Commit bcc05910 authored by Bart Van Assche's avatar Bart Van Assche Committed by Roland Dreier

IB/srp: Fix deadlock between host removal and multipathd

If scsi_remove_host() is invoked after a SCSI device has been blocked,
if the fast_io_fail_tmo or dev_loss_tmo work gets scheduled on the
workqueue executing srp_remove_work() and if an I/O request is
scheduled after the SCSI device had been blocked by e.g. multipathd
then the following deadlock can occur:

    kworker/6:1     D ffff880831f3c460     0   195      2 0x00000000
    Call Trace:
     [<ffffffff814aafd9>] schedule+0x29/0x70
     [<ffffffff814aa0ef>] schedule_timeout+0x10f/0x2a0
     [<ffffffff8105af6f>] msleep+0x2f/0x40
     [<ffffffff8123b0ae>] __blk_drain_queue+0x4e/0x180
     [<ffffffff8123d2d5>] blk_cleanup_queue+0x225/0x230
     [<ffffffffa0010732>] __scsi_remove_device+0x62/0xe0 [scsi_mod]
     [<ffffffffa000ed2f>] scsi_forget_host+0x6f/0x80 [scsi_mod]
     [<ffffffffa0002eba>] scsi_remove_host+0x7a/0x130 [scsi_mod]
     [<ffffffffa07cf5c5>] srp_remove_work+0x95/0x180 [ib_srp]
     [<ffffffff8106d7aa>] process_one_work+0x1ea/0x6c0
     [<ffffffff8106dd9b>] worker_thread+0x11b/0x3a0
     [<ffffffff810758bd>] kthread+0xed/0x110
     [<ffffffff814b972c>] ret_from_fork+0x7c/0xb0
    multipathd      D ffff880096acc460     0  5340      1 0x00000000
    Call Trace:
     [<ffffffff814aafd9>] schedule+0x29/0x70
     [<ffffffff814aa0ef>] schedule_timeout+0x10f/0x2a0
     [<ffffffff814ab79b>] io_schedule_timeout+0x9b/0xf0
     [<ffffffff814abe1c>] wait_for_completion_io_timeout+0xdc/0x110
     [<ffffffff81244b9b>] blk_execute_rq+0x9b/0x100
     [<ffffffff8124f665>] sg_io+0x1a5/0x450
     [<ffffffff8124fd21>] scsi_cmd_ioctl+0x2a1/0x430
     [<ffffffff8124fef2>] scsi_cmd_blk_ioctl+0x42/0x50
     [<ffffffffa00ec97e>] sd_ioctl+0xbe/0x140 [sd_mod]
     [<ffffffff8124bd04>] blkdev_ioctl+0x234/0x840
     [<ffffffff811cb491>] block_ioctl+0x41/0x50
     [<ffffffff811a0df0>] do_vfs_ioctl+0x300/0x520
     [<ffffffff811a1051>] SyS_ioctl+0x41/0x80
     [<ffffffff814b9962>] tracesys+0xd0/0xd5

Fix this by scheduling removal work on another workqueue than the
transport layer timers.
Signed-off-by: default avatarBart Van Assche <bvanassche@acm.org>
Reviewed-by: default avatarSagi Grimberg <sagig@mellanox.com>
Reviewed-by: default avatarDavid Dillow <dave@thedillows.org>
Cc: Sebastian Parschauer <sebastian.riemer@profitbricks.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: default avatarRoland Dreier <roland@purestorage.com>
parent cd53eb68
......@@ -130,6 +130,7 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr);
static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event);
static struct scsi_transport_template *ib_srp_transport_template;
static struct workqueue_struct *srp_remove_wq;
static struct ib_client srp_client = {
.name = "srp",
......@@ -731,7 +732,7 @@ static bool srp_queue_remove_work(struct srp_target_port *target)
spin_unlock_irq(&target->lock);
if (changed)
queue_work(system_long_wq, &target->remove_work);
queue_work(srp_remove_wq, &target->remove_work);
return changed;
}
......@@ -3261,9 +3262,10 @@ static void srp_remove_one(struct ib_device *device)
spin_unlock(&host->target_lock);
/*
* Wait for target port removal tasks.
* Wait for tl_err and target port removal tasks.
*/
flush_workqueue(system_long_wq);
flush_workqueue(srp_remove_wq);
kfree(host);
}
......@@ -3313,16 +3315,22 @@ static int __init srp_init_module(void)
indirect_sg_entries = cmd_sg_entries;
}
srp_remove_wq = create_workqueue("srp_remove");
if (IS_ERR(srp_remove_wq)) {
ret = PTR_ERR(srp_remove_wq);
goto out;
}
ret = -ENOMEM;
ib_srp_transport_template =
srp_attach_transport(&ib_srp_transport_functions);
if (!ib_srp_transport_template)
return -ENOMEM;
goto destroy_wq;
ret = class_register(&srp_class);
if (ret) {
pr_err("couldn't register class infiniband_srp\n");
srp_release_transport(ib_srp_transport_template);
return ret;
goto release_tr;
}
ib_sa_register_client(&srp_sa_client);
......@@ -3330,13 +3338,22 @@ static int __init srp_init_module(void)
ret = ib_register_client(&srp_client);
if (ret) {
pr_err("couldn't register IB client\n");
srp_release_transport(ib_srp_transport_template);
ib_sa_unregister_client(&srp_sa_client);
class_unregister(&srp_class);
return ret;
goto unreg_sa;
}
return 0;
out:
return ret;
unreg_sa:
ib_sa_unregister_client(&srp_sa_client);
class_unregister(&srp_class);
release_tr:
srp_release_transport(ib_srp_transport_template);
destroy_wq:
destroy_workqueue(srp_remove_wq);
goto out;
}
static void __exit srp_cleanup_module(void)
......@@ -3345,6 +3362,7 @@ static void __exit srp_cleanup_module(void)
ib_sa_unregister_client(&srp_sa_client);
class_unregister(&srp_class);
srp_release_transport(ib_srp_transport_template);
destroy_workqueue(srp_remove_wq);
}
module_init(srp_init_module);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment