Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Mon,  3 Feb 2020 15:22:45 -0800
In-Reply-To: <20200203232248.104733-1-almasrymina@google.com>
Message-Id: <20200203232248.104733-6-almasrymina@google.com>
Mime-Version: 1.0
References: <20200203232248.104733-1-almasrymina@google.com>
Subject: [PATCH v11 6/9] hugetlb_cgroup: support noreserve mappings
From:   Mina Almasry <almasrymina@google.com>
To:     mike.kravetz@oracle.com
Cc:     shuah@kernel.org, almasrymina@google.com, rientjes@google.com,
        shakeelb@google.com, gthelen@google.com, akpm@linux-foundation.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-kselftest@vger.kernel.org, cgroups@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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>

---

Changes in v10:
- Refactored deferred_reserve check.

---
 mm/hugetlb.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 33818ccaf7e89..ec0b55ea1506e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1339,6 +1339,9 @@ static 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++;

@@ -2172,6 +2175,7 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 	long gbl_chg;
 	int ret, idx;
 	struct hugetlb_cgroup *h_cg;
+	bool deferred_reserve;

 	idx = hstate_index(h);
 	/*
@@ -2209,10 +2213,20 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 			gbl_chg = 1;
 	}

+	/* If this allocation is not consuming a reservation, charge it now.
+	 */
+	deferred_reserve = map_chg || avoid_reserve || !vma_resv_map(vma);
+	if (deferred_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);
 	/*
@@ -2236,6 +2250,14 @@ 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 (deferred_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);
@@ -2261,6 +2283,10 @@ 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 (deferred_reserve)
+		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);
--
2.25.0.341.g760bfbb309-goog