ionic: add FW_STOPPING state

Between fw running and fw actually stopped into reset, we need
a fw_stopping concept to catch and block some actions while
we're transitioning to FW_RESET state.  This will help to be
sure the fw_up task is not scheduled until after the fw_down
task has completed.

On some rare occasion timing, it is possible for the fw_up task
to try to run before the fw_down task, then not get run after
the fw_down task has run, leaving the device in a down state.
This is possible if the watchdog goes off in between finding the
down transition and starting the fw_down task, where the later
watchdog sees the FW is back up and schedules a fw_up task.

Fixes: c672412f6172 ("ionic: remove lifs on fw reset")
Signed-off-by: Shannon Nelson <snelson@pensando.io>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 19 insertions, 12 deletions

diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
index 86791e0f2d72..8edbd7c30ccc 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
@@ -197,21 +197,24 @@ do_check_time:
 		struct ionic_lif *lif = ionic->lif;
 		bool trigger = false;
 
-		idev->fw_status_ready = fw_status_ready;
-
-		if (!fw_status_ready) {
-			dev_info(ionic->dev, "FW stopped %u\n", fw_status);
-			if (lif && !test_bit(IONIC_LIF_F_FW_RESET, lif->state))
-				trigger = true;
-		} else {
-			dev_info(ionic->dev, "FW running %u\n", fw_status);
-			if (lif && test_bit(IONIC_LIF_F_FW_RESET, lif->state))
-				trigger = true;
+		if (!fw_status_ready && lif &&
+		    !test_bit(IONIC_LIF_F_FW_RESET, lif->state) &&
+		    !test_and_set_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) {
+			dev_info(ionic->dev, "FW stopped 0x%02x\n", fw_status);
+			trigger = true;
+
+		} else if (fw_status_ready && lif &&
+			   test_bit(IONIC_LIF_F_FW_RESET, lif->state) &&
+			   !test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) {
+			dev_info(ionic->dev, "FW running 0x%02x\n", fw_status);
+			trigger = true;
 		}
 
 		if (trigger) {
 			struct ionic_deferred_work *work;
 
+			idev->fw_status_ready = fw_status_ready;
+
 			work = kzalloc(sizeof(*work), GFP_ATOMIC);
 			if (work) {
 				work->type = IONIC_DW_TYPE_LIF_RESET;
@@ -221,7 +224,7 @@ do_check_time:
 		}
 	}
 
-	if (!fw_status_ready)
+	if (!idev->fw_status_ready)
 		return -ENXIO;
 
 	/* wait at least one watchdog period since the last heartbeat */
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 2ff7be17e5af..08c8589e875a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -2835,6 +2835,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif)
 
 	mutex_unlock(&lif->queue_lock);
 
+	clear_bit(IONIC_LIF_F_FW_STOPPING, lif->state);
 	dev_info(ionic->dev, "FW Down: LIFs stopped\n");
 }
 
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 9f7ab2f17f93..2db708df6b55 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -135,6 +135,7 @@ enum ionic_lif_state_flags {
 	IONIC_LIF_F_LINK_CHECK_REQUESTED,
 	IONIC_LIF_F_FILTER_SYNC_NEEDED,
 	IONIC_LIF_F_FW_RESET,
+	IONIC_LIF_F_FW_STOPPING,
 	IONIC_LIF_F_SPLIT_INTR,
 	IONIC_LIF_F_BROKEN,
 	IONIC_LIF_F_TX_DIM_INTR,
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index a548f2a01806..449e9ee2acf0 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -332,7 +332,9 @@ int ionic_adminq_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx,
 			break;
 
 		/* interrupt the wait if FW stopped */
-		if (test_bit(IONIC_LIF_F_FW_RESET, lif->state)) {
+		if ((test_bit(IONIC_LIF_F_FW_RESET, lif->state) &&
+		     !lif->ionic->idev.fw_status_ready) ||
+		    test_bit(IONIC_LIF_F_FW_STOPPING, lif->state)) {
 			if (do_msg)
 				netdev_err(netdev, "%s (%d) interrupted, FW in reset\n",
 					   name, ctx->cmd.cmd.opcode);