fcoe: Fix deadlock between create and destroy paths

We can deadlock (s_active and fcoe_config_mutex) if a
port is being destroyed at the same time one is being created.

[ 4200.503113] ======================================================
[ 4200.503114] [ INFO: possible circular locking dependency detected ]
[ 4200.503116] 3.8.0-rc5+ #8 Not tainted
[ 4200.503117] -------------------------------------------------------
[ 4200.503118] kworker/3:2/2492 is trying to acquire lock:
[ 4200.503119]  (s_active#292){++++.+}, at: [<ffffffff8122d20b>] sysfs_addrm_finish+0x3b/0x70
[ 4200.503127]
but task is already holding lock:
[ 4200.503128]  (fcoe_config_mutex){+.+.+.}, at: [<ffffffffa02f3338>] fcoe_destroy_work+0xe8/0x120 [fcoe]
[ 4200.503133]
which lock already depends on the new lock.

[ 4200.503135]
the existing dependency chain (in reverse order) is:
[ 4200.503136]
-> #1 (fcoe_config_mutex){+.+.+.}:
[ 4200.503139]        [<ffffffff810c7711>] lock_acquire+0xa1/0x140
[ 4200.503143]        [<ffffffff816ca7be>] mutex_lock_nested+0x6e/0x360
[ 4200.503146]        [<ffffffffa02f11bd>] fcoe_enable+0x1d/0xb0 [fcoe]
[ 4200.503148]        [<ffffffffa02f127d>] fcoe_ctlr_enabled+0x2d/0x50 [fcoe]
[ 4200.503151]        [<ffffffffa02ffbe8>] store_ctlr_enabled+0x38/0x90 [libfcoe]
[ 4200.503154]        [<ffffffff81424878>] dev_attr_store+0x18/0x30
[ 4200.503157]        [<ffffffff8122b750>] sysfs_write_file+0xe0/0x150
[ 4200.503160]        [<ffffffff811b334c>] vfs_write+0xac/0x180
[ 4200.503162]        [<ffffffff811b3692>] sys_write+0x52/0xa0
[ 4200.503164]        [<ffffffff816d7159>] system_call_fastpath+0x16/0x1b
[ 4200.503167]
-> #0 (s_active#292){++++.+}:
[ 4200.503170]        [<ffffffff810c680f>] __lock_acquire+0x135f/0x1c90
[ 4200.503172]        [<ffffffff810c7711>] lock_acquire+0xa1/0x140
[ 4200.503174]        [<ffffffff8122c626>] sysfs_deactivate+0x116/0x160
[ 4200.503176]        [<ffffffff8122d20b>] sysfs_addrm_finish+0x3b/0x70
[ 4200.503178]        [<ffffffff8122b2eb>] sysfs_hash_and_remove+0x5b/0xb0
[ 4200.503180]        [<ffffffff8122f3d1>] sysfs_remove_group+0x61/0x100
[ 4200.503183]        [<ffffffff814251eb>] device_remove_groups+0x3b/0x60
[ 4200.503185]        [<ffffffff81425534>] device_remove_attrs+0x44/0x80
[ 4200.503187]        [<ffffffff81425e97>] device_del+0x127/0x1c0
[ 4200.503189]        [<ffffffff81425f52>] device_unregister+0x22/0x60
[ 4200.503191]        [<ffffffffa0300970>] fcoe_ctlr_device_delete+0xe0/0xf0 [libfcoe]
[ 4200.503194]        [<ffffffffa02f1b5c>] fcoe_interface_cleanup+0x6c/0xa0 [fcoe]
[ 4200.503196]        [<ffffffffa02f3355>] fcoe_destroy_work+0x105/0x120 [fcoe]
[ 4200.503198]        [<ffffffff8107ee91>] process_one_work+0x1a1/0x580
[ 4200.503203]        [<ffffffff81080c6e>] worker_thread+0x15e/0x440
[ 4200.503205]        [<ffffffff8108715a>] kthread+0xea/0xf0
[ 4200.503207]        [<ffffffff816d70ac>] ret_from_fork+0x7c/0xb0

[ 4200.503209]
other info that might help us debug this:

[ 4200.503211]  Possible unsafe locking scenario:

[ 4200.503212]        CPU0                    CPU1
[ 4200.503213]        ----                    ----
[ 4200.503214]   lock(fcoe_config_mutex);
[ 4200.503215]                                lock(s_active#292);
[ 4200.503218]                                lock(fcoe_config_mutex);
[ 4200.503219]   lock(s_active#292);
[ 4200.503221]
 *** DEADLOCK ***

[ 4200.503223] 3 locks held by kworker/3:2/2492:
[ 4200.503224]  #0:  (fcoe){.+.+.+}, at: [<ffffffff8107ee2b>] process_one_work+0x13b/0x580
[ 4200.503228]  #1:  ((&port->destroy_work)){+.+.+.}, at: [<ffffffff8107ee2b>] process_one_work+0x13b/0x580
[ 4200.503232]  #2:  (fcoe_config_mutex){+.+.+.}, at: [<ffffffffa02f3338>] fcoe_destroy_work+0xe8/0x120 [fcoe]
[ 4200.503236]
stack backtrace:
[ 4200.503238] Pid: 2492, comm: kworker/3:2 Not tainted 3.8.0-rc5+ #8
[ 4200.503240] Call Trace:
[ 4200.503243]  [<ffffffff816c2f09>] print_circular_bug+0x1fb/0x20c
[ 4200.503246]  [<ffffffff810c680f>] __lock_acquire+0x135f/0x1c90
[ 4200.503248]  [<ffffffff810c463a>] ? debug_check_no_locks_freed+0x9a/0x180
[ 4200.503250]  [<ffffffff810c7711>] lock_acquire+0xa1/0x140
[ 4200.503253]  [<ffffffff8122d20b>] ? sysfs_addrm_finish+0x3b/0x70
[ 4200.503255]  [<ffffffff8122c626>] sysfs_deactivate+0x116/0x160
[ 4200.503258]  [<ffffffff8122d20b>] ? sysfs_addrm_finish+0x3b/0x70
[ 4200.503260]  [<ffffffff8122d20b>] sysfs_addrm_finish+0x3b/0x70
[ 4200.503262]  [<ffffffff8122b2eb>] sysfs_hash_and_remove+0x5b/0xb0
[ 4200.503265]  [<ffffffff8122f3d1>] sysfs_remove_group+0x61/0x100
[ 4200.503273]  [<ffffffff814251eb>] device_remove_groups+0x3b/0x60
[ 4200.503275]  [<ffffffff81425534>] device_remove_attrs+0x44/0x80
[ 4200.503277]  [<ffffffff81425e97>] device_del+0x127/0x1c0
[ 4200.503279]  [<ffffffff81425f52>] device_unregister+0x22/0x60
[ 4200.503282]  [<ffffffffa0300970>] fcoe_ctlr_device_delete+0xe0/0xf0 [libfcoe]
[ 4200.503285]  [<ffffffffa02f1b5c>] fcoe_interface_cleanup+0x6c/0xa0 [fcoe]
[ 4200.503287]  [<ffffffffa02f3355>] fcoe_destroy_work+0x105/0x120 [fcoe]
[ 4200.503290]  [<ffffffff8107ee91>] process_one_work+0x1a1/0x580
[ 4200.503292]  [<ffffffff8107ee2b>] ? process_one_work+0x13b/0x580
[ 4200.503295]  [<ffffffffa02f3250>] ? fcoe_if_destroy+0x230/0x230 [fcoe]
[ 4200.503297]  [<ffffffff81080c6e>] worker_thread+0x15e/0x440
[ 4200.503299]  [<ffffffff81080b10>] ? busy_worker_rebind_fn+0x100/0x100
[ 4200.503301]  [<ffffffff8108715a>] kthread+0xea/0xf0
[ 4200.503304]  [<ffffffff81087070>] ? kthread_create_on_node+0x160/0x160
[ 4200.503306]  [<ffffffff816d70ac>] ret_from_fork+0x7c/0xb0
[ 4200.503308]  [<ffffffff81087070>] ? kthread_create_on_node+0x160/0x160

Signed-off-by: Robert Love <robert.w.love@intel.com>
Tested-by: Jack Morgan <jack.morgan@intel.com>

diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index b5d92fc..9bfdc9a 100644 (file)
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -490,7 +490,6 @@ static void fcoe_interface_cleanup(struct fcoe_interface *fcoe)
 {
        struct net_device *netdev = fcoe->netdev;
        struct fcoe_ctlr *fip = fcoe_to_ctlr(fcoe);
-       struct fcoe_ctlr_device *ctlr_dev = fcoe_ctlr_to_ctlr_dev(fip);
 
        rtnl_lock();
        if (!fcoe->removed)
@@ -501,7 +500,6 @@ static void fcoe_interface_cleanup(struct fcoe_interface *fcoe)
        /* tear-down the FCoE controller */
        fcoe_ctlr_destroy(fip);
        scsi_host_put(fip->lp->host);
-       fcoe_ctlr_device_delete(ctlr_dev);
        dev_put(netdev);
        module_put(THIS_MODULE);
 }
@@ -2194,6 +2192,8 @@ out_nodev:
  */
 static void fcoe_destroy_work(struct work_struct *work)
 {
+       struct fcoe_ctlr_device *cdev;
+       struct fcoe_ctlr *ctlr;
        struct fcoe_port *port;
        struct fcoe_interface *fcoe;
        struct Scsi_Host *shost;
@@ -2224,10 +2224,15 @@ static void fcoe_destroy_work(struct work_struct *work)
        mutex_lock(&fcoe_config_mutex);
 
        fcoe = port->priv;
+       ctlr = fcoe_to_ctlr(fcoe);
+       cdev = fcoe_ctlr_to_ctlr_dev(ctlr);
+
        fcoe_if_destroy(port->lport);
        fcoe_interface_cleanup(fcoe);
 
        mutex_unlock(&fcoe_config_mutex);
+
+       fcoe_ctlr_device_delete(cdev);
 }
 
 /**
@@ -2335,7 +2340,9 @@ static int _fcoe_create(struct net_device *netdev, enum fip_state fip_mode,
                rc = -EIO;
                rtnl_unlock();
                fcoe_interface_cleanup(fcoe);
-               goto out_nortnl;
+               mutex_unlock(&fcoe_config_mutex);
+               fcoe_ctlr_device_delete(ctlr_dev);
+               goto out;
        }
 
        /* Make this the "master" N_Port */
@@ -2375,8 +2382,8 @@ static int _fcoe_create(struct net_device *netdev, enum fip_state fip_mode,
 
 out_nodev:
        rtnl_unlock();
-out_nortnl:
        mutex_unlock(&fcoe_config_mutex);
+out:
        return rc;
 }