:
hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg,
false);
+out_uncharge_cgroup_reservation:
+ if (map_chg || avoid_reserve || !vma_resv_map(vma))
+ hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h),
+ h_cg, true);
out_subpool_put:
if (map_chg || avoid_reserve)
hugepage_subpool_put_pages(spool, 1);
--
2.24.1.735.g03f4e72817-goog
