From 112f661d6dac9af1235d2d05299fc2c9cb876ae7 Mon Sep 17 00:00:00 2001 From: Nithin Nayak Sujir Date: Mon, 25 Apr 2011 12:30:06 -0700 Subject: [PATCH] [SCSI] scsi_transport_fc: Fix deadlock during fc_remove_host Creating and destroying fcoe interface in a tight loop leads to a system deadlock with the following call traces: Call Trace: [] schedule_timeout+0x1fd/0x2c0 [] ? wait_for_common+0x4f/0x190 [] ? wait_for_common+0x4f/0x190 [] wait_for_common+0xe7/0x190 [] ? default_wake_function+0x0/0x20 [] ? trace_hardirqs_on+0xd/0x10 [] wait_for_completion+0x1d/0x20 [] flush_workqueue+0x290/0x5f0 [] ? flush_workqueue+0x0/0x5f0 [] destroy_workqueue+0x38/0x340 [] fc_remove_host+0x1b9/0x1f0 [scsi_transport_fc] [] bnx2fc_if_destroy+0xc5/0x1f0 [bnx2fc] [] bnx2fc_destroy+0x7a/0x100 [bnx2fc] [] fcoe_transport_destroy+0x9b/0x1b0 [libfcoe] [] param_attr_store+0x52/0x80 [] module_attr_store+0x26/0x30 [] sysfs_write_file+0xe6/0x170 [] vfs_write+0xd0/0x1a0 [] sys_write+0x54/0xa0 [] system_call_fastpath+0x16/0x1b Call Trace: [] async_synchronize_cookie_domain+0x75/0x120 [] ? autoremove_wake_function+0x0/0x40 [] async_synchronize_cookie+0x15/0x20 [] async_synchronize_full+0x1c/0x40 [] sd_remove+0x36/0xc0 [sd_mod] [] __device_release_driver+0x75/0xe0 [] device_release_driver+0x2f/0x50 [] bus_remove_device+0xbe/0x120 [] device_del+0x12f/0x1e0 [] __scsi_remove_device+0xbd/0xc0 [] scsi_remove_device+0x35/0x50 [] __scsi_remove_target+0xe7/0x110 [] ? __remove_child+0x0/0x30 [] __remove_child+0x23/0x30 [] device_for_each_child+0x4c/0x80 [] scsi_remove_target+0x33/0x60 [] fc_starget_delete+0x26/0x30 [scsi_transport_fc] [] fc_rport_final_delete+0xaa/0x200 [scsi_transport_fc] [] process_one_work+0x1aa/0x540 [] ? process_one_work+0x13b/0x540 [] ? fc_rport_final_delete+0x0/0x200 [scsi_transport_fc] [] worker_thread+0x179/0x410 [] ? worker_thread+0x0/0x410 [] kthread+0xb6/0xc0 [] ? finish_task_switch+0x4b/0xe0 [] kernel_thread_helper+0x4/0x10 [] ? restore_args+0x0/0x30 [] ? kthread+0x0/0xc0 [] ? kernel_thread_helper+0x0/0x10 fc_remove_host() waits for flushing the workqueue, but it is stuck at flushing the first work. The first work doesnt complete, because it is waiting for async layer to complete the IOs. The async layer cannot complete the IO as the terminate_rport_io for the second work was not called, which will be called only when the first work completes. Hence the deadlock. To resolve this deadlock, the workqueue allocation has been modified from create_singlethread_workqueue() to alloc_workqueue(). In addition, fc_terminate_rport_io() should be called before the scsi_flush_work() to avoid the similar deadlock as above. scsi fc alloc queue. move terminate rport io before flush Signed-off-by: Nithin Nayak Sujir Signed-off-by: Bhanu Prakash Gollapudi Signed-off-by: James Bottomley --- drivers/scsi/scsi_transport_fc.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c index fdf3fa639056..358dff6732ea 100644 --- a/drivers/scsi/scsi_transport_fc.c +++ b/drivers/scsi/scsi_transport_fc.c @@ -422,8 +422,7 @@ static int fc_host_setup(struct transport_container *tc, struct device *dev, snprintf(fc_host->work_q_name, sizeof(fc_host->work_q_name), "fc_wq_%d", shost->host_no); - fc_host->work_q = create_singlethread_workqueue( - fc_host->work_q_name); + fc_host->work_q = alloc_workqueue(fc_host->work_q_name, 0, 0); if (!fc_host->work_q) return -ENOMEM; @@ -431,8 +430,8 @@ static int fc_host_setup(struct transport_container *tc, struct device *dev, snprintf(fc_host->devloss_work_q_name, sizeof(fc_host->devloss_work_q_name), "fc_dl_%d", shost->host_no); - fc_host->devloss_work_q = create_singlethread_workqueue( - fc_host->devloss_work_q_name); + fc_host->devloss_work_q = + alloc_workqueue(fc_host->devloss_work_q_name, 0, 0); if (!fc_host->devloss_work_q) { destroy_workqueue(fc_host->work_q); fc_host->work_q = NULL; @@ -2489,6 +2488,8 @@ fc_rport_final_delete(struct work_struct *work) unsigned long flags; int do_callback = 0; + fc_terminate_rport_io(rport); + /* * if a scan is pending, flush the SCSI Host work_q so that * that we can reclaim the rport scan work element. @@ -2496,8 +2497,6 @@ fc_rport_final_delete(struct work_struct *work) if (rport->flags & FC_RPORT_SCAN_PENDING) scsi_flush_work(shost); - fc_terminate_rport_io(rport); - /* * Cancel any outstanding timers. These should really exist * only when rmmod'ing the LLDD and we're asking for