Recently Dough Ledford reported a deadlock happening
between ocrdma-load sequence and NetworkManager service
issueing "open" on be2net interface.
The deadlock happens when any be2net hook (e.g. open/close) is called
in parallel to insmod ocrdma.ko.
A. be2net is sending administrative open/close event to ocrdma holding
device_list_mutex. It does this from ndo_open/ndo_stop hooks of be2net.
So sequence of locks is rtnl_lock---> device_list lock
B. When new ocrdma roce device gets registered, infiniband stack now
takes rtnl_lock in ib_register_device() in GID initialization routines.
So sequence of locks in this path is device_list lock ---> rtnl_lock.
This improper locking sequence causes deadlock.
In order to resolve the above deadlock condition, ocrdma intorduced a
patch to stop listening to administrative open/close events generated from
be2net driver. It now depends on link-state-change async-event generated from
CNA. This change leaves behind dead code which used to generate administrative
open/close events. This patch cleans-up all that dead code from be2net.
Reported-by: Doug Ledford <dledford@xxxxxxxxxx>
CC: Sathya Perla <sathya.perla@xxxxxxxxxxxxx>
Signed-off-by: Padmanabh Ratnakar <padmanabh.ratnakar@xxxxxxxxxxxxx>
Signed-off-by: Selvin Xavier <selvin.xavier@xxxxxxxxxxxxx>
Signed-off-by: Devesh Sharma <devesh.sharma@xxxxxxxxxxxxx>
---
drivers/net/ethernet/emulex/benet/be.h | 2 --
drivers/net/ethernet/emulex/benet/be_main.c | 4 ----
drivers/net/ethernet/emulex/benet/be_roce.c | 36 -----------------------------
drivers/net/ethernet/emulex/benet/be_roce.h | 4 +---
4 files changed, 1 insertion(+), 45 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index d463563..6ee78c2 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -848,8 +848,6 @@ void be_roce_dev_remove(struct be_adapter *);
/*
* internal function to open-close roce device during ifup-ifdown.
*/
-void be_roce_dev_open(struct be_adapter *);
-void be_roce_dev_close(struct be_adapter *);
void be_roce_dev_shutdown(struct be_adapter *);
#endif /* BE_H */
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index b6ad029..ff2ff89 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3432,8 +3432,6 @@ static int be_close(struct net_device *netdev)
be_disable_if_filters(adapter);
- be_roce_dev_close(adapter);
-
if (adapter->flags & BE_FLAGS_NAPI_ENABLED) {
for_all_evt_queues(adapter, eqo, i) {
napi_disable(&eqo->napi);
@@ -3601,8 +3599,6 @@ static int be_open(struct net_device *netdev)
be_link_status_update(adapter, link_status);
netif_tx_start_all_queues(netdev);
- be_roce_dev_open(adapter);
-
#ifdef CONFIG_BE2NET_VXLAN
if (skyhawk_chip(adapter))
vxlan_get_rx_port(netdev);
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.c b/drivers/net/ethernet/emulex/benet/be_roce.c
index 6036820..4089156 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.c
+++ b/drivers/net/ethernet/emulex/benet/be_roce.c
@@ -116,40 +116,6 @@ void be_roce_dev_remove(struct be_adapter *adapter)
}
}
-static void _be_roce_dev_open(struct be_adapter *adapter)
-{
- if (ocrdma_drv && adapter->ocrdma_dev &&
- ocrdma_drv->state_change_handler)
- ocrdma_drv->state_change_handler(adapter->ocrdma_dev,
- BE_DEV_UP);
-}
-
-void be_roce_dev_open(struct be_adapter *adapter)
-{
- if (be_roce_supported(adapter)) {
- mutex_lock(&be_adapter_list_lock);
- _be_roce_dev_open(adapter);
- mutex_unlock(&be_adapter_list_lock);
- }
-}
-
-static void _be_roce_dev_close(struct be_adapter *adapter)
-{
- if (ocrdma_drv && adapter->ocrdma_dev &&
- ocrdma_drv->state_change_handler)
- ocrdma_drv->state_change_handler(adapter->ocrdma_dev,
- BE_DEV_DOWN);
-}
-
-void be_roce_dev_close(struct be_adapter *adapter)
-{
- if (be_roce_supported(adapter)) {
- mutex_lock(&be_adapter_list_lock);
- _be_roce_dev_close(adapter);
- mutex_unlock(&be_adapter_list_lock);
- }
-}
-
void be_roce_dev_shutdown(struct be_adapter *adapter)
{
if (be_roce_supported(adapter)) {
@@ -177,8 +143,6 @@ int be_roce_register_driver(struct ocrdma_driver *drv)
_be_roce_dev_add(dev);
netdev = dev->netdev;
- if (netif_running(netdev) && netif_oper_up(netdev))
- _be_roce_dev_open(dev);
}
mutex_unlock(&be_adapter_list_lock);
return 0;
diff --git a/drivers/net/ethernet/emulex/benet/be_roce.h b/drivers/net/ethernet/emulex/benet/be_roce.h
index cde6ef9..fde6097 100644
--- a/drivers/net/ethernet/emulex/benet/be_roce.h
+++ b/drivers/net/ethernet/emulex/benet/be_roce.h
@@ -60,9 +60,7 @@ struct ocrdma_driver {
void (*state_change_handler) (struct ocrdma_dev *, u32 new_state);
};
-enum {
- BE_DEV_UP = 0,
- BE_DEV_DOWN = 1,
+enum be_roce_event {
BE_DEV_SHUTDOWN = 2
};
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
