[PATCH 4.14 25/61] xen/xenbus: fix self-deadlock after killing user process

From: Greg Kroah-Hartman
Date: Thu Oct 10 2019 - 04:53:49 EST


From: Juergen Gross <jgross@xxxxxxxx>

commit a8fabb38525c51a094607768bac3ba46b3f4a9d5 upstream.

In case a user process using xenbus has open transactions and is killed
e.g. via ctrl-C the following cleanup of the allocated resources might
result in a deadlock due to trying to end a transaction in the xenbus
worker thread:

[ 2551.474706] INFO: task xenbus:37 blocked for more than 120 seconds.
[ 2551.492215] Tainted: P OE 5.0.0-29-generic #5
[ 2551.510263] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 2551.528585] xenbus D 0 37 2 0x80000080
[ 2551.528590] Call Trace:
[ 2551.528603] __schedule+0x2c0/0x870
[ 2551.528606] ? _cond_resched+0x19/0x40
[ 2551.528632] schedule+0x2c/0x70
[ 2551.528637] xs_talkv+0x1ec/0x2b0
[ 2551.528642] ? wait_woken+0x80/0x80
[ 2551.528645] xs_single+0x53/0x80
[ 2551.528648] xenbus_transaction_end+0x3b/0x70
[ 2551.528651] xenbus_file_free+0x5a/0x160
[ 2551.528654] xenbus_dev_queue_reply+0xc4/0x220
[ 2551.528657] xenbus_thread+0x7de/0x880
[ 2551.528660] ? wait_woken+0x80/0x80
[ 2551.528665] kthread+0x121/0x140
[ 2551.528667] ? xb_read+0x1d0/0x1d0
[ 2551.528670] ? kthread_park+0x90/0x90
[ 2551.528673] ret_from_fork+0x35/0x40

Fix this by doing the cleanup via a workqueue instead.

Reported-by: James Dingwall <james@xxxxxxxxxxxxxx>
Fixes: fd8aa9095a95c ("xen: optimize xenbus driver for multiple concurrent xenstore accesses")
Cc: <stable@xxxxxxxxxxxxxxx> # 4.11
Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
drivers/xen/xenbus/xenbus_dev_frontend.c | 20 ++++++++++++++++++--
1 file changed, 18 insertions(+), 2 deletions(-)

--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -55,6 +55,7 @@
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/miscdevice.h>
+#include <linux/workqueue.h>

#include <xen/xenbus.h>
#include <xen/xen.h>
@@ -113,6 +114,8 @@ struct xenbus_file_priv {
wait_queue_head_t read_waitq;

struct kref kref;
+
+ struct work_struct wq;
};

/* Read out any raw xenbus messages queued up. */
@@ -297,14 +300,14 @@ static void watch_fired(struct xenbus_wa
mutex_unlock(&adap->dev_data->reply_mutex);
}

-static void xenbus_file_free(struct kref *kref)
+static void xenbus_worker(struct work_struct *wq)
{
struct xenbus_file_priv *u;
struct xenbus_transaction_holder *trans, *tmp;
struct watch_adapter *watch, *tmp_watch;
struct read_buffer *rb, *tmp_rb;

- u = container_of(kref, struct xenbus_file_priv, kref);
+ u = container_of(wq, struct xenbus_file_priv, wq);

/*
* No need for locking here because there are no other users,
@@ -330,6 +333,18 @@ static void xenbus_file_free(struct kref
kfree(u);
}

+static void xenbus_file_free(struct kref *kref)
+{
+ struct xenbus_file_priv *u;
+
+ /*
+ * We might be called in xenbus_thread().
+ * Use workqueue to avoid deadlock.
+ */
+ u = container_of(kref, struct xenbus_file_priv, kref);
+ schedule_work(&u->wq);
+}
+
static struct xenbus_transaction_holder *xenbus_get_transaction(
struct xenbus_file_priv *u, uint32_t tx_id)
{
@@ -626,6 +641,7 @@ static int xenbus_file_open(struct inode
INIT_LIST_HEAD(&u->watches);
INIT_LIST_HEAD(&u->read_buffers);
init_waitqueue_head(&u->read_waitq);
+ INIT_WORK(&u->wq, xenbus_worker);

mutex_init(&u->reply_mutex);
mutex_init(&u->msgbuffer_mutex);