Merge tag 'net-6.16-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from can and xfrm.

  The TI regression notified last week is actually on our net-next tree,
  it does not affect 6.16.

  We are investigating a virtio regression which is quite hard to
  reproduce - currently only our CI sporadically hits it. Hopefully it
  should not be critical, and I'm not sure that an additional week would
  be enough to solve it.

  Current release - fix to a fix:

   - sched: sch_qfq: avoid sleeping in atomic context in qfq_delete_class

  Previous releases - regressions:

   - xfrm:
      - set transport header to fix UDP GRO handling
      - delete x->tunnel as we delete x

   - eth:
      - mlx5: fix memory leak in cmd_exec()
      - i40e: when removing VF MAC filters, avoid losing PF-set MAC
      - gve: fix stuck TX queue for DQ queue format

  Previous releases - always broken:

   - can: fix NULL pointer deref of struct can_priv::do_set_mode

   - eth:
      - ice: fix a null pointer dereference in ice_copy_and_init_pkg()
      - ism: fix concurrency management in ism_cmd()
      - dpaa2: fix device reference count leak in MAC endpoint handling
      - icssg-prueth: fix buffer allocation for ICSSG

  Misc:

   - selftests: mptcp: increase code coverage"

* tag 'net-6.16-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (34 commits)
  net: hns3: default enable tx bounce buffer when smmu enabled
  net: hns3: fixed vf get max channels bug
  net: hns3: disable interrupt when ptp init failed
  net: hns3: fix concurrent setting vlan filter issue
  s390/ism: fix concurrency management in ism_cmd()
  selftests: drv-net: wait for iperf client to stop sending
  MAINTAINERS: Add in6.h to MAINTAINERS
  selftests: netfilter: tone-down conntrack clash test
  can: netlink: can_changelink(): fix NULL pointer deref of struct can_priv::do_set_mode
  net/sched: sch_qfq: Avoid triggering might_sleep in atomic context in qfq_delete_class
  gve: Fix stuck TX queue for DQ queue format
  net: appletalk: Fix use-after-free in AARP proxy probe
  net: bcmasp: Restore programming of TX map vector register
  selftests: mptcp: connect: also cover checksum
  selftests: mptcp: connect: also cover alt modes
  e1000e: ignore uninitialized checksum word on tgp
  e1000e: disregard NVM checksum on tgp when valid checksum bit is not set
  ice: Fix a null pointer dereference in ice_copy_and_init_pkg()
  i40e: When removing VF MAC filters, only check PF-set MAC
  i40e: report VF tx_dropped with tx_errors instead of tx_discards
  ...

Author: torvalds

MAINTAINERS

@@ -17383,6 +17383,7 @@ F:	include/linux/ethtool.h
 F:	include/linux/framer/framer-provider.h
 F:	include/linux/framer/framer.h
 F:	include/linux/in.h
+F:	include/linux/in6.h
 F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/inet.h
 F:	include/linux/inet_diag.h

drivers/bus/fsl-mc/fsl-mc-bus.c

@@ -943,6 +943,7 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
 	struct fsl_mc_obj_desc endpoint_desc = {{ 0 }};
 	struct dprc_endpoint endpoint1 = {{ 0 }};
 	struct dprc_endpoint endpoint2 = {{ 0 }};
+	struct fsl_mc_bus *mc_bus;
 	int state, err;
 
 	mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent);
@@ -966,24 +967,22 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
 	strcpy(endpoint_desc.type, endpoint2.type);
 	endpoint_desc.id = endpoint2.id;
 	endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev);
+	if (endpoint)
+		return endpoint;
 
 	/*
 	 * We know that the device has an endpoint because we verified by
 	 * interrogating the firmware. This is the case when the device was not
 	 * yet discovered by the fsl-mc bus, thus the lookup returned NULL.
 	 * Force a rescan of the devices in this container and retry the lookup.
 	 */
-	if (!endpoint) {
-		struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
-
-		if (mutex_trylock(&mc_bus->scan_mutex)) {
-			err = dprc_scan_objects(mc_bus_dev, true);
-			mutex_unlock(&mc_bus->scan_mutex);
-		}
-
-		if (err < 0)
-			return ERR_PTR(err);
+	mc_bus = to_fsl_mc_bus(mc_bus_dev);
+	if (mutex_trylock(&mc_bus->scan_mutex)) {
+		err = dprc_scan_objects(mc_bus_dev, true);
+		mutex_unlock(&mc_bus->scan_mutex);
 	}
+	if (err < 0)
+		return ERR_PTR(err);
 
 	endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev);
 	/*

drivers/net/can/dev/dev.c

@@ -145,13 +145,16 @@ void can_change_state(struct net_device *dev, struct can_frame *cf,
 EXPORT_SYMBOL_GPL(can_change_state);
 
 /* CAN device restart for bus-off recovery */
-static void can_restart(struct net_device *dev)
+static int can_restart(struct net_device *dev)
 {
 	struct can_priv *priv = netdev_priv(dev);
 	struct sk_buff *skb;
 	struct can_frame *cf;
 	int err;
 
+	if (!priv->do_set_mode)
+		return -EOPNOTSUPP;
+
 	if (netif_carrier_ok(dev))
 		netdev_err(dev, "Attempt to restart for bus-off recovery, but carrier is OK?\n");
 
@@ -173,10 +176,14 @@ static void can_restart(struct net_device *dev)
 	if (err) {
 		netdev_err(dev, "Restart failed, error %pe\n", ERR_PTR(err));
 		netif_carrier_off(dev);
+
+		return err;
 	} else {
 		netdev_dbg(dev, "Restarted\n");
 		priv->can_stats.restarts++;
 	}
+
+	return 0;
 }
 
 static void can_restart_work(struct work_struct *work)
@@ -201,9 +208,8 @@ int can_restart_now(struct net_device *dev)
 		return -EBUSY;
 
 	cancel_delayed_work_sync(&priv->restart_work);
-	can_restart(dev);
 
-	return 0;
+	return can_restart(dev);
 }
 
 /* CAN bus-off

drivers/net/can/dev/netlink.c

@@ -285,13 +285,25 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 	}
 
 	if (data[IFLA_CAN_RESTART_MS]) {
+		if (!priv->do_set_mode) {
+			NL_SET_ERR_MSG(extack,
+				       "Device doesn't support restart from Bus Off");
+			return -EOPNOTSUPP;
+		}
+
 		/* Do not allow changing restart delay while running */
 		if (dev->flags & IFF_UP)
 			return -EBUSY;
 		priv->restart_ms = nla_get_u32(data[IFLA_CAN_RESTART_MS]);
 	}
 
 	if (data[IFLA_CAN_RESTART]) {
+		if (!priv->do_set_mode) {
+			NL_SET_ERR_MSG(extack,
+				       "Device doesn't support restart from Bus Off");
+			return -EOPNOTSUPP;
+		}
+
 		/* Do not allow a restart while not running */
 		if (!(dev->flags & IFF_UP))
 			return -EINVAL;

drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c

@@ -818,6 +818,9 @@ static void bcmasp_init_tx(struct bcmasp_intf *intf)
 	/* Tx SPB */
 	tx_spb_ctrl_wl(intf, ((intf->channel + 8) << TX_SPB_CTRL_XF_BID_SHIFT),
 		       TX_SPB_CTRL_XF_CTRL2);
+
+	if (intf->parent->tx_chan_offset)
+		tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR);
 	tx_spb_top_wl(intf, 0x1e, TX_SPB_TOP_BLKOUT);
 
 	tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_READ);

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

@@ -4666,12 +4666,19 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 		return PTR_ERR(dpmac_dev);
 	}
 
-	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+	if (IS_ERR(dpmac_dev))
 		return 0;
 
+	if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) {
+		err = 0;
+		goto out_put_device;
+	}
+
 	mac = kzalloc(sizeof(struct dpaa2_mac), GFP_KERNEL);
-	if (!mac)
-		return -ENOMEM;
+	if (!mac) {
+		err = -ENOMEM;
+		goto out_put_device;
+	}
 
 	mac->mc_dev = dpmac_dev;
 	mac->mc_io = priv->mc_io;
@@ -4705,6 +4712,8 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv)
 	dpaa2_mac_close(mac);
 err_free_mac:
 	kfree(mac);
+out_put_device:
+	put_device(&dpmac_dev->dev);
 	return err;
 }
 

drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c

@@ -1448,12 +1448,19 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv)
 	if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER)
 		return PTR_ERR(dpmac_dev);
 
-	if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type)
+	if (IS_ERR(dpmac_dev))
 		return 0;
 
+	if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) {
+		err = 0;
+		goto out_put_device;
+	}
+
 	mac = kzalloc(sizeof(*mac), GFP_KERNEL);
-	if (!mac)
-		return -ENOMEM;
+	if (!mac) {
+		err = -ENOMEM;
+		goto out_put_device;
+	}
 
 	mac->mc_dev = dpmac_dev;
 	mac->mc_io = port_priv->ethsw_data->mc_io;
@@ -1483,6 +1490,8 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv)
 	dpaa2_mac_close(mac);
 err_free_mac:
 	kfree(mac);
+out_put_device:
+	put_device(&dpmac_dev->dev);
 	return err;
 }
 

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

@@ -1917,49 +1917,56 @@ static void gve_turnup_and_check_status(struct gve_priv *priv)
 	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
 }
 
-static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
+static struct gve_notify_block *gve_get_tx_notify_block(struct gve_priv *priv,
+							unsigned int txqueue)
 {
-	struct gve_notify_block *block;
-	struct gve_tx_ring *tx = NULL;
-	struct gve_priv *priv;
-	u32 last_nic_done;
-	u32 current_time;
 	u32 ntfy_idx;
 
-	netdev_info(dev, "Timeout on tx queue, %d", txqueue);
-	priv = netdev_priv(dev);
 	if (txqueue > priv->tx_cfg.num_queues)
-		goto reset;
+		return NULL;
 
 	ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue);
 	if (ntfy_idx >= priv->num_ntfy_blks)
-		goto reset;
+		return NULL;
+
+	return &priv->ntfy_blocks[ntfy_idx];
+}
+
+static bool gve_tx_timeout_try_q_kick(struct gve_priv *priv,
+				      unsigned int txqueue)
+{
+	struct gve_notify_block *block;
+	u32 current_time;
 
-	block = &priv->ntfy_blocks[ntfy_idx];
-	tx = block->tx;
+	block = gve_get_tx_notify_block(priv, txqueue);
+
+	if (!block)
+		return false;
 
 	current_time = jiffies_to_msecs(jiffies);
-	if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time)
-		goto reset;
+	if (block->tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time)
+		return false;
 
-	/* Check to see if there are missed completions, which will allow us to
-	 * kick the queue.
-	 */
-	last_nic_done = gve_tx_load_event_counter(priv, tx);
-	if (last_nic_done - tx->done) {
-		netdev_info(dev, "Kicking queue %d", txqueue);
-		iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block));
-		napi_schedule(&block->napi);
-		tx->last_kick_msec = current_time;
-		goto out;
-	} // Else reset.
+	netdev_info(priv->dev, "Kicking queue %d", txqueue);
+	napi_schedule(&block->napi);
+	block->tx->last_kick_msec = current_time;
+	return true;
+}
 
-reset:
-	gve_schedule_reset(priv);
+static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	struct gve_notify_block *block;
+	struct gve_priv *priv;
 
-out:
-	if (tx)
-		tx->queue_timeout++;
+	netdev_info(dev, "Timeout on tx queue, %d", txqueue);
+	priv = netdev_priv(dev);
+
+	if (!gve_tx_timeout_try_q_kick(priv, txqueue))
+		gve_schedule_reset(priv);
+
+	block = gve_get_tx_notify_block(priv, txqueue);
+	if (block)
+		block->tx->queue_timeout++;
 	priv->tx_timeo_cnt++;
 }
 

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

@@ -11,6 +11,7 @@
 #include <linux/irq.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/skbuff.h>
@@ -1039,6 +1040,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring,
 static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 {
 	u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size;
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_tx_spare *tx_spare;
 	struct page *page;
 	dma_addr_t dma;
@@ -1080,6 +1083,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 	tx_spare->buf = page_address(page);
 	tx_spare->len = PAGE_SIZE << order;
 	ring->tx_spare = tx_spare;
+	ring->tx_copybreak = priv->tx_copybreak;
 	return;
 
 dma_mapping_error:
@@ -4874,6 +4878,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
 	devm_kfree(&pdev->dev, priv->tqp_vector);
 }
 
+static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv)
+{
+#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024)
+#define HNS3_MAX_PACKET_SIZE (64 * 1024)
+
+	struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
+	struct hnae3_handle *handle = priv->ae_handle;
+
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3)
+		return;
+
+	if (!(domain && iommu_is_dma_domain(domain)))
+		return;
+
+	priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE;
+	priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE;
+
+	if (priv->tx_copybreak < priv->min_tx_copybreak)
+		priv->tx_copybreak = priv->min_tx_copybreak;
+	if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size)
+		handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size;
+}
+
 static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 			      unsigned int ring_type)
 {
@@ -5107,6 +5135,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv)
 	int i, j;
 	int ret;
 
+	hns3_update_tx_spare_buf_config(priv);
 	for (i = 0; i < ring_num; i++) {
 		ret = hns3_alloc_ring_memory(&priv->ring[i]);
 		if (ret) {
@@ -5311,6 +5340,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->ae_handle = handle;
 	priv->tx_timeout_count = 0;
 	priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num;
+	priv->min_tx_copybreak = 0;
+	priv->min_tx_spare_buf_size = 0;
 	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
 	handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);

drivers/net/ethernet/hisilicon/hns3/hns3_enet.h

@@ -596,6 +596,8 @@ struct hns3_nic_priv {
 	struct hns3_enet_coalesce rx_coal;
 	u32 tx_copybreak;
 	u32 rx_copybreak;
+	u32 min_tx_copybreak;
+	u32 min_tx_spare_buf_size;
 };
 
 union l3_hdr_info {