| Message ID | 20191217231615.164161-6-almasrymina@google.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [v9,1/8] hugetlb_cgroup: Add hugetlb_cgroup reservation counter | expand |
On Tue, 17 Dec 2019, Mina Almasry wrote: > 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)) { These conditions are checked three times in this function, maybe better set a bool on the stack and use it throughout the function to guarantee it remains consistent? bool deferred_reserve = !vma_resv_map(vma) || map_chg || avoid_reserve; > + 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 >
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);
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@google.com> --- mm/hugetlb.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) -- 2.24.1.735.g03f4e72817-goog