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, a new global blktrace mutex is now used
to protect against concurrent access, creation and destruction of the
blk_trace structure that is used only in the blktrace.c file. As
blktrace files will not be frequently accessed, using a global mutex
should not cause any performance problem.
Signed-off-by: Waiman Long <[email protected]>
---
v4:
- Use blktrace_mutex in blk_trace_ioctl() as well.
v3:
- Use a global blktrace_mutex to serialize sysfs attribute accesses
instead of the bd_mutex.
v2:
- Use READ_ONCE() and smp_store_mb() to read and write bd_deleting.
- Check for signal in the mutex_trylock loops.
- Use usleep() instead of schedule() for RT tasks.
kernel/trace/blktrace.c | 23 +++++++++++++++++------
1 file changed, 17 insertions(+), 6 deletions(-)
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index bc364f8..ec5a919 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -624,6 +624,17 @@ int blk_trace_startstop(struct request_queue *q, int start)
}
EXPORT_SYMBOL_GPL(blk_trace_startstop);
+/*
+ * The bd_mutex was used previously for protecting blk_trace structure.
+ * That could lead to deadlock with concurrent block device deletion and
+ * sysfs access. So a global blktrace_mutex is now used instead for
+ * protecting the blk_trace structure.
+ *
+ * The references to the opened sysfs or device files should prevent the
+ * underlying block device from being removed.
+ */
+static DEFINE_MUTEX(blktrace_mutex);
+
/**
* blk_trace_ioctl: - handle the ioctls associated with tracing
* @bdev: the block device
@@ -641,7 +652,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned
cmd, char __user *arg)
if (!q)
return -ENXIO;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&blktrace_mutex);
switch (cmd) {
case BLKTRACESETUP:
@@ -667,7 +678,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned
cmd, char __user *arg)
break;
}
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&blktrace_mutex);
return ret;
}
@@ -1622,7 +1633,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device
*dev,
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&blktrace_mutex);
if (attr == &dev_attr_enable) {
ret = sprintf(buf, "%u\n", !!q->blk_trace);
@@ -1641,7 +1652,7 @@ 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(&blktrace_mutex);
out_bdput:
bdput(bdev);
out:
@@ -1683,7 +1694,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device
*dev,
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&blktrace_mutex);
if (attr == &dev_attr_enable) {
if (value)
@@ -1709,7 +1720,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device
*dev,
}
out_unlock_bdev:
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&blktrace_mutex);
out_bdput:
bdput(bdev);
out:
--
1.8.3.1
