gve: Alloc before freeing when adjusting queues

Previously, existing queues were being freed before the resources for
the new queues were being allocated. This would take down the interface
if someone were to attempt to change queue counts under a resource
crunch.
Signed-off-by: Shailend Chand <shailend@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jeroen de Borst <jeroendb@google.com>
Link: https://lore.kernel.org/r/20240122182632.1102721-6-shailend@google.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/google/gve/gve_main.c

@@ -1869,42 +1869,87 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
-int gve_adjust_queues(struct gve_priv *priv,
-		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config)
+static int gve_adjust_config(struct gve_priv *priv,
+			     struct gve_qpls_alloc_cfg *qpls_alloc_cfg,
+			     struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
+			     struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
 {
 	int err;
 
-	if (netif_carrier_ok(priv->dev)) {
-		/* To make this process as simple as possible we teardown the
-		 * device, set the new configuration, and then bring the device
-		 * up again.
-		 */
+	/* Allocate resources for the new confiugration */
+	err = gve_queues_mem_alloc(priv, qpls_alloc_cfg,
+				   tx_alloc_cfg, rx_alloc_cfg);
+	if (err) {
+		netif_err(priv, drv, priv->dev,
+			  "Adjust config failed to alloc new queues");
+		return err;
+	}
+
+	/* Teardown the device and free existing resources */
 	err = gve_close(priv->dev);
-		/* we have already tried to reset in close,
-		 * just fail at this point
-		 */
-		if (err)
+	if (err) {
+		netif_err(priv, drv, priv->dev,
+			  "Adjust config failed to close old queues");
+		gve_queues_mem_free(priv, qpls_alloc_cfg,
+				    tx_alloc_cfg, rx_alloc_cfg);
 		return err;
-		priv->tx_cfg = new_tx_config;
-		priv->rx_cfg = new_rx_config;
+	}
 
-		err = gve_open(priv->dev);
-		if (err)
-			goto err;
+	/* Bring the device back up again with the new resources. */
+	err = gve_queues_start(priv, qpls_alloc_cfg,
+			       tx_alloc_cfg, rx_alloc_cfg);
+	if (err) {
+		netif_err(priv, drv, priv->dev,
+			  "Adjust config failed to start new queues, !!! DISABLING ALL QUEUES !!!\n");
+		/* No need to free on error: ownership of resources is lost after
+		 * calling gve_queues_start.
+		 */
+		gve_turndown(priv);
+		return err;
+	}
 
 	return 0;
+}
+
+int gve_adjust_queues(struct gve_priv *priv,
+		      struct gve_queue_config new_rx_config,
+		      struct gve_queue_config new_tx_config)
+{
+	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
+	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
+	struct gve_qpls_alloc_cfg qpls_alloc_cfg = {0};
+	struct gve_qpl_config new_qpl_cfg;
+	int err;
+
+	gve_get_curr_alloc_cfgs(priv, &qpls_alloc_cfg,
+				&tx_alloc_cfg, &rx_alloc_cfg);
+
+	/* qpl_cfg is not read-only, it contains a map that gets updated as
+	 * rings are allocated, which is why we cannot use the yet unreleased
+	 * one in priv.
+	 */
+	qpls_alloc_cfg.qpl_cfg = &new_qpl_cfg;
+	tx_alloc_cfg.qpl_cfg = &new_qpl_cfg;
+	rx_alloc_cfg.qpl_cfg = &new_qpl_cfg;
+
+	/* Relay the new config from ethtool */
+	qpls_alloc_cfg.tx_cfg = &new_tx_config;
+	tx_alloc_cfg.qcfg = &new_tx_config;
+	rx_alloc_cfg.qcfg_tx = &new_tx_config;
+	qpls_alloc_cfg.rx_cfg = &new_rx_config;
+	rx_alloc_cfg.qcfg = &new_rx_config;
+	tx_alloc_cfg.num_rings = new_tx_config.num_queues;
+
+	if (netif_carrier_ok(priv->dev)) {
+		err = gve_adjust_config(priv, &qpls_alloc_cfg,
+					&tx_alloc_cfg, &rx_alloc_cfg);
+		return err;
 	}
 	/* Set the config for the next up. */
 	priv->tx_cfg = new_tx_config;
 	priv->rx_cfg = new_rx_config;
 
 	return 0;
-err:
-	netif_err(priv, drv, priv->dev,
-		  "Adjust queues failed! !!! DISABLING ALL QUEUES !!!\n");
-	gve_turndown(priv);
-	return err;
 }
 
 static void gve_turndown(struct gve_priv *priv)