linux-kernel - [PATCH v1 1/7] mm/memcontrol: move locking page out of mem_cgroup_move

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

Date:   Wed, 04 Sep 2019 16:53:10 +0300
From:   Konstantin Khlebnikov <khlebnikov@...dex-team.ru>
To:     linux-mm@...ck.org, linux-kernel@...r.kernel.org,
        cgroups@...r.kernel.org
Cc:     Michal Hocko <mhocko@...e.com>, Roman Gushchin <guro@...com>,
        Johannes Weiner <hannes@...xchg.org>
Subject: [PATCH v1 1/7] mm/memcontrol: move locking page out of
 mem_cgroup_move_account

Required for calling mem_cgroup_move_account() for already locked page.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@...dex-team.ru>
---
 mm/memcontrol.c |   64 +++++++++++++++++++++++++++----------------------------
 1 file changed, 31 insertions(+), 33 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9ec5e12486a7..40ddc233e973 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5135,7 +5135,8 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
  * @from: mem_cgroup which the page is moved from.
  * @to:	mem_cgroup which the page is moved to. @from != @to.
  *
- * The caller must make sure the page is not on LRU (isolate_page() is useful.)
+ * The caller must lock the page and make sure it is not on LRU
+ * (isolate_page() is useful.)
  *
  * This function doesn't do "charge" to new cgroup and doesn't do "uncharge"
  * from old cgroup.
@@ -5147,24 +5148,15 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	unsigned long flags;
 	unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1;
-	int ret;
 	bool anon;
 
 	VM_BUG_ON(from == to);
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageLRU(page), page);
 	VM_BUG_ON(compound && !PageTransHuge(page));
 
-	/*
-	 * Prevent mem_cgroup_migrate() from looking at
-	 * page->mem_cgroup of its source page while we change it.
-	 */
-	ret = -EBUSY;
-	if (!trylock_page(page))
-		goto out;
-
-	ret = -EINVAL;
 	if (page->mem_cgroup != from)
-		goto out_unlock;
+		return -EINVAL;
 
 	anon = PageAnon(page);
 
@@ -5204,18 +5196,14 @@ static int mem_cgroup_move_account(struct page *page,
 	page->mem_cgroup = to;
 	spin_unlock_irqrestore(&from->move_lock, flags);
 
-	ret = 0;
-
 	local_irq_disable();
 	mem_cgroup_charge_statistics(to, page, compound, nr_pages);
 	memcg_check_events(to, page);
 	mem_cgroup_charge_statistics(from, page, compound, -nr_pages);
 	memcg_check_events(from, page);
 	local_irq_enable();
-out_unlock:
-	unlock_page(page);
-out:
-	return ret;
+
+	return 0;
 }
 
 /**
@@ -5535,36 +5523,42 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	struct vm_area_struct *vma = walk->vma;
 	pte_t *pte;
 	spinlock_t *ptl;
-	enum mc_target_type target_type;
 	union mc_target target;
 	struct page *page;
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
+		bool device = false;
+
 		if (mc.precharge < HPAGE_PMD_NR) {
 			spin_unlock(ptl);
 			return 0;
 		}
-		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
-		if (target_type == MC_TARGET_PAGE) {
-			page = target.page;
-			if (!isolate_lru_page(page)) {
-				if (!mem_cgroup_move_account(page, true,
-							     mc.from, mc.to)) {
-					mc.precharge -= HPAGE_PMD_NR;
-					mc.moved_charge += HPAGE_PMD_NR;
-				}
-				putback_lru_page(page);
-			}
-			put_page(page);
-		} else if (target_type == MC_TARGET_DEVICE) {
+
+		switch (get_mctgt_type_thp(vma, addr, *pmd, &target)) {
+		case MC_TARGET_DEVICE:
+			device = true;
+			/* fall through */
+		case MC_TARGET_PAGE:
 			page = target.page;
+			if (!trylock_page(page))
+				goto put_huge;
+			if (!device && isolate_lru_page(page))
+				goto unlock_huge;
 			if (!mem_cgroup_move_account(page, true,
 						     mc.from, mc.to)) {
 				mc.precharge -= HPAGE_PMD_NR;
 				mc.moved_charge += HPAGE_PMD_NR;
 			}
+			if (!device)
+				putback_lru_page(page);
+unlock_huge:
+			unlock_page(page);
+put_huge:
 			put_page(page);
+			break;
+		default:
+			break;
 		}
 		spin_unlock(ptl);
 		return 0;
@@ -5596,8 +5590,10 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 			 */
 			if (PageTransCompound(page))
 				goto put;
-			if (!device && isolate_lru_page(page))
+			if (!trylock_page(page))
 				goto put;
+			if (!device && isolate_lru_page(page))
+				goto unlock;
 			if (!mem_cgroup_move_account(page, false,
 						mc.from, mc.to)) {
 				mc.precharge--;
@@ -5606,6 +5602,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 			}
 			if (!device)
 				putback_lru_page(page);
+unlock:
+			unlock_page(page);
 put:			/* get_mctgt_type() gets the page */
 			put_page(page);
 			break;