linux-kernel - [PATCH 06/50] mm: Prevent parallel splits during THP 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 for Android: free password hash cracker in your pocket

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

Message-Id: <1378805550-29949-7-git-send-email-mgorman@suse.de>
Date:	Tue, 10 Sep 2013 10:31:46 +0100
From:	Mel Gorman <mgorman@...e.de>
To:	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Rik van Riel <riel@...hat.com>
Cc:	Srikar Dronamraju <srikar@...ux.vnet.ibm.com>,
	Ingo Molnar <mingo@...nel.org>,
	Andrea Arcangeli <aarcange@...hat.com>,
	Johannes Weiner <hannes@...xchg.org>,
	Linux-MM <linux-mm@...ck.org>,
	LKML <linux-kernel@...r.kernel.org>, Mel Gorman <mgorman@...e.de>
Subject: [PATCH 06/50] mm: Prevent parallel splits during THP migration

THP migrations are serialised by the page lock but on its own that does
not prevent THP splits. If the page is split during THP migration then
the pmd_same checks will prevent page table corruption but the unlock page
and other fix-ups potentially will cause corruption. This patch takes the
anon_vma lock to prevent parallel splits during migration.

Signed-off-by: Mel Gorman <mgorman@...e.de>
---
 mm/huge_memory.c | 43 +++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 14 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d0a3fce..981d8a2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1290,18 +1290,18 @@ out:
 int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp)
 {
+	struct anon_vma *anon_vma = NULL;
 	struct page *page;
 	unsigned long haddr = addr & HPAGE_PMD_MASK;
 	int target_nid;
 	int current_nid = -1;
-	bool migrated;
+	bool migrated, page_locked;
 
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
 	page = pmd_page(pmd);
-	get_page(page);
 	current_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
 	if (current_nid == numa_node_id())
@@ -1311,12 +1311,29 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * Acquire the page lock to serialise THP migrations but avoid dropping
 	 * page_table_lock if at all possible
 	 */
-	if (trylock_page(page))
-		goto got_lock;
+	page_locked = trylock_page(page);
+	target_nid = mpol_misplaced(page, vma, haddr);
+	if (target_nid == -1) {
+		/* If the page was locked, there are no parallel migrations */
+		if (page_locked) {
+			unlock_page(page);
+			goto clear_pmdnuma;
+		}
 
-	/* Serialise against migrationa and check placement check placement */
+		/* Otherwise wait for potential migrations to complete */
+		spin_unlock(&mm->page_table_lock);
+		wait_on_page_locked(page);
+		goto check_same;
+	}
+
+	/* Page is misplaced, serialise migrations and parallel THP splits */
+	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	lock_page(page);
+	if (!page_locked) {
+		lock_page(page);
+		page_locked = true;
+	}
+	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PMD did not change while page_table_lock was released */
 	spin_lock(&mm->page_table_lock);
@@ -1326,14 +1343,6 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_unlock;
 	}
 
-got_lock:
-	target_nid = mpol_misplaced(page, vma, haddr);
-	if (target_nid == -1) {
-		unlock_page(page);
-		put_page(page);
-		goto clear_pmdnuma;
-	}
-
 	/* Migrate the THP to the requested node */
 	spin_unlock(&mm->page_table_lock);
 	migrated = migrate_misplaced_transhuge_page(mm, vma,
@@ -1342,6 +1351,8 @@ got_lock:
 		goto check_same;
 
 	task_numa_fault(target_nid, HPAGE_PMD_NR, true);
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
 	return 0;
 
 check_same:
@@ -1358,6 +1369,10 @@ clear_pmdnuma:
 	update_mmu_cache_pmd(vma, addr, pmdp);
 out_unlock:
 	spin_unlock(&mm->page_table_lock);
+
+	if (anon_vma)
+		page_unlock_anon_vma_read(anon_vma);
+
 	if (current_nid != -1)
 		task_numa_fault(current_nid, HPAGE_PMD_NR, false);
 	return 0;
-- 
1.8.1.4

--
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/