net/smc: fix sleep bug in smc_pnet_find_roce_resource()

Tests showed this BUG:
[572555.252867] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:935
[572555.252876] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 131031, name: smcapp
[572555.252879] INFO: lockdep is turned off.
[572555.252883] CPU: 1 PID: 131031 Comm: smcapp Tainted: G           O      5.7.0-rc3uschi+ #356
[572555.252885] Hardware name: IBM 3906 M03 703 (LPAR)
[572555.252887] Call Trace:
[572555.252896]  [<00000000ac364554>] show_stack+0x94/0xe8
[572555.252901]  [<00000000aca1f400>] dump_stack+0xa0/0xe0
[572555.252906]  [<00000000ac3c8c10>] ___might_sleep+0x260/0x280
[572555.252910]  [<00000000acdc0c98>] __mutex_lock+0x48/0x940
[572555.252912]  [<00000000acdc15c2>] mutex_lock_nested+0x32/0x40
[572555.252975]  [<000003ff801762d0>] mlx5_lag_get_roce_netdev+0x30/0xc0 [mlx5_core]
[572555.252996]  [<000003ff801fb3aa>] mlx5_ib_get_netdev+0x3a/0xe0 [mlx5_ib]
[572555.253007]  [<000003ff80063848>] smc_pnet_find_roce_resource+0x1d8/0x310 [smc]
[572555.253011]  [<000003ff800602f0>] __smc_connect+0x1f0/0x3e0 [smc]
[572555.253015]  [<000003ff80060634>] smc_connect+0x154/0x190 [smc]
[572555.253022]  [<00000000acbed8d4>] __sys_connect+0x94/0xd0
[572555.253025]  [<00000000acbef620>] __s390x_sys_socketcall+0x170/0x360
[572555.253028]  [<00000000acdc6800>] system_call+0x298/0x2b8
[572555.253030] INFO: lockdep is turned off.

Function smc_pnet_find_rdma_dev() might be called from
smc_pnet_find_roce_resource(). It holds the smc_ib_devices list
spinlock while calling infiniband op get_netdev(). At least for mlx5
the get_netdev operation wants mutex serialization, which conflicts
with the smc_ib_devices spinlock.
This patch switches the smc_ib_devices spinlock into a mutex to
allow sleeping when calling get_netdev().

Fixes: a4cf0443c414 ("smc: introduce SMC as an IB-client")
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 6 insertions, 5 deletions

diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 562a52d01ad1..7637fdebbb78 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -16,6 +16,7 @@
 #include <linux/workqueue.h>
 #include <linux/scatterlist.h>
 #include <linux/wait.h>
+#include <linux/mutex.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
 
@@ -33,7 +34,7 @@
 #define SMC_QP_RNR_RETRY			7 /* 7: infinite */
 
 struct smc_ib_devices smc_ib_devices = {	/* smc-registered ib devices */
-	.lock = __SPIN_LOCK_UNLOCKED(smc_ib_devices.lock),
+	.mutex = __MUTEX_INITIALIZER(smc_ib_devices.mutex),
 	.list = LIST_HEAD_INIT(smc_ib_devices.list),
 };
 
@@ -565,9 +566,9 @@ static int smc_ib_add_dev(struct ib_device *ibdev)
 	INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work);
 	atomic_set(&smcibdev->lnk_cnt, 0);
 	init_waitqueue_head(&smcibdev->lnks_deleted);
-	spin_lock(&smc_ib_devices.lock);
+	mutex_lock(&smc_ib_devices.mutex);
 	list_add_tail(&smcibdev->list, &smc_ib_devices.list);
-	spin_unlock(&smc_ib_devices.lock);
+	mutex_unlock(&smc_ib_devices.mutex);
 	ib_set_client_data(ibdev, &smc_ib_client, smcibdev);
 	INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
 			      smc_ib_global_event_handler);
@@ -602,9 +603,9 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
 {
 	struct smc_ib_device *smcibdev = client_data;
 
-	spin_lock(&smc_ib_devices.lock);
+	mutex_lock(&smc_ib_devices.mutex);
 	list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
-	spin_unlock(&smc_ib_devices.lock);
+	mutex_unlock(&smc_ib_devices.mutex);
 	pr_warn_ratelimited("smc: removing ib device %s\n",
 			    smcibdev->ibdev->name);
 	smc_smcr_terminate_all(smcibdev);