blktrace: Fix potential deadlock between delete & sysfs ops

The lockdep code had reported the following unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(s_active#228);
                               lock(&bdev->bd_mutex/1);
                               lock(s_active#228);
  lock(&bdev->bd_mutex);

 *** DEADLOCK ***

The deadlock may happen when one task (CPU1) is trying to delete a
partition in a block device and another task (CPU0) is accessing
tracing sysfs file (e.g. /sys/block/dm-1/trace/act_mask) in that
partition.

The s_active isn't an actual lock. It is a reference count (kn->count)
on the sysfs (kernfs) file. Removal of a sysfs file, however, require
a wait until all the references are gone. The reference count is
treated like a rwsem using lockdep instrumentation code.

The fact that a thread is in the sysfs callback method or in the
ioctl call means there is a reference to the opended sysfs or device
file. That should prevent the underlying block structure from being
removed.

Instead of using bd_mutex in the block_device structure, a new
blk_trace_mutex is now added to the request_queue structure to protect
access to the blk_trace structure.

Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

Fix typo in patch subject line, and prune a comment detailing how
the code used to work.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 16 insertions, 6 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index aebe676225e6..048be4aa6024 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -854,6 +854,9 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	kobject_init(&q->kobj, &blk_queue_ktype);
 
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+	mutex_init(&q->blk_trace_mutex);
+#endif
 	mutex_init(&q->sysfs_lock);
 	spin_lock_init(&q->__queue_lock);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 460294bb0fa5..02fa42d24b52 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -551,6 +551,7 @@ struct request_queue {
 	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace	*blk_trace;
+	struct mutex		blk_trace_mutex;
 #endif
 	/*
 	 * for flush operations
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 2a685b45b73b..45a3928544ce 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start)
 }
 EXPORT_SYMBOL_GPL(blk_trace_startstop);
 
+/*
+ * When reading or writing the blktrace sysfs files, the references to the
+ * opened sysfs or device files should prevent the underlying block device
+ * from being removed. So no further delete protection is really needed.
+ */
+
 /**
  * blk_trace_ioctl: - handle the ioctls associated with tracing
  * @bdev:	the block device
@@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	if (!q)
 		return -ENXIO;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	switch (cmd) {
 	case BLKTRACESETUP:
@@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 		break;
 	}
 
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 	return ret;
 }
 
@@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	if (attr == &dev_attr_enable) {
 		ret = sprintf(buf, "%u\n", !!q->blk_trace);
@@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 		ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
 
 out_unlock_bdev:
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 out_bdput:
 	bdput(bdev);
 out:
@@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&bdev->bd_mutex);
+	mutex_lock(&q->blk_trace_mutex);
 
 	if (attr == &dev_attr_enable) {
 		if (value)
@@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 out_unlock_bdev:
-	mutex_unlock(&bdev->bd_mutex);
+	mutex_unlock(&q->blk_trace_mutex);
 out_bdput:
 	bdput(bdev);
 out: