linux-kernel - [PATCH 06/11] blkcg: make sure blkg_lookup() returns %NULL if @q is bypassing

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]

Message-Id: <1334347895-6268-7-git-send-email-tj@kernel.org>
Date:	Fri, 13 Apr 2012 13:11:30 -0700
From:	Tejun Heo <tj@...nel.org>
To:	axboe@...nel.dk
Cc:	vgoyal@...hat.com, ctalbott@...gle.com, rni@...gle.com,
	linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
	containers@...ts.linux-foundation.org, Tejun Heo <tj@...nel.org>
Subject: [PATCH 06/11] blkcg: make sure blkg_lookup() returns %NULL if @q is bypassing

Currently, blkg_lookup() doesn't check @q bypass state.  This patch
updates blk_queue_bypass_start() to do synchronize_rcu() before
returning and updates blkg_lookup() to check blk_queue_bypass() and
return %NULL if bypassing.  This ensures blkg_lookup() returns %NULL
if @q is bypassing.

This is to guarantee that nobody is accessing policy data while @q is
bypassing, which is necessary to allow replacing blkio_cgroup->pd[] in
place on policy [de]activation.

v2: Added more comments explaining bypass guarantees as suggested by
    Vivek.

Signed-off-by: Tejun Heo <tj@...nel.org>
Cc: Vivek Goyal <vgoyal@...hat.com>
---
 block/blk-cgroup.c |   50 +++++++++++++++++++++++++++++++++-----------------
 block/blk-core.c   |    5 ++++-
 2 files changed, 37 insertions(+), 18 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index f6581a0..d6e4555 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -137,6 +137,38 @@ static struct blkio_group *blkg_alloc(struct blkio_cgroup *blkcg,
 	return blkg;
 }
 
+static struct blkio_group *__blkg_lookup(struct blkio_cgroup *blkcg,
+					 struct request_queue *q)
+{
+	struct blkio_group *blkg;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node)
+		if (blkg->q == q)
+			return blkg;
+	return NULL;
+}
+
+/**
+ * blkg_lookup - lookup blkg for the specified blkcg - q pair
+ * @blkcg: blkcg of interest
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for the @blkcg - @q pair.  This function should be called
+ * under RCU read lock and is guaranteed to return %NULL if @q is bypassing
+ * - see blk_queue_bypass_start() for details.
+ */
+struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
+				struct request_queue *q)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (unlikely(blk_queue_bypass(q)))
+		return NULL;
+	return __blkg_lookup(blkcg, q);
+}
+EXPORT_SYMBOL_GPL(blkg_lookup);
+
 struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
 				       struct request_queue *q,
 				       bool for_root)
@@ -150,13 +182,11 @@ struct blkio_group *blkg_lookup_create(struct blkio_cgroup *blkcg,
 	/*
 	 * This could be the first entry point of blkcg implementation and
 	 * we shouldn't allow anything to go through for a bypassing queue.
-	 * The following can be removed if blkg lookup is guaranteed to
-	 * fail on a bypassing queue.
 	 */
 	if (unlikely(blk_queue_bypass(q)) && !for_root)
 		return ERR_PTR(blk_queue_dead(q) ? -EINVAL : -EBUSY);
 
-	blkg = blkg_lookup(blkcg, q);
+	blkg = __blkg_lookup(blkcg, q);
 	if (blkg)
 		return blkg;
 
@@ -185,20 +215,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(blkg_lookup_create);
 
-/* called under rcu_read_lock(). */
-struct blkio_group *blkg_lookup(struct blkio_cgroup *blkcg,
-				struct request_queue *q)
-{
-	struct blkio_group *blkg;
-	struct hlist_node *n;
-
-	hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node)
-		if (blkg->q == q)
-			return blkg;
-	return NULL;
-}
-EXPORT_SYMBOL_GPL(blkg_lookup);
-
 static void blkg_destroy(struct blkio_group *blkg)
 {
 	struct request_queue *q = blkg->q;
diff --git a/block/blk-core.c b/block/blk-core.c
index 991c1d6..a4b3eaf 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -416,7 +416,8 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
  * In bypass mode, only the dispatch FIFO queue of @q is used.  This
  * function makes @q enter bypass mode and drains all requests which were
  * throttled or issued before.  On return, it's guaranteed that no request
- * is being throttled or has ELVPRIV set.
+ * is being throttled or has ELVPRIV set and blk_queue_bypass() %true
+ * inside queue or RCU read lock.
  */
 void blk_queue_bypass_start(struct request_queue *q)
 {
@@ -426,6 +427,8 @@ void blk_queue_bypass_start(struct request_queue *q)
 	spin_unlock_irq(q->queue_lock);
 
 	blk_drain_queue(q, false);
+	/* ensure blk_queue_bypass() is %true inside RCU read lock */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(blk_queue_bypass_start);
 
-- 
1.7.7.3

--
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/