[SCSI] BNX2FC: hung task timeout warning observed when rmmod bnx2x with active FCoE...
authorEddie Wai <eddie.wai@broadcom.com>
Thu, 26 Sep 2013 05:01:20 +0000 (22:01 -0700)
committerJames Bottomley <JBottomley@Parallels.com>
Fri, 25 Oct 2013 08:58:02 +0000 (09:58 +0100)
[v2] - removed the interface->enabled flag setting which prevented the
       fcoe ctlr link from being brought back up after a MTU change

A rtnl_lock deadlock was observed from the rmmod thread where it
tries to unregister the fcoe_ctlr device.  This unregistration
triggered a flush of the sysfs queue of the associated ctlr and led to
a call to the set_fcoe_ctlr_enabled routine.  This will eventually propagate
down to call the bnx2fc_disable routine and contented for the rtnl_lock
in the same context.

This patch creates a subset of the bnx2fc_enable/disable routine which
removes the unnecesary rtnl_lock and the bnx2fc_dev_lock acquisition from
the set_fcoe_ctlr_enabled path.

 kernel: INFO: task rmmod:7874 blocked for more than 120 seconds.
 kernel:      Tainted: G        W  ---------------    2.6.32-415.0.1.el6.x86_64 #1
 kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 kernel: rmmod         D 000000000000000f     0  7874   6518 0x00000080
 kernel: ffff88022158f7d8 0000000000000086 0000000000000000 0000000000000000
 kernel: ffff88023fe72600 ffff88043c74d410 ffff88043c74d400 ffff88043c74d000
 kernel: ffff88021ecbe5f8 ffff88022158ffd8 000000000000fbc8 ffff88021ecbe5f8
 kernel: Call Trace:
 kernel: [<ffffffff81525985>] schedule_timeout+0x215/0x2e0
 kernel: [<ffffffff810680c0>] ? pick_next_task_fair+0xd0/0x130
 kernel: [<ffffffff81524858>] ? schedule+0x178/0x3b2
 kernel: [<ffffffff81525603>] wait_for_common+0x123/0x180
 kernel: [<ffffffff81066b40>] ? default_wake_function+0x0/0x20
 kernel: [<ffffffff811a486e>] ? ifind_fast+0x5e/0xb0
 kernel: [<ffffffff8152571d>] wait_for_completion+0x1d/0x20
 kernel: [<ffffffff81203868>] sysfs_addrm_finish+0x228/0x270
 kernel: [<ffffffff812014ab>] sysfs_hash_and_remove+0x5b/0x90
 kernel: [<ffffffff812056af>] sysfs_remove_group+0x5f/0x100
 kernel: [<ffffffff81367e8b>] device_remove_groups+0x3b/0x60
 kernel: [<ffffffff8136811d>] device_remove_attrs+0x3d/0x90
 kernel: [<ffffffff81368295>] device_del+0x125/0x1e0
 kernel: [<ffffffff81368372>] device_unregister+0x22/0x60
 kernel: [<ffffffffa038ead2>] fcoe_ctlr_device_delete+0xe2/0xf4 [libfcoe]
 kernel: [<ffffffffa03c43cb>] bnx2fc_interface_release+0x5b/0x90 [bnx2fc]
 kernel: [<ffffffffa03c4370>] ? bnx2fc_interface_release+0x0/0x90 [bnx2fc]
 kernel: [<ffffffff812835e7>] kref_put+0x37/0x70
 kernel: [<ffffffffa03c4192>] __bnx2fc_destroy+0x72/0xa0 [bnx2fc]
 kernel: [<ffffffffa03c5265>] bnx2fc_ulp_exit+0xf5/0x160 [bnx2fc]    <- got bnx2fc_dev_lock mutex_lock
 kernel: [<ffffffffa03b03c6>] cnic_ulp_exit+0xb6/0xc0 [cnic]
 kernel: [<ffffffffa03b5418>] cnic_netdev_event+0x368/0x370 [cnic]
 kernel: [<ffffffffa038c56c>] ? fcoe_del_netdev_mapping+0x8c/0xa0 [libfcoe]
 kernel: [<ffffffff8152a6e5>] notifier_call_chain+0x55/0x80
 kernel: [<ffffffff810a0a46>] raw_notifier_call_chain+0x16/0x20
 kernel: [<ffffffff81459beb>] call_netdevice_notifiers+0x1b/0x20
 kernel: [<ffffffff8145ab34>] rollback_registered_many+0x154/0x280
 kernel: [<ffffffff8145ad08>] rollback_registered+0x38/0x50
 kernel: [<ffffffff8145ad78>] unregister_netdevice_queue+0x58/0xa0
 kernel: [<ffffffff8145add0>] unregister_netdevice+0x10/0x20
 kernel: [<ffffffff8145adfe>] unregister_netdev+0x1e/0x30                  <- got rtnl_lock!!!!!!!!!
 kernel: [<ffffffffa0122278>] __bnx2x_remove+0x48/0x270 [bnx2x] <- got & rel rtnl_lock
 kernel: [<ffffffffa0122554>] bnx2x_remove_one+0x44/0x80 [bnx2x]
 kernel: [<ffffffff812a3af7>] pci_device_remove+0x37/0x70
 kernel: [<ffffffff8136b2ef>] __device_release_driver+0x6f/0xe0
 kernel: [<ffffffff8136b428>] driver_detach+0xc8/0xd0
 kernel: [<ffffffff8136a22e>] bus_remove_driver+0x8e/0x110
 kernel: [<ffffffff8136bc12>] driver_unregister+0x62/0xa0
 kernel: [<ffffffff812a3e04>] pci_unregister_driver+0x44/0xb0
 kernel: [<ffffffffa0191954>] bnx2x_cleanup+0x18/0x73 [bnx2x]
 kernel: [<ffffffff810b8be4>] sys_delete_module+0x194/0x260
 kernel: [<ffffffff810e1347>] ? audit_syscall_entry+0x1d7/0x200
 kernel: [<ffffffff8100b072>] system_call_fastpath+0x16/0x1b

Signed-off-by: Eddie Wai <eddie.wai@broadcom.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
drivers/scsi/bnx2fc/bnx2fc_fcoe.c

index 69ac55495c1d7479d75f79b13fdb22659875b95c..7a25766b0fcd814ecd3dd37f328d54317233b4fd 100644 (file)
@@ -2004,6 +2004,24 @@ static void bnx2fc_ulp_init(struct cnic_dev *dev)
                set_bit(BNX2FC_CNIC_REGISTERED, &hba->reg_with_cnic);
 }
 
+/* Assumes rtnl_lock and the bnx2fc_dev_lock are already taken */
+static int __bnx2fc_disable(struct fcoe_ctlr *ctlr)
+{
+       struct bnx2fc_interface *interface = fcoe_ctlr_priv(ctlr);
+
+       if (interface->enabled == true) {
+               if (!ctlr->lp) {
+                       pr_err(PFX "__bnx2fc_disable: lport not found\n");
+                       return -ENODEV;
+               } else {
+                       interface->enabled = false;
+                       fcoe_ctlr_link_down(ctlr);
+                       fcoe_clean_pending_queue(ctlr->lp);
+               }
+       }
+       return 0;
+}
+
 /**
  * Deperecated: Use bnx2fc_enabled()
  */
@@ -2018,20 +2036,34 @@ static int bnx2fc_disable(struct net_device *netdev)
 
        interface = bnx2fc_interface_lookup(netdev);
        ctlr = bnx2fc_to_ctlr(interface);
-       if (!interface || !ctlr->lp) {
+
+       if (!interface) {
                rc = -ENODEV;
-               printk(KERN_ERR PFX "bnx2fc_disable: interface or lport not found\n");
+               pr_err(PFX "bnx2fc_disable: interface not found\n");
        } else {
-               interface->enabled = false;
-               fcoe_ctlr_link_down(ctlr);
-               fcoe_clean_pending_queue(ctlr->lp);
+               rc = __bnx2fc_disable(ctlr);
        }
-
        mutex_unlock(&bnx2fc_dev_lock);
        rtnl_unlock();
        return rc;
 }
 
+static int __bnx2fc_enable(struct fcoe_ctlr *ctlr)
+{
+       struct bnx2fc_interface *interface = fcoe_ctlr_priv(ctlr);
+
+       if (interface->enabled == false) {
+               if (!ctlr->lp) {
+                       pr_err(PFX "__bnx2fc_enable: lport not found\n");
+                       return -ENODEV;
+               } else if (!bnx2fc_link_ok(ctlr->lp)) {
+                       fcoe_ctlr_link_up(ctlr);
+                       interface->enabled = true;
+               }
+       }
+       return 0;
+}
+
 /**
  * Deprecated: Use bnx2fc_enabled()
  */
@@ -2046,12 +2078,11 @@ static int bnx2fc_enable(struct net_device *netdev)
 
        interface = bnx2fc_interface_lookup(netdev);
        ctlr = bnx2fc_to_ctlr(interface);
-       if (!interface || !ctlr->lp) {
+       if (!interface) {
                rc = -ENODEV;
-               printk(KERN_ERR PFX "bnx2fc_enable: interface or lport not found\n");
-       } else if (!bnx2fc_link_ok(ctlr->lp)) {
-               fcoe_ctlr_link_up(ctlr);
-               interface->enabled = true;
+               pr_err(PFX "bnx2fc_enable: interface not found\n");
+       } else {
+               rc = __bnx2fc_enable(ctlr);
        }
 
        mutex_unlock(&bnx2fc_dev_lock);
@@ -2072,14 +2103,12 @@ static int bnx2fc_enable(struct net_device *netdev)
 static int bnx2fc_ctlr_enabled(struct fcoe_ctlr_device *cdev)
 {
        struct fcoe_ctlr *ctlr = fcoe_ctlr_device_priv(cdev);
-       struct fc_lport *lport = ctlr->lp;
-       struct net_device *netdev = bnx2fc_netdev(lport);
 
        switch (cdev->enabled) {
        case FCOE_CTLR_ENABLED:
-               return bnx2fc_enable(netdev);
+               return __bnx2fc_enable(ctlr);
        case FCOE_CTLR_DISABLED:
-               return bnx2fc_disable(netdev);
+               return __bnx2fc_disable(ctlr);
        case FCOE_CTLR_UNUSED:
        default:
                return -ENOTSUPP;