>From 0f72b28329342346980ae99c69d19b7adb0123bc Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@sandisk.com>
Date: Thu, 24 Mar 2016 11:01:14 -0700
Subject: [PATCH 1/4] IB/cm: Fix a recently introduced locking bug

ib_cm_notify() can be called from interrupt context. Hence do not
reenable interrupts unconditionally in cm_establish().

This patch avoids that lockdep reports the following warning:

WARNING: CPU: 0 PID: 23317 at kernel/locking/lockdep.c:2624 trace _hardirqs_on_caller+0x112/0x1b0
DEBUG_LOCKS_WARN_ON(current->hardirq_context)
Call Trace:
 <IRQ>  [<ffffffff812bd0e5>] dump_stack+0x67/0x92
 [<ffffffff81056f21>] __warn+0xc1/0xe0
 [<ffffffff81056f8a>] warn_slowpath_fmt+0x4a/0x50
 [<ffffffff810a5932>] trace_hardirqs_on_caller+0x112/0x1b0
 [<ffffffff810a59dd>] trace_hardirqs_on+0xd/0x10
 [<ffffffff815992c7>] _raw_spin_unlock_irq+0x27/0x40
 [<ffffffffa0382e9c>] ib_cm_notify+0x25c/0x290 [ib_cm]
 [<ffffffffa068fbc1>] srpt_qp_event+0xa1/0xf0 [ib_srpt]
 [<ffffffffa04efb97>] mlx4_ib_qp_event+0x67/0xd0 [mlx4_ib]
 [<ffffffffa034ec0a>] mlx4_qp_event+0x5a/0xc0 [mlx4_core]
 [<ffffffffa03365f8>] mlx4_eq_int+0x3d8/0xcf0 [mlx4_core]
 [<ffffffffa0336f9c>] mlx4_msi_x_interrupt+0xc/0x20 [mlx4_core]
 [<ffffffff810b0914>] handle_irq_event_percpu+0x64/0x100
 [<ffffffff810b09e4>] handle_irq_event+0x34/0x60
 [<ffffffff810b3a6a>] handle_edge_irq+0x6a/0x150
 [<ffffffff8101ad05>] handle_irq+0x15/0x20
 [<ffffffff8101a66c>] do_IRQ+0x5c/0x110
 [<ffffffff8159a2c9>] common_interrupt+0x89/0x89
 [<ffffffff81297a17>] blk_run_queue_async+0x37/0x40
 [<ffffffffa0163e53>] rq_completed+0x43/0x70 [dm_mod]
 [<ffffffffa0164896>] dm_softirq_done+0x176/0x280 [dm_mod]
 [<ffffffff812a26c2>] blk_done_softirq+0x52/0x90
 [<ffffffff8105bc1f>] __do_softirq+0x10f/0x230
 [<ffffffff8105bec8>] irq_exit+0xa8/0xb0
 [<ffffffff8103653e>] smp_trace_call_function_single_interrupt+0x2e/0x30
 [<ffffffff81036549>] smp_call_function_single_interrupt+0x9/0x10
 [<ffffffff8159a959>] call_function_single_interrupt+0x89/0x90
 <EOI>

Fixes: commit be4b499323bf ("IB/cm: Do not queue work to a device that's going away")
Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Erez Shitrit <erezsh@mellanox.com>
Cc: Doug Ledford <dledford@redhat.com>
Cc: stable <stable@vger.kernel.org> # v4.2+
---
 drivers/infiniband/core/cm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 1d92e09..c995255 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -3452,14 +3452,14 @@ static int cm_establish(struct ib_cm_id *cm_id)
 	work->cm_event.event = IB_CM_USER_ESTABLISHED;
 
 	/* Check if the device started its remove_one */
-	spin_lock_irq(&cm.lock);
+	spin_lock_irqsave(&cm.lock, flags);
 	if (!cm_dev->going_down) {
 		queue_delayed_work(cm.wq, &work->work, 0);
 	} else {
 		kfree(work);
 		ret = -ENODEV;
 	}
-	spin_unlock_irq(&cm.lock);
+	spin_unlock_irqrestore(&cm.lock, flags);
 
 out:
 	return ret;
-- 
2.7.3