linux-kernel - [RFC][PATCH] memcg: avoid THP split in task migration

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-Id: <1330463552-18473-1-git-send-email-n-horiguchi@ah.jp.nec.com>
Date:	Tue, 28 Feb 2012 16:12:32 -0500
From:	Naoya Horiguchi <n-horiguchi@...jp.nec.com>
To:	linux-mm@...ck.org
Cc:	Andrew Morton <akpm@...ux-foundation.org>,
	Andrea Arcangeli <aarcange@...hat.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>,
	Daisuke Nishimura <nishimura@....nes.nec.co.jp>,
	Hillf Danton <dhillf@...il.com>, linux-kernel@...r.kernel.org,
	Naoya Horiguchi <n-horiguchi@...jp.nec.com>
Subject: [RFC][PATCH] memcg: avoid THP split in task migration

Currently we can't do task migration among memory cgroups without THP split,
which means processes heavily using THP experience large overhead in task
migration. This patch introduce the code for moving charge of THP and makes
THP more valuable.

Signed-off-by: Naoya Horiguchi <n-horiguchi@...jp.nec.com>
Cc: Hillf Danton <dhillf@...il.com>
---
 mm/memcontrol.c |   76 ++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 files changed, 70 insertions(+), 6 deletions(-)

diff --git linux-next-20120228.orig/mm/memcontrol.c linux-next-20120228/mm/memcontrol.c
index c83aeb5..e97c041 100644
--- linux-next-20120228.orig/mm/memcontrol.c
+++ linux-next-20120228/mm/memcontrol.c
@@ -5211,6 +5211,42 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma,
 	return ret;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * We don't consider swapping or file mapped pages because THP does not
+ * support them for now.
+ */
+static int is_target_huge_pmd_for_mc(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t pmd, union mc_target *target)
+{
+	struct page *page = NULL;
+	struct page_cgroup *pc;
+	int ret = 0;
+
+	if (pmd_present(pmd))
+		page = pmd_page(pmd);
+	if (!page)
+		return 0;
+	VM_BUG_ON(!PageHead(page));
+	get_page(page);
+	pc = lookup_page_cgroup(page);
+	if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+		ret = MC_TARGET_PAGE;
+		if (target)
+			target->page = page;
+	}
+	if (!ret || !target)
+		put_page(page);
+	return ret;
+}
+#else
+static inline int is_target_huge_pmd_for_mc(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t pmd, union mc_target *target)
+{
+	return 0;
+}
+#endif
+
 static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 					unsigned long addr, unsigned long end,
 					struct mm_walk *walk)
@@ -5219,7 +5255,13 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		if (is_target_huge_pmd_for_mc(vma, addr, *pmd, NULL))
+			mc.precharge += HPAGE_PMD_NR;
+		spin_unlock(&walk->mm->page_table_lock);
+		cond_resched();
+		return 0;
+	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
@@ -5378,16 +5420,38 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	struct vm_area_struct *vma = walk->private;
 	pte_t *pte;
 	spinlock_t *ptl;
+	int type;
+	union mc_target target;
+	struct page *page;
+	struct page_cgroup *pc;
+
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		if (!mc.precharge)
+			return 0;
+		type = is_target_huge_pmd_for_mc(vma, addr, *pmd, &target);
+		if (type == MC_TARGET_PAGE) {
+			page = target.page;
+			if (!isolate_lru_page(page)) {
+				pc = lookup_page_cgroup(page);
+				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,
+							     pc, mc.from, mc.to,
+							     false)) {
+					mc.precharge -= HPAGE_PMD_NR;
+					mc.moved_charge += HPAGE_PMD_NR;
+				}
+				putback_lru_page(page);
+			}
+			put_page(page);
+		}
+		spin_unlock(&walk->mm->page_table_lock);
+		cond_resched();
+		return 0;
+	}
 
-	split_huge_page_pmd(walk->mm, pmd);
 retry:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
 		pte_t ptent = *(pte++);
-		union mc_target target;
-		int type;
-		struct page *page;
-		struct page_cgroup *pc;
 		swp_entry_t ent;
 
 		if (!mc.precharge)
-- 
1.7.7.6

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/