ib/ipoib: Fix deadlock between rmmod and set_mode

set_mod called from sys/fs, takes sys/fs lock and tries to
take rtnl_lock, rmmod takes rtnl_lock and now tries to take
sys/fs lock, that causes deadlock.
deadloc a->b, b->a

The problem starts when ipoib_set_mod free it's rtnl_lck and
tries to get it after that.

set_mod:

[<ffffffff8104f2bd>] ? check_preempt_curr+0x6d/0x90
[<ffffffff814fee8e>] __mutex_lock_slowpath+0x13e/0x180
[<ffffffff81448655>] ? __rtnl_unlock+0x15/0x20
[<ffffffff814fed2b>] mutex_lock+0x2b/0x50
[<ffffffff81448675>] rtnl_lock+0x15/0x20
[<ffffffffa02ad807>] ipoib_set_mode+0x97/0x160 [ib_ipoib]
[<ffffffffa02b5f5b>] set_mode+0x3b/0x80 [ib_ipoib]
[<ffffffff8134b840>] dev_attr_store+0x20/0x30
[<ffffffff811f0fe5>] sysfs_write_file+0xe5/0x170
[<ffffffff8117b068>] vfs_write+0xb8/0x1a0
[<ffffffff8117ba81>] sys_write+0x51/0x90
[<ffffffff8100b0f2>] system_call_fastpath+0x16/0x1b
INFO: task rmmod:8057 blocked for more than 120 seconds.
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.

rmmod:
[<ffffffff81279ffc>] ? put_dec+0x10c/0x110
[<ffffffff8127a2ee>] ? number+0x2ee/0x320
[<ffffffff814fe6a5>] schedule_timeout+0x215/0x2e0
[<ffffffff8127cc04>] ? vsnprintf+0x484/0x5f0
[<ffffffff8127b550>] ? string+0x40/0x100
[<ffffffff814fe323>] wait_for_common+0x123/0x180
[<ffffffff81060250>] ? default_wake_function+0x0/0x20
[<ffffffff8119661e>] ? ifind_fast+0x5e/0xb0
[<ffffffff814fe43d>] wait_for_completion+0x1d/0x20
[<ffffffff811f2e68>] sysfs_addrm_finish+0x228/0x270
[<ffffffff811f2fb3>] sysfs_remove_dir+0xa3/0xf0
[<ffffffff81273f66>] kobject_del+0x16/0x40
[<ffffffff8134cd14>] device_del+0x184/0x1e0
[<ffffffff8144e59b>] netdev_unregister_kobject+0xab/0xc0
[<ffffffff8143c05e>] rollback_registered+0xae/0x130
[<ffffffff8143c102>] unregister_netdevice+0x22/0x70
[<ffffffff8143c16e>] unregister_netdev+0x1e/0x30
[<ffffffffa02a91b0>] ipoib_remove_one+0xe0/0x120 [ib_ipoib]
[<ffffffffa01ed95f>] ib_unregister_device+0x4f/0x100 [ib_core]
[<ffffffffa021f5e1>] mlx4_ib_remove+0x41/0x180 [mlx4_ib]
[<ffffffffa01ab771>] mlx4_remove_device+0x71/0x90 [mlx4_core]
[<ffffffffa01ab863>] mlx4_unregister_interface+0x43/0x80 [mlx4_core]
[<ffffffffa02324f3>] __exit_compat+0x15/0x4e [mlx4_ib]
[<ffffffff810addd4>] sys_delete_module+0x194/0x260
[<ffffffff8150326e>] ? do_page_fault+0x3e/0xa0
[<ffffffff8100b0f2>] system_call_fastpath+0x16/0x1b
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
(Ported from Mellanox OFED 2.4)

Signed-off-by: Mukesh Kacker <mukesh.kacker@oracle.com>

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index a4569d77d1a5e62d0f5661f40b780f3a4259a090..cf7d15323fee942ab9ae3511f219c4d3c277df0b 100644 (file)
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -1518,9 +1518,14 @@ static ssize_t set_mode(struct device *d, struct device_attribute *attr,
 
        ret = ipoib_set_mode(dev, buf);
 
-       rtnl_unlock();
+       /* the assumption is that the func ipoib_set_mode returned with the
+        * rtnl held by it, if not the value -EBUSY returned,
+        * so no need to rtnl_unlock
+        */
+       if (ret != -EBUSY)
+               rtnl_unlock();
 
-       if (!ret)
+       if (!ret || ret == -EBUSY)
                return count;
 
        return ret;

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 53c012ddffcc2668e4d847f8a2fb8842b76b3a3b..194bce6fc00bdd2728cbad8714b75824cbde45bf 100644 (file)
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -236,7 +236,10 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
                priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
 
                ipoib_flush_paths(dev);
-               rtnl_lock();
+
+               if (!rtnl_trylock())
+                       return -EBUSY;
+
                return 0;
        }
 
@@ -246,7 +249,10 @@ int ipoib_set_mode(struct net_device *dev, const char *buf)
                dev_set_mtu(dev, min(priv->mcast_mtu, dev->mtu));
                rtnl_unlock();
                ipoib_flush_paths(dev);
-               rtnl_lock();
+
+               if (!rtnl_trylock())
+                       return -EBUSY;
+
                return 0;
        }