linux-kernel - [PATCH v2 7/7] memcg: supports movement of surplus hugepages statistics

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <caab17ea-840e-c9c3-4da1-e99050c4256d@ascade.co.jp>
Date:   Fri, 18 May 2018 13:41:15 +0900
From:   TSUKADA Koutaro <tsukada@...ade.co.jp>
To:     Johannes Weiner <hannes@...xchg.org>,
        Michal Hocko <mhocko@...nel.org>,
        Vladimir Davydov <vdavydov.dev@...il.com>,
        Jonathan Corbet <corbet@....net>,
        "Luis R. Rodriguez" <mcgrof@...nel.org>,
        Kees Cook <keescook@...omium.org>
Cc:     Andrew Morton <akpm@...ux-foundation.org>,
        Roman Gushchin <guro@...com>,
        David Rientjes <rientjes@...gle.com>,
        Mike Kravetz <mike.kravetz@...cle.com>,
        "Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>,
        Naoya Horiguchi <n-horiguchi@...jp.nec.com>,
        Anshuman Khandual <khandual@...ux.vnet.ibm.com>,
        Marc-Andre Lureau <marcandre.lureau@...hat.com>,
        Punit Agrawal <punit.agrawal@....com>,
        Dan Williams <dan.j.williams@...el.com>,
        Vlastimil Babka <vbabka@...e.cz>, linux-doc@...r.kernel.org,
        linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
        linux-mm@...ck.org, cgroups@...r.kernel.org, tsukada@...ade.co.jp
Subject: [PATCH v2 7/7] memcg: supports movement of surplus hugepages
 statistics

When the task that charged surplus hugepages moves memory cgroup, it
updates the statistical information correctly.

Signed-off-by: TSUKADA Koutaro <tsukada@...ade.co.jp>
---
 memcontrol.c |   99 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 99 insertions(+)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a8f1ff8..63f0922 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4698,12 +4698,110 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	return 0;
 }

+#ifdef CONFIG_HUGETLB_PAGE
+static enum mc_target_type get_mctgt_type_hugetlb(struct vm_area_struct *vma,
+			unsigned long addr, pte_t *pte, union mc_target *target)
+{
+	struct page *page = NULL;
+	pte_t entry;
+	enum mc_target_type ret = MC_TARGET_NONE;
+
+	if (!(mc.flags & MOVE_ANON))
+		return ret;
+
+	entry = huge_ptep_get(pte);
+	if (!pte_present(entry))
+		return ret;
+
+	page = pte_page(entry);
+	VM_BUG_ON_PAGE(!page || !PageHead(page), page);
+	if (likely(!PageSurplusCharge(page)))
+		return ret;
+	if (page->mem_cgroup == mc.from) {
+		ret = MC_TARGET_PAGE;
+		if (target) {
+			get_page(page);
+			target->page = page;
+		}
+	}
+
+	return ret;
+}
+
+static int hugetlb_count_precharge_pte_range(pte_t *pte, unsigned long hmask,
+					unsigned long addr, unsigned long end,
+					struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+	struct mm_struct *mm = walk->mm;
+	spinlock_t *ptl;
+	union mc_target target;
+
+	ptl = huge_pte_lock(hstate_vma(vma), mm, pte);
+	if (get_mctgt_type_hugetlb(vma, addr, pte, &target) == MC_TARGET_PAGE) {
+		mc.precharge += (1 << compound_order(target.page));
+		put_page(target.page);
+	}
+	spin_unlock(ptl);
+
+	return 0;
+}
+
+static int hugetlb_move_charge_pte_range(pte_t *pte, unsigned long hmask,
+					unsigned long addr, unsigned long end,
+					struct mm_walk *walk)
+{
+	struct vm_area_struct *vma = walk->vma;
+	struct mm_struct *mm = walk->mm;
+	spinlock_t *ptl;
+	enum mc_target_type target_type;
+	union mc_target target;
+	struct page *page;
+	unsigned long nr_pages;
+
+	ptl = huge_pte_lock(hstate_vma(vma), mm, pte);
+	target_type = get_mctgt_type_hugetlb(vma, addr, pte, &target);
+	if (target_type == MC_TARGET_PAGE) {
+		page = target.page;
+		nr_pages = (1 << compound_order(page));
+		if (mc.precharge < nr_pages) {
+			put_page(page);
+			goto unlock;
+		}
+		if (!mem_cgroup_move_account(page, true, mc.from, mc.to)) {
+			mc.precharge -= nr_pages;
+			mc.moved_charge += nr_pages;
+		}
+		put_page(page);
+	}
+unlock:
+	spin_unlock(ptl);
+
+	return 0;
+}
+#else
+static int hugetlb_count_precharge_pte_range(pte_t *pte, unsigned long hmask,
+					unsigned long addr, unsigned long end,
+					struct mm_walk *walk)
+{
+	return 0;
+}
+
+static int hugetlb_move_charge_pte_range(pte_t *pte, unsigned long hmask,
+					unsigned long addr, unsigned long end,
+					struct mm_walk *walk)
+{
+	return 0;
+}
+#endif
+
 static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
 {
 	unsigned long precharge;

 	struct mm_walk mem_cgroup_count_precharge_walk = {
 		.pmd_entry = mem_cgroup_count_precharge_pte_range,
+		.hugetlb_entry = hugetlb_count_precharge_pte_range,
 		.mm = mm,
 	};
 	down_read(&mm->mmap_sem);
@@ -4981,6 +5079,7 @@ static void mem_cgroup_move_charge(void)
 {
 	struct mm_walk mem_cgroup_move_charge_walk = {
 		.pmd_entry = mem_cgroup_move_charge_pte_range,
+		.hugetlb_entry = hugetlb_move_charge_pte_range,
 		.mm = mc.mm,
 	};

-- 
Tsukada