@@ -183,11 +183,16 @@ static void ncsi_channel_monitor(unsigned long data)
monitor_state = nc->monitor.state;
spin_unlock_irqrestore(&nc->lock, flags);
- if (!enabled || chained)
+ if (!enabled || chained) {
+ ncsi_stop_channel_monitor(nc);
return;
+ }
+
if (state != NCSI_CHANNEL_INACTIVE &&
- state != NCSI_CHANNEL_ACTIVE)
+ state != NCSI_CHANNEL_ACTIVE) {
+ ncsi_stop_channel_monitor(nc);
return;
+ }
switch (monitor_state) {
case NCSI_CHANNEL_MONITOR_START:
@@ -199,6 +204,7 @@ static void ncsi_channel_monitor(unsigned long data)
nca.req_flags = 0;
ret = ncsi_xmit_cmd(&nca);
if (ret) {
+ ncsi_stop_channel_monitor(nc);
netdev_err(ndp->ndev.dev, "Error %d sending GLS\n",
ret);
return;
@@ -218,6 +224,8 @@ static void ncsi_channel_monitor(unsigned long data)
nc->state = NCSI_CHANNEL_INVISIBLE;
spin_unlock_irqrestore(&nc->lock, flags);
+ ncsi_stop_channel_monitor(nc);
+
spin_lock_irqsave(&ndp->lock, flags);
nc->state = NCSI_CHANNEL_INACTIVE;
list_add_tail_rcu(&nc->link, &ndp->channel_queue);
@@ -257,6 +265,10 @@ void ncsi_stop_channel_monitor(struct ncsi_channel *nc)
nc->monitor.enabled = false;
spin_unlock_irqrestore(&nc->lock, flags);
+ /* The timer isn't in pending state if we're deleting the timer
+ * in its handler. del_timer_sync() can detect it and just does
+ * nothing.
+ */
del_timer_sync(&nc->monitor.timer);
}
The field @monitor.enabled in the NCSI channel descriptor is used to track the state of channel monitor timer. It indicates the timer's state (pending or not). We could not start the timer again in its handler. In that case, We missed to update @monitor.enabled to false. It leads to below warning printed by WARN_ON_ONCE() when the monitor is restarted afterwards. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 411 at /var/lib/jenkins/workspace/openbmc-build \ /distro/ubuntu/target/palmetto/openbmc/build/tmp/work-shared/palmetto \ net/ncsi/ncsi-manage.c:240 ncsi_start_channel_monitor+0x44/0x7c CPU: 0 PID: 411 Comm: kworker/0:3 Not tainted \ 4.7.10-f26558191540830589fe03932d05577957670b8d #1 Hardware name: ASpeed SoC Workqueue: events ncsi_dev_work [<c0106cbc>] (unwind_backtrace) from [<c0104f04>] (show_stack+0x10/0x14) [<c0104f04>] (show_stack) from [<c010eef8>] (__warn+0xc4/0xf0) [<c010eef8>] (__warn) from [<c010f018>] (warn_slowpath_null+0x1c/0x24) [<c010f018>] (warn_slowpath_null) from [<c03e1d10>] (ncsi_start_channel_monitor+0x44/0x7c) [<c03e1d10>] (ncsi_start_channel_monitor) from [<c03e29c4>] (ncsi_configure_channel+0x27c/0x2dc) [<c03e29c4>] (ncsi_configure_channel) from [<c03e31d0>] (ncsi_dev_work+0x39c/0x3e8) [<c03e31d0>] (ncsi_dev_work) from [<c0120288>] (process_one_work+0x1b8/0x2fc) [<c0120288>] (process_one_work) from [<c01206bc>] (worker_thread+0x2c0/0x3f8) [<c01206bc>] (worker_thread) from [<c0124b10>] (kthread+0xd0/0xe8) [<c0124b10>] (kthread) from [<c0102250>] (ret_from_fork+0x14/0x24) ---[ end trace 110cccf2b038c44d ]--- This fixes the issue by updating @monitor.enabled to false if needed. Reported-by: Sridevi Ramesh <sridevra@in.ibm.com> Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com> --- net/ncsi/ncsi-manage.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-)