[PATCH net 2/3] igb: link queues to NAPIs under RTNL after runtime resume

[Antonio Quartulli <antonio@mandelbit.com>]

__igb_open() links queues to NAPIs with netif_queue_set_napi(), which
requires RTNL, but RTNL isn't held when resuming from runtime suspend:
this triggers "RTNL: assertion failed".

Don't link them in __igb_open() when resuming: do it right away on
system resume (RTNL held) and from a work item taking RTNL on runtime
resume. The links can't be kept across a suspend, because
__igb_shutdown() frees the q_vectors. These are only freed under RTNL
with __IGB_DOWN set, so the work item checks __IGB_DOWN under RTNL.

Fixes: b75a1dea500f ("igb: Link queues to NAPI instances")
Cc: stable@vger.kernel.org # 6.16+
Closes: https://bugzilla.ipfire.org/show_bug.cgi?id=13562
Signed-off-by: Antonio Quartulli <antonio@mandelbit.com>
---
Note: igc may have the same issue: __igc_open() also links queues to NAPIs
(igc_set_queue_napi()) on the RTNL-less runtime resume path. We didn't
have igc hardware to test a fix with, so no igc patch is sent for now.

 drivers/net/ethernet/intel/igb/igb.h      |  1 +
 drivers/net/ethernet/intel/igb/igb_main.c | 38 +++++++++++++++++++++--
 2 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 0fff1df..ea2d739 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -585,6 +585,7 @@ struct igb_adapter {
 
 	struct work_struct reset_task;
 	struct work_struct watchdog_task;
+	struct work_struct queue_napi_task;
 	bool fc_autoneg;
 	u8  tx_timeout_factor;
 	struct timer_list blink_timer;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index bd1185d..4d97399 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2115,6 +2115,30 @@ void igb_set_queue_napi(struct igb_adapter *adapter, int vector,
 				     NETDEV_QUEUE_TYPE_TX, napi);
 }
 
+static void igb_link_queue_napis(struct igb_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_q_vectors; i++)
+		igb_set_queue_napi(adapter, i, &adapter->q_vector[i]->napi);
+}
+
+/* Linking queues to NAPIs requires RTNL, which isn't held when resuming
+ * from runtime suspend: do it from here instead. The q_vectors are only
+ * freed under RTNL with __IGB_DOWN set, so checking it under RTNL is safe.
+ */
+static void igb_queue_napi_task(struct work_struct *work)
+{
+	struct igb_adapter *adapter = container_of(work, struct igb_adapter,
+						   queue_napi_task);
+
+	rtnl_lock();
+	if (!test_bit(__IGB_DOWN, &adapter->state) &&
+	    netif_running(adapter->netdev))
+		igb_link_queue_napis(adapter);
+	rtnl_unlock();
+}
+
 /**
  *  igb_up - Open the interface and prepare it to handle traffic
  *  @adapter: board private structure
@@ -3426,6 +3450,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&adapter->reset_task, igb_reset_task);
 	INIT_WORK(&adapter->watchdog_task, igb_watchdog_task);
+	INIT_WORK(&adapter->queue_napi_task, igb_queue_napi_task);
 
 	/* Initialize link properties that are user-changeable */
 	adapter->fc_autoneg = true;
@@ -3890,6 +3915,7 @@ static void igb_remove(struct pci_dev *pdev)
 
 	cancel_work_sync(&adapter->reset_task);
 	cancel_work_sync(&adapter->watchdog_task);
+	cancel_work_sync(&adapter->queue_napi_task);
 
 #ifdef CONFIG_IGB_DCA
 	if (adapter->flags & IGB_FLAG_DCA_ENABLED) {
@@ -4184,7 +4210,8 @@ static int __igb_open(struct net_device *netdev, bool resuming)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		napi = &adapter->q_vector[i]->napi;
 		napi_enable(napi);
-		igb_set_queue_napi(adapter, i, napi);
+		if (!resuming)
+			igb_set_queue_napi(adapter, i, napi);
 	}
 
 	/* Clear any pending interrupts. */
@@ -9631,8 +9658,15 @@ static int __igb_resume(struct device *dev, bool rpm)
 
 	if (!rpm)
 		rtnl_lock();
-	if (!err && netif_running(netdev))
+	if (!err && netif_running(netdev)) {
 		err = __igb_open(netdev, true);
+		if (!err) {
+			if (rpm)
+				schedule_work(&adapter->queue_napi_task);
+			else
+				igb_link_queue_napis(adapter);
+		}
+	}
 
 	if (!err)
 		netif_device_attach(netdev);
-- 
2.56.0