qlge: Fix a deadlock when the interface is going down

Currently qlge can deadlock when the interface is going
down, and the mpi_port_cfg_work() is executing on another
processor. It happens because unregister_netdev() holds
the rtnl lock, and the mpi_port_cfg_work() also request
this lock.

Since unregiter_netdev() may wait mpi_port_cfg_work(), who
also request the holding lock, it can cause an deadlock,
displaying the following error:

 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
 rmmod         D 00000080c6c1d190     0  3993   2081 0x00008080
 Call Trace:
 [c000000975f56ee0] [c0000000000152a0] .__switch_to+0x100/0x1d0
 [c000000975f56f70] [c0000000005781b4] .schedule+0x3a4/0x8c0
 [c000000975f570c0] [c000000000578e8c] .schedule_timeout+0x24c/0x350
 [c000000975f571e0] [c000000000578a88] .wait_for_common+0x198/0x210
 [c000000975f572c0] [c0000000000abbb4] .__cancel_work_timer+0x2c4/0x2e0
 [c000000975f57400] [d0000000078e7a20] .ql_adapter_down+0x80/0x260 [qlge]
 [c000000975f574b0] [d0000000078e7d80] .qlge_close+0x70/0x130 [qlge]
 [c000000975f57540] [c000000000497ef8] .__dev_close+0x98/0xf0
 [c000000975f575d0] [c000000000497f74] .dev_close+0x24/0x60
 [c000000975f57650] [c000000000498080] .rollback_registered_many+0xd0/0x2b0
 [c000000975f576f0] [c000000000498338] .rollback_registered+0x38/0x50
 [c000000975f57780] [c0000000004983d8] .unregister_netdevice_queue+0x88/0xe0
 [c000000975f57810] [c000000000498574] .unregister_netdev+0x24/0x40
 [c000000975f57890] [d0000000078f6f38] .qlge_remove+0x3c/0x78 [qlge]
 [c000000975f57920] [c0000000002d9298] .pci_device_remove+0x48/0x90
 [c000000975f579a0] [c000000000372850] .__device_release_driver+0xa0/0x130
 [c000000975f57a30] [c000000000372a08] .driver_detach+0x128/0x150
 [c000000975f57ad0] [c000000000371134] .bus_remove_driver+0xc4/0x1a0
 [c000000975f57b70] [c00000000037357c] .driver_unregister+0x8c/0xd0
 [c000000975f57c00] [c0000000002d968c] .pci_unregister_driver+0x5c/0x110
 [c000000975f57ca0] [d0000000078f6ee4] .qlge_exit+0x1c/0x34 [qlge]

Signed-off-by: Breno Leitao <leitao@linux.vnet.ibm.com>
Signed-off-by: Ron Mercer <ron.mercer@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/qlge/qlge_main.c b/drivers/net/qlge/qlge_main.c
index c9f9754..5a24521 100644 (file)
--- a/drivers/net/qlge/qlge_main.c
+++ b/drivers/net/qlge/qlge_main.c
@@ -3889,11 +3889,8 @@ int ql_wol(struct ql_adapter *qdev)
        return status;
 }
 
-static int ql_adapter_down(struct ql_adapter *qdev)
+static void ql_cancel_all_work_sync(struct ql_adapter *qdev)
 {
-       int i, status = 0;
-
-       ql_link_off(qdev);
 
        /* Don't kill the reset worker thread if we
         * are in the process of recovery.
@@ -3905,6 +3902,15 @@ static int ql_adapter_down(struct ql_adapter *qdev)
        cancel_delayed_work_sync(&qdev->mpi_idc_work);
        cancel_delayed_work_sync(&qdev->mpi_core_to_log);
        cancel_delayed_work_sync(&qdev->mpi_port_cfg_work);
+}
+
+static int ql_adapter_down(struct ql_adapter *qdev)
+{
+       int i, status = 0;
+
+       ql_link_off(qdev);
+
+       ql_cancel_all_work_sync(qdev);
 
        for (i = 0; i < qdev->rss_ring_count; i++)
                napi_disable(&qdev->rx_ring[i].napi);
@@ -4727,6 +4733,7 @@ static void __devexit qlge_remove(struct pci_dev *pdev)
        struct net_device *ndev = pci_get_drvdata(pdev);
        struct ql_adapter *qdev = netdev_priv(ndev);
        del_timer_sync(&qdev->timer);
+       ql_cancel_all_work_sync(qdev);
        unregister_netdev(ndev);
        ql_release_all(pdev);
        pci_disable_device(pdev);
@@ -4746,13 +4753,7 @@ static void ql_eeh_close(struct net_device *ndev)
 
        /* Disabling the timer */
        del_timer_sync(&qdev->timer);
-       if (test_bit(QL_ADAPTER_UP, &qdev->flags))
-               cancel_delayed_work_sync(&qdev->asic_reset_work);
-       cancel_delayed_work_sync(&qdev->mpi_reset_work);
-       cancel_delayed_work_sync(&qdev->mpi_work);
-       cancel_delayed_work_sync(&qdev->mpi_idc_work);
-       cancel_delayed_work_sync(&qdev->mpi_core_to_log);
-       cancel_delayed_work_sync(&qdev->mpi_port_cfg_work);
+       ql_cancel_all_work_sync(qdev);
 
        for (i = 0; i < qdev->rss_ring_count; i++)
                netif_napi_del(&qdev->rx_ring[i].napi);