linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Andrea Righi <andrea.righi@canonical.com>
To: Boris Ostrovsky <boris.ostrovsky@oracle.com>,
	Juergen Gross <jgross@suse.com>,
	Stefano Stabellini <sstabellini@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	xen-devel@lists.xenproject.org, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH] xen-netfront: fix potential deadlock in xennet_remove()
Date: Wed, 22 Jul 2020 08:52:11 +0200	[thread overview]
Message-ID: <20200722065211.GA841369@xps-13> (raw)

There's a potential race in xennet_remove(); this is what the driver is
doing upon unregistering a network device:

  1. state = read bus state
  2. if state is not "Closed":
  3.    request to set state to "Closing"
  4.    wait for state to be set to "Closing"
  5.    request to set state to "Closed"
  6.    wait for state to be set to "Closed"

If the state changes to "Closed" immediately after step 1 we are stuck
forever in step 4, because the state will never go back from "Closed" to
"Closing".

Make sure to check also for state == "Closed" in step 4 to prevent the
deadlock.

Also add a 5 sec timeout any time we wait for the bus state to change,
to avoid getting stuck forever in wait_event() and add a debug message
to help tracking down potential similar issues.

Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
---
 drivers/net/xen-netfront.c | 79 +++++++++++++++++++++++++++-----------
 1 file changed, 57 insertions(+), 22 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 482c6c8b0fb7..e09caba93dd9 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -63,6 +63,8 @@ module_param_named(max_queues, xennet_max_queues, uint, 0644);
 MODULE_PARM_DESC(max_queues,
 		 "Maximum number of queues per virtual interface");
 
+#define XENNET_TIMEOUT  (5 * HZ)
+
 static const struct ethtool_ops xennet_ethtool_ops;
 
 struct netfront_cb {
@@ -1334,12 +1336,20 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
 
 	netif_carrier_off(netdev);
 
-	xenbus_switch_state(dev, XenbusStateInitialising);
-	wait_event(module_wq,
-		   xenbus_read_driver_state(dev->otherend) !=
-		   XenbusStateClosed &&
-		   xenbus_read_driver_state(dev->otherend) !=
-		   XenbusStateUnknown);
+	do {
+		dev_dbg(&dev->dev,
+			"%s: switching to XenbusStateInitialising\n",
+			dev->nodename);
+		xenbus_switch_state(dev, XenbusStateInitialising);
+		err = wait_event_timeout(module_wq,
+				 xenbus_read_driver_state(dev->otherend) !=
+				 XenbusStateClosed &&
+				 xenbus_read_driver_state(dev->otherend) !=
+				 XenbusStateUnknown, XENNET_TIMEOUT);
+		dev_dbg(&dev->dev, "%s: state = %d\n", dev->nodename,
+			xenbus_read_driver_state(dev->otherend));
+	} while (!err);
+
 	return netdev;
 
  exit:
@@ -2139,28 +2149,53 @@ static const struct attribute_group xennet_dev_group = {
 };
 #endif /* CONFIG_SYSFS */
 
-static int xennet_remove(struct xenbus_device *dev)
+static void xennet_bus_close(struct xenbus_device *dev)
 {
-	struct netfront_info *info = dev_get_drvdata(&dev->dev);
-
-	dev_dbg(&dev->dev, "%s\n", dev->nodename);
+	int ret;
 
-	if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) {
+	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+		return;
+	do {
+		dev_dbg(&dev->dev, "%s: switching to XenbusStateClosing\n",
+			dev->nodename);
 		xenbus_switch_state(dev, XenbusStateClosing);
-		wait_event(module_wq,
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateClosing ||
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateUnknown);
+		ret = wait_event_timeout(module_wq,
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosing ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosed ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateUnknown,
+				   XENNET_TIMEOUT);
+		dev_dbg(&dev->dev, "%s: state = %d\n", dev->nodename,
+			xenbus_read_driver_state(dev->otherend));
+	} while (!ret);
+
+	if (xenbus_read_driver_state(dev->otherend) == XenbusStateClosed)
+		return;
 
+	do {
+		dev_dbg(&dev->dev, "%s: switching to XenbusStateClosed\n",
+			dev->nodename);
 		xenbus_switch_state(dev, XenbusStateClosed);
-		wait_event(module_wq,
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateClosed ||
-			   xenbus_read_driver_state(dev->otherend) ==
-			   XenbusStateUnknown);
-	}
+		ret = wait_event_timeout(module_wq,
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateClosed ||
+				   xenbus_read_driver_state(dev->otherend) ==
+				   XenbusStateUnknown,
+				   XENNET_TIMEOUT);
+		dev_dbg(&dev->dev, "%s: state = %d\n", dev->nodename,
+			xenbus_read_driver_state(dev->otherend));
+	} while (!ret);
+}
+
+static int xennet_remove(struct xenbus_device *dev)
+{
+	struct netfront_info *info = dev_get_drvdata(&dev->dev);
+
+	dev_dbg(&dev->dev, "%s\n", dev->nodename);
 
+	xennet_bus_close(dev);
 	xennet_disconnect_backend(info);
 
 	if (info->netdev->reg_state == NETREG_REGISTERED)
-- 
2.25.1


             reply	other threads:[~2020-07-22  6:52 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-22  6:52 Andrea Righi [this message]
2020-07-23 21:57 ` [PATCH] xen-netfront: fix potential deadlock in xennet_remove() David Miller
2020-07-24  6:30   ` Andrea Righi

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=20200722065211.GA841369@xps-13 \
    --to=andrea.righi@canonical.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=davem@davemloft.net \
    --cc=jgross@suse.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=sstabellini@kernel.org \
    --cc=xen-devel@lists.xenproject.org \
    /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;
as well as URLs for NNTP newsgroup(s).