linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Joonsoo Kim <iamjoonsoo.kim@lge.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Rik van Riel <riel@redhat.com>, Mel Gorman <mgorman@suse.de>,
	Michal Hocko <mhocko@suse.cz>,
	"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Hugh Dickins <hughd@google.com>,
	Davidlohr Bueso <davidlohr.bueso@hp.com>,
	David Gibson <david@gibson.dropbear.id.au>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	Joonsoo Kim <js1304@gmail.com>,
	Wanpeng Li <liwanp@linux.vnet.ibm.com>,
	Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
	Hillf Danton <dhillf@gmail.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>
Subject: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock
Date: Mon, 29 Jul 2013 14:31:56 +0900	[thread overview]
Message-ID: <1375075929-6119-6-git-send-email-iamjoonsoo.kim@lge.com> (raw)
In-Reply-To: <1375075929-6119-1-git-send-email-iamjoonsoo.kim@lge.com>

There is a race condition if we map a same file on different processes.
Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex.
When we do mmap, we don't grab a hugetlb_instantiation_mutex, but,
grab a mmap_sem. This doesn't prevent other process to modify region
structure, so it can be modified by two processes concurrently.

To solve this, I introduce a lock to resv_map and make region manipulation
function grab a lock before they do actual work. This makes region
tracking safe.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2677c07..e29e28f 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -26,6 +26,7 @@ struct hugepage_subpool {
 
 struct resv_map {
 	struct kref refs;
+	spinlock_t lock;
 	struct list_head regions;
 };
 extern struct resv_map *resv_map_alloc(void);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 24c0111..bf2ee11 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -134,15 +134,8 @@ static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
  * Region tracking -- allows tracking of reservations and instantiated pages
  *                    across the pages in a mapping.
  *
- * The region data structures are protected by a combination of the mmap_sem
- * and the hugetlb_instantiation_mutex.  To access or modify a region the caller
- * must either hold the mmap_sem for write, or the mmap_sem for read and
- * the hugetlb_instantiation_mutex:
- *
- *	down_write(&mm->mmap_sem);
- * or
- *	down_read(&mm->mmap_sem);
- *	mutex_lock(&hugetlb_instantiation_mutex);
+ * The region data structures are embedded into a resv_map and
+ * protected by a resv_map's lock
  */
 struct file_region {
 	struct list_head link;
@@ -155,6 +148,7 @@ static long region_add(struct resv_map *resv, long f, long t)
 	struct list_head *head = &resv->regions;
 	struct file_region *rg, *nrg, *trg;
 
+	spin_lock(&resv->lock);
 	/* Locate the region we are either in or before. */
 	list_for_each_entry(rg, head, link)
 		if (f <= rg->to)
@@ -184,6 +178,7 @@ static long region_add(struct resv_map *resv, long f, long t)
 	}
 	nrg->from = f;
 	nrg->to = t;
+	spin_unlock(&resv->lock);
 	return 0;
 }
 
@@ -193,6 +188,7 @@ static long region_chg(struct resv_map *resv, long f, long t)
 	struct file_region *rg, *nrg;
 	long chg = 0;
 
+	spin_lock(&resv->lock);
 	/* Locate the region we are before or in. */
 	list_for_each_entry(rg, head, link)
 		if (f <= rg->to)
@@ -203,14 +199,18 @@ static long region_chg(struct resv_map *resv, long f, long t)
 	 * size such that we can guarantee to record the reservation. */
 	if (&rg->link == head || t < rg->from) {
 		nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
-		if (!nrg)
-			return -ENOMEM;
+		if (!nrg) {
+			chg = -ENOMEM;
+			goto out;
+		}
+
 		nrg->from = f;
 		nrg->to   = f;
 		INIT_LIST_HEAD(&nrg->link);
 		list_add(&nrg->link, rg->link.prev);
 
-		return t - f;
+		chg = t - f;
+		goto out;
 	}
 
 	/* Round our left edge to the current segment if it encloses us. */
@@ -223,7 +223,7 @@ static long region_chg(struct resv_map *resv, long f, long t)
 		if (&rg->link == head)
 			break;
 		if (rg->from > t)
-			return chg;
+			goto out;
 
 		/* We overlap with this area, if it extends further than
 		 * us then we must extend ourselves.  Account for its
@@ -234,6 +234,9 @@ static long region_chg(struct resv_map *resv, long f, long t)
 		}
 		chg -= rg->to - rg->from;
 	}
+
+out:
+	spin_unlock(&resv->lock);
 	return chg;
 }
 
@@ -243,12 +246,13 @@ static long region_truncate(struct resv_map *resv, long end)
 	struct file_region *rg, *trg;
 	long chg = 0;
 
+	spin_lock(&resv->lock);
 	/* Locate the region we are either in or before. */
 	list_for_each_entry(rg, head, link)
 		if (end <= rg->to)
 			break;
 	if (&rg->link == head)
-		return 0;
+		goto out;
 
 	/* If we are in the middle of a region then adjust it. */
 	if (end > rg->from) {
@@ -265,6 +269,9 @@ static long region_truncate(struct resv_map *resv, long end)
 		list_del(&rg->link);
 		kfree(rg);
 	}
+
+out:
+	spin_unlock(&resv->lock);
 	return chg;
 }
 
@@ -274,6 +281,7 @@ static long region_count(struct resv_map *resv, long f, long t)
 	struct file_region *rg;
 	long chg = 0;
 
+	spin_lock(&resv->lock);
 	/* Locate each segment we overlap with, and count that overlap. */
 	list_for_each_entry(rg, head, link) {
 		long seg_from;
@@ -289,6 +297,7 @@ static long region_count(struct resv_map *resv, long f, long t)
 
 		chg += seg_to - seg_from;
 	}
+	spin_unlock(&resv->lock);
 
 	return chg;
 }
@@ -386,6 +395,7 @@ struct resv_map *resv_map_alloc(void)
 		return NULL;
 
 	kref_init(&resv_map->refs);
+	spin_lock_init(&resv_map->lock);
 	INIT_LIST_HEAD(&resv_map->regions);
 
 	return resv_map;
-- 
1.7.9.5

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2013-07-29  5:32 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-07-29  5:31 [PATCH 00/18] mm, hugetlb: remove a hugetlb_instantiation_mutex Joonsoo Kim
2013-07-29  5:31 ` [PATCH 01/18] mm, hugetlb: protect reserved pages when softofflining requests the pages Joonsoo Kim
2013-07-29  7:24   ` Hillf Danton
2013-07-31  2:27     ` Joonsoo Kim
2013-07-31  2:49       ` Hillf Danton
2013-07-31  4:41         ` Joonsoo Kim
2013-07-31  6:21           ` Hillf Danton
2013-07-31  6:37             ` Joonsoo Kim
2013-07-31 15:25               ` Hillf Danton
2013-08-01  6:07                 ` Joonsoo Kim
2013-08-01 16:17                 ` Aneesh Kumar K.V
2013-08-04  5:10                   ` Hillf Danton
2013-08-05  5:17                     ` Aneesh Kumar K.V
2013-07-30 16:49   ` Aneesh Kumar K.V
2013-07-29  5:31 ` [PATCH 02/18] mm, hugetlb: change variable name reservations to resv Joonsoo Kim
2013-07-30 16:50   ` Aneesh Kumar K.V
2013-07-29  5:31 ` [PATCH 03/18] mm, hugetlb: unify region structure handling Joonsoo Kim
2013-07-30 17:27   ` Aneesh Kumar K.V
2013-07-31  2:36     ` Joonsoo Kim
2013-07-29  5:31 ` [PATCH 04/18] mm, hugetlb: region manipulation functions take resv_map rather list_head Joonsoo Kim
2013-07-29  5:31 ` Joonsoo Kim [this message]
2013-07-29  8:58   ` [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock Hillf Danton
2013-07-31  2:41     ` Joonsoo Kim
2013-07-29 18:53   ` Davidlohr Bueso
2013-07-31  2:43     ` Joonsoo Kim
2013-07-29  5:31 ` [PATCH 06/18] mm, hugetlb: remove vma_need_reservation() Joonsoo Kim
2013-07-29 17:52   ` Naoya Horiguchi
2013-07-31  4:53     ` Joonsoo Kim
2013-07-30 17:49   ` Aneesh Kumar K.V
2013-07-31  4:56     ` Joonsoo Kim
2013-07-29  5:31 ` [PATCH 07/18] mm, hugetlb: pass has_reserve to dequeue_huge_page_vma() Joonsoo Kim
2013-07-29  5:31 ` [PATCH 08/18] mm, hugetlb: do hugepage_subpool_get_pages() when avoid_reserve Joonsoo Kim
2013-07-29 18:05   ` Naoya Horiguchi
2013-07-31  5:02     ` Joonsoo Kim
2013-07-31 20:55       ` Naoya Horiguchi
2013-07-29  5:32 ` [PATCH 09/18] mm, hugetlb: unify has_reserve and avoid_reserve to use_reserve Joonsoo Kim
2013-07-29  5:32 ` [PATCH 10/18] mm, hugetlb: call vma_has_reserve() before entering alloc_huge_page() Joonsoo Kim
2013-07-29 18:27   ` Naoya Horiguchi
2013-07-31  5:06     ` Joonsoo Kim
2013-07-29  5:32 ` [PATCH 11/18] mm, hugetlb: move down outside_reserve check Joonsoo Kim
2013-07-29 18:39   ` Naoya Horiguchi
2013-07-31  5:08     ` Joonsoo Kim
2013-07-31 20:46       ` Naoya Horiguchi
2013-07-29  5:32 ` [PATCH 12/18] mm, hugetlb: remove a check for return value of alloc_huge_page() Joonsoo Kim
2013-07-29  5:32 ` [PATCH 13/18] mm, hugetlb: grab a page_table_lock after page_cache_release Joonsoo Kim
2013-07-29 18:50   ` Naoya Horiguchi
2013-07-29  5:32 ` [PATCH 14/18] mm, hugetlb: clean-up error handling in hugetlb_cow() Joonsoo Kim
2013-07-29  5:32 ` [PATCH 15/18] mm, hugetlb: move up anon_vma_prepare() Joonsoo Kim
2013-07-29 19:05   ` Naoya Horiguchi
2013-07-29 19:19     ` Naoya Horiguchi
2013-07-31  5:12       ` Joonsoo Kim
2013-07-31 16:43         ` Naoya Horiguchi
2013-07-29  5:32 ` [PATCH 16/18] mm, hugetlb: return a reserved page to a reserved pool if failed Joonsoo Kim
2013-07-29 20:19   ` Naoya Horiguchi
2013-07-31  5:21     ` Joonsoo Kim
2013-07-29  5:32 ` [PATCH 17/18] mm, hugetlb: retry if we fail to allocate a hugepage with use_reserve Joonsoo Kim
2013-07-29  7:28   ` David Gibson
2013-07-31  5:37     ` Joonsoo Kim
2013-08-03 10:43       ` David Gibson
2013-08-05  7:36         ` Joonsoo Kim
2013-08-07  0:18           ` Davidlohr Bueso
2013-08-07  1:03             ` David Gibson
2013-08-07  1:38               ` Davidlohr Bueso
2013-08-07  9:18                 ` Joonsoo Kim
2013-08-09  0:02                   ` David Gibson
2013-08-09  9:37                     ` Joonsoo Kim
2013-07-29  5:32 ` [PATCH 18/18] mm, hugetlb: remove a hugetlb_instantiation_mutex Joonsoo Kim

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1375075929-6119-6-git-send-email-iamjoonsoo.kim@lge.com \
    --to=iamjoonsoo.kim@lge.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=david@gibson.dropbear.id.au \
    --cc=davidlohr.bueso@hp.com \
    --cc=dhillf@gmail.com \
    --cc=hughd@google.com \
    --cc=js1304@gmail.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=liwanp@linux.vnet.ibm.com \
    --cc=mgorman@suse.de \
    --cc=mhocko@suse.cz \
    --cc=n-horiguchi@ah.jp.nec.com \
    --cc=riel@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox